Virtual environment pushing method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a virtual environment pushing method and device, electronic equipment and a storage medium. The method comprises: when detecting that a virtual pet of a user is in a preset state, obtaining current weather information; generating a target appearance image corresponding to the virtual pet according to the weather information and a kind of the virtual pet; adjusting weather in a current virtual environment of the virtual pet according to the weather information to obtain a target virtual environment; and sending the target virtual environment to a user terminal of the user to display the current virtual environment and the target virtual environment on the same screen of the user terminal, wherein the current virtual environment comprises the current appearance image and the target virtual environment comprises the target appearance image. The embodiments of the present application reduce the complexity of appearance image replacement of the virtual pet.

Description

Technical Field

[0001] This application relates to the field of information push technology, specifically to a virtual environment push method, device, electronic device, and storage medium. Background Technology

[0002] Currently, with the booming pet market, almost everyone wants to own a pet. However, pet ownership presents several challenges, such as busy work schedules, the relatively short lifespan of pets, or restrictions on pet ownership in certain areas. These factors prevent many aspiring pet owners from fulfilling their desires. Virtual pets offer a solution: long lifespan (can grow indefinitely), can be cared for anytime, anywhere without requiring special feeding or care, and are not limited by living environment—users only need to install a corresponding application and operate it online to raise their virtual pet. Therefore, virtual pets are gradually becoming more active in people's lives.

[0003] However, in the process of raising virtual pets, the appearance of the virtual pets needs to be changed and adjusted by the user, which is a complicated process and results in a poor user experience. Summary of the Invention

[0004] This application provides a virtual environment push method, device, electronic device, and storage medium, which pushes matching virtual environments and appearances to user terminals based on weather information, thereby improving the intelligence and simplicity of changing the appearance of virtual pets and enhancing user experience.

[0005] In a first aspect, embodiments of this application provide a method for pushing virtual environments to virtual pets, including:

[0006] When the user's virtual pet is detected to be in a preset state, the current weather information is obtained;

[0007] Based on the weather information and the type of the virtual pet, generate a target appearance image corresponding to the virtual pet;

[0008] Based on the weather information, the weather in the current virtual environment of the virtual pet is adjusted to obtain the target virtual environment;

[0009] The target virtual environment is sent to the user's terminal so that the current virtual environment and the target virtual environment are displayed on the same screen on the user's terminal. The current virtual environment includes the current appearance image, and the target virtual environment includes the target appearance image.

[0010] Secondly, embodiments of this application provide a virtual environment push device, including: an acquisition unit, a processing unit, and a sending unit;

[0011] The acquisition unit is used to acquire current weather information when it detects that the user's virtual pet is in a preset state;

[0012] The processing unit is used to generate a target appearance image corresponding to the virtual pet based on the weather information and the type of the virtual pet;

[0013] Based on the weather information, the weather in the current virtual environment of the virtual pet is adjusted to obtain the target virtual environment;

[0014] The sending unit is used to send the target virtual environment to the user's user terminal so that the current virtual environment and the target virtual environment are displayed on the same screen on the user terminal. The current virtual environment includes the current appearance image, and the target virtual environment includes the target appearance image.

[0015] Thirdly, embodiments of this application provide an electronic device, including: a processor connected to a memory for storing a computer program, and the processor for executing the computer program stored in the memory to cause the electronic device to perform the method as described in the first aspect.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform the method described in the first aspect.

[0017] Fifthly, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, the computer being operable to perform the method as described in the first aspect.

[0018] Implementing the embodiments of this application has the following beneficial effects:

[0019] As can be seen in this embodiment, when the virtual pet display device detects that the user's virtual pet is in a preset state, it acquires the current weather information, determines the target appearance matching the user's virtual pet based on the weather information, and adjusts the virtual pet's current virtual environment to the target virtual environment based on the weather information. Finally, the target appearance and target virtual environment are pushed to the user terminal, so that the current virtual environment (including the current appearance) and the target virtual environment (including the target appearance) can be displayed on the same screen on the user terminal. This allows the virtual pet's appearance and virtual environment to be automatically adjusted based on the user's response, without requiring the user to manually change them. This simplifies the automation of virtual pet appearance changes, streamlines the changing process, and improves the user experience. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of a virtual environment push system provided in an embodiment of this application;

[0022] Figure 2 A flowchart illustrating a virtual environment push method provided in an embodiment of this application;

[0023] Figure 3 A schematic diagram of a multi-task model provided in an embodiment of this application;

[0024] Figure 4 This is a schematic diagram illustrating the construction of base textures for various body parts, as provided in an embodiment of this application.

