CN115079979A

CN115079979A - Virtual character driving method, device, equipment and storage medium

Info

Publication number: CN115079979A
Application number: CN202210692273.1A
Authority: CN
Inventors: 雷凯翔
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2022-06-17
Filing date: 2022-06-17
Publication date: 2022-09-20

Abstract

The embodiment of the disclosure provides a virtual role driving method, a virtual role driving device, virtual role driving equipment and a storage medium, wherein the method comprises the following steps: analyzing the current action of the target object to obtain a first driving data packet of the current action in a first fusion deformation form; according to a predetermined data conversion configuration file, carrying out format conversion on the drive data in the first drive data packet to obtain a second drive data packet in a second fusion deformation form; and driving the virtual role model to present the current action according to the driving data in the second driving data packet so as to perform virtual simulation of the action on the target object. By utilizing the method, the driving data packet which is matched with the virtual character model in a fusion deformation form can be obtained through the added format conversion operation, and the consistency of actions of the virtual character and the target object can be ensured through virtual character driving performed through the matched driving data packet, so that the simulation effect of the virtual character on the target object is improved, and the user experience of virtual character simulation is enhanced.

Description

Virtual character driving method, device, equipment and storage medium

Technical Field

The disclosed embodiments relate to the field of virtual character technologies, and in particular, to a virtual character driving method, device, apparatus, and storage medium.

Background

The narrow definition of digital human can be regarded as a product of the fusion of information science and life science, which can be abstractly understood as a virtual character. In practical application, the virtual roles can be utilized through an information science means to perform virtual simulation on the entity objects on different levels of morphology and functions.

At present, the development of virtual characters enters a rapid growth stage, and the virtual characters can be applied to various different scenes with virtual character requirements, such as live broadcast scenes, short video scenes, game industries and the like. In a scenario in which a virtual character is introduced to perform virtual simulation, a virtual character model is often constructed. Then, when the physical object is virtually simulated in shape or function, the constructed virtual character is rendered on the display, and the initially rendered virtual character is static. The virtual character may then be driven by the drive data formed against the physical object actions, thereby enabling the virtual character rendered on the display to mimic the physical object as a corresponding action.

In the prior art, in the implementation of driving a virtual character to perform virtual simulation, the situation that the fusion deformation form adopted by an entity object and the virtual character is different exists, and the situation can cause the problem that the virtual character cannot be normally driven by the driving data captured based on the entity object, so that the virtual simulation effect of the virtual character is influenced.

Disclosure of Invention

The present disclosure provides a virtual role driving method, device, equipment, and storage medium, so as to implement effective simulation of an action of an entity object by a virtual role under the condition that fusion deformation forms corresponding to the entity object and the virtual role are different.

In a first aspect, an embodiment of the present disclosure provides a virtual character driving method, where the method includes:

analyzing the current action of the target object to obtain a first driving data packet of the current action in a first fusion deformation form;

according to a predetermined data conversion configuration file, carrying out format conversion on the drive data in the first drive data packet to obtain a second drive data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information for converting the drive data format;

and driving a virtual role model to present a virtual action corresponding to the current action according to the driving data in the second driving data packet, wherein the virtual role model is constructed in the second fusion deformation form.

In a second aspect, an embodiment of the present disclosure further provides a virtual character driving apparatus, including:

the first driving determining module is used for analyzing the current action of the target object and obtaining a first driving data packet of the current action in a first fusion deformation form;

the second driving determining module is used for performing format conversion on driving data in the first driving data packet according to a predetermined data conversion configuration file to obtain a second driving data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information used for converting the driving data format;

and the driving execution module is used for driving a virtual role model to present a virtual action corresponding to the current action according to the driving data in the second driving data packet, wherein the virtual role model is constructed in the second fusion deformation form.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when the one or more programs are executed by the one or more processors, the one or more processors implement the virtual role driving method provided in the first aspect of the embodiments of the present disclosure.

In a fourth aspect, the embodiments of the present disclosure also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are used to execute a virtual role driving method provided by implementing the first aspect of the embodiments of the present disclosure.

The embodiment of the disclosure provides a virtual role driving method, a virtual role driving device and a storage medium, wherein the method comprises the following steps: the method comprises the steps of firstly analyzing the current action of a target object, obtaining a first driving data packet of the current action in a first fusion deformation form, then carrying out format conversion on driving data in the first driving data packet according to a predetermined data conversion configuration file, and obtaining a second driving data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information for converting the driving data format. And finally, driving a virtual role model to present the current action according to the driving data in the second driving data packet so as to perform virtual simulation of the action on the target object, wherein the virtual role model is constructed in the second fusion deformation form. According to the technical scheme, before virtual role driving is carried out through the driving data packet, format conversion operation of driving data in the driving data packet is added, and the driving data packet which is matched with the constructed virtual role model in a fusion deformation mode can be obtained through the added format conversion operation. And virtual role driving is carried out through the matched driving data packet, so that the consistency of the action presented by the virtual role and the action made by the entity object user is ensured, the simulation reality and the accuracy of the virtual role are enhanced, the simulation effect of the virtual role on the entity object is effectively improved, and the user experience of virtual role simulation is improved.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1 is a schematic flowchart of a virtual role driving method according to an embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of a virtual character driving apparatus according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "target", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

It is understood that before the technical solutions disclosed in the embodiments of the present disclosure are used, the type, the use range, the use scene, etc. of the personal information related to the present disclosure should be informed to the user and obtain the authorization of the user through a proper manner according to the relevant laws and regulations.

For example, in response to receiving an active request from a user, a prompt message is sent to the user to explicitly prompt the user that the requested operation to be performed would require the acquisition and use of personal information to the user. Thus, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operations of the disclosed technical solution, according to the prompt information.

As an optional but non-limiting implementation manner, in response to receiving an active request from the user, the manner of sending the prompt information to the user may be, for example, a pop-up window, and the prompt information may be presented in a text manner in the pop-up window. In addition, a selection control for providing personal information to the electronic device by the user's selection of "agreeing" or "disagreeing" can be carried in the pop-up window.

It is understood that the above notification and user authorization process is only illustrative and not limiting, and other ways of satisfying relevant laws and regulations may be applied to the implementation of the present disclosure.

Fig. 1 is a flowchart of a virtual role driving method provided in an embodiment of the present disclosure, where the embodiment of the present disclosure is applicable to a situation of driving a virtual role in virtual simulation implementation of an entity object, and the method may be executed by a virtual role driving apparatus, the apparatus may be implemented in a form of software and/or hardware, and optionally, may be implemented by using an electronic device as an execution terminal, and the electronic device may be a mobile terminal, a PC terminal, a server, or the like.

