A method and device for setting the physical condition of a virtual pet based on multiple parameters

Abstract

The embodiments of the present application disclose a method and device for setting the physical condition of a virtual pet based on multiple parameters. The method includes: obtaining the care data information of the virtual pet by a first user and the movement parameter information of the virtual pet, wherein the virtual pet is a pet without physiological characteristics implemented through technology; generating at least one virtual pet disease based on a multi-task learning algorithm according to the care data information of the virtual pet by the first user and the movement parameter information of the virtual pet; marking the at least one virtual pet disease for the virtual pet; and adjusting the appearance or internal structure of the virtual pet according to the marked at least one virtual pet disease. The embodiments of the present application can fill the gap in the technology of virtual pet diseases and make the virtual pet more realistic.

Description

Technical Field

[0001] The present application relates to Internet of Things technology and is applied to fields such as virtual pets. In particular, it relates to a method and device for setting the physical condition of a virtual pet based on multiple parameters. Background Art

[0002] In recent years, with the development of the economy and the continuous improvement of living standards, while people are pursuing a rich material life, they are also seeking different ways of spiritual comfort and sustenance. Raising pets has gradually become one of the ways for people in big cities to seek spiritual comfort and sustenance in recent years. At the same time, the demand for pet companionship is also increasing. However, many people have many inconveniences in raising physical pets or find it troublesome to raise physical pets but still need spiritual sustenance. Therefore, emerging virtual pets have emerged.

[0003] Virtual pets in the virtual world will also become more and more realistic. For example, virtual pets can be born, grow, reproduce, and die just like pets in real life. However, at present, the technology regarding the diseases of virtual pets is still in a blank stage. Summary of the Invention

[0004] The embodiments of the present application provide a method and device for setting the physical condition of a virtual pet based on multiple parameters, which can make up for the blank in the technology of virtual pet diseases, make virtual pets more realistic, enable them to get sick like physical pets, and make the external image of the virtual pet present a state corresponding to the virtual pet disease.

[0005] In a first aspect, the embodiments of the present application provide a method for setting the physical condition of a virtual pet based on multiple parameters, including:

[0006] Obtain the care data information of the virtual pet by a first user and the motion parameter information of the virtual pet, where the virtual pet is a pet without physiological characteristics realized through technology;

[0007] Based on the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, generate at least one virtual pet disease based on a multi-task learning algorithm;

[0008] Mark the at least one virtual pet disease for the virtual pet;

[0009] Adjust the external shape or internal structure of the virtual pet according to the marked at least one virtual pet disease.

[0010] In the current prior art, there is no technology for marking diseases of virtual pets. In this application, after obtaining the care data information of the virtual pet by the first user (such as how much the user cares for the virtual pet and whether the user's care method is appropriate) and the movement parameter information of the virtual pet (such as the movement frequency information, intensity information, and step count information of the virtual pet), based on the multi-task learning algorithm, at least one virtual pet disease is determined (for example, the movement frequency information of the virtual pet is 2 times per week, the intensity information is 2 stars for the exercise intensity, where the highest intensity of the exercise amount is 5 stars, the step count information is that the distance of each exercise does not exceed 2 km, and the user's accompanying time for this virtual pet is too little. Then, various related virtual pet diseases, such as depression and obesity, can be generated according to the above information. Then, according to the preset conditions, it is determined whether the virtual pet meets the conditions of depression and obesity. If it meets, the virtual pet is marked as having depression and obesity. An appearance corresponding to the virtual pet disease can also be set for the virtual pet (for example, if the virtual pet is marked as having obesity, the external image of the virtual pet is adjusted to an image with a thicker waist, a larger face, and an uncoordinated proportion compared to the previous body proportion). Through this application, the gap in virtual pet disease technology can be filled, making the virtual pet more realistic, able to get sick like a physical pet, and making the external image of the virtual pet present a state corresponding to the virtual pet disease.

[0011] In a possible implementation manner, the care data information of the first user for the virtual pet includes one or more of the accompanying duration information of the first user for the virtual pet, the attitude information of the first user towards the virtual pet, and the interaction times information between the first user and the virtual pet;

[0012] The movement parameter information includes one or more of the movement frequency information of the virtual pet, the movement step count information of the virtual pet, the movement intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction times information between the virtual pet and other virtual pets.

[0013] In the above method, the care data information of the virtual pet by the first user can be one or more of the following: the duration of the first user's company with the virtual pet (e.g., the user accompanies the virtual pet at least 3 days a week), the attitude information of the first user towards the virtual pet (e.g., the user loves the virtual pet very much), and the interaction frequency information between the first user and the virtual pet (e.g., the interaction frequency is relatively high after the user returns home). The exercise parameter information can be one or more of the following: the exercise frequency information of the virtual pet, the exercise step information of the virtual pet, the exercise intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction frequency information between the virtual pet and other virtual pets (e.g., the exercise frequency of the virtual pet is 2 times a week, the exercise intensity is 2 stars, the exercise steps are more than 2 km per day for a walk, the normal cycle of the virtual pet is to survive for 3 - 5 years, and the interaction frequency between the virtual pet and other virtual pets is relatively high). Obtaining the care data information of the virtual pet by the first user and the exercise parameter information of the virtual pet provides a prerequisite for generating at least one pet disease based on the above data information.

[0014] In another possible implementation, according to the care data information of the virtual pet by the first user and the exercise parameter information of the virtual pet, generating at least one pet disease based on a multi - task learning algorithm includes:

[0015] Based on the care data information of the virtual pet by the first user and the exercise parameter information of the virtual pet, determining the probability value of each pet disease among multiple pet diseases based on the multi - task learning algorithm;

[0016] Selecting at least one pet disease from the multiple pet diseases whose probability value is greater than a preset threshold.

[0017] In the above method, the probability value of each pet disease among multiple pet diseases can be obtained based on the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet. Then, the probability value of each pet disease among the multiple pet diseases is compared with a preset threshold, and at least one pet disease whose probability value of the pet disease is greater than the preset threshold is selected from the multiple pet diseases. For example, if the motion frequency information of the virtual pet is 2 times per week, the intensity information is 2 stars for the amount of exercise (where the highest intensity of the amount of exercise is 5 stars), the step information is that the distance of each exercise does not exceed 2 km, and the user's company time with the virtual pet is too little, then the probability of generating various related virtual pet diseases marked for the virtual pet can be generated according to the above information. For example, the probability of being marked with depression is 48%, the probability of obesity is 82%, and the probability of arthritis is 46%. Among them, the preset threshold probability is 50%. Since the probability of being marked with obesity among the above virtual pet diseases is greater than the preset threshold, it is determined that the virtual pet is marked with obesity. By determining the probability value of each pet disease among the multiple pet diseases and marking the virtual pet diseases that meet the conditions, the virtual pet can get sick like a physical pet, making it more realistic.

[0018] In yet another possible implementation, it further includes:

[0019] Generating an adjustment plan according to the at least one pet disease, where the adjustment plan is used to indicate the adjustment of the care method and the exercise method;

[0020] Sending the adjustment plan to the first user.

[0021] In the above method, further, according to the marked virtual pet disease, a corresponding adjustment plan can be generated for the virtual pet, and the adjustment plan is sent to the user so that the user can adjust the care method of the virtual pet and the exercise method of the virtual pet. For example, if the virtual pet is marked by the server as suffering from depression, and the server learns that the user's concern for the virtual pet before adjustment is relatively low, and the interaction times between the user and the virtual pet and between the virtual pet and other virtual pets are both relatively few, then the adjustment plan can be to suggest that the user care more about the physical and mental health of the virtual pet and accompany the virtual pet more. Another example is that if the virtual pet is marked by the server as suffering from obesity, and the server learns that the user's exercise task for the virtual pet before adjustment is relatively light, and the number of times, intensity, and steps of the virtual pet's exercise are all relatively few, then the adjustment plan can be to suggest that the user appropriately increase the amount of exercise of the virtual pet. By generating an adjustment plan according to the virtual pet disease, the virtual pet can be like a physical pet, and can be treated after getting sick, making the virtual pet more realistic and improving the user experience.