[0025] Figure 5 A schematic diagram illustrating the simultaneous display of the current virtual environment and the target virtual environment, provided as an embodiment of this application;

[0026] Figure 6 A flowchart illustrating a full-screen display of a target virtual environment provided in an embodiment of this application;

[0027] Figure 7 A functional unit block diagram of a virtual environment push device provided in this application embodiment;

[0028] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0031] In this document, the term "embodiment" means that a particular feature, result, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0032] See Figure 1 , Figure 1 This is a schematic diagram of a virtual environment push system provided in an embodiment of this application. The virtual environment push system includes a virtual environment push device 10, a user terminal 20, and one or more wearable devices 30, wherein the virtual environment push device 10, the user terminal 20, and the one or more wearable devices 30 maintain a communication connection.

[0033] The virtual environment push device 10 maintains a front-end application, and the user terminal 20 has the front-end application installed on it. The user can send a request to the virtual environment push device 10 through the front-end application installed on the user terminal 20, so as to generate a virtual pet, edit the appearance of the virtual pet, or cancel the virtual pet, etc.

[0034] For example, when a user's virtual pet is detected to be in a preset state, the virtual environment push device 10 obtains the current weather information, generates a target virtual pet corresponding to the virtual pet based on the weather information and the type of virtual pet; adjusts the weather in the current virtual environment of the virtual pet according to the target's appearance and the weather information to obtain the target virtual environment; finally, sends the target virtual environment to the user terminal 20 so that the current virtual environment and the target virtual environment are displayed on the same screen on the user terminal, such as... Figure 1 As shown, when displaying on the same screen, the current appearance is displayed in the current virtual environment, and the target appearance is displayed in the target virtual environment.

[0035] Furthermore, after obtaining weather information, the virtual environment push device 10 can also obtain physiological parameters through one or more wearable devices 30, and then combine the weather information, the type of virtual pet, and the physiological parameters to comprehensively generate a target appearance image corresponding to the virtual pet.

[0036] As can be seen in this embodiment, when the virtual pet display device detects that the user's virtual pet is in a preset state, it acquires the current weather information, determines the target appearance matching the user's virtual pet based on the weather information, and adjusts the virtual pet's current virtual environment to the target virtual environment based on the weather information. Finally, the target appearance and target virtual environment are pushed to the user terminal, so that the current virtual environment (including the current appearance) and the target virtual environment (including the target appearance) can be displayed on the same screen on the user terminal. This allows the virtual pet's appearance and virtual environment to be automatically adjusted based on the user's response, without requiring the user to manually change them. This simplifies the automation of virtual pet appearance changes, streamlines the changing process, and improves the user experience.

[0037] See Figure 2 , Figure 2 This is a flowchart illustrating a virtual environment push method provided in an embodiment of this application. The method is applied to the aforementioned virtual environment push device 10. The method includes, but is not limited to, the following steps:

[0038] 201: When the user's virtual pet is detected to be in a preset state, the virtual environment push device obtains the current weather information.

[0039] For example, a front-end application maintained by the virtual environment push device 10 is installed on the user terminal. Accordingly, the user can log in to their virtual pet, wake up the virtual pet, or activate the virtual pet on the front-end application. Therefore, the preset state of this application can be that the virtual pet is in a logged-in state, a woke-up state, or an activated state, and this application does not limit the specific type of the preset state.

[0040] 202: The virtual environment push device generates a target appearance image corresponding to the virtual pet based on the weather information and the type of the virtual pet.

[0041] For example, the virtual environment push device can determine the body characteristics of each body part corresponding to the virtual pet based on weather information, the type of virtual pet, and the correspondence between body parts and their physical characteristics. This correspondence is pre-set.

[0042] It should be noted that the weather information in this application includes, but is not limited to, temperature, humidity, wind speed, air quality, and light intensity. Of course, in practical applications, weather information may also include wind direction, air pressure, solar radiation intensity, and so on. The body characteristics in this application are color characteristics, that is, the colors of various body parts. For example, for the head of a virtual pet, its color characteristics could be off-white, gray, yellow, etc. It should be noted that in practical applications, body parts may also include other body characteristics, such as body size.

[0043] Table 1 shows the correspondence between weather information, types of virtual pets, and physical characteristics of body parts.