It should be noted that one of the application scenarios of the virtual character driving method provided in this embodiment may be described as follows: in a live broadcast application, a live broadcast user can select a pre-constructed virtual character model as a virtual anchor. By the virtual role driving method provided by the embodiment, the virtual anchor can simulate the anchor user, that is, the anchor user can do an action, the virtual anchor can also do the action and display the action on the screen, and the virtual anchor can effectively simulate the anchor user.

In addition, the virtual role driving method provided in this embodiment may be used as a plug-in application software with a virtual simulation function, and is used to implement simulation of a target object by a virtual role. In terms of bottom-layer technical support, the embodiment needs to perform three-dimensional modeling on the target object, so that the target object is represented by a three-dimensional model, and on this basis, the action made by the target object can be represented by data values of deformation parameters included in a fusion deformation form. Similarly, the virtual role for performing virtual simulation on the virtual user also needs to be modeled in advance, and the attribute data values are different after modeling, so that the virtual role can present different characteristics. And a fusion deformation model on which action driving depends is also set for the virtual role in advance, and generally, the fusion deformation model is designed to be different from the fusion deformation form adopted for performing deformation representation on the target object.

As shown in fig. 1, a virtual character driving method provided in the embodiment of the present disclosure specifically includes operations of:

s110, analyzing the current action of the target object, and obtaining a first driving data packet of the current action in a first fusion deformation form.

In this embodiment, it can be considered that each step in this embodiment can be executed in real time as long as the function of the virtual simulation is started. The target object may be regarded as a physical object to be virtually simulated in the present embodiment, the physical object may be a real human being, an animal, a doll model in a real scene, and the like, and the current motion of the target object may be regarded as a motion made by the target object at the current execution time. The first driving data packet may be considered as a data packet including a plurality of driving data, and each driving data may be understood as deformation data of a relevant deformation parameter when each key portion of the target object deforms when the target object performs the current motion. And the characteristic form of the driving data included in the first driving data packet is determined by a first fusion deformation form adopted in advance, and different first fusion deformation forms can have different deformation parameters, so that one action has different representation forms.

It should be noted that the first fusion deformation and the second fusion deformation appearing in this embodiment may be considered as a fusion deformation blendshape model used for representing motion changes of a three-dimensional object in the three-dimensional object construction, and the fusion deformation blendshape model has different expression forms according to different design styles. In this embodiment, the first fusion deformation form and the second fusion deformation form may be regarded as two different expression forms of the fusion deformation blendshape model in different design styles.

In this embodiment, for a target object, the target object may correspond to a pre-constructed three-dimensional model, static characteristics of the target object may be determined through mesh data in the three-dimensional model, and after an action is made by the target object, the static characteristics may be analyzed through a corresponding action-driven algorithm, and finally, a deformation generated when the target object makes an action is represented in a fusion deformation form matched with the algorithm.

In this embodiment, different fusion deformation forms may be adopted when analyzing the motion of the target object, and different deformation parameters for characterizing the motion of the target object in different fusion deformation forms are different, so that the obtained driving data packets are different. In this embodiment, the fusion deformation form used for analyzing the current action is denoted as a first fusion deformation form, and the driving data packet formed in the first fusion deformation form with respect to the current action is denoted as a first driving data packet. In this step, the current action may be analyzed through an algorithm, and the deformation of the current action is recorded in a first fusion deformation form matched with the algorithm, so as to form a driving data packet, and the driving data packet is recorded as a first driving data packet.

For example, a first fusion deformation form used for analyzing the current action may include 52 deformation parameters, after the analysis is completed, one deformation data may be obtained for some or all of the 52 deformation parameters, and the obtained deformation data is recorded as driving data, and a first driving data packet of the current action may be formed based on the determined driving data. Among them, this example shows some deformation parameters of 52 deformation parameters, such as downward bDl for left eyebrow, downward bDr for right eyebrow, upward bIu for brow root, upward bOl for left brow tail, and upward bOr for right brow tail.

And S120, according to a predetermined data conversion configuration file, performing format conversion on the drive data in the first drive data packet to obtain a second drive data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information for converting the drive data format.

In this embodiment, this step specifically implements the transformation of a drive packet representing an action from one form to another. And the transformation of the characterization form of the drive data packet is mainly formed based on a predetermined data transformation profile.

It can be understood that the fusion form for representing the motion of the target object is different from the fusion deformation form for driving the virtual character to present the dynamic motion in design. It can be known that, after a first driving data packet corresponding to one motion of a target object is determined, if a virtual character is to make the same motion as the target object, the virtual character needs to be driven by driving data, and it needs to be considered that the driving data for driving the virtual character matches a pre-designed fusion deformation form. Therefore, format conversion needs to be performed on the first data packet corresponding to the current action under the first fusion transformation through the step.

In this embodiment, the fusion deformation form used for driving the virtual role model is denoted as a second fusion deformation form, and the corresponding driving data packet in the second fusion deformation form is denoted as a second driving data packet. In this embodiment, the digital conversion configuration file for format conversion of the first driving data packet includes conversion mapping information, and the conversion mapping information preferably includes a plurality of mapping relations.

For example, unlike the first fusion deformation form including 52 deformation parameters, the second fusion deformation form set relative to the virtual character may include only 17 deformation parameters, for example, some of the 17 deformation parameters are: happy J, sad S, surprised U, happy F, angry A, blinking B, etc. Referring to the above description of the deformation parameters under the first fusion deformation form, it can be seen that the deformation parameters included under the second fusion deformation form are completely different from the characterization form of the deformation parameters included under the first fusion deformation form.

The process of implementing the driving data packet conversion by converting the mapping information in this step can be described as follows: firstly, determining which second deformation parameters are possessed under the second fusion deformation form and which first deformation parameters are possessed under the first fusion deformation form; by converting the fusion information, a matching mapping relation can be found for the second deformation parameters, wherein some first deformation parameters related to the second deformation parameters are given in the mapping relation, and the mapping relation is formed by the first deformation parameters and the second deformation parameters.

As described above, on the premise that the driving data corresponding to the first deformation parameters are known, the driving data corresponding to the second deformation parameters can be determined by combining the mapping relationship between the first deformation parameters and the second deformation parameters, and the driving data can be recorded as the second driving data. In this way, the determination of the second driving data may be performed for some or all of the second deformation parameters in the second fusion deformation form, thereby obtaining a second driving data packet constituted by the determined second driving data.

S130, according to the driving data in the second driving data packet, driving a virtual role model to present a virtual action corresponding to the current action, wherein the virtual role model is constructed in the second fusion deformation form.

It can be known that the virtual character model for the virtual simulation of the target object is pre-constructed, and the data for determining the change of the action form of the virtual character model can be represented by the deformation parameters pre-designed for the virtual character model, and the deformation parameters adopted by the virtual character model in this embodiment have the second fusion deformation form.