[0022] In yet another possible implementation, it further includes:

[0023] Collect the new care data information of the virtual pet by the first user and the new motion parameter information of the virtual pet;

[0024] If the new care data information and the new motion parameter information meet the preset conditions, the appearance or internal structure of the virtual pet is restored to the state before adjustment.

[0025] In the above method, after the user adjusts the care mode of the virtual pet and the motion mode of the virtual pet according to the adjustment plan, the server obtains the new care data information of the virtual pet and the new motion parameter information of the virtual pet. If the server detects that the new care data information and the new motion parameter information meet the preset conditions (the preset conditions can be that the new probability value of marking at least one pet disease for the virtual pet is less than the preset threshold), then the appearance or internal structure of the virtual pet is restored to the normal state, and this normal state indicates that the virtual pet is in normal physical condition and is not marked with virtual pet diseases. By generating an adjustment plan to restore the appearance or internal structure of the virtual pet to the original state, the virtual pet can not only be marked with virtual pet diseases, but also the disease can be adjusted to restore the virtual pet to the original state. This solution can improve the user experience.

[0026] In another possible implementation manner, the step of if the new care data information and the new motion parameter information meet the preset conditions, then the appearance or internal structure of the virtual pet is restored to the state before adjustment includes:

[0027] Detect whether the first user adjusts the care mode of the virtual pet or the motion mode of the virtual pet;

[0028] If it is detected that the first user adjusts the care mode of the virtual pet or the motion mode of the virtual pet, then based on the adjusted care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, the probability value of marking the at least one pet disease for the virtual pet is determined again based on the multi-task learning algorithm, and a new probability value of marking the at least one pet disease for the virtual pet is obtained;

[0029] If the new probability value of marking the at least one pet disease for the virtual pet is less than the preset threshold, then an adjustment plan corresponding to the adjusted care data information of the virtual pet by the first user and the motion parameter information of the virtual pet is generated.

[0030] In the above method, if the server detects that the first user adjusts the care method of the virtual pet or the movement method of the virtual pet, then based on the adjusted new care data information and new movement parameter information, the probability value of marking at least one pet disease for the virtual pet is determined again based on the multi-task learning algorithm. If the new probability value of marking the at least one pet disease for the virtual pet is less than the preset threshold, it indicates that this adjustment plan can make the virtual pet return to the state before being marked with the disease. This solution can restore the virtual pet to a disease-free state after being marked with the disease, making the virtual pet as realistic as a physical pet.

[0031] In yet another possible implementation, it further includes:

[0032] Train the care data information of the virtual pet by the first user, the movement parameter information of the virtual pet, and the probability value of marking the at least one pet disease for the virtual pet to obtain a generation model, where the care data information of the virtual pet by the first user and the movement parameter information of the virtual pet are feature information, and the probability value of marking the at least one pet disease for the virtual pet is label information;

[0033] Obtain the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user;

[0034] Input the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user into the generation model to obtain the probability value of marking the at least one pet disease for the virtual pet of the new user.

[0035] In the above method, a training model is obtained by training with a batch of data of the entire process. The obtained training model provides an accurate mapping from the input to the required output. When a new user appears, only the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user need to be obtained, and then the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user are analyzed for features to obtain a feature vector, and this feature vector is input into the training model, without having to execute the entire process again, so as to complete the business assignment for the new user, that is, obtain the probability value of marking at least one pet disease for the virtual pet of the new user. By using the training model, the efficiency of marking the probability value of at least one pet disease for the virtual pet of the new user is improved.

[0036] In a second aspect, an embodiment of the present application provides a device for setting the physical condition of a virtual pet based on multiple parameters. The device includes a selection unit, an acquisition unit, a calculation unit, and an input unit. The device is used to implement the method described in the first aspect or any one of the possible implementation manners of the first aspect.

[0037] It should be noted that the processor included in the device described in the second aspect above can be a processor dedicated to executing these methods (conveniently called a dedicated processor for distinction), or a processor that executes these methods by calling a computer program, such as a general-purpose processor. Optionally, at least one processor may also include both a dedicated processor and a general-purpose processor.

[0038] Optionally, the above computer program may be stored in a memory. Exemplarily, the memory may be a non-transitory memory, such as a Read Only Memory (ROM), which may be integrated with the processor on the same device, or may be separately provided on different devices. The embodiments of the present application do not limit the type of the memory and the setting manner of the memory and the processor.

[0039] In a possible implementation manner, at least one of the above memories is located outside the setting device.

[0040] In another possible implementation manner, at least one of the above memories is located inside the setting device.

[0041] In another possible implementation manner, a part of at least one of the above memories is located inside the setting device, and another part of the memory is located outside the setting device.

[0042] In the present application, the processor and the memory may also be integrated into one device, that is, the processor and the memory may also be integrated together.

[0043] In a third aspect, an embodiment of the present application provides a device for setting the physical condition of a virtual pet based on multiple parameters. The device includes a processor and a memory; a computer program is stored in the memory; when the processor executes the computer program, the computing device executes the method described in any item of the foregoing first or first aspect.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions run on at least one processor, the method described in any item of the foregoing first aspect is implemented.

[0045] In a fifth aspect, the present application provides a computer program product. The computer program product includes computer instructions. When the instructions run on at least one processor, the method described in any item of the foregoing first aspect is implemented. The computer program product may be a software installation package. In the case where the foregoing method needs to be used, the computer program product can be downloaded and executed on a computing device.

[0046] For the technical methods provided in the second to fifth aspects of this application, the beneficial effects can refer to the beneficial effects of the technical solution in the first aspect, and will not be elaborated here. Brief Description of the Drawings

[0047] The following will briefly introduce the drawings required for the description of the embodiments.

[0048] Figure 1 is an application scenario of a virtual pet provided by an embodiment of this application;

[0049] Figure 2 is a schematic structural diagram of a system for setting the physical condition of a virtual pet based on multiple parameters provided by an embodiment of this application;

[0050] Figure 3 is a schematic flowchart of a method for setting the physical condition of a virtual pet based on multiple parameters provided by an embodiment of this application;

[0051] Figure 4 is a schematic diagram of the care data information of a virtual pet and the exercise parameter information of the virtual pet provided by an embodiment of this application;

[0052] Figure 5 is a schematic structural diagram of a device 50 for setting the physical condition of a virtual pet based on multiple parameters provided by an embodiment of this application;

[0053] Figure 6 is a schematic structural diagram of a device 60 for setting the physical condition of a virtual pet based on multiple parameters provided by an embodiment of this application. Detailed Embodiments

[0054] The following describes the embodiments of this application with reference to the drawings in the embodiments of this application. Figure 1 Illustrated is an application scenario of a virtual pet. In Figure 1Among them, the virtual pet can be realized panoramically through virtual reality (VR) technology. Through the 360° lens mode, the user's vision can rotate 360° to see the content, allowing the user to immerse in this environment. The virtual pet generated based on VR technology can be a physical machine, such as a virtual pet that can accompany the user and travel together, or a virtual machine, such as a virtual pet that exists in the server and interacts with the user. It should be noted that this application does not limit the virtual pet to only one possible situation. The application scenario of this application is mainly to transform new technologies into the information model of virtual pets and the corresponding cloud tools, and establish a virtual pet disease setting platform. Based on the multi-objective learning algorithm, this application can generate virtual pet diseases and mark the virtual pets, so that the virtual pets can be as realistic as physical pets. And continuously research and develop a series of application products related to virtual pets, providing intelligent solutions for the upstream and downstream of the industrial chain. The embodiments of this application will focus on the description of the physical condition setting of virtual pets in the following.