[0044] Table 1:

[0045]

[0046]

[0047] For example, weather information is obtained when each of the multiple registered users adjusts the appearance of their virtual pet. It should be noted that any one of these registered users has pre-registered on the front-end application maintained by the virtual environment push device and has granted the virtual environment push device permission to access that user's historical actions regarding their virtual pet. Then, the virtual pets of the multiple registered users are grouped according to their types, resulting in multiple virtual pets; that is, the types of virtual pets from the multiple registered users are merged to obtain multiple virtual pets.

[0048] The following explanation uses the establishment of a correspondence between each type of virtual pet as an example.

[0049] For example, for each type of virtual pet, firstly, multiple candidate registered users corresponding to that type of virtual pet are obtained from the multiple registered users; that is, registered users who own that type of virtual pet are considered candidate registered users. Then, the weather information when each candidate registered user adjusts the appearance of their virtual pet is used as sample data, and the adjusted appearance of the virtual pet is used as a supervision label to construct training samples corresponding to each candidate registered user. Finally, the model is trained based on the training samples corresponding to each candidate registered user to obtain the correspondence between weather information, virtual pet type, and body features of body parts for that type of virtual pet.

[0050] Specifically, for each candidate registered user's training sample under each virtual pet, feature prediction is performed based on the weather information when adjusting the virtual pet for each candidate registered user, resulting in predicted body features for each body part corresponding to the training sample. For example, for each virtual pet, a multi-task model corresponding to each virtual pet is pre-built. Then, the weather information from the training sample for each candidate registered user under that virtual pet is used as input data. For instance, the various parameter values ​​in the weather information (e.g., temperature, humidity, wind speed, air quality, and light intensity) are vectorized to obtain feature vectors corresponding to each parameter value. These feature vectors are then concatenated to obtain the input data corresponding to the training sample. For example, the feature vectors corresponding to each parameter value can be concatenated column-wise to obtain a two-dimensional matrix. This two-dimensional matrix is ​​used as the input data, where the length of the two-dimensional matrix is ​​the dimension of each feature vector, and the width is the number of parameter values. Further, the input data is fed into the multi-task model for feature prediction to obtain the predicted body features for each body part corresponding to the training sample.

[0051] Specifically, such as Figure 3 As shown, the above multi-task model includes n third networks (such as...). Figure 3 The diagram shows third network 1, third network 2, ..., third network n), and multiple first classification networks (such as...). Figure 3 The first classification network 1 and the first classification network 2 shown) and multiple second classification networks (such as Figure 3 The second classification network 1 and the second classification network 2 shown are in one-to-one correspondence with the first classification network and the second classification network. Multiple second classification networks correspond one-to-one with multiple body parts of the aforementioned virtual pet types. That is, the number of second classification networks is set according to the number of body parts included in the aforementioned virtual pet types. Each second classification network is used to predict the physical characteristics of one body part, and different second classification networks are used to predict the physical characteristics of different body parts. For example, one second classification network is used to predict the color of the head, and another second classification network is used to predict the color of the tail.

[0052] Furthermore, the input data is processed by each third network to obtain a feature vector corresponding to each third network; then, the input data is classified by each first classification network, i.e., softmax classification is performed to obtain a classification result corresponding to each first classification network, and the classification result is used as the probability of falling into each third network.

[0053] Furthermore, based on the classification results corresponding to each first classification network, the weights of each third network are determined when performing classification processing through each first classification network. For example, the probability of falling into each third network can be directly used as the weight of each third network.

[0054] Furthermore, based on the weights of each third network during classification processing by each first classification network, the feature vectors corresponding to multiple third networks are weighted to obtain the input data for the second classification network corresponding to each first classification network. That is, based on the weights of each third network during classification processing by each first classification network, the feature vectors corresponding to each third network are weighted to obtain a weighted result corresponding to each first classification network. This weighted result is then used as the input data for the second classification network corresponding to each first classification network, thus obtaining the input data for each second classification network.

[0055] Furthermore, the input data of each second classification network is classified to obtain a classification result corresponding to each second classification network. This classification result represents the probability of falling into each color, and the color with the highest probability is taken as the body feature of the body part corresponding to that second classification network. Finally, based on the classification results of each second classification network, the predicted body features corresponding to each body part of the virtual pet can be obtained, that is, the predicted body features of each body part corresponding to the training samples.

[0056] Furthermore, based on the predicted body features of each body part corresponding to the training sample and the supervision label of the training sample, the loss corresponding to the training sample is determined; then, the model is trained according to the loss corresponding to the training sample until the model converges, and the target model corresponding to each virtual pet is obtained. That is, the network parameters of the multi-task model are adjusted based on the loss until the multi-task model converges, and the target model corresponding to each virtual pet can be obtained.