In this embodiment, the second driving data packet in the second fusion deformation form is obtained through the above steps, and conforms to the second fusion deformation form adopted by the virtual character model, in this step, the virtual character model can be driven to make a virtual motion through the driving data in the second driving data packet, where the motion form represented by the virtual motion is similar to the expression form of the current motion made by the target object, so that the virtual simulation of the motion made by the virtual character model on the target object is realized.

In the virtual role driving method provided in this embodiment, before virtual role driving is performed through a driving data packet, format conversion operation of driving data in the driving data packet is added, and through the added format conversion operation, a driving data packet in which a fusion deformation form is matched with a constructed virtual role model can be obtained. And virtual role driving is carried out through the matched driving data packet, so that the consistency of the actions presented by the virtual roles and the actions made by the entity object user is ensured, the simulation authenticity and accuracy of the virtual roles are enhanced, the simulation effect of the virtual roles on the entity object is effectively improved, and the user experience of virtual role simulation is improved.

As a first optional embodiment of this embodiment, on the basis of the above embodiment, the first optional embodiment is to analyze the current action of the target object, and obtain the first driving data packet of the current action in the first fusion deformation form, and specifically:

a1) acquiring a current motion image of the target object, wherein the current motion image is obtained by capturing the target object by an image capturing device.

In the present embodiment, the target object can optionally make various emotional motions, and the emotional motions made by the target object can be captured by the image capturing device and form a motion image containing the motions of the target object. This step can acquire a current motion image formed after the image capturing device captures the motion made by the target object at the current time.

b1) And analyzing the current motion image through a set motion capture driving algorithm to obtain driving data corresponding to the first deformation parameter in the first fusion deformation form.

In this embodiment, a motion capture driving algorithm set at the bottom layer may be called to determine, for the target object, deformation data corresponding to each first deformation parameter in the first fusion deformation form, which is recorded as driving data corresponding to the first deformation parameter in this embodiment.

For the implementation of this step, it can be specifically described as: firstly, feature analysis can be carried out on a current action image to determine position information of each key part of a target object at the current execution time, then, the change of each key part on the position can be determined by combining the position information of each key part of the target object at the previous execution time, and an action capture driving algorithm can represent the position change condition of each key part by using driving data of each first deformation parameter contained in a first fusion deformation form, so that driving data corresponding to each first deformation parameter in the first fusion deformation form can be obtained.

c1) And forming a first driving data packet of the current action based on the driving data of the first deformation parameter.

In this embodiment, after determining the driving data of each first deformation parameter through the above steps, the step may summarize each driving data, so as to obtain a first driving data packet representing the current action of the target object.

The above alternative embodiment of this embodiment provides a specific determination process for the first driving data packet, and provides basic data for the subsequent conversion from the first driving data packet to the second driving data packet.

As a second optional embodiment of this embodiment, on the basis of the foregoing embodiment, the format conversion may be performed on the drive data in the first drive data packet according to a predetermined data conversion configuration file, and the obtaining of the second drive data packet in the second fusion deformation form may be embodied as:

a2) and searching the data conversion configuration file to obtain conversion mapping information corresponding to the second fusion deformation form.

In this embodiment, a plurality of second fusion deformation forms may exist in relation to the virtual character model design, and thus the data conversion configuration file may include conversion mapping information of the plurality of second fusion deformation forms. The step may preferentially find the conversion mapping information corresponding to the second fusion deformation form adopted in this embodiment.

For example, in the data conversion configuration file, different second fusion deformation forms may have different deformation form identifiers, and after knowing that the deformation form identifier of the second fusion deformation form is adopted in this embodiment, the relevant conversion mapping information may be found correspondingly. The conversion mapping information may include a mapping relationship between each second deformation parameter in the second fusion deformation form and the first deformation parameter in the first fusion deformation form.

b2) And determining second driving data of a second deformation parameter in the second fusion deformation form according to the driving data of the first deformation parameter in the first driving data packet and by combining the conversion mapping information.

As described above, it can be known that the conversion mapping information includes a mapping relation between each second deformation parameter and each first deformation parameter, and the mapping relation represents an association relation between the second deformation parameter and the associated deformation parameter associated in the first deformation form.

In this step, second driving data of the second deformation parameter may be determined by using driving data corresponding to part or all of the first deformation parameters in the first driving data packet obtained in advance, and by using an association relationship between the second deformation parameter in the mapping relationship and each associated deformation parameter (from the first deformation parameter in the first fusion deformation form).

c2) And forming a second driving data packet according to the second driving data of the second deformation parameters.

In this embodiment, after the second driving data of part or all of the second deformation parameters are determined through the above steps, the determined second driving data may be summarized into a driving data set through this step, and the driving data set may be regarded as a second driving data packet in the second fusion deformation form.

Further, the specific implementation steps of determining, according to the driving data of each first deformation parameter included in the first driving data packet and in combination with the conversion mapping information, second driving data of each second deformation parameter included in the second fusion deformation form may be described as follows:

b21) and for each second deformation parameter in the second deformation parameter set in the second fusion deformation form, obtaining a mapping relation corresponding to the second deformation parameter from the conversion mapping information.

In the embodiment, the second deformation parameters included in the second fusion deformation form designed for the virtual character constitute a second deformation parameter set, and this step can be regarded as an operation performed on each of the second deformation parameters in the second deformation parameter set, that is, each of the second deformation parameters can perform the operations of this step and the following steps.

Specifically, this step may obtain a corresponding mapping relation for each second transformation parameter from the transformation mapping information. That is, it can be considered that the same number of mapping expressions as the number of second deformation parameters are included in the conversion mapping information.

For each second deformation parameter, the corresponding mapping relation can be regarded as an association relation formed by all the related first deformation parameters.

b22) And searching the associated deformation parameters included in the mapping relation from the first deformation parameter set of the first fusion deformation form.

Similarly, the first set of deformation parameters may be considered to be formed by the first deformation parameters in the first fusion deformation form designed with respect to the target object. After the mapping relation of the second deformation parameter is determined in the above step, the mapping relation can be traversed, which first deformation parameters in the first deformation parameter set are associated with the second deformation parameter is determined from the mapping relation, and the associated first deformation parameters can be recorded as associated deformation parameters.

b23) And obtaining the associated driving data of each associated deformation parameter from the first driving data packet.

It can be known that the first driving data packet includes driving data corresponding to each first deformation parameter, and after determining the associated deformation parameter of the second deformation parameter in the first fusion deformation form in the above step, the driving data of each associated deformation parameter can be found from the first driving data packet through this step, which can be recorded as associated driving data in this embodiment.

b24) And determining second driving data of the second deformation parameter by combining the associated driving data according to the association relation in the mapping relation.