[0055] Please refer to Figure 2 , Figure 2 FIG. is a schematic structural diagram of a physical condition setting system for a virtual pet based on multiple parameters provided by an embodiment of this application. This system includes a server 201.

[0056] The server 201 can be a single server or a server cluster composed of multiple servers, specifically it can be a computer or a host computer. The server 201 includes a virtual pet disease setting platform 203, and the virtual pet disease setting platform 203 provides application services for the user device 202.

[0057] The user device 202 is a device with processing capabilities and data transceiver capabilities. The user device 202 can be a computer, a laptop, a tablet computer, a handheld computer, a desktop computer, a diagnostic instrument, a mobile phone, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. In the embodiments of this application, the user device 202 is a virtual pet disease setting application program (APP) 204.

[0058] The user groups corresponding to the users of the user device 202 can be ordinary users, system administrators, and R & D personnel. Among them, ordinary users can include, but are not limited to, people who have virtual pets, people who are interested in virtual pets, or people who already have virtual pets and hope that their virtual pets can have the same physical feeling as real pets. The above-mentioned people can select or design and develop virtual pet disease settings for their virtual pets on the virtual pet disease setting platform 203. The user logs in through the user device 202, uploads the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet to the server 201 through the user device 202, and the user can also receive, through the user device 202, a push message from the virtual pet disease setting platform 203 that marks at least one virtual pet disease for the virtual pet.

[0059] The main function of the virtual pet disease setting platform 203 is to analyze the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet uploaded by the user, or analyze the keywords input by the user, and feedback to the user and display at least one virtual pet disease marked for the virtual pet and the appearance or internal structure of the virtual pet after marking.

[0060] The method of the embodiment of the present application will be introduced in detail below.

[0061] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of a method for setting the physical condition of a virtual pet based on multiple parameters provided by the embodiment of the present application. Optionally, this method can be applied Figure 2 to the

[0062] As Figure 3 the method for setting the physical condition of a virtual pet based on multiple parameters described above includes at least steps S301 to S304.

[0063] Step S301: The server obtains the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet.

[0064] Among them, the care data information of the first user for the virtual pet includes one or more of the accompanying duration information of the first user for the virtual pet, the attitude information of the first user towards the virtual pet, and the interaction times information between the first user and the virtual pet. For example, as Figure 4 shown, Figure 4A schematic diagram of the care data information of a virtual pet and the motion parameter information of the virtual pet provided by an embodiment of the present application. The care data information of user A for his virtual pet can be: Since user A often works overtime and goes home very late, the longest duration for user A to accompany his virtual pet (such as a Papillon) is 2 hours per day. And user A loves the Papillon very much and often interacts with the Papillon as much as possible during the accompanying time. For another example, since user B has a flexible working time and stays at home for a longer time, the longest duration for user B to accompany his virtual pet (such as a British Shorthair Blue) is 5 hours per day. And user B loves the British Shorthair Blue very much and often interacts with the British Shorthair Blue during the accompanying time. For another example, user B prefers his British Shorthair Blue more and has too little accompanying time for the Teddy, with the longest being 2 hours per day. And user B loves the British Shorthair Blue very much and often interacts with the British Shorthair Blue during the accompanying time but does not often interact with his Teddy.

[0065] In addition, the motion parameter information includes one or more of the motion frequency information of the virtual pet, the motion step information of the virtual pet, the motion intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction frequency information between the virtual pet and other virtual pets. For example, still as Figure 4 shown, the motion parameter information of user A's virtual pet (such as a Papillon) can be: the motion frequency is that it goes out for exercise almost every day within a week, the intensity information is that the motion intensity is 3 stars, where the highest motion intensity is 5 stars, and the step information is that the distance of each exercise exceeds 2 km. For another example, the motion parameter information of user B's virtual pet (such as a British Shorthair Blue) can be: the motion frequency is 2 times a week, the intensity information is that the motion intensity is 2 stars, where the highest motion intensity is 5 stars, and the step information is that the distance of each exercise does not exceed 2 km. For another example, the motion parameter information of user B's virtual pet (such as a Teddy) can be: the motion frequency is 2 times a week, the intensity information is that the motion intensity is 1 star, where the highest motion intensity is 5 stars, and the step information is that the distance of each exercise does not exceed 1 km.

[0066] Specifically, there are many sources of the care data information of the first user for the virtual pet and the motion parameter information of the virtual pet. For example, the first user uploads the above data information on the platform. The platform can be an application (APP, Application), a cloud platform, or a web page, etc. The server receives the above data information and can mark and display the above data information on the platform in the form of a tree diagram or a schematic diagram. Still as Figure 4As shown, for example, if user A has 1 virtual pet dog (such as a Papillon), the server marks the care data information of user A for the Papillon and the movement parameter information of the Papillon on the platform. Then, if user B has 1 virtual pet cat (such as a British Shorthair Blue), the server marks the care data information of user B for the British Shorthair Blue and the movement parameter information of the British Shorthair Blue on the platform. Also, if user B has another Teddy dog, the server marks the care information of user B for the Teddy dog and the movement parameter information of the Teddy dog on the platform. The server comprehensively marks the above data information on the platform and outputs a schematic diagram of the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet.

[0067] Step S302: The server generates at least one virtual pet disease based on the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet, using a multi-task learning algorithm.

[0068] It should be noted that the care data information of the first user for the virtual pet can be one or more care data information of the first user for the virtual pet. A first user can have multiple virtual pets. This application does not limit the first user to a specific user, nor does it limit that a first user can only have one virtual pet.

[0069] Specifically, the server first determines the probability value of each virtual pet disease among multiple virtual pet diseases based on the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet, using a multi-task learning algorithm. Then, it selects at least one virtual pet disease whose probability value is greater than a preset threshold from the multiple virtual pet diseases.

[0070] The way to generate at least one virtual pet disease can be elaborated in detail from non-model-based and model-based ways.

[0071] I. Generating at least one virtual pet disease through a non-model-based way:

[0072] The non-modeling method can be that the server first determines the probability value of each virtual pet disease among multiple virtual pet diseases based on the multi-task learning algorithm according to the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet. For example, if the care data information of user A for their virtual pet is that due to user A's frequent overtime and often coming home very late, the longest time user A accompanies their virtual pet (such as a Papillon) is 2 hours per day, and user A loves Papillon 1 very much and often interacts with Papillon as much as possible during the accompanying time. The motion parameter information of user A's virtual pet (such as a Papillon) can be: the exercise frequency is that it goes out for exercise almost every day within a week, the intensity information is an exercise intensity of 3 stars, where the highest exercise intensity is 5 stars, and the step information is that the distance of each exercise exceeds 2 km. Then, the probability value of each virtual pet disease among multiple virtual pet diseases is calculated through the algorithm (such as according to the above information, the probability of marking various related virtual pet diseases for this Papillon can be generated through the algorithm. For example, the probability of marking this Papillon as having depression is 23%, the probability of having obsessive-compulsive disorder is 60%, the probability of having obesity is 36%, and the probability of having arthritis is 73%. Among them, the preset threshold probability is 50%. Since the probabilities of marking arthritis and obsessive-compulsive disorder among the above virtual pet diseases are greater than the preset threshold, it can be determined that this Papillon is marked with arthritis and obsessive-compulsive disorder).