[0057] After obtaining the target model, each type of weather information is input into the target model corresponding to each virtual pet to predict the body characteristics of each body part under each virtual pet. Then, based on the body characteristics of each body part of each virtual pet under each type of weather information predicted by the target model corresponding to each virtual pet, the above correspondence is constructed, that is, the correspondence between the type of virtual pet, weather information, and body characteristics of body parts under each virtual pet is constructed.

[0058] This document explains that the virtual pet device maintains multiple base textures for each body part of each virtual pet. Each base texture is used to generate a basic body feature for that body part. It should be noted that the basic body feature in this application refers to the color of the body part; generally, basic body features include red, green, and blue. For example, each body feature for each body part can be represented by a matrix. For example, as shown... Figure 4 As shown, firstly, a base matrix corresponding to the virtual pet is constructed. This base matrix is ​​then rendered to obtain a solid-color virtual pet. Next, for each body part of the virtual pet, multiple base matrices are constructed based on this base matrix to obtain multiple base textures for each body part. For example, for the head of the virtual pet, a first filter matrix is ​​constructed to generate a red head. This involves obtaining the position of the virtual pet's head in the base matrix, setting the position value in the base matrix to the value corresponding to red, and then performing a dot product between the first filter matrix and the base matrix to obtain the first base matrix. Finally, this first base matrix is ​​rendered to obtain a virtual pet with a red head. Similarly, a second filter matrix is ​​constructed to generate a green head. This involves obtaining the position of the virtual pet's head in the base matrix, setting the position value in the base matrix to the value corresponding to green, and then performing a dot product between the second filter matrix and the base matrix to obtain the second base matrix. Finally, this second base matrix is ​​rendered to obtain a virtual pet with a green head. Similarly, a third filtering matrix is ​​constructed to generate a blue head. This involves obtaining the position of the virtual pet's head in the base matrix, setting the position value in the base matrix to the value corresponding to blue, and obtaining the third filtering matrix. Then, the third filtering matrix is ​​multiplied by the base matrix to obtain the third base matrix. Finally, the second base matrix is ​​rendered to obtain a virtual pet with a blue head.

[0059] It is understandable that the physical characteristics of each body part can be described in a similar manner. Figure 4The process involves processing the data in a way that yields a base map of the basic body features for each body part, which is essentially a base matrix corresponding to the basic body features of each body part. Therefore, after determining the body features of each body part of the user's virtual pet, pet stickers for generating these body features are obtained. For example, at least one base map corresponding to the body features of each body part is obtained; that is, based on the color mixing principle and the body features of each body part, at least one base map is determined for synthesizing that body feature. Then, based on the color mixing principle and the body features of each body part, the weight coefficient of each base map in the at least one base map is determined. Then, based on the weight coefficient of each base map, the base matrix corresponding to each base map is weighted to obtain the target matrix of each base map. Finally, the target matrix corresponding to each base map in the at least one base map is multiplied by a dot product to obtain the pet sticker corresponding to the body features of each body part, i.e., the matrix used to represent the pet sticker.

[0060] 203: The virtual environment push device adjusts the weather in the current virtual environment of the virtual pet according to the weather information to obtain the target virtual environment.

[0061] For example, before adjusting the weather in the current virtual environment of the virtual pet, it is first determined whether the target appearance is the same as the current appearance. If they are the same, there is no need to adjust the current virtual environment. If they are different, then the weather in the current virtual environment is adjusted.

[0062] For example, environmental elements corresponding to the weather information are obtained, and the current virtual environment is adjusted based on these environmental elements to obtain the target virtual environment. Figure 5 As shown, when the weather information is windy and rainy, the environmental elements corresponding to wind and rain are loaded. The newly loaded environmental elements are then rendered based on the current virtual environment to obtain the target virtual environment.

[0063] 204: The virtual environment push device sends the target virtual environment to the user's user terminal to display the current virtual environment and the target virtual environment on the same screen on the user terminal, wherein the current virtual environment includes the current appearance image and the target virtual environment includes the target appearance image.

[0064] For example, after determining the target virtual environment, the virtual environment push device pushes the target virtual environment to the user terminal and instructs the user terminal to display the current environment and the target virtual environment on the same screen to reflect the difference between the current virtual environment and the target virtual environment. The current appearance is displayed in the current virtual environment and the target appearance is displayed in the target virtual environment to reflect the difference between the target appearance and the current appearance.