In this embodiment, the mapping relation corresponding to one second deformation parameter includes, in addition to the associated deformation parameter associated therewith, a relation representing the association relation between the second deformation parameter and the associated deformation parameter, and the association weight and the association form of each associated deformation parameter and the second deformation parameter can be known through the relation. This step may determine the second driving data of the second deformation parameter based on the association given in the mapping equation in combination with the determined associated driving data.

It is to be understood that, by the determination of the second driving data given above in this alternative embodiment, the second driving data of each second deformation parameter in the second deformation parameter set can be determined.

The second optional embodiment described above provides a specific implementation manner for converting the first driving data packet into the second driving data packet, and provides specific implementation steps in the conversion implementation. Through the optional embodiment, the problem of inaccurate virtual simulation caused by inconsistent fusion deformation forms is solved equivalently through format conversion of the driving data packet before the virtual role is driven, and the simulation effect of the virtual role on the target object in the virtual simulation scene can be effectively improved through the technical characteristics of the second optional embodiment.

As a third optional embodiment of this embodiment, on the basis of the above embodiment, a determination step of the conversion mapping information in the data conversion configuration file is further given. In this embodiment, the format conversion of the first driving data packet mainly depends on the conversion mapping information in the data conversion configuration file, and under the condition that the first fusion deformation form is the same, the conversion mapping information adopted by the second driving data packet converted into the different second fusion deformation form is different.

Meanwhile, the conversion mapping information adopted by the embodiment needs to be predetermined by a corresponding determination rule before virtual role driving is performed, and is recorded in the data conversion configuration file, so that the required conversion mapping information can be called from the data conversion configuration file when format conversion of a driving data packet needs to be performed. The optional embodiment provides a determination implementation of the transformation mapping information, and whether the second fusion deformation form to be transformed is different, the transformation mapping information matched with the second fusion deformation form can be determined by the determination method provided by the optional embodiment.

Specifically, the step of determining the conversion mapping information according to the third alternative embodiment may include:

a3) and obtaining a corresponding first deformation parameter set under the first fusion deformation form and a corresponding second deformation parameter set under the second fusion deformation form.

It can be known from the above description that the determination of the transformation mapping information is the previous step executed by the virtual character driving method, and in order to determine the transformation mapping information, it is necessary to first know what transformation parameter sets the first fusion transformation form (the first fusion transformation form) and the fusion transformation form to be transformed (the second fusion transformation form) respectively include. Thus, a first set of deformation parameters in the first fused deformation form and a second set of deformation parameters in the second fused deformation form can be obtained by this step.

It should be appreciated that after determining the fused deformation form, the corresponding included set of deformation parameters may also be determined. For example, the first set of deformation parameters provided in the first fusion deformation form may be a set of parameters including 52 deformation parameters, and the set of parameters may be considered as one of the design forms of the first fusion deformation, and the second set of deformation parameters provided in the second fusion deformation form may be a set of parameters including 17 deformation parameters, and the set of parameters may also be considered as one of the design forms of the second fusion deformation.

b3) And determining a mapping relation between the second deformation parameter in the second deformation parameter set and the first deformation parameter in the first deformation parameter set.

In this embodiment, after the second deformation parameter in the second deformation parameter set and the first deformation parameter in the first deformation parameter set are obtained, the second deformation parameter and the first deformation parameter may be analyzed, the association between the second deformation parameter and the first deformation parameter is established according to the analysis result, and finally, the mapping relationship of the second deformation parameter is formed by combining the existing association relationship with the first deformation parameter associated with the second deformation parameter.

For example, the analysis of the second deformation parameter and the first deformation parameter may be semantic analysis of the deformation parameter, and then the second deformation parameter and the first deformation parameter whose semantic similarity is close to a certain upper limit may be determined as similar association; and when the second deformation parameter does not have the first deformation parameter with similar association, searching the relevant first deformation parameter relevant to the second deformation parameter through the second deformation parameter and the keyword included in the first deformation parameter. To establish the association of the second deformation parameter and the first deformation parameter in the above-described manner.

As described above, after determining the association, the association coefficient (also referred to as the association weight or the conversion coefficient) of the associated first deformation parameter with respect to the second deformation parameter may be further determined, and finally, based on the association coefficient, the second deformation parameter may be formed into a mapping relationship with the associated first deformation parameters.

Preferably, the third alternative embodiment provides a specific implementation of the step b3), that is, the third alternative embodiment may specifically optimize the determination of the mapping relationship between the second deformation parameter in the second deformation parameter set and the first deformation parameter in the first deformation parameter set as follows:

b31) and performing semantic analysis on the first deformation parameters in the first deformation parameter set and the second deformation parameters in the second deformation parameter set to respectively obtain a first semantic result of the first deformation parameters and a second semantic result of the second deformation parameters.

In this embodiment, semantic analysis may be performed on the first deformation parameter and the second deformation parameter by calling a bottom-layer semantic analysis algorithm, so as to obtain a first semantic result of the first deformation parameter and a second semantic result of the second deformation parameter.

The semantic meaning of each deformation parameter to be expressed can be clear through the semantic result of the deformation parameter, so that the similarity or the correlation between one deformation parameter and other deformation parameters can be determined conveniently.

b32) For each second deformation parameter, if a similar first semantic result with the similarity value of the second semantic result being greater than a first set threshold value exists, determining a mapping relation of the second deformation parameter based on a similar first deformation parameter corresponding to the similar first semantic result; otherwise, step b33) is performed.

The execution of this step is applied to each second deformation parameter of the set of second deformation parameters, i.e. for each second deformation parameter, the corresponding mapping relation may be determined by this step b32) or step b 33).

It should be noted that, in this alternative embodiment, the step b32) or the step b33) is two ways of determining the mapping relation for the second transformation parameter, but the two ways are actually executed alternatively. Specifically, after determining semantic results for each first deformation parameter and each second deformation parameter through the above steps, for each second deformation parameter, the step determines a similarity value between the second deformation parameter and each first deformation parameter according to the semantic result of the second deformation parameter and the semantic result of each first deformation parameter; then, the step can determine whether a similar first semantic result with the similarity value of the semantic result of the second deformation parameter larger than a first set threshold exists.

If the semantic result of the second deformation parameter is the same as the semantic result of the first deformation parameter, the mapping relation expression of the second deformation parameter can be determined based on the semantic result of the second deformation parameter.

If not, it can be considered that there is no similar first deformation parameter in the first deformation parameters that clearly corresponds to the semantics of the second deformation parameter, and thus step b33) needs to be performed.

Further, for the above similar first deformation parameter corresponding to the similar first semantic result, one implementation manner of determining the mapping relation of the second deformation parameter may be specifically described as:

b321) and determining similar first deformation parameters corresponding to similar first semantic results from the first deformation parameter set.

