阅读说明：本技术 虚拟机器人形象优化方法、系统、存储介质及计算机设备 (Virtual robot shape optimization method, system, storage medium and computer equipment ) 是由 杜国威 于 2020-04-29 设计创作，主要内容包括：本发明适用于虚拟机器人技术领域,提供了一种虚拟机器人形象优化方法,包括：解析识别语音信息中的播放歌曲的指令,生成所述歌曲的槽位参数信息；分析判断所述槽位参数信息中所述歌曲对应的类型,生成匹配所述类型的形象标签；根据所述形象标签对应的人物形象以变换虚拟机器人。还提供了一种虚拟机器人形象优化系统、用于存储执行所述方法的计算机程序的存储介质以及实现所述方法的计算机设备。借此,本发明能够有效的减少在播放歌曲时,降低歌曲本身与虚拟机器人的落差感,使虚拟人物形象和歌曲类型趋同,使用户在听虚拟机器人唱歌时更自然。(The invention is suitable for the technical field of virtual robots, and provides a virtual robot shape optimization method, which comprises the following steps: analyzing and identifying a song playing instruction in the voice information, and generating slot position parameter information of the song; analyzing and judging the type corresponding to the song in the slot position parameter information, and generating an image label matched with the type; and transforming the virtual robot according to the character image corresponding to the image label. A virtual robot appearance optimization system, a storage medium for storing a computer program for executing the method, and a computer apparatus implementing the method are also provided. Therefore, the virtual robot can effectively reduce the difference between the songs and the virtual robot when the songs are played, so that the virtual character images and the song types converge, and a user can listen to the virtual robot to sing the songs more naturally.)

1. A virtual robot appearance optimization method is characterized by comprising the following steps:

analyzing and identifying, namely analyzing and identifying a song playing instruction in the voice information to generate slot position parameter information of the song;

analyzing and judging, namely analyzing and judging the type corresponding to the song in the slot position parameter information, and generating an image tag matched with the type;

and an image optimization step, namely changing the virtual robot according to the character image corresponding to the image label.

2. The virtual robot imagery optimization method according to claim 1, wherein said parsing step comprises:

a music element step, namely performing natural language analysis processing on the voice information to identify and judge whether the voice information comprises the music element;

broadcasting elements, namely identifying and judging whether the voice information comprises prefabricated broadcasting elements or not if the music elements comprise the music elements;

and a slot position parameter information step, namely outputting slot position parameter information of a corresponding song if the broadcasting element is included.

3. The virtual robot imagery optimization method according to claim 1, wherein said analysis determining step comprises:

analyzing the song resource association information in the slot position parameter information, and obtaining the type corresponding to the song according to the song resource association information;

and a label matching step, namely generating an image label matched with the type according to the type.

4. The virtual robot avatar optimization method of claim 1, wherein said avatar optimization step comprises:

and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

5. A virtual robot avatar optimization system, comprising:

the analysis and identification unit is used for analyzing and identifying a song playing instruction in the voice information and generating slot position parameter information of the song;

the analysis and judgment unit is used for analyzing and judging the type corresponding to the song in the slot position parameter information and generating an image label matched with the type;

and the image optimization unit is used for transforming the virtual robot according to the character image corresponding to the image label.

6. The virtual robot avatar optimization system of claim 5, wherein the parsing identification unit comprises:

the music element subunit is used for carrying out natural language analysis processing on the voice information so as to identify and judge whether the voice information comprises music elements;

the broadcasting element subunit is used for identifying and judging whether the voice information comprises a prefabricated broadcasting element or not if the music element is included;

and the slot position parameter information subunit is used for outputting the slot position parameter information of the corresponding song if the broadcasting element is included.

7. The virtual robot imagery optimization system according to claim 5, wherein the analysis determination unit comprises:

the type analysis subunit is used for analyzing song resource association information in the slot position parameter information and obtaining the type corresponding to the song according to the song resource association information;

and the label matching subunit is used for generating an image label matched with the type according to the type.

8. The virtual robot avatar optimization system of claim 5, wherein the avatar optimization unit is configured to:

and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

9. A storage medium storing a computer program for executing the virtual robot appearance optimization method according to any one of claims 1 to 4.