[0065] For example, the user terminal can overlay the target virtual environment onto the current virtual environment for screen mirroring, such as... Figure 5 As shown, the lower right corner of the current virtual environment can be covered, thus enabling the current virtual environment and the target virtual environment to be displayed on the same screen.

[0066] As can be seen in this embodiment, when the virtual pet display device detects that the user's virtual pet is in a preset state, it acquires the current weather information, determines the target appearance matching the user's virtual pet based on the weather information, and adjusts the virtual pet's current virtual environment to the target virtual environment based on the weather information. Finally, the target appearance and target virtual environment are pushed to the user terminal, so that the current virtual environment (including the current appearance) and the target virtual environment (including the target appearance) can be displayed on the same screen on the user terminal. This allows the virtual pet's appearance and virtual environment to be automatically adjusted based on the user's response, without requiring the user to manually change them. This simplifies the automation of virtual pet appearance changes, streamlines the changing process, and improves the user experience.

[0067] In one embodiment of this application, display information corresponding to the weather information is obtained; the display information is sent to the user terminal, and the user terminal is instructed to display the display information in the target virtual environment when the target virtual environment is displayed in full screen.

[0068] In one embodiment of this application, such as Figure 6 As shown, the user terminal responds to a preset operation for the display area where the target virtual environment is located by displaying the target virtual environment in full screen. This preset operation can be a zoom operation, a full-screen display operation, a double-click operation, etc.

[0069] As can be seen, when the user terminal detects a preset operation, the target virtual environment can be displayed in full screen, thereby automatically changing the virtual environment and appearance of the virtual pet, improving the flexibility of user interaction with the virtual pet.

[0070] In another embodiment of this application, before generating a target appearance image corresponding to the virtual pet based on the weather information and the type of the virtual pet, the method further includes:

[0071] The system acquires the user's current physiological parameters. For example, it can send a physiological parameter acquisition request to a wearable device, which then sends the user's current physiological parameters to the virtual pet display device. Based on these parameters, the user's current mood is determined. After obtaining the current mood, the target appearance of the virtual pet can be determined based on weather information, the type of virtual pet, and the current mood. For example, the target appearance of the virtual pet can be determined based on the correspondence between weather information, the type of virtual pet, and the current mood.

[0072] As can be seen in this embodiment, when determining the appearance of the virtual pet, the user's current mood can also be taken into account to comprehensively determine the appearance, so that the determined target appearance is more in line with the user's current needs and improves the success rate of virtual environment push.

[0073] In another embodiment of this application, the virtual environment push device receives a query request from the user terminal, the query request including a first historical moment; the virtual environment push device obtains weather information for the first historical moment according to the query request; the virtual environment push device determines the appearance of the virtual pet at the first historical moment based on the weather information, that is, the appearance at the first historical moment can be obtained according to the above correspondence; the virtual environment push device sends the appearance of the virtual pet at the first historical moment to the user terminal to display the appearance of the virtual pet at the first historical moment, thereby displaying the user's mood at the first historical moment. The user terminal can display this appearance on the display interface, through which the user can know their mood at the first moment, thus visually displaying the user's mood through the appearance, improving the diversity of mood display.

[0074] See Figure 7 , Figure 7 This application provides a functional unit block diagram of a virtual environment push device. The virtual environment push device 700 includes: an acquisition unit 701, a processing unit 702, and a sending unit 703. Wherein:

[0075] The acquisition unit 701 is used to acquire the current weather information when it detects that the user's virtual pet is in a preset state;

[0076] Processing unit 702 is used to generate a target appearance image corresponding to the virtual pet based on the weather information and the type of the virtual pet;

[0077] Based on the weather information, the weather in the current virtual environment of the virtual pet is adjusted to obtain the target virtual environment;

[0078] The sending unit 703 is used to send the target virtual environment to the user's user terminal so as to display the current virtual environment and the target virtual environment on the same screen on the user terminal, wherein the current virtual environment includes the current appearance image and the target virtual environment includes the target appearance image.

[0079] In some possible implementations, in generating a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet, the processing unit 702 is specifically used for:

[0080] Based on the correspondence between weather information, the types of virtual pets, and the physical characteristics of body parts, determine the physical characteristics of each body part corresponding to the type of virtual pet.

[0081] Obtain pet textures used to generate body features for each body part;

[0082] The pet textures corresponding to each body part are superimposed to obtain the target appearance.