It can be known that, after determining the similar first semantic result, it can be determined from the first set of deformation parameters what first deformation parameter the similar first semantic result specifically corresponds to, and can be recorded as the similar first deformation parameter. Wherein, a plurality of similar first deformation parameters may exist in one second deformation parameter.

b322) And determining a similar weight value of the similar first deformation parameter according to a set similar weight determination rule.

It should be noted that, after one or more similar first deformation parameters are determined according to one second deformation parameter through the above steps, similar weight values of different similar first deformation parameters relative to the second deformation parameter may be the same or different. Thus, a similar weight value of the similar first deformation parameter with respect to the second deformation parameter can be determined by this step.

When determining the similar weight value of the similar first deformation parameter in this step, the determination may be performed according to a determination rule formed by historical experience, or may be performed directly according to a given weight division rule, or a pre-stored constant value is used as the similar weight value.

For example, taking the second deformation parameter of anger a in the second fusion deformation form as an example, in the above manner, the first deformation parameters of the left eyebrow downward bDl and the right eyebrow downward bDr in the first fusion deformation form can be determined to be similar first deformation parameters of the anger a. The embodiment may determine that the similar weight values of the left eyebrow downward bDl and the right eyebrow downward bDr relative to the angry a are 0.5 and 0.5, respectively, directly according to the weight division rule (1 is averaged according to the number of the similar first deformation parameters, and the average value is used as the similar weight value of each similar first deformation parameter).

For another example, taking the second deformation parameter sadness S in the second fusion deformation form as an example, by the above method, it can be determined that the first deformation parameter brow root lift bIu in the first fusion deformation form is the similar first deformation parameter of sadness S, and only the first deformation parameter brow root lift bIu is provided as a similar first deformation parameter. In this embodiment, 1 may be directly used as the similar weight value of the similar first deformation parameter.

b323) And taking the similar first deformation parameters as independent variables, and combining corresponding similar weight values to form a mapping relation of the second deformation parameters.

After the similar first deformation parameter and the similar weight value of the similar first deformation parameter relative to the second deformation parameter are determined through the steps, a relational expression can be established to display the first deformation parameter to represent the second deformation parameter.

For example, the similar first deformation parameter may be used as an argument and weighted in combination with a corresponding similar weight value, so as to form a mapping relation that may represent an association relation between the second deformation parameter and the similar first deformation parameter. Taking the second deformation parameter of anger a as an example, the mapping relation between anger a and the similar first deformation parameters of left eyebrow downward bDl and right eyebrow downward bDr can be expressed as follows:

gas generation a is 0.5 ═ 0.5 (bDl + bDr). Among them, bDl and bDr may be used as arguments to be given to the determined data values of the different drive data.

b33) And determining a relevant first deformation parameter related to the second deformation parameter from the first deformation parameters, and determining a mapping relation of the second deformation parameter based on the relevant first deformation parameter.

As can be understood from the above description, when there is no similar first deformation parameter in the first deformation parameter that obviously corresponds to the semantic meaning of the second deformation parameter, the mapping relation of the second deformation parameter can be determined by this step.

It can be known that, in the present embodiment, if a similar first deformation parameter of the second deformation parameter is not found through the above steps, it can be considered that there is no first deformation parameter in the first deformation parameter set that clearly corresponds to the semantics of the second deformation parameter, and thus it is necessary to determine a relatively relevant first deformation parameter from the first deformation parameters whose semantic correspondence is not obvious through this step.

In an embodiment of the third optional embodiment, one implementation manner of determining a relevant first deformation parameter related to the second deformation parameter from the first deformation parameters, and determining a mapping relation of the second deformation parameter based on the relevant first deformation parameter is given, and may specifically be described as:

b331) and determining a target semantic keyword of the second deformation parameter and a first semantic keyword of the corresponding first deformation parameter based on a second semantic result of the second deformation parameter and a first semantic result of the first deformation parameter.

In the step, the target semantic keywords contained in the second deformation parameters can be determined through the second semantic results of the second deformation parameters, and the first semantic keywords contained in the first deformation parameters can be determined through the first semantic results of the first deformation parameters. In this embodiment, the semantic keyword may be understood as a word representing related information in the deformation parameter.

Illustratively, taking the second deformation parameter I for characterizing the expression corresponding to the I-pronunciation as an example, performing semantic analysis on the second deformation parameter I can know that mouth is enlarged to issue the deformation of the I-pronunciation, wherein mouth is enlarged to be regarded as the target semantic keyword of the second deformation parameter I. Similarly, first semantic keywords respectively exist in the first deformation parameters in the first fusion deformation form, and the mouth can be opened if the first semantic keywords of the first deformation parameters left mouth corner stretching mL are used.

b332) And screening a first deformation parameter of the first semantic keyword and the target semantic keyword in a set word meaning range to serve as a related first deformation parameter of the second deformation parameter.

After the semantic keywords (the first semantic keyword and the target semantic keyword) of the deformation parameters (the first deformation parameter and the second deformation parameter) are obtained, for one second deformation parameter, the semantic keyword of each first deformation parameter can be compared with the target semantic keyword of the second deformation parameter, so that the first deformation parameter in a similar range of the word senses to the target semantic keyword can be screened out, and the first deformation parameter can be recorded as the related first deformation parameter.

For example, the target semantic keyword corresponding to the second shape variation parameter I is mouth, and after determining that the first semantic keyword of the left mouth angle stretching mL and the right mouth angle stretching mR is mouth, the keyword related to mouth may be regarded as a similar keyword in the set semantic range, so that the left mouth angle stretching mL and the right mouth angle stretching mR may be used as the related first shape variation parameter of the second shape variation parameter I.

As described above, in the first deformation parameter, the first semantic keyword may also determine that the upper lip movement Su, the lower lip movement Ldl, the lower lip movement Ldl, and other related first deformation parameters also belong to the second deformation parameter I. It is understood that there may be a plurality of associated first deformation parameters determined with respect to one second deformation parameter.

After determining the relevant first parameter with respect to each second deformation parameter, the mapping relation of the second deformation parameter needs to be determined through steps b333) to b335) described below.

b333) And determining a target action corresponding to the second deformation parameter, and acquiring related driving data corresponding to the related first deformation parameter when the sample object makes the target action.

In the present embodiment, the target action of the second deformation parameter management can be determined through the above analysis of the semantics and the keywords, etc. The embodiment may select a sample object, and let the sample object perform the target action, wherein the sample object may be understood as a physical object such as a real person or an animal. The execution subject of this embodiment may capture a target motion image when the sample object makes the target motion, and thus, the motion capture driving algorithm may be used to analyze the related driving data corresponding to each first deformation parameter involved in the first fusion deformation form when the sample object makes the target motion.

For example, for a second deformation parameter without a distinct semantically similar first deformation parameter, the second deformation parameter may be denoted as A _i . Assuming that there are n second deformation parameters for mainly performing step b33) throughout the second fusion deformation form, i starts from 1 and has a maximum value of n.