10. A computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the virtual robot imagery optimization method of any one of claims 1 to 4 when executing the computer program.

Technical Field

The invention relates to the technical field of virtual robots, in particular to a virtual robot shape optimization method, a virtual robot shape optimization system, a virtual robot shape optimization storage medium and a virtual robot shape optimization computer device.

Background

The virtual home robot was originally present in 2016, and japan released a Gatebox (a home-use intelligent holographic robot customized for a house man) in 2016 in a limited amount, and recognized the face and motion of a user through a camera and a human body sensor, and when it was detected that the user returned home, the virtual character showed smile when the user came home, and personally called the user, and actively developed interaction. In addition, weather, news and other information can be reported through the network even when the wife is in contact with the light, and electrical appliances such as televisions, electric lamps and cold air in the house can be remotely controlled by the infrared function. Gatebox is also one of the top manufacturers currently in holographic projection applications.

The Gatebox positioning is a family accompanying robot, which can be understood as an 'upgraded' version of a sound box with a screen in essence, and a character role of a life image can accompany a host to jointly live and grow together. The virtual robot is definitely a channel capable of singing, jumping and speaking when developing to the end. Listening to music and watching video, like a sound box with a screen, can be the most used skill of the user. However, unlike a speaker box, the virtual robot preferably presents music in such a way that the virtual robot can give the user the ability to speak while holding a microphone to sing. But there is a disadvantage: when the virtual robot is a girl image, the girl can sing the Shuihu song of 'flowing from the great river to the east' with strange and non-overlapping feelings.

As can be seen, the conventional method has many problems in practical use, and therefore, needs to be improved.

Disclosure of Invention

In view of the above-mentioned drawbacks, the present invention provides a virtual robot image optimization method, system, storage medium and computer device thereof, which effectively reduces the sense of difference between the song itself and the virtual robot when playing the song, so that the virtual robot image and the song type converge, and the user can listen to the virtual robot to sing the song more naturally.

In order to achieve the above object, the present invention provides a virtual robot image optimization method, comprising:

analyzing and identifying, namely analyzing and identifying a song playing instruction in the voice information to generate slot position parameter information of the song;

analyzing and judging, namely analyzing and judging the type corresponding to the song in the slot position parameter information, and generating an image tag matched with the type;

and an image optimization step, namely changing the virtual robot according to the character image corresponding to the image label.

According to the virtual robot image optimization method, the analyzing and identifying step comprises the following steps:

a music element step, namely performing natural language analysis processing on the voice information to identify and judge whether the voice information comprises the music element;

broadcasting elements, namely identifying and judging whether the voice information comprises prefabricated broadcasting elements or not if the music elements comprise the music elements;

and a slot position parameter information step, namely outputting slot position parameter information of a corresponding song if the broadcasting element is included.

According to the virtual robot shape optimization method, the analyzing and judging step comprises the following steps:

analyzing the song resource association information in the slot position parameter information, and obtaining the type corresponding to the song according to the song resource association information;

and a label matching step, namely generating an image label matched with the type according to the type.

Preferably, the image optimization step includes:

and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

There is also provided a virtual robot avatar optimization system, comprising:

the analysis and identification unit is used for analyzing and identifying a song playing instruction in the voice information and generating slot position parameter information of the song;

the analysis and judgment unit is used for analyzing and judging the type corresponding to the song in the slot position parameter information and generating an image label matched with the type;

and the image optimization unit is used for transforming the virtual robot according to the character image corresponding to the image label.

According to the virtual robot image optimization system, the analysis and identification unit comprises:

the music element subunit is used for carrying out natural language analysis processing on the voice information so as to identify and judge whether the voice information comprises music elements;

the broadcasting element subunit is used for identifying and judging whether the voice information comprises a prefabricated broadcasting element or not if the music element is included;

and the slot position parameter information subunit is used for outputting the slot position parameter information of the corresponding song if the broadcasting element is included.

According to the virtual robot image optimization system, the analysis and judgment unit includes:

the type analysis subunit is used for analyzing song resource association information in the slot position parameter information and obtaining the type corresponding to the song according to the song resource association information;

and the label matching subunit is used for generating an image label matched with the type according to the type.