[0083] In some possible implementations, before determining the body characteristics of each body part corresponding to the type of virtual pet based on the correspondence between weather information, the type of virtual pet, and the body characteristics of body parts, the processing unit 702 is further configured to:

[0084] Retrieve weather information for each of the multiple registered users when they adjust the appearance of their virtual pet;

[0085] The virtual pets of the multiple registered users are grouped according to their types, resulting in a variety of virtual pets;

[0086] Obtain multiple candidate registered users corresponding to each virtual pet from among the multiple registered users;

[0087] The weather information when each candidate registered user adjusts the appearance of their virtual pet is used as sample data, and the appearance of the virtual pet after the candidate registered user adjusts it is used as supervision label to construct training samples corresponding to each candidate registered user.

[0088] The model is trained based on the training samples corresponding to each candidate registered user to obtain the correspondence between weather information, types of virtual pets, and physical characteristics of body parts.

[0089] In some possible implementations, in training the model based on training samples corresponding to each candidate registered user to obtain the correspondence between weather information, virtual pet types, and body features of body parts, the processing unit 702 is specifically used for:

[0090] For each candidate registered user under each virtual pet, the training sample is used to predict the features based on the weather information when the candidate registered user under each virtual pet adjusts the virtual pet. This yields the predicted body features of each body part corresponding to the training sample.

[0091] Based on the predicted body features of each body part corresponding to the training sample, and the supervision label of the training sample, determine the loss corresponding to the training sample.

[0092] The model is trained based on the loss corresponding to the training sample until the model converges, thus obtaining the target model corresponding to each virtual pet.

[0093] Each type of weather information is input into the target model corresponding to each virtual pet to predict the physical characteristics of each body part under each virtual pet;

[0094] The correspondence is constructed based on the type of virtual pet and the physical characteristics of each body part of each virtual pet under each weather condition, predicted by the target model corresponding to each virtual pet.

[0095] In some possible implementations, the processing unit 702 is further configured to acquire display information corresponding to the weather information; the sending unit 703 is further configured to send the display information to the user terminal and instruct the user terminal to display the display information in the target virtual environment when the target virtual environment is displayed in full screen.

[0096] In some possible implementations, before generating a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet, the acquisition unit 701 is further configured to acquire the user's current physiological parameters; the processing unit 702 is further configured to determine the user's current mood based on the current physiological parameters; in generating a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet, the processing unit 702 is specifically configured to:

[0097] Based on the weather information, the type of the virtual pet, and the current mood, determine the target appearance of the virtual pet.

[0098] In some possible implementations, the acquisition unit 701 is further configured to receive a query request from the user terminal, the query request including a first historical moment; the processing unit 702 is further configured to: acquire weather information at the first historical moment according to the query request; determine the appearance of the virtual pet at the first historical moment according to the weather information at the first historical moment; and the sending unit 703 is further configured to: send the appearance of the virtual pet at the first historical moment to the user terminal to display the appearance of the virtual pet at the first historical moment on the user terminal, so as to display the user's mood at the first historical moment.

[0099] See Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 8 As shown, the electronic device 800 includes a transceiver 801, a processor 802, and a memory 803. These are connected via a bus 804. The memory 803 stores computer programs and data, and can transfer data stored in the memory 803 to the processor 802.

[0100] Processor 802 is used to read the computer program in memory 803 and perform the following operations:

[0101] When the user's virtual pet is detected to be in a preset state, the current weather information is obtained;

[0102] Based on the weather information and the type of the virtual pet, generate a target appearance image corresponding to the virtual pet;

[0103] Based on the weather information, the weather in the current virtual environment of the virtual pet is adjusted to obtain the target virtual environment;

[0104] The target virtual environment is sent to the user's terminal so that the current virtual environment and the target virtual environment are displayed on the same screen on the user's terminal. The current virtual environment includes the current appearance image, and the target virtual environment includes the target appearance image.

[0105] In some possible implementations, in generating a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet, the processor 802 is specifically configured to perform the following operations:

[0106] Based on the correspondence between weather information, the types of virtual pets, and the physical characteristics of body parts, determine the physical characteristics of each body part corresponding to the type of virtual pet.

[0107] Obtain pet textures used to generate body features for each body part;

[0108] The pet textures corresponding to each body part are superimposed to obtain the target appearance.

[0109] In some possible implementations, before determining the body characteristics of each body part corresponding to the type of virtual pet based on the correspondence between weather information, the type of virtual pet, and the body characteristics of body parts, the processor 802 is further configured to perform the following operations:

[0110] Retrieve weather information for each of the multiple registered users when they adjust the appearance of their virtual pet;

[0111] The virtual pets of the multiple registered users are grouped according to their types, resulting in a variety of virtual pets;

[0112] Obtain multiple candidate registered users corresponding to each virtual pet from among the multiple registered users;

[0113] The weather information when each candidate registered user adjusts the appearance of their virtual pet is used as sample data, and the appearance of the virtual pet after the candidate registered user adjusts it is used as supervision label to construct training samples corresponding to each candidate registered user.