[0073] Again, for example, if the care data information of user B for their virtual pet is that due to user B's free working hours and spending more time at home, user B accompanies their virtual pet (such as a British Shorthair Blue Cat) for up to 5 hours per day, and user B loves the British Shorthair Blue Cat very much and often interacts with the British Shorthair Blue Cat during the accompanying time. The motion parameter information of user B's virtual pet (such as a British Shorthair Blue Cat) can be: the exercise frequency is 2 times a week, the intensity information is an exercise intensity of 2 stars, where the highest exercise intensity is 5 stars, and the step information is that the distance of each exercise does not exceed 2 km. Then, the probability value of each virtual pet disease among multiple virtual pet diseases is calculated through the algorithm (such as according to the above information, the probability of marking various related virtual pet diseases for this British Shorthair Blue Cat can be generated through the algorithm. For example, the probability of marking this British Shorthair Blue Cat as having depression is 48%, the probability of having obesity is 82%, and the probability of having arthritis is 46%. Among them, the preset threshold probability is 50%. Since the probability of marking obesity among the above virtual pet diseases is greater than the preset threshold, it can be determined that this British Shorthair Blue Cat is marked with obesity).

[0074] For another example, User B prefers his British Shorthair Blue Cat more. The time spent with the Teddy dog is too little, with a maximum of 2 hours per day. User B loves the British Shorthair Blue Cat very much and often interacts with it during the accompanying time, but does not often interact with his Teddy dog. The exercise parameter information of User B's virtual pet (such as the Teddy dog) can be: the exercise frequency is 2 times a week, the intensity information is 1 star of exercise intensity (where the highest exercise intensity is 5 stars), and the step information is that the distance of each exercise does not exceed 1 km. Then, the probability value of each virtual pet disease among multiple virtual pet diseases is calculated through an algorithm (for example, according to the above information, the probability of marking various related virtual pet diseases for this Teddy dog can be generated through an algorithm. For example, the probability of marking this Teddy dog with depression is 78%, the probability of obesity is 33%, and the probability of arthritis is 25%. Among them, the preset threshold probability is 50%. Since the probability of depression marked among the above virtual pet diseases is greater than the preset threshold, this Teddy dog can be marked with depression). By determining the probability value of each pet disease among multiple pet diseases and marking the virtual pet diseases that meet the conditions, the virtual pet can get sick like a physical pet, which is more realistic and enables users to have a more real experience of raising virtual pets.

[0075] II. Generating at least one virtual pet disease in a model-based manner:

[0076] Specifically, by training a generation model, the care data information of the first user for the virtual pet and the exercise parameter information of the virtual pet are used as feature information and input into the generation model. According to a specific algorithm, the probability value of each virtual pet disease among multiple virtual pet diseases is determined. Specifically, the care data information of the first user for the virtual pet and the exercise parameter information of the virtual pet can be extracted, and the first feature vector and the second feature vector are respectively generated. The first feature vector and the second feature vector are combined and input into the model, and the mean value of the maximum similarity is obtained to get the target feature vector. Then, the target feature vector is decoded to generate the probability value of each virtual pet disease among multiple virtual pet diseases. Then, the server selects at least one pet disease from multiple pet diseases whose probability value is greater than the preset threshold to obtain the virtual pet disease that finally needs to be marked for the virtual pet.

[0077] Step S303: The server marks at least one virtual pet disease for the virtual pet.

[0078] Specifically, the specific steps for a virtual pet to be marked with at least one virtual pet disease are as follows: After the server selects at least one pet disease with a probability value greater than a preset threshold from multiple pet diseases, it outputs the relevant information of each virtual pet of each user on the platform. This relevant information may include, for example, the self-information of the British Shorthair Blue Cat of user B, and the probability value that this British Shorthair Blue Cat is marked with at least one virtual pet disease. For example, if the probability that the British Shorthair Blue Cat of user B is marked with depression is 48%, the probability of obesity is 82%, and the probability of arthritis is 46%, where the preset threshold probability is 50%. Since the probability of being marked with obesity among the above virtual pet diseases is greater than the preset threshold, obesity can be marked for this British Shorthair Blue Cat. This virtual pet disease can be marked in the setting parameter information of the virtual pet, laying the groundwork for subsequent corresponding adjustments to the appearance or internal structure of the virtual pet according to this virtual pet disease.

[0079] Optionally, after the server marks at least one virtual pet disease for the virtual pet, it can also generate an adjustment plan according to the at least one virtual pet disease. The adjustment plan is used to indicate the adjustment of the care method and exercise method. For example, for the virtual pet disease of the British Shorthair Blue Cat of user B, the main reason for the British Shorthair Blue Cat being marked with obesity is that the exercise frequency is too low and the exercise intensity is too low. Therefore, the server can generate an adjustment plan according to the probability value of obesity marked for the British Shorthair Blue Cat. Specifically, it may include: Since the duration of user B's company with the British Shorthair Blue Cat accounts for a relatively long time in user B's free time, and there are not too many problems with the way user B accompanies the British Shorthair Blue Cat, the server can suggest that user B start from the exercise method of the British Shorthair Blue Cat and adjust the obesity of the British Shorthair Blue Cat by changing its exercise method. For example, user B can take the British Shorthair Blue Cat out for a walk after work every day, such as extending the walking time to 3 hours every day and increasing the exercise intensity to 3 stars, or engaging in entertainment activities such as chasing a frisbee with the British Shorthair Blue Cat in the park or guiding the British Shorthair Blue Cat to exercise with a cat teaser to increase the amount of exercise of the British Shorthair Blue Cat. After the server adjusts the exercise method of the British Shorthair Blue Cat, it sends the generated adjustment plan to user B.

[0080] Step S304: The server adjusts the appearance or internal structure of the virtual pet according to the marked at least one virtual pet disease.

[0081] Specifically, to make the virtual pet more realistic, the server adjusts the appearance or internal structure of the virtual pet according to the virtual pet diseases marked with obsessive-compulsive disorder and arthritis for User A's Papillon, and obesity for User B's British Shorthair Blue Cat. For example, the server can adjust the internal structure of the Papillon according to the marked arthritis and obsessive-compulsive disorder of User A's Papillon. For arthritis, the server can adjust the parameter information of the Papillon and change the structure of the Papillon's leg trunk. For another example, for obsessive-compulsive disorder, the server can change the code operation of the Papillon so that the behaviors shown by the Papillon conform to the characteristics of obsessive-compulsive disorder. The server can also adjust the appearance of User B's British Shorthair Blue Cat according to the marked obesity, such as adjusting the external image of the British Shorthair Blue Cat to an image with a thicker waist, a larger face, and an uncoordinated proportion compared to the previous body proportion, so that the body appearance of the British Shorthair Blue Cat conforms to the characteristics of obesity.

[0082] Optionally, collect new care data information of the virtual pet and new exercise parameter information of the virtual pet from the first user;

[0083] If the new care data information and the new exercise parameter information meet the preset conditions, restore the appearance or internal structure of the virtual pet to the state before adjustment.

[0084] Specifically, it is detected whether the first user adjusts the care method of the virtual pet or the movement method of the virtual pet. If it is detected that the first user adjusts the care method of the virtual pet or the movement method of the virtual pet, then based on the adjusted care data information of the virtual pet by the first user and the movement parameter information of the virtual pet, the probability value of marking at least one virtual pet disease for the virtual pet is determined again based on the multi-task learning algorithm, and a new probability value of marking at least one virtual pet disease for the virtual pet is obtained (for example, the server detects that user A takes the papillon out for a walk after work every day, and user A extends the papillon's walking time to 3 hours every day, and increases the exercise intensity to 3 stars, or user A plays a frisbee chasing activity with the papillon in the park, increasing the papillon's exercise amount). After user A adjusts the movement method of the papillon, the care data information of the papillon by user A and the movement parameter information of the papillon will also change with the adjustment of the papillon's movement method. Then the server can determine the probability value of marking at least one virtual pet disease for the papillon again based on the adjusted care data information of the papillon by user A and the movement parameter information of the papillon, based on the multi-task learning algorithm; if the new probability value of marking at least one virtual pet disease for the papillon is less than the preset threshold (for example, after user A adjusts the movement method of the papillon, the new probability value of marking obesity for the papillon is 37%, the new probability value of marking depression for the papillon is 39%, and the new probability value of marking obsessive-compulsive disorder for the papillon is 30%. At this time, the new probability value of marking at least one virtual pet disease for the papillon is less than the preset threshold probability of 50%, indicating that the physical condition of the papillon has returned to the normal state), then the appearance or internal structure of the papillon is restored to the normal state according to the adjusted care data information of the virtual pet by the first user and the movement parameter information of the virtual pet.