Preferably, the image optimization unit is configured to:

and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

In addition, a storage medium for storing a computer program for executing the virtual robot appearance optimization method described above and a computer apparatus are also provided.

The computer device comprises a storage medium, a processor and a computer program stored on the storage medium and capable of running on the processor, wherein the processor implements the virtual robot image optimization method when executing the computer program.

The virtual robot figure optimization method and the virtual robot figure optimization system can effectively reduce the difference between the song and the virtual robot when the song is played, so that the virtual figure and the song type are converged, and a user can listen to the virtual robot to sing more naturally.

Drawings

FIG. 1 is a flowchart illustrating steps of a method for optimizing a virtual robot shape according to a first embodiment of the present invention;

FIG. 2 is a flowchart illustrating steps of a method for optimizing a virtual robot shape according to a second embodiment of the present invention;

fig. 3 is a flowchart of the optional parsing and recognizing step of the virtual robot image optimization method according to the first embodiment and/or the second embodiment of the present invention;

fig. 4 is a flowchart of the optional analysis and judgment step of the virtual robot image optimization method according to the first embodiment and/or the second embodiment of the present invention;

fig. 5 is a block diagram illustrating a configuration of a virtual robot image optimization system according to a first embodiment of the present invention;

fig. 6 is a block diagram illustrating a virtual robot image optimization system according to a second embodiment of the present invention;

fig. 7 is a block diagram of an optional parsing and recognizing unit of the virtual robot image optimization system according to the first embodiment and/or the second embodiment of the present invention;

fig. 8 is a block diagram of an optional analysis and judgment unit of the virtual robot image optimization method according to the first embodiment and/or the second embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

It should be noted that references in the specification to "one embodiment," "an example embodiment," etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not intended to refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

Moreover, where certain terms are used throughout the description and following claims to refer to particular components or features, those skilled in the art will understand that manufacturers may refer to a component or feature by different names or terms. This specification and the claims that follow do not intend to distinguish between components or features that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. In addition, the term "connected" as used herein includes any direct and indirect electrical connection. Indirect electrical connection means include connection by other means.

Fig. 5 shows a virtual robot avatar optimization system 100 according to a first embodiment of the present invention, which includes an analysis recognition unit 10, an analysis determination unit 20, and an avatar optimization unit 30, where the analysis recognition unit 10, the analysis determination unit 20, and the avatar optimization unit 30 may be implemented by software and hardware integrated in a cloud server, where:

the analyzing and identifying unit 10 is used for analyzing and identifying a song playing instruction in the voice information and generating slot position parameter information of the song; the analyzing and judging unit 20 is used for analyzing and judging the type corresponding to the song in the slot position parameter information and generating an image tag matched with the type; the avatar optimization unit 30 serves to transform the virtual robot according to the character avatar corresponding to the avatar label. The method specifically comprises the steps that a plurality of image label matching generation standards respectively corresponding to different character images are prefabricated, the type corresponding to a song is judged according to slot position parameter information of the song needing to be played in recognition voice information, and the type corresponding to the type singing image is such as a man middle-aged man luxury image, a woman young lovely image and the like; the slot parameter information comprises a song name, related resource information corresponding to the song and the like; the method for screening out the keywords in the slot position parameter information can be used for matching and generating the image label which is consistent with the slot position parameter information, for example, the type analyzed according to the slot position parameter information is the man Zhongnian heroic image, the image label which is matched with the man Zhongnian heroic image is generated, the virtual robot is further deformed according to the character type corresponding to the image label, and finally the man Zhongnian heroic image is generated to sing the song, so that the character type which is matched with the generation of the suitability corresponding to different song types is deduced, the difference between the song and the virtual robot is effectively reduced when the song is played, the virtual character image and the song type are similar, and a user can hear the song more naturally when the virtual robot sings. The virtual robot in this embodiment is preferably a holographic projection robot; of course, other types of virtual robots are possible, such as two-dimensional virtual robots, etc.

Fig. 6 shows a virtual robot avatar optimization system 200 according to a second embodiment of the present invention, which includes an analysis recognition unit 10, an analysis determination unit 20, and an avatar optimization unit 30, which are the same as those of the first embodiment; the differences from the first embodiment are: the embodiment further comprises an avatar initialization unit 40, wherein the avatar initialization unit 40 is configured to automatically transform the current avatar of the virtual robot into a pre-manufactured initial avatar if the virtual robot finishes playing the song. For example, the initial character image of the virtual robot is the original female image, and the played song is the middle-aged male image, and after the played song is finished, the initial character image is automatically switched to the original female image.