At the same time, the second deformation parameter A can be adjusted _i The corresponding related first deformation parameters are respectively distinguished by subscript j, and each related first deformation parameter can be represented as B _j And the subscript j takes a value of 1-m, and m is the total number of the related first deformation parameters of one second deformation parameter.

After the relevant driving data corresponding to each relevant first deformation parameter is obtained when the sample object performs the target action, corresponding to each relevant first deformation parameter B _j And related driving data b of each related first deformation parameter can be acquired _ij Wherein i is a second deformation parameter A _i Is the associated first deformation parameter B _j The subscript of (1).

b334) And determining the conversion coefficient of the related first deformation parameter based on a set target solving algorithm and in combination with the related driving data.

As described above, this step may set a second deformation parameter A _i Relative first deformation parameter B _j The relational expression (c) of (c). Illustratively, the relationship may be expressed as:

A _i ＝∑ _j x _ij B _j wherein x is _ij Is represented as being in [0, 1 ]]Conversion factor within the range.

The above relation may be regarded as a correlation relation that characterizes the second deformation parameter by using the relevant first deformation parameter in combination with the transformation coefficient, and the relation may be regarded as a mapping relation of the second deformation parameter.

In the above mapping relation, the coefficient x is converted _ij For the object to be solved, this embodiment provides an objective function to convert the coefficient x _ij And (4) solving. The objective function can be described as:

wherein, a and β are equal to preset algorithm parameters, n is the total amount of the second deformation parameters, and m is the total amount of the relevant first deformation parameters contained in the n second deformation parameters; i is an e [1, n ]]An integer of (d); j is an element of [1, m ]]An integer of (d); b _ij And the related driving data are determined relative to the jth related first deformation parameter when the sample object performs the target motion of the ith second deformation parameter.

The above objective function can be understood as: under the condition that the sample object performs the target action corresponding to the ith second deformation parameter, the collected related driving data b is used _i1 ，b _i2 ，b _i3 .....b _im Can determine x respectively _i1 ，x _i2 ，x _i3 .......x _im So as to substitute for A _i ＝∑ _j x _ij B _j Then obtained A _i Is infinitely close to 1, and makes substitution a _k ＝∑ _j x _ij B _j Then obtained A _k Is infinitely close to 0, where k is not equal to i.

For a second deformation parameter, the step may determine corresponding transformation coefficients respectively corresponding to the related first deformation parameters corresponding to the second deformation parameter by solving the objective function.

b335) And forming a mapping relation of the second deformation parameter by taking the relevant first deformation parameter as an independent variable and combining a corresponding conversion coefficient.

It is to be noted that the step may perform weighting based on the conversion coefficient of each relevant first deformation parameter, and use the formed weighting relation as the mapping relation of the second deformation parameter.

For example, assuming that the second deformation parameter I corresponds to the associated first deformation parameters, which may be the left mouth angle stretching mL, the right mouth angle stretching mR, the upper lip movement Su, the lower lip movement Ldl, the lower lip movement Ldr, and the left nasal flapping nL, the transformation coefficients may be determined for each associated first deformation parameter by the above steps, which are 0.02, 0.04, 0.01, 0.03, and 0.01, respectively.

Furthermore, the mapping relation of the second deformation parameter I can be expressed as:

I＝0.02*mL+0.04*mR+0.01*Su+0.03*Ldl+0.03*Ldl+0.01*nL。

it should be noted that, the second deformation parameters mentioned in the above step b33) and its subsequent expanded descriptions can be regarded as deformation parameters in which the similar first deformation parameters cannot be clearly determined in the second deformation parameter set.

The above steps of the third alternative embodiment provide a specific description of the determination of the mapping relationship between the second deformation parameter and the first deformation parameter. The similarity between the semantic result of the second deformation parameter and the semantic result of the first deformation parameter is mainly considered, the first deformation parameter associated with the second deformation parameter is determined through the similarity, and finally the determination of the mapping relation between the second deformation parameter and the associated first deformation parameter is completed. According to the embodiment, the associated first deformation parameter of the second deformation parameter is effectively determined, and accurate precondition data is provided for the conversion of the subsequent first driving data to the second driving data.

c3) And based on each mapping relational expression, forming conversion mapping information for converting the first fusion deformation form into the second fusion deformation form.

After the mapping relation of each second deformation parameter is determined through the above steps a3) and b3), this step may summarize the mapping relations to form the conversion mapping information required for converting the first fusion deformation form into the second fusion deformation form. The transformation mapping information may be associated with the deformation form identifier of the second fusion deformation form and recorded in the data transformation configuration file.

The third alternative embodiment described above shows the determination of the mapping relationship between the second deformation parameter and the first deformation parameter. The conversion mapping information provided by the embodiment can provide key data information for format conversion of the driving data packet in the virtual role driving, and the accuracy of the virtual role driving is ensured.

Fig. 2 is a schematic structural diagram of an avatar driving apparatus according to an embodiment of the present disclosure, and as shown in fig. 2, the apparatus includes: a first drive determination module 210, a second drive determination module 220, and a drive execution module 230.

The first driving determining module 210 is configured to analyze a current action of the target object, and obtain a first driving data packet of the current action in a first fusion deformation form.

The second driving determining module 220 is configured to perform format conversion on the driving data in the first driving data packet according to a predetermined data conversion configuration file, so as to obtain a second driving data packet in a second fusion deformation form, where the data conversion configuration file includes conversion mapping information for converting the format of the driving data.

And a driving execution module 230, configured to drive a virtual role model to present the current action according to the driving data in the second driving data packet, so as to perform virtual simulation on the action of the target object, where the virtual role model is constructed in the second fusion deformation form.

According to the technical scheme provided by the embodiment of the disclosure, before virtual role driving is carried out through the driving data packet, format conversion operation of driving data in the driving data packet is added, and the driving data packet which is matched with the constructed virtual role model in a fusion deformation form can be obtained through the added format conversion operation. And virtual role driving is carried out through the matched driving data packet, so that the consistency of the action presented by the virtual role and the action made by the entity object user is ensured, the simulation reality and the accuracy of the virtual role are enhanced, the simulation effect of the virtual role on the entity object is effectively improved, and the user experience of virtual role simulation is improved.

Further, the first driving determination module 210 may specifically be configured to:

acquiring a current motion image of the target object, wherein the current motion image is obtained by capturing the motion of the target object by an image capturing device;

analyzing the current motion image through a set motion capture driving algorithm to obtain driving data corresponding to a first deformation parameter in a first fusion deformation form;

and forming a first driving data packet of the current action based on the driving data of the first deformation parameter.