[0085] Optionally, in the above steps of the embodiments of the present application, at least one virtual pet disease has been marked for the virtual pets corresponding to multiple users, but no mention has been made on how to more conveniently mark at least one virtual pet disease for the virtual pet of a new user. To make the process of marking virtual pet diseases for the virtual pets of new users more convenient for subsequent system administrators, a predetermined training algorithm can be used. This training algorithm accepts the input existing user data (such as the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet), and then performs arithmetic training. The result of the arithmetic forms a generation model. This generation model is specifically used to obtain the probability value of marking at least one virtual pet disease for the virtual pet of a new user. The method of establishing a model is used to train the data of multiple users according to the above steps to obtain a generation model. Among them, the care data information of the first user for the virtual pet and the movement parameter information of the virtual pet are feature information, and the probability value of marking at least one pet disease for the virtual pet is label information. Obtain the care data information of the new user for the virtual pet and the movement parameter information of the new user's virtual pet, and then input the obtained care data information of the new user for the virtual pet and the movement parameter information of the new user's virtual pet into the generation model, and the probability value of marking at least one virtual pet disease for the virtual pet of the new user can be obtained. The relevant step processes described above will not be repeated here.

[0086] In the current prior art, there is no technology for marking diseases for virtual pets. After the present application obtains the care data information of the first user for the virtual pet (such as how the user cares for the virtual pet and whether the user's care method is appropriate) and the movement parameter information of the virtual pet (such as the movement frequency information, intensity information, and step information of the virtual pet), at least one virtual pet disease is determined based on a multi-task learning algorithm (such as the movement frequency information of the virtual pet is 2 times per week, the intensity information is 2 stars for the exercise intensity, where the highest intensity of the exercise amount is 5 stars, the step information is that the distance of each exercise does not exceed 2 km, and the user's company time for this virtual pet is too little. Then, various related virtual pet diseases can be generated based on the above information, such as depression and obesity. Then, according to preset conditions, it is determined whether the virtual pet meets the conditions of depression and obesity. If it meets, the virtual pet is marked as having depression and obesity. The external shape corresponding to the virtual pet disease can also be set for the virtual pet (if the virtual pet is marked as having obesity, the external image of the virtual pet is adjusted to an image with a thicker waist, a larger face, and an uncoordinated proportion compared to the previous body proportion). Through the present application, the blank of virtual pet disease technology can be filled, making the virtual pet more realistic, and it can also get sick like a physical pet, and the external image of the virtual pet presents a state corresponding to the virtual pet disease.

[0087] The method of the embodiments of the present application is described in detail above. Next, the devices of the embodiments of the present application are provided.

[0088] It can be understood that for multiple devices provided in the embodiments of the present application, such as a setting device, in order to implement the functions in the above method embodiments, it includes corresponding hardware structures, software modules, or a combination of hardware structures and software structures for executing each function.

[0089] Those skilled in the art should easily realize that, for each example of the units and algorithm steps described in combination with the embodiments disclosed in this article, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different device implementation methods to implement the foregoing method embodiments in different usage scenarios, and different implementation methods of the device should not be considered to exceed the scope of the embodiments of the present application.

[0090] The embodiments of the present application can perform a functional module division on the device. For example, each functional module can be corresponding to each function, or two or more functions can be integrated into one functional module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical functional division. There can be other division methods in actual implementation.

[0091] For example, in the case where the device's various functional modules are divided in an integrated manner, several possible processing devices are exemplified in the embodiments of the present application.

[0092] Please refer to Figure 5 , Figure 5 FIG. is a schematic structural diagram of a device 50 for setting the physical condition of a virtual pet based on multiple parameters provided by an embodiment of the present application. The setting device 50 can be a server or a component in the server, such as a chip, a software module, an integrated circuit, etc. The setting device 50 is used to implement the foregoing method for setting the physical condition of a virtual pet based on multiple parameters, such as Figure 3 the method for setting the physical condition of a virtual pet based on multiple parameters described above.

[0093] In a possible implementation manner, the setting device 50 may include an acquisition unit 501, a generation unit 502, a marking unit 503, and an adjustment unit 504.

[0094] The acquisition unit 501 is used to acquire the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, where the virtual pet is a pet without physiological characteristics implemented through technology;

[0095] The generating unit 502 is configured to generate at least one virtual pet disease based on the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, using a multi-task learning algorithm.

[0096] The marking unit 503 is configured to mark the at least one virtual pet disease for the virtual pet.

[0097] The adjusting unit 504 is configured to adjust the appearance or internal structure of the virtual pet according to the marked at least one virtual pet disease.

[0098] In the current prior art, there is no technology for marking diseases for virtual pets. In this application, after obtaining the care data information of the virtual pet by the first user (such as how much the user cares for the virtual pet and whether the user's care method is appropriate) and the motion parameter information of the virtual pet (such as the number of times the virtual pet moves, the intensity information, the number of steps information), based on the multi-task learning algorithm, at least one virtual pet disease is determined (for example, the number of times the virtual pet moves is 2 times a week, the intensity information is 2 stars for the amount of exercise, where the highest intensity of the amount of exercise is 5 stars, the number of steps information is that the distance of each exercise does not exceed 2 km, and the user's accompanying time for this virtual pet is too little. Then, various related virtual pet diseases, such as depression and obesity, can be generated according to the above information. Then, according to preset conditions, it is determined whether the virtual pet meets the conditions of depression and obesity. If it meets, the virtual pet is marked as having depression and obesity. The appearance corresponding to the virtual pet disease can also be set for the virtual pet (for example, if the virtual pet is marked as having obesity, the external image of the virtual pet is adjusted to an image with a thicker waist, a larger face, and an uncoordinated proportion compared to the previous body proportion). Through this application, the gap in virtual pet disease technology can be filled, making the virtual pet more realistic, being able to get sick like a physical pet, and making the external image of the virtual pet present a state corresponding to the virtual pet disease.

[0099] In another possible implementation manner, the care data information of the virtual pet by the first user includes one or more of the accompanying duration information of the first user for the virtual pet, the attitude information of the first user towards the virtual pet, and the interaction times information between the first user and the virtual pet.

[0100] The motion parameter information includes one or more of the number of times the virtual pet moves, the number of steps the virtual pet moves, the motion intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction times information between the virtual pet and other virtual pets.

[0101] In the embodiment of the present application, the care data information of the first user for the virtual pet may be one or more of the following: the companionship duration information of the first user for the virtual pet (e.g., the user accompanies the virtual pet at least 3 days a week), the attitude information of the first user towards the virtual pet (e.g., the user loves the virtual pet very much), and the interaction times information between the first user and the virtual pet (e.g., the interaction times are relatively high after the user gets home). The motion parameter information may be one or more of the following: the motion times information of the virtual pet, the motion step information of the virtual pet, the motion intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction times information between the virtual pet and other virtual pets (e.g., the motion frequency of the virtual pet is 2 times a week, the motion intensity is 2 stars, the motion steps are more than 2 km per day for walking, the normal cycle of the virtual pet is to survive for 3 - 5 years, and the interaction times between the virtual pet and other virtual pets are relatively high). Obtaining the care data information of the first user for the virtual pet and the motion parameter information of the virtual pet provides a prerequisite for generating at least one pet disease based on the above data information.