Referring to fig. 7, optionally, the parsing and identifying unit 10 includes a music element subunit 11, a broadcast element subunit 12, and a slot parameter information subunit 13; wherein:

the music element subunit 11 is configured to perform natural speech analysis processing on the speech information to identify and determine whether a music element is included in the speech information; the music element may be a song name, song lyrics, song melody, etc., such as a user saying: playing the Shuihu Chuan, or singing lyrics of the Shuihu Chuan, or humming melody of the Shuihu Chuan, and the like, and analyzing the voice information to judge the song of the Shuihu Chuan; the playing element subunit 12 is configured to, if the music element is included, recognize and determine whether the voice information includes a prefabricated playing element; the play elements may include, but are not limited to, the following words: the words such as "play", "sing", "switch to", "come" and the like are not limited to the playing elements of the artificial intelligence training of the machine, of course; for example, the user says: the playing element subunit 12 recognizes that the voice information of the user includes "playing", that is, the will of the user is determined. The slot position parameter information subunit 13 is configured to output slot position parameter information of a corresponding song if the play element is included; namely, the slot position parameter information of 'Shuihu Chun' is output by combining the above.

Referring to fig. 8, optionally, the analysis judging unit 20 includes a type analyzing subunit 21 and a tag matching subunit 22; wherein:

the type analyzing subunit 21 is configured to analyze song resource association information in the slot parameter information, and obtain a type of a corresponding song according to the song resource association information; the slot parameter information includes a corresponding song name and song resource association information corresponding to the song, and the song resource association information includes but is not limited to the following contents: song name, artist, album name, title, year, genre, type, remarks, etc. In combination with the above, as song names: water entertain propaganda and singer: name of plum tree and album: haohangge, title: haohongge, age: age 80, category: a national song. And analyzing the song resource correlation information to obtain the song types corresponding to the character images of the middle-aged man and the luxury man. The label matching subunit 22 is used for generating an image label matching the type according to the type; namely, the tag is a song lyric for the middle-aged man, and corresponds to the character image of the middle-aged man and the luxury man. Further, the character optimizing unit 30 transforms the external shape of the virtual robot into a character of a man, a middle-aged person or a luxury person according to the character tag. The present invention includes, but is not limited to, the transformation of the figures of men and women.

Optionally, the image optimizing unit 30 is configured to correspondingly transform the appearance image of the virtual robot according to at least one appearance part corresponding to the image tag. For example, the appearance of the current virtual robot is like a dead and sprouted maiden, and the image label corresponds to a rock and roll wild maiden; corresponding deformation can be carried out on the hair and the clothes of the virtual robot, and other appearance parts are reserved; or if the image standard corresponds to a luxury middle-aged man, the appearance parts of the man, including skin color, height and the like, need to be correspondingly deformed.

Optionally, the virtual robot further comprises a coefficient set prefabricating unit, wherein the coefficient set prefabricating unit is used for prefabricating image characteristics of virtual robot layer gradual transformation, and the image characteristics sequentially correspond to coefficient values in a coefficient set; as in the first or second embodiment, the integer coefficient values from 0 to 10 are pre-fabricated for the virtual robot, i.e. the coefficient set includes coefficient values from 0 to 10, where 0 represents the feminization extreme and 10 represents the masculinization extreme; for example, the initial image of the virtual robot is prefabricated into a dead sprout female image with the coefficient value of 2; the coefficient value of the Chinese-aged luxury male combined with the singing of the Shuihu Chuan is 8; therefore, the character images of the virtual robot comprise 0-10 11 appearance images for transformation; the analysis and judgment unit 20 is used for generating an image label according to the type and a first coefficient value matched with the coefficient value; i.e. the character tag comprises a first coefficient value of the corresponding song, e.g. 8; the character optimizing unit 30 may perform character image transformation directly according to the corresponding first coefficient value 8 in the character tag.