[0114] The model is trained based on the training samples corresponding to each candidate registered user to obtain the correspondence between weather information, types of virtual pets, and physical characteristics of body parts.

[0115] In some possible implementations, in training the model based on training samples corresponding to each candidate registered user to obtain the correspondence between weather information, virtual pet types, and body features of body parts, the processor 802 is specifically configured to perform the following operations:

[0116] For each candidate registered user under each virtual pet, the training sample is used to predict the features based on the weather information when the candidate registered user under each virtual pet adjusts the virtual pet. This yields the predicted body features of each body part corresponding to the training sample.

[0117] Based on the predicted body features of each body part corresponding to the training sample, and the supervision label of the training sample, determine the loss corresponding to the training sample.

[0118] The model is trained based on the loss corresponding to the training sample until the model converges, thus obtaining the target model corresponding to each virtual pet.

[0119] Each type of weather information is input into the target model corresponding to each virtual pet to predict the physical characteristics of each body part under each virtual pet;

[0120] The correspondence is constructed based on the type of virtual pet and the physical characteristics of each body part of each virtual pet under each weather condition, predicted by the target model corresponding to each virtual pet.

[0121] In some possible implementations, the processor 802 is also specifically configured to perform the following operations:

[0122] Obtain display information corresponding to the weather information; send the display information to the user terminal, and instruct the user terminal to display the display information in the target virtual environment when the target virtual environment is displayed in full screen.

[0123] In some possible implementations, before generating a target appearance image corresponding to the virtual pet based on the weather information and the type of the virtual pet, the processor 802 is specifically configured to perform the following operations:

[0124] To acquire the user's current physiological parameters; to determine the user's current mood based on the current physiological parameters; and to generate a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet, the processor 802 is specifically configured to perform the following operations:

[0125] Based on the weather information, the type of the virtual pet, and the current mood, determine the target appearance of the virtual pet.

[0126] In some possible implementations, processor 802 is specifically configured to perform the following operations:

[0127] The system receives a query request from the user terminal, the query request including a first historical moment; based on the query request, it obtains weather information for the first historical moment; based on the weather information for the first historical moment, it determines the appearance of the virtual pet at the first historical moment; and sends the appearance of the virtual pet at the first historical moment to the user terminal to display the appearance of the virtual pet at the first historical moment, thereby displaying the user's mood at the first historical moment.

[0128] Specifically, the transceiver 801 described above can be Figure 7 The virtual environment push device 700 of the embodiment described includes an acquisition unit 701 and a sending unit 703. The processor 802 can be... Figure 7 The processing unit 702 of the virtual environment push device 700 in the embodiment described above.

[0129] It should be understood that the electronic devices, mobile internet devices (MIDs), computer devices, etc. mentioned in this application are included.

[0130] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any of the virtual environment push methods described in the above method embodiments.

[0131] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the virtual environment push methods described in the above method embodiments.