[0102] In another possible implementation manner, the determining unit is configured to determine the probability value of each virtual pet disease among multiple virtual pet diseases based on the multi - task learning algorithm according to the care data information of the first user for the virtual pet and the motion parameter information of the virtual pet;

[0103] The selecting unit is configured to select at least one virtual pet disease whose probability value of the virtual pet disease is greater than a preset threshold from the multiple virtual pet diseases.

[0104] In an embodiment of the present application, the probability value of each pet disease among multiple pet diseases can be obtained based on the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet. Then, the probability value of each pet disease among the multiple pet diseases is compared with a preset threshold, and at least one pet disease whose probability value of the pet disease is greater than the preset threshold is selected from the multiple pet diseases. For example, if the motion frequency information of the virtual pet is 2 times per week, the intensity information is 2 stars for the amount of exercise (where the highest intensity of the amount of exercise is 5 stars), the step information is that the distance of each exercise does not exceed 2 km, and the user's accompanying time for the virtual pet is too little, then the probability of marking various related virtual pet diseases for the virtual pet can be generated according to the above information. For example, the probability of being marked with depression is 48%, the probability of obesity is 82%, and the probability of arthritis is 46%. Among them, the preset threshold probability is 50%. Since the probability of being marked with obesity among the above virtual pet diseases is greater than the preset threshold, it is determined that the virtual pet is marked with obesity. By determining the probability value of each pet disease among the multiple pet diseases and marking the virtual pet diseases that meet the conditions, the virtual pet can be made to get sick like a physical pet, making it more realistic.

[0105] In another possible implementation manner, it further includes:

[0106] The generating unit 502 is further configured to generate an adjustment plan according to the at least one virtual pet disease, where the adjustment plan is used to indicate the adjustment of the care method and the exercise method;

[0107] The sending unit is configured to send the adjustment plan to the first user.

[0108] In an embodiment of the present application, further, according to the marked virtual pet disease, a corresponding adjustment plan can be generated for the virtual pet and sent to the user, so that the user can adjust the care method for the virtual pet and the exercise method of the virtual pet. For example, if the virtual pet is marked by the server as suffering from depression, and the server learns that the user's concern for the virtual pet before adjustment is relatively low, and the interaction times between the user and the virtual pet and between the virtual pet and other virtual pets are both relatively few, then the adjustment plan can be to suggest that the user pay more attention to the physical and mental health of the virtual pet and accompany the virtual pet more. Again, if the virtual pet is marked by the server as suffering from obesity, and the server learns that the user's exercise task for the virtual pet before adjustment is relatively light, and the number of times, intensity, and steps of the virtual pet's exercise are all relatively few, then the adjustment plan can be to suggest that the user appropriately increase the amount of exercise of the virtual pet. By generating an adjustment plan according to the virtual pet disease, the virtual pet can be made to be the same as a physical pet, and can be treated after getting sick, making the virtual pet more realistic and improving the user experience.

[0109] In another possible implementation manner, it further includes:

[0110] A collection unit for collecting new care data information of the virtual pet by the first user and new motion parameter information of the virtual pet;

[0111] If the new care data information and the new motion parameter information meet the preset conditions, a restoration unit for restoring the appearance or internal structure of the virtual pet to the state before adjustment.

[0112] In an embodiment of the present application, after the user adjusts the care method of the virtual pet and the motion method of the virtual pet according to the adjustment plan, the server obtains the new care data information of the virtual pet and the new motion parameter information of the virtual pet. If the server detects that the new care data information and the new motion parameter information meet the preset conditions (the preset conditions may be that the new probability value of marking at least one pet disease for the virtual pet is less than the preset threshold), then the appearance or internal structure of the virtual pet is restored to the normal state, and this normal state indicates that the virtual pet is in good health and is not marked with virtual pet diseases. By generating an adjustment plan to restore the appearance or internal structure of the virtual pet to the original state, the virtual pet can not only be marked with virtual pet diseases, but also the disease can be adjusted to restore the virtual pet to the original state. This solution can improve the user experience.

[0113] In another possible implementation manner, a detection unit for detecting whether the first user adjusts the care method of the virtual pet or the motion method of the virtual pet;

[0114] If it is detected that the first user adjusts the care method of the virtual pet or the motion method of the virtual pet, the determination unit is further configured to, based on the adjusted care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, re-determine the probability value of marking the at least one pet disease for the virtual pet based on the multi-task learning algorithm, and obtain a new probability value of marking the at least one pet disease for the virtual pet;

[0115] If the new probability value of marking the at least one pet disease for the virtual pet is less than the preset threshold, the generation unit 502 is further configured to generate a corresponding adjustment plan according to the adjusted care data information of the virtual pet by the first user and the motion parameter information of the virtual pet.

[0116] In an embodiment of the present application, if the server detects that the first user adjusts the care method of the virtual pet or the movement method of the virtual pet, then based on the adjusted new care data information and new movement parameter information, the probability value of marking at least one pet disease for the virtual pet is determined again based on the multi-task learning algorithm. If the new probability value of marking the at least one pet disease for the virtual pet is less than the preset threshold, it indicates that this adjustment plan can make the virtual pet return to the state before being marked with the disease. This solution can restore the virtual pet to a disease-free state after being marked with the disease, making the virtual pet as realistic as a physical pet.

[0117] In another possible implementation manner, it further includes:

[0118] A training unit, configured to train the care data information of the virtual pet by the first user, the movement parameter information of the virtual pet, and the probability value of marking the at least one pet disease for the virtual pet to obtain a generation model, where the care data information of the virtual pet by the first user and the movement parameter information of the virtual pet are feature information, and the probability value of marking the at least one pet disease for the virtual pet is label information;

[0119] The obtaining unit 501 is further configured to obtain the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user;

[0120] An input unit, configured to input the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user into the generation model to obtain the probability value of marking the at least one pet disease for the virtual pet of the new user.

[0121] In an embodiment of the present application, a training model is obtained by training with a batch of data of the entire process. The obtained training model provides an accurate mapping from the input to the required output. When a new user appears, only the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user need to be obtained, and then the care data information of the virtual pet by the new user and the movement parameter information of the virtual pet of the new user are subjected to feature analysis to obtain a feature vector, and the feature vector is input into the training model, without having to execute the entire process again, so as to complete the business allocation for the new user, that is, obtain the probability value of marking at least one pet disease for the virtual pet of the new user. By using the training model, the efficiency of marking the probability value of at least one pet disease for the virtual pet of the new user is improved.

[0122] Please refer to Figure 6 , Figure 6FIG. 0 is a schematic structural diagram of a physical condition setting device 60 for a multi-parameter based virtual pet provided by an embodiment of the present application. The setting device 60 can be a server or a component in a server, such as a chip, a software module, an integrated circuit, etc. The setting device 60 can include at least one processor 601. Optionally, it can further include at least one memory 603. Further optionally, the setting device 60 can further include a communication interface 602. Even more optionally, it can further include a bus 604, wherein the processor 601, the communication interface 602, and the memory 603 are connected through the bus 604.

[0123] Among them, the processor 601 is a module for performing arithmetic operations and / or logical operations, and can specifically be a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor unit (MPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), a coprocessor (assisting the central processing unit to complete corresponding processing and applications), a microcontroller unit (MCU), or a combination of one or more of such processing modules.