In other embodiments, the avatar optimization unit 30 further includes an acquisition subunit, a calculation subunit, and a transformation subunit; wherein:

the acquiring subunit is used for acquiring the first coefficient value corresponding to the image label and a second coefficient value of the virtual robot corresponding to the coefficient set currently; the calculation subunit is used for calculating an average value of the first coefficient value and the second coefficient value, and the transformation subunit is used for transforming the virtual robot according to a third coefficient value in the coefficient set corresponding to the average value. Combining the above, if the first coefficient value is 8 and the second coefficient value is 2, calculating the third coefficient value to be 5, and finally, the virtual robot performs transformation according to the character image with the coefficient value of 5; the corresponding type of the played song and the character image initialized by the virtual robot are adopted for neutralization and average value taking, so that the phenomenon that the difference of appearance image transformation is too large can be avoided.

Optionally, the virtual robot receives and recognizes the voice information in the environmental sound. Or it may be a user manually inputting voice information.

Fig. 1 shows a virtual robot shape optimization method according to a first embodiment of the present invention, which includes the steps of:

s101: analyzing and identifying a song playing instruction in the voice information, and generating slot position parameter information of the song;

s102: analyzing and judging the type corresponding to the song in the slot position parameter information, and generating an image label matched with the type;

s103: and transforming the virtual robot according to the character image corresponding to the image label.

The virtual robot is a holographic projection robot, and receives and recognizes the voice information in the environmental sound.

Referring to fig. 3, optionally, the step S101 includes:

s1011: carrying out natural language analysis processing on voice information to identify and judge whether the voice information comprises music elements;

s1012: if the music elements are included, identifying and judging whether the voice information includes prefabricated broadcast elements;

s1013: and if the broadcasting element is included, outputting slot position parameter information of the corresponding song.

Referring to fig. 4, optionally, the step S102 includes:

s1021: analyzing song resource association information in the slot position parameter information, and obtaining the type corresponding to the song according to the song resource association information;

s1022: and generating an image label matched with the type according to the type.

Optionally, the step S103 includes: and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

Optionally, the method further comprises a coefficient set prefabricating step: pre-preparing the gradually-changed image characteristics of the virtual robot layer, wherein the image characteristics sequentially correspond to coefficient values in a coefficient set;

step S102 further includes:

generating the image label according to the type and a first coefficient value matching the coefficient value.

More preferably, the step S103 further includes:

an obtaining step, obtaining the first coefficient value corresponding to the image label and a second coefficient value of the virtual robot currently corresponding to the coefficient set;

a calculating step of calculating an average value of the first coefficient value and the second coefficient value;

and a transformation step of transforming the virtual robot according to the average value corresponding to a third coefficient value in the coefficient set.

Fig. 2 shows a virtual robot shape optimization method according to a second embodiment of the present invention, which includes the following steps:

s101: analyzing and identifying a song playing instruction in the voice information, and generating slot position parameter information of the song;

s102: analyzing and judging the type corresponding to the song in the slot position parameter information, and generating an image label matched with the type;

s103: transforming the virtual robot according to the character image corresponding to the image tag;

s104: and if the virtual robot finishes playing the song, automatically transforming the current character image of the virtual robot into a prefabricated initial character image.

The method is exemplified by a Gatebox image of a maiden, namely 'wife light' and a song name 'Shuihu Chun', and comprises the following steps:

1. the user inputs a voice command 'I wants to listen to a song transmitted by the water enterprisers' to the virtual robot.

2. The virtual robot uploads the instruction to a cloud for NLP (Natural Language Processing, a sub-field of artificial intelligence) Processing, the cloud recognizes that the field to which the instruction belongs is music through NLP analysis, further recognizes that the instruction belongs is 'broadcast song', and then outputs and obtains slot position parameter information. The slot parameter includes the name of the broadcast song. Correspondingly, the resources of the songs of the 'songs transmitted by the water and the margin' and the related information of the resources comprise information such as song names, singers, album names, titles, ages, styles, types, notes and the like. Such as song name: water entertain propaganda and singer: name of plum tree and album: haohangge, title: haohongge, age: age 80, category: a national song.

3. And analyzing the related information of the resources to obtain the type of the song and simultaneously giving a corresponding matched image label. If the character tag is a song expressing the male middle-aged song, a character image of the male middle-aged song and the male luxury song is generated.