Further, the first driving determination module 220 may include:

the searching unit is used for searching the data conversion configuration file to obtain conversion mapping information corresponding to the second fusion deformation form;

a first determining unit, configured to determine, according to the driving data of the first deformation parameter included in the first driving data packet, second driving data of a second deformation parameter included in the second fusion deformation form in combination with the conversion mapping information;

and the information summarizing unit is used for forming a second driving data packet according to the second driving data of the second deformation parameter.

Further, the first determining unit may specifically be configured to:

obtaining a mapping relation corresponding to a second deformation parameter from the conversion mapping information aiming at the second deformation parameter included in a second deformation parameter set in the second fusion deformation form;

searching for associated deformation parameters included in the mapping relation from the first deformation parameter set of the first fusion deformation form;

obtaining associated driving data of each associated deformation parameter from the first driving data packet;

and determining second driving data of the second deformation parameter by combining the associated driving data according to the association relation in the mapping relation.

Further, the apparatus further includes an information determining module, where the information determining module is configured to drive the conversion mapping information in the data conversion configuration file, and the information determining module may specifically include:

the acquisition unit is used for acquiring a first deformation parameter set corresponding to the first fusion deformation form and a second deformation parameter set corresponding to the second fusion deformation form;

the mapping determining unit is used for determining a mapping relation between the second deformation parameters in the second deformation parameter set and the first deformation parameters in the first deformation parameter set;

and the information forming unit is used for forming conversion mapping information for converting the first fusion deformation form into the second fusion deformation form based on each mapping relational expression.

Further, the mapping determining unit may include:

the semantic analysis subunit is used for performing semantic analysis on a first deformation parameter in the first deformation parameter set and a second deformation parameter in the second deformation parameter set to respectively obtain a first semantic result of the first deformation parameter and a second semantic result of the second deformation parameter;

the first execution subunit is used for determining, for each second deformation parameter, if a similar first semantic result with a similarity value larger than a first set threshold value to the second semantic result exists, a mapping relation of the second deformation parameter based on a similar first deformation parameter corresponding to the similar first semantic result;

and the second execution subunit is used for determining a related first deformation parameter related to the second deformation parameter from the first deformation parameters if a similar first semantic result with the similarity value of the second semantic result larger than a first set threshold does not exist, and determining a mapping relation of the second deformation parameter based on the related first deformation parameter.

Further, the first execution unit may specifically be configured to:

determining similar first deformation parameters corresponding to similar first semantic results from the first deformation parameter set;

determining a similar weight value of the similar first deformation parameter according to a set similar weight determination rule;

and taking the similar first deformation parameters as independent variables, and combining corresponding similar weight values to form a mapping relation of the second deformation parameters.

Further, the second execution unit may specifically be configured to:

determining a target semantic keyword of the second deformation parameter and a first semantic keyword of the corresponding first deformation parameter based on a second semantic result of the second deformation parameter and a first semantic result of the first deformation parameter;

screening a first deformation parameter of the first semantic keyword and the target semantic keyword in a set word meaning range, and taking the first deformation parameter as a related first deformation parameter of the second deformation parameter;

determining a target action corresponding to the second deformation parameter, and acquiring related driving data corresponding to the related first deformation parameter when the sample object makes the target action;

determining a conversion coefficient of the relevant first deformation parameter based on a set target solving algorithm and in combination with the relevant driving data;

and forming a mapping relation of the second deformation parameter by taking the relevant first deformation parameter as an independent variable and combining a corresponding conversion coefficient.

The virtual character driving device provided by the embodiment of the disclosure can execute the virtual character driving method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method.

It should be noted that, the units and modules included in the apparatus are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the embodiments of the present disclosure.

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. Referring now to FIG. 3, a block diagram of an electronic device (e.g., the terminal device or server of FIG. 3) 300 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An edit/output (I/O) interface 305 is also connected to bus 304.

Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 309, or installed from the storage means 308, or installed from the ROM 302. The computer program, when executed by the processing device 301, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

The electronic device provided by the embodiment of the present disclosure and the virtual character driving method provided by the above embodiment belong to the same inventive concept, and technical details that are not described in detail in the embodiment can be referred to the above embodiment, and the embodiment and the above embodiment have the same beneficial effects.

The disclosed embodiments provide a computer storage medium on which a computer program is stored, which when executed by a processor implements the virtual character driving method provided by the above embodiments.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:

the computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: analyzing the current action of the target object to obtain a first driving data packet of the current action in a first fusion deformation form; according to a predetermined data conversion configuration file, carrying out format conversion on the drive data in the first drive data packet to obtain a second drive data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information for converting the drive data format; and driving a virtual role model to present a virtual action corresponding to the current action according to the driving data in the second driving data packet, wherein the virtual role model is constructed in the second fusion deformation form.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, [ example one ] there is provided a virtual character driving method, the method including: analyzing the current action of the target object to obtain a first driving data packet of the current action in a first fusion deformation form; according to a predetermined data conversion configuration file, carrying out format conversion on the drive data in the first drive data packet to obtain a second drive data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information for converting the drive data format; and driving a virtual role model to present a virtual action corresponding to the current action according to the driving data in the second driving data packet, wherein the virtual role model is constructed in the second fusion deformation form.

According to one or more embodiments of the present disclosure, [ example two ] there is provided a virtual character driving method, including analyzing a current motion of a target object, and obtaining a further optimization of a first driving data packet of the current motion in a first fusion deformation form, which may be specifically optimized as: acquiring a current motion image of the target object, wherein the current motion image is obtained by capturing the motion of the target object by an image capturing device; analyzing the current motion image through a set motion capture driving algorithm to obtain driving data corresponding to a first deformation parameter in a first fusion deformation form; and forming a first driving data packet of the current action based on the driving data of the first deformation parameter.

According to one or more embodiments of the present disclosure, an example three provides a virtual role driving method, where the method includes performing format conversion on driving data in a first driving data packet according to a predetermined data conversion configuration file, and obtaining further optimization of a second driving data packet in a second fusion deformation form, where the further optimization may specifically be: searching the data conversion configuration file to obtain conversion mapping information corresponding to the second fusion deformation form; determining second driving data of a second deformation parameter in the second fusion deformation form according to driving data of the first deformation parameter included in the first driving data packet and by combining the conversion mapping information; and forming a second driving data packet according to the second driving data of the second deformation parameters.

According to one or more embodiments of the present disclosure, an example four provides a virtual character driving method, which includes determining, according to driving data including a first deformation parameter in the first driving data packet, and in combination with the transformation mapping information, further optimization of second driving data including a second deformation parameter in the second fused deformation form, which may be specifically optimized as: obtaining a mapping relation corresponding to a second deformation parameter from the conversion mapping information aiming at the second deformation parameter included in a second deformation parameter set in the second fusion deformation form; searching for associated deformation parameters included in the mapping relation from the first deformation parameter set of the first fusion deformation form; obtaining associated driving data of each associated deformation parameter from the first driving data packet; and determining second driving data of the second deformation parameter by combining the associated driving data according to the association relation in the mapping relation.