[0124] The communication interface 602 can be used to provide information input or output for the at least one processor. And / or, the communication interface 602 can be used to receive data sent externally and / or send data to the outside, and can be a wired link interface including, for example, an Ethernet cable, or a wireless link (Wi-Fi, Bluetooth, general wireless transmission, vehicle short-range communication technology, and other short-range wireless communication technologies, etc.) interface. Optionally, the communication interface 602 can further include a transmitter (such as a radio frequency transmitter, an antenna, etc.) coupled to the interface, or a receiver, etc.

[0125] The memory 603 is used to provide storage space, in which data such as an operating system and computer programs can be stored. The memory 603 can be one or a combination of several of Random Access Memory (RAM), Read-only Memory (ROM), Erasable Programmable Read-only Memory (EPROM), or Compact Disc Read-only Memory (CD-ROM), etc.

[0126] At least one processor 601 in the setting device 60 is used to execute the foregoing methods, such as Figure 3 the methods described in the foregoing embodiments.

[0127] Optionally, the processor 601 can be a processor dedicated to executing these methods (conveniently called a dedicated processor for distinction), or a processor that executes these methods by calling a computer program, such as a general-purpose processor. Optionally, at least one processor can also include both a dedicated processor and a general-purpose processor. Optionally, when the computing device includes at least one processor 601, the above computer program can be stored in the memory 603.

[0128] Optionally, at least one processor 601 in the setting device 60 is used to execute and call computer instructions to perform the following operations:

[0129] Obtain the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, wherein the virtual pet is a pet without physiological characteristics implemented through technology;

[0130] Generate at least one virtual pet disease based on the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, based on a multi-task learning algorithm;

[0131] Mark the at least one virtual pet disease for the virtual pet;

[0132] Adjust the appearance or internal structure of the virtual pet according to the marked at least one virtual pet disease.

[0133] In the current prior art, there is no technology for marking diseases of virtual pets. In this application, after obtaining the care data information of the virtual pet by the first user (such as how the user cares for the virtual pet and whether the user's care method is appropriate) and the movement parameter information of the virtual pet (such as the movement frequency information, intensity information, and step count information of the virtual pet), based on the multi-task learning algorithm, at least one virtual pet disease is determined (for example, the movement frequency information of the virtual pet is 2 times per week, the intensity information is 2 stars for the exercise intensity, where the highest exercise intensity is 5 stars, and the step count information is that the distance of each exercise does not exceed 2 km, and the user's companionship time with this virtual pet is too little. Then, various related virtual pet diseases, such as depression and obesity, can be generated according to the above information. Then, according to the preset conditions, it is determined whether this virtual pet meets the conditions of depression and obesity. If it meets, this virtual pet is marked as having depression and obesity. An appearance corresponding to the virtual pet disease can also be set for this virtual pet (for example, if this virtual pet is marked as having obesity, the external image of this virtual pet is adjusted to an image with a thicker waist, a larger face, and an uncoordinated proportion compared to the previous body proportion). Through this application, the gap in virtual pet disease technology can be filled, making virtual pets more realistic, being able to get sick like physical pets, and making the external image of this virtual pet present a state corresponding to the virtual pet disease.

[0134] Optionally, the care data information of the virtual pet by the first user includes one or more of the companion duration information of the first user with the virtual pet, the attitude information of the first user towards the virtual pet, and the interaction frequency information between the first user and the virtual pet;

[0135] The movement parameter information includes one or more of the movement frequency information of the virtual pet, the movement step count information of the virtual pet, the movement intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction frequency information between the virtual pet and other virtual pets.

[0136] In the embodiments of the present application, the care data information of the virtual pet by the first user may be one or more of the following: the duration of the first user's company with the virtual pet (e.g., the user accompanies the virtual pet at least 3 days a week), the attitude information of the first user towards the virtual pet (e.g., the user loves the virtual pet very much), and the number of interactions between the first user and the virtual pet (e.g., the number of interactions is relatively large after the user returns home). The exercise parameter information may be one or more of the following: the number of exercise times of the virtual pet, the number of exercise steps of the virtual pet, the exercise intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the number of interactions between the virtual pet and other virtual pets (e.g., the exercise frequency of the virtual pet is 2 times a week, the exercise intensity is 2 stars, the number of exercise steps is more than 2 km per day for walking, the normal cycle of the virtual pet is to survive for 3 - 5 years, and the number of interactions between the virtual pet and other virtual pets is relatively large). Obtaining the care data information of the virtual pet by the first user and the exercise parameter information of the virtual pet provides a prerequisite for generating at least one pet disease based on the above data information.

[0137] Optionally, the processor 601 is further configured to:

[0138] Based on the care data information of the virtual pet by the first user and the exercise parameter information of the virtual pet, determine the probability value of each pet disease among multiple pet diseases based on the multi - task learning algorithm;

[0139] Select at least one pet disease from the multiple pet diseases whose probability value of the pet disease is greater than a preset threshold.

[0140] In the embodiments of the present application, the probability value of each pet disease among multiple pet diseases can be obtained according to the care data information of the virtual pet by the first user and the exercise parameter information of the virtual pet, and then the probability value of each pet disease among the multiple pet diseases is compared with the preset threshold, and at least one pet disease whose probability value of the pet disease is greater than the preset threshold is selected from the multiple pet diseases. For example, if the exercise frequency of the virtual pet in the number of exercise times information is 2 times a week, the intensity information is 2 stars for the exercise intensity (where the highest exercise intensity is 5 stars), the number of steps information is that the distance of each exercise does not exceed 2 km, and the user's company time with the virtual pet is too little, then the probability of marking various related virtual pet diseases for the virtual pet can be generated according to the above information. For example, the probability of being marked with depression is 48%, the probability of obesity is 82%, and the probability of arthritis is 46%. Among them, the preset threshold probability is 50%. Since the probability of being marked with obesity among the above virtual pet diseases is greater than the preset threshold, it is determined that the virtual pet is marked with obesity. By determining the probability value of each pet disease among multiple pet diseases and marking the virtual pet diseases that meet the conditions, the virtual pet can be made to get sick like a real pet, making it more realistic.

[0141] Optionally, the processor 601 is further configured to:

[0142] Generate an adjustment plan according to the at least one pet disease, where the adjustment plan is used to indicate the adjustment of the care method and the exercise method;

[0143] Send the adjustment plan to the first user.

[0144] In the embodiments of the present application, further, according to the marked virtual pet diseases, corresponding adjustment plans can be generated for the virtual pets, and the adjustment plans are sent to the users, so that the users can also adjust the care method of the virtual pets and the exercise method of the virtual pets. If the virtual pet is marked by the server as suffering from depression, the server learns that the user's concern for the virtual pet before adjustment is relatively low, and the interaction times between the user and the virtual pet and between the virtual pet and other virtual pets are relatively few, then the adjustment plan can be to suggest that the user pay more attention to the physical and mental health of the virtual pet and accompany the virtual pet more. If the virtual pet is marked by the server as suffering from obesity, the server learns that the exercise task of the virtual pet by the user before adjustment is relatively light, and the exercise times, intensity, and steps of the virtual pet are relatively few, then the adjustment plan can be to suggest that the user appropriately increase the exercise amount of the virtual pet. By generating an adjustment plan according to the virtual pet diseases, the virtual pet can be treated when it is sick like a physical pet, making the virtual pet more realistic and improving the user experience.

[0145] Optionally, the processor 601 is further configured to:

[0146] Collect new care data information of the first user for the virtual pet and new exercise parameter information of the virtual pet;

[0147] If the new care data information and the new exercise parameter information meet the preset conditions, the appearance or internal structure of the virtual pet is restored to the state before adjustment.