4. And the cloud end acquires image tag information of the virtual robot, and if the image tag information is image tags such as young girls who stay in bud and love in satay, the image of the virtual robot is corrected to a certain degree according to the image of the middle-aged man-man's woollen man analyzed by the song. Suppose 0 represents the feminization extreme and 10 represents the masculinization extreme. When the level of the light of the wife is 2, the figure image of the song transferred by the water enterpriser is 8; the final integrated coefficient should be 5.

5. And the cloud end issues the coefficient value obtained by the final synthesis, so that the character image of the virtual robot is influenced. The dimension which particularly influences the character image can be from the angles of hair, dresses, face lines, skin color and the like, so that the character image is more neutral.

6. And when the song is played, the virtual robot is automatically switched into the original character image.

The present invention also provides a storage medium for storing a computer program of the virtual robot image optimization method as described in fig. 1 to 4. Such as computer program instructions, which when executed by a computer, may invoke or otherwise provide methods and/or techniques in accordance with the present application through the operation of the computer. Program instructions which invoke the methods of the present application may be stored on fixed or removable storage media and/or transmitted via a data stream over a broadcast or other signal-bearing medium and/or stored on a storage medium of a computer device operating in accordance with the program instructions. Here, an embodiment according to the present application includes a computer device of the virtual robot image optimization system as shown in fig. 5 or fig. 6, the computer device preferably includes a storage medium for storing a computer program and a processor for executing the computer program, wherein when the computer program is executed by the processor, the computer device is triggered to execute the method and/or the technical solution based on the foregoing embodiments.

It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the above steps or functions. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

The method according to the invention can be implemented on a computer as a computer-implemented method, or in dedicated hardware, or in a combination of both. Executable code for the method according to the invention or parts thereof may be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, and so forth. Preferably, the computer program product comprises non-transitory program code means stored on a computer readable medium for performing the method according to the invention when said program product is executed on a computer.

In a preferred embodiment, the computer program comprises computer program code means adapted to perform all the steps of the method according to the invention when the computer program is run on a computer. Preferably, the computer program is embodied on a computer readable medium.

In summary, the user inputs a voice message command to the virtual robot, the virtual robot uploads the command to the cloud for NLP processing, and the cloud performs NLP analysis to identify the field to which the command belongs, further identify the intention of the command, and then output the slot position parameter information. The slot parameter includes the name of the broadcast song. Correspondingly, the method also comprises resources and related information of the songs, wherein the related information of the resources comprises information such as song names, singers, album names, titles, years, styles, categories, notes and the like. The type of the song is obtained by analyzing the related information of the resources, and corresponding image labels are given. The cloud end obtains image label information of the virtual robot, and the image of the virtual robot is corrected to a certain degree according to the analyzed image of the song. And the cloud end issues the coefficient value obtained by the final synthesis, so that the character image of the virtual robot is influenced. The dimension which particularly influences the character image can be from the angles of hair, dresses, face lines, skin color and the like, so that the character image is more neutral. And when the song is played, the virtual robot is automatically switched into the original character image.

The present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof, and it should be understood that various changes and modifications can be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.

The invention also provides A1, a virtual robot image optimization method, comprising:

analyzing and identifying, namely analyzing and identifying a song playing instruction in the voice information to generate slot position parameter information of the song;

analyzing and judging, namely analyzing and judging the type corresponding to the song in the slot position parameter information, and generating an image tag matched with the type;

and an image optimization step, namely changing the virtual robot according to the character image corresponding to the image label.

A2, the method for optimizing the shape of the virtual robot according to the A1, wherein the step of analyzing and identifying comprises:

a music element step, namely performing natural language analysis processing on the voice information to identify and judge whether the voice information comprises the music element;

broadcasting elements, namely identifying and judging whether the voice information comprises prefabricated broadcasting elements or not if the music elements comprise the music elements;

and a slot position parameter information step, namely outputting slot position parameter information of a corresponding song if the broadcasting element is included.

A3, the method for optimizing the shape of the virtual robot according to A1, wherein the analyzing and determining step comprises:

analyzing the song resource association information in the slot position parameter information, and obtaining the type corresponding to the song according to the song resource association information;

and a label matching step, namely generating an image label matched with the type according to the type.