[0132] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0133] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0135] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0136] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0137] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0138] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0139] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for pushing content in a virtual environment, characterized in that, include: When the user's virtual pet is detected to be in a preset state, the current weather information is obtained; Based on the weather information and the type of the virtual pet, a target appearance image corresponding to the virtual pet is generated, including: For each virtual pet, a multi-task model corresponding to each virtual pet is pre-built. The multi-task model includes n third networks, multiple first classification networks, and multiple second classification networks. The first classification networks and second classification networks correspond one-to-one. Each second classification network is used to predict the body features of a body part, and different second classification networks are used to predict the body features of different body parts. The input data consists of weather information from the training samples of each candidate registered user for each virtual pet. Each third network processes the input data to obtain a feature vector corresponding to each third network. Each first classification network classifies the input data to obtain a classification result corresponding to each first classification network, and this classification result is used as the probability of falling into each third network. Based on the classification result of each first classification network, the weights of each third network are determined. Based on the weights of each third network, the feature vectors of each third network are weighted to obtain a weighted result corresponding to each first classification network. This weighted result is used as the input data for the second classification network corresponding to each first classification network. Each second classification network classifies the input data to obtain a classification result corresponding to each second classification network. Based on the classification result of each second classification network, the predicted body features corresponding to each body part of the virtual pet are obtained. Based on the predicted body features of each body part corresponding to the training sample, and the supervision label of the training sample, the loss corresponding to the training sample is determined; the multi-task model is trained based on the loss corresponding to the training sample until the multi-task model converges, and the target model corresponding to each virtual pet is obtained. Each type of weather information is input into the target model corresponding to each virtual pet to predict the physical characteristics of each body part under each virtual pet; Based on the types of virtual pets and the body characteristics of each virtual pet's body parts predicted by the target model corresponding to each virtual pet under each weather information, a correspondence between weather information, types of virtual pets, and body characteristics of body parts is constructed. Based on the correspondence, determine the body features of each body part corresponding to the type of the virtual pet; obtain pet textures for generating the body features of each body part, wherein the body features of the body part are the color of the body part, including: Construct a basic matrix corresponding to the types of virtual pets; Based on the positions of each body part of this type of virtual pet in the base matrix, the values ​​of the positions in the base matrix are set to values ​​corresponding to the basic body features, and filter matrices corresponding to each body part of this type of virtual pet are constructed; the filter matrices corresponding to each body part are multiplied by the base matrix to obtain multiple base matrices corresponding to each body part; based on the multiple base matrices corresponding to each body part, multiple base textures for each body part are obtained. Based on the color mixing principle and the color of each body part of the virtual pet, determine at least one base texture required to synthesize the color; Based on the color mixing principle and the color of the body part, the weight coefficient of each base texture in the at least one base texture is determined; based on the weight coefficient of each base texture, the base matrix corresponding to each base texture is weighted to obtain the target matrix of each base texture; the target matrix of each base texture in the at least one base texture is multiplied to obtain the pet texture corresponding to the body part. The pet textures corresponding to each body part are superimposed to obtain the target appearance; Based on the weather information, the weather in the current virtual environment of the virtual pet is adjusted to obtain the target virtual environment; The target virtual environment is sent to the user's terminal so that the current virtual environment and the target virtual environment are displayed on the same screen on the user terminal. The current virtual environment includes the current appearance, and the target virtual environment includes the target appearance.

2. The method according to claim 1, characterized in that, The method further includes: Retrieve weather information for each of the multiple registered users when they adjust the appearance of their virtual pet; The virtual pets of the multiple registered users are grouped according to their types, resulting in a variety of virtual pets; Obtain multiple candidate registered users corresponding to each virtual pet from among the multiple registered users; The weather information when each candidate registered user adjusts the appearance of their virtual pet is used as sample data, and the appearance of the virtual pet after the candidate registered user adjusts it is used as supervision label to construct training samples corresponding to each candidate registered user. The model is trained based on the training samples corresponding to each candidate registered user to obtain the correspondence between weather information, types of virtual pets, and physical characteristics of body parts.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the display information corresponding to the weather information; The display information is sent to the user terminal, and the user terminal is instructed to display the display information in the target virtual environment when the target virtual environment is displayed in full screen.

4. The method according to claim 1, characterized in that, Before generating a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet, the method further includes: Obtain the user's current physiological parameters; Determine the user's current mood based on the current physiological parameters; The step of generating a target appearance corresponding to the virtual pet based on the weather information and the type of the virtual pet includes: Based on the weather information, the type of the virtual pet, and the current mood, determine the target appearance of the virtual pet.

5. The method according to claim 1, characterized in that, The method further includes: Receive a query request from the user's terminal, the query request including a first historical moment; Based on the query request, obtain the weather information for the first historical moment; Based on the weather information at the first historical moment, determine the appearance of the virtual pet at the first historical moment; The appearance of the virtual pet at the first historical moment is sent to the user terminal so as to display the appearance of the virtual pet at the first historical moment on the user terminal, thereby reflecting the user's mood at the first historical moment.

6. A virtual environment push device, characterized in that, The virtual environment push device is used to perform the method according to any one of claims 1-5, and the virtual environment push device includes: an acquisition unit, a processing unit, and a sending unit; The acquisition unit is used to acquire current weather information when it detects that the user's virtual pet is in a preset state; The processing unit is used to generate a target appearance image corresponding to the virtual pet based on the weather information and the type of the virtual pet; Based on the weather information, the weather in the current virtual environment of the virtual pet is adjusted to obtain the target virtual environment; The sending unit is used to send the target virtual environment to the user's user terminal so that the current virtual environment and the target virtual environment are displayed on the same screen on the user terminal. The current virtual environment includes the current appearance image, and the target virtual environment includes the target appearance image.

7. An electronic device, characterized in that, include: A processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-5.

Images