According to one or more embodiments of the present disclosure, [ example five ] there is provided a virtual character driving method, including determining conversion mapping information in a data conversion configuration file, where the determining step may specifically include: obtaining a first deformation parameter set corresponding to the first fusion deformation form and a second deformation parameter set corresponding to the second fusion deformation form; determining a mapping relation between a second deformation parameter in the second deformation parameter set and a first deformation parameter in the first deformation parameter set; and based on each mapping relational expression, forming conversion mapping information for converting the first fusion deformation form into the second fusion deformation form.

According to one or more embodiments of the present disclosure, [ example six ] there is provided a virtual character driving method, including further optimization of the determination of the mapping relation between the second deformation parameter in the second deformation parameter set and the first deformation parameter in the first deformation parameter set, which may be specifically optimized as: performing semantic analysis on a first deformation parameter in the first deformation parameter set and a second deformation parameter in the second deformation parameter set to respectively obtain a first semantic result of the first deformation parameter and a second semantic result of the second deformation parameter; for each second deformation parameter, if a similar first semantic result with the similarity value of the second semantic result being greater than a first set threshold exists, determining a mapping relation of the second deformation parameter based on a similar first deformation parameter corresponding to the similar first semantic result; otherwise, determining a related first deformation parameter related to the second deformation parameter from the first deformation parameters, and determining a mapping relation of the second deformation parameter based on the related first deformation parameter.

According to one or more embodiments of the present disclosure, an example seven provides a virtual character driving method, where the method includes further optimizing, on a similar first deformation parameter corresponding to the similar first semantic result, a mapping relation equation that determines the second deformation parameter, and specifically may be optimized as follows: determining similar first deformation parameters corresponding to similar first semantic results from the first deformation parameter set; determining a similar weight value of the similar first deformation parameter according to a set similar weight determination rule; and taking the similar first deformation parameters as independent variables, and combining corresponding similar weight values to form a mapping relation of the second deformation parameters.

According to one or more embodiments of the present disclosure, [ example eight ] there is provided a virtual character driving method, including further optimization of determining a relevant first deformation parameter related to the second deformation parameter from the first deformation parameters, and determining a mapping relation of the second deformation parameter based on the relevant first deformation parameter, which may be specifically optimized as: determining a target semantic keyword of the second deformation parameter and a first semantic keyword of the corresponding first deformation parameter based on a second semantic result of the second deformation parameter and a first semantic result of the first deformation parameter; screening a first deformation parameter of the first semantic keyword and the target semantic keyword in a set word meaning range, and taking the first deformation parameter as a related first deformation parameter of the second deformation parameter; determining a target action corresponding to the second deformation parameter, and acquiring related driving data corresponding to the related first deformation parameter when the sample object makes the target action; determining a conversion coefficient of the relevant first deformation parameter based on a set target solving algorithm and in combination with the relevant driving data; and forming a mapping relation of the second deformation parameter by taking the relevant first deformation parameter as an independent variable and combining a corresponding conversion coefficient.

According to one or more embodiments of the present disclosure, [ example nine ] there is provided an avatar driving apparatus, including: the first driving determining module is used for analyzing the current action of the target object and obtaining a first driving data packet of the current action in a first fusion deformation form; the second driving determining module is used for performing format conversion on driving data in the first driving data packet according to a predetermined data conversion configuration file to obtain a second driving data packet in a second fusion deformation form, wherein the data conversion configuration file comprises conversion mapping information used for converting the driving data format; and the driving execution module is used for driving a virtual role model to present a virtual action corresponding to the current action according to the driving data in the second driving data packet, wherein the virtual role model is constructed in the second fusion deformation form.

According to one or more embodiments of the present disclosure, [ example ten ] there is provided an electronic device comprising one or more processors; a storage device configured to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the virtual character driving method as described in any one of examples one to eight above.

According to one or more embodiments of the present disclosure, [ example ten ] there is provided a storage medium containing computer-executable instructions for performing the avatar driving method according to any one of example one to example eight when executed by a computer processor.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A virtual character driving method, comprising:

2. The method according to claim 1, wherein the analyzing the current action of the target object to obtain the first driving data packet of the current action in the first fusion deformation form comprises:

3. The method according to claim 1, wherein the performing format conversion on the driving data in the first driving data packet according to a predetermined data conversion configuration file to obtain a second driving data packet in a second fusion deformation form includes:

searching the data conversion configuration file to obtain conversion mapping information corresponding to the second fusion deformation form;

determining second driving data of a second deformation parameter in the second fusion deformation form according to driving data of the first deformation parameter included in the first driving data packet and by combining the conversion mapping information;

and forming a second driving data packet according to the second driving data of the second deformation parameters.

4. The method according to claim 3, wherein the determining, according to the driving data of the first deformation parameter included in the first driving data packet and in combination with the transformation mapping information, second driving data of a second deformation parameter included in the second fused deformation form includes:

5. The method of claim 1, wherein the step of determining the transformation mapping information in the data transformation profile comprises:

obtaining a first deformation parameter set corresponding to the first fusion deformation form and a second deformation parameter set corresponding to the second fusion deformation form;

determining a mapping relation between a second deformation parameter in the second deformation parameter set and a first deformation parameter in the first deformation parameter set;

and based on each mapping relational expression, forming conversion mapping information for converting the first fusion deformation form into the second fusion deformation form.

6. The method of claim 5, wherein determining the mapping of the second set of deformation parameters to the first set of deformation parameters comprises:

performing semantic analysis on a first deformation parameter in the first deformation parameter set and a second deformation parameter in the second deformation parameter set to respectively obtain a first semantic result of the first deformation parameter and a second semantic result of the second deformation parameter;

for each second deformation parameter, if a similar first semantic result with the similarity value of the second semantic result being greater than a first set threshold value exists, determining a mapping relation of the second deformation parameter based on a similar first deformation parameter corresponding to the similar first semantic result; if not, then,

and determining a relevant first deformation parameter related to the second deformation parameter from the first deformation parameters, and determining a mapping relation of the second deformation parameter based on the relevant first deformation parameter.

7. The method according to claim 6, wherein the determining the mapping relation of the second deformation parameter based on the similar first deformation parameter corresponding to the similar first semantic result comprises:

8. The method according to claim 6, wherein the determining a relevant first deformation parameter related to the second deformation parameter from the first deformation parameters and determining a mapping relation of the second deformation parameter based on the relevant first deformation parameter comprises:

9. A virtual character driving apparatus, comprising:

10. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the virtual character driven method of any of claims 1-8.

11. A storage medium containing computer-executable instructions for performing the virtual character driven method of any of claims 1-8 when executed by a computer processor.