[0148] In an embodiment of the present application, after the user adjusts the virtual pet care method and the virtual pet's movement method according to the adjustment plan, the server obtains the new care data information of the virtual pet and the new movement parameter information of the virtual pet. If the server detects that the new care data information and the new movement parameter information meet the preset conditions (the preset conditions may require that the new probability value of marking at least one pet disease for the virtual pet is less than the preset threshold), then the appearance or internal structure of the virtual pet is restored to the normal state, and this normal state indicates that the virtual pet is in good health and is not marked with virtual pet diseases. By generating an adjustment plan and restoring the appearance or internal structure of the virtual pet to the original state, the virtual pet can not only be marked with virtual pet diseases, but also adjust the disease to restore the virtual pet to the original state. This solution can improve the user experience.

[0149] Optionally, the processor 601 is further configured to:

[0150] Detect whether the first user adjusts the virtual pet care method or the virtual pet's movement method;

[0151] If it is detected that the first user adjusts the virtual pet care method or the virtual pet's movement method, then based on the adjusted care data information of the virtual pet and the movement parameter information of the virtual pet by the first user, the probability value of marking the at least one pet disease for the virtual pet is determined again based on the multi-task learning algorithm, and a new probability value of marking the at least one pet disease for the virtual pet is obtained;

[0152] If the new probability value of marking the at least one pet disease for the virtual pet is less than the preset threshold, then an adjustment plan corresponding to the adjusted care data information of the virtual pet and the movement parameter information of the virtual pet by the first user is generated.

[0153] In an embodiment of the present application, if the server detects that the first user adjusts the virtual pet care method or the virtual pet's movement method, then based on the adjusted new care data information and new movement parameter information, the probability value of marking at least one pet disease for the virtual pet is determined again based on the multi-task learning algorithm. If the new probability value of marking the at least one pet disease for the virtual pet is less than the preset threshold, it indicates that this adjustment plan can restore the virtual pet to the state before being marked with the disease. This solution can restore the virtual pet to a disease-free state after being marked with the disease, making the virtual pet as realistic as a physical pet.

[0154] Optionally, the processor 601 is further configured to:

[0155] Training the first user's care data information on the virtual pet, the motion parameter information of the virtual pet, and the probability value of marking the at least one pet disease for the virtual pet to obtain a generation model, wherein the first user's care data information on the virtual pet and the motion parameter information of the virtual pet are feature information, and the probability value of marking the at least one pet disease for the virtual pet is label information;

[0156] Acquire the care data information of the new user for the virtual pet and the motion parameter information of the new user's virtual pet;

[0157] The care data information of the new user on the virtual pet and the motion parameter information of the new user's virtual pet are input into the generation model to obtain a probability value of marking the at least one pet disease for the new user's virtual pet.

[0158] In an embodiment of the present application, a training model is obtained by obtaining a batch of data of the entire process for training, and the obtained training model provides an accurate mapping from input to required output. When a new user appears, it is only necessary to obtain the new user's care data information for the virtual pet and the motion parameter information of the new user's virtual pet, and then perform feature analysis on the new user's care data information for the virtual pet and the motion parameter information of the new user's virtual pet to obtain a feature vector, which is input into the training model without having to re-execute the entire process, and the service allocation for the new user can be completed, that is, the probability value of marking at least one pet disease for the new user's virtual pet is obtained. The use of the training model improves the efficiency of marking at least one pet disease for the new user's virtual pet.

[0159] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on at least one processor, the aforementioned method for setting the physical condition of a virtual pet based on multiple parameters is implemented, for example Figure 3 The method described.

[0160] The present application also provides a computer program product, which includes computer instructions, and when executed by a computing device, implements the aforementioned method for setting the physical condition of a virtual pet based on multiple parameters, such as Figure 3 The method described.

[0161] In the embodiments of the present application, the words "for example" or "such as" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "such as" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the words "for example" or "such as" is intended to present related concepts in a specific way.

[0162] As used in the embodiments of this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or a similar expression means any combination of these items, including any combination of single item(s) or plural item(s). For example, at least one of a, b, or c can represent: a, b, c, (a and b), (a and c), (b and c), or (a and b and c), where a, b, and c can be single or multiple. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0163] Moreover, unless otherwise stated, the ordinal numbers such as "first" and "second" used in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, time sequence, priority, or importance of multiple objects. For example, the first device and the second device are only for ease of description and do not indicate differences in the structure, importance, etc. of the first device and the second device. In some embodiments, the first device and the second device can also be the same device.

[0164] As used in the above embodiments, depending on the context, the term "when..." can be interpreted to mean "if...", "after...", "in response to determining...", or "in response to detecting...". The above are only optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the concept and principle of this application should be included in the protection scope of this application.

[0165] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware or can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc.

[0166] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of various equivalent modifications or replacements, and these modifications or replacements should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for setting the physical condition of a virtual pet based on multiple parameters, characterized in that, The method includes: Obtaining the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, where the virtual pet is a pet without physiological characteristics implemented through technology, and the care data information of the virtual pet by the first user includes one or more of the companion duration information of the first user for the virtual pet, the attitude information of the first user towards the virtual pet, and the interaction times information between the first user and the virtual pet, and the motion parameter information includes one or more of the motion times information of the virtual pet, the motion step information of the virtual pet, the motion intensity information of the virtual pet, the online duration information of the virtual pet, the life cycle information of the virtual pet, and the interaction times information between the virtual pet and other virtual pets; Generating at least one virtual pet disease based on the multi-task learning algorithm according to the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet; Marking the at least one virtual pet disease for the virtual pet; Adjusting the appearance or internal structure of the virtual pet according to the marked at least one virtual pet disease; The generating at least one pet disease based on the multi-task learning algorithm according to the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet includes: Determining the probability value of each virtual pet disease in a plurality of virtual pet diseases based on the multi-task learning algorithm according to the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet; Selecting at least one virtual pet disease from the plurality of virtual pet diseases whose probability value of the virtual pet disease is greater than a preset threshold.

2. The method according to claim 1, wherein It further includes: Generating an adjustment plan according to the at least one virtual pet disease, where the adjustment plan is used to indicate the adjustment of the care method and the motion method; Sending the adjustment plan to the first user.

3. The method according to claim 2, wherein It further includes: Collecting the new care data information of the virtual pet by the first user and the new motion parameter information of the virtual pet; If the new care data information and the new motion parameter information meet the preset conditions, restoring the appearance or internal structure of the virtual pet to the state before adjustment.

4. The method according to any one of claims 1 to 3, characterized in that It further includes: Training the care data information of the virtual pet by the first user, the motion parameter information of the virtual pet, and the probability value of marking the at least one pet disease for the virtual pet to obtain a generation model, where the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet are feature information, and the probability value of marking the at least one pet disease for the virtual pet is label information; Obtaining the care data information of the virtual pet by the new user and the motion parameter information of the virtual pet of the new user; Inputting the care data information of the virtual pet by the new user and the motion parameter information of the virtual pet of the new user into the generation model to obtain the probability value of marking the at least one virtual pet disease for the virtual pet of the new user.

5. A body condition setting device for a virtual pet based on multiple parameters, which is used to implement the method described in any one of claims 1-4, characterized in that, It includes an acquisition unit, a generation unit, a marking unit and an adjustment unit, where: The acquisition unit is configured to acquire the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet, where the virtual pet is a pet without physiological characteristics implemented through technology; The generation unit is configured to generate at least one virtual pet disease based on the multi-task learning algorithm according to the care data information of the virtual pet by the first user and the motion parameter information of the virtual pet; The marking unit is configured to mark the at least one virtual pet disease for the virtual pet; The adjustment unit is configured to adjust the appearance or internal structure of the virtual pet according to the marked at least one virtual pet disease.

6. A device for setting the physical condition of a virtual pet based on multiple parameters, characterized in that, The device includes a processor and a memory, the memory is used to store computer instructions, and the processor is used to call the computer instructions to implement the method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, Instructions are stored in the computer-readable storage medium, and when the instructions are run on at least one processor, the method according to any one of claims 1-4 is implemented.

Images