A4, the virtual robot avatar optimization method of A1, the avatar optimization step comprising:

and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

A5, the method for optimizing the shape of the virtual robot according to A1, further comprising:

a coefficient set prefabricating step, prefabricating image characteristics of the virtual robot layer gradual change sequentially corresponding to coefficient values in a coefficient set;

the analyzing and judging step further comprises:

generating the image label according to the type and a first coefficient value matching the coefficient value.

A6, the virtual robot avatar optimization method of A5, the avatar optimization step further comprising:

an obtaining step, obtaining the first coefficient value corresponding to the image label and a second coefficient value of the virtual robot currently corresponding to the coefficient set;

a calculating step of calculating an average value of the first coefficient value and the second coefficient value;

and a transformation step of transforming the virtual robot according to the average value corresponding to a third coefficient value in the coefficient set.

A7, the method for optimizing the virtual robot figure according to A1, further comprising the following steps after the figure optimizing step:

and an image initialization step, wherein if the virtual robot finishes playing the song, the current character image of the virtual robot is automatically transformed into a prefabricated initial character image.

A8, the method for optimizing the shape of a virtual robot according to A1, wherein the step of analyzing and identifying comprises:

the virtual robot receives and recognizes the voice information in the environmental sound.

A9, the virtual robot shape optimization method according to A1, wherein the virtual robot is a holographic projection robot.

There is also provided B10, a virtual robot image optimization system, comprising:

the analysis and identification unit is used for analyzing and identifying a song playing instruction in the voice information and generating slot position parameter information of the song;

the analysis and judgment unit is used for analyzing and judging the type corresponding to the song in the slot position parameter information and generating an image label matched with the type;

and the image optimization unit is used for transforming the virtual robot according to the character image corresponding to the image label.

B11, the virtual robot appearance optimization system according to B10, wherein the parsing and identifying unit comprises:

the music element subunit is used for carrying out natural language analysis processing on the voice information so as to identify and judge whether the voice information comprises music elements;

the broadcasting element subunit is used for identifying and judging whether the voice information comprises a prefabricated broadcasting element or not if the music element is included;

and the slot position parameter information subunit is used for outputting the slot position parameter information of the corresponding song if the broadcasting element is included.

B12, the virtual robot shape optimization system according to B10, wherein the analysis and judgment unit comprises:

the type analysis subunit is used for analyzing song resource association information in the slot position parameter information and obtaining the type corresponding to the song according to the song resource association information;

and the label matching subunit is used for generating an image label matched with the type according to the type.

B13, the virtual robot imagery optimization system of B10, the imagery optimization unit to:

and correspondingly transforming the appearance image of the virtual robot according to at least one appearance part corresponding to the image label.

B14, the virtual robot appearance optimization system according to B10, further comprising:

the coefficient set prefabricating unit is used for prefabricating image characteristics of the virtual robot layer gradual transformation, wherein the image characteristics sequentially correspond to coefficient values in a coefficient set;

the analysis and judgment unit is further used for:

generating the image label according to the type and a first coefficient value matching the coefficient value.

B15, the virtual robot avatar optimization system of B14, the avatar optimization unit further comprising:

the obtaining subunit is used for obtaining the first coefficient value corresponding to the image label and a second coefficient value of the virtual robot currently corresponding to the coefficient set;

a calculating subunit, configured to calculate an average value of the first coefficient value and the second coefficient value;

a transformation subunit, configured to transform the virtual robot according to the average value corresponding to a third coefficient value in the coefficient set.

B16, the virtual robot appearance optimization system according to B10, further comprising:

and the image initialization unit is used for automatically transforming the current character image of the virtual robot into a prefabricated initial character image if the virtual robot finishes playing the song.

B17, the virtual robot shape optimization system of B10, the virtual robot receiving and recognizing the voice information in the environmental sound.

B18, the virtual robot shape optimization system according to B10, wherein the virtual robot is a holographic projection robot.

C19, a storage medium storing a computer program for executing the virtual robot image optimization method of any one of a1 to a9 is also provided.

There is also provided D20, a computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, the processor implementing the virtual robot imagery optimization method of any one of claims a 1-a 9 when executing the computer program.