CN115914366B - Virtual character object language pushing method, system and electronic equipment - Google Patents
Virtual character object language pushing method, system and electronic equipment Download PDFInfo
- Publication number
- CN115914366B CN115914366B CN202310032652.2A CN202310032652A CN115914366B CN 115914366 B CN115914366 B CN 115914366B CN 202310032652 A CN202310032652 A CN 202310032652A CN 115914366 B CN115914366 B CN 115914366B
- Authority
- CN
- China
- Prior art keywords
- novel
- module
- object language
- language
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Machine Translation (AREA)
Abstract
The invention provides a virtual character and object language pushing method, a virtual character and object language pushing system and electronic equipment, and relates to the field of artificial intelligence. The event information corresponding to the virtual character is obtained through the event pool module, and a trigger instruction is sent to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to the user terminal. The method and the device realize the generation of the characteristic object language based on the event corresponding to the virtual character, improve the richness and diversity of the object language, and improve the user experience when pushing the user.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a virtual character object language pushing method, a virtual character object language pushing system and electronic equipment.
Background
The existing object language creation needs to manually give a section of quotation for writing, does not integrate events occurring around virtual characters, and has the defects of high repeatability, lack of characteristics, difficulty in resonance generation of users and poor user experience. Meanwhile, the existing object language is pushed to the user in a text form such as a novel, so that the attraction to the user is limited, and the user experience is also influenced.
Therefore, the object language pushing method based on the virtual characters is provided, and the object language with characteristics is generated based on the events corresponding to the virtual characters, so that the user experience is improved, and the method is an important development direction at present.
Disclosure of Invention
The invention provides a virtual character object language pushing method, a virtual character object language pushing system and electronic equipment, which are used for solving the defects that in the prior art, events occurring around virtual characters are not integrated, so that object language repeatability is high, characteristics are lacking, resonance is difficult to generate for a user, and user experience is poor. The method and the device realize the generation of the characteristic object language based on the event corresponding to the virtual character, improve the richness and diversity of the object language, and improve the user experience when pushing the user.
The invention provides a virtual character and object language pushing method which is applied to a character and object language pushing system, wherein the character and object language pushing system comprises an event pool module, a triggering module, an object language generating module and a pushing module, and the method comprises the following steps:
the event pool module acquires event information corresponding to the virtual character and sends a trigger instruction to the trigger module;
the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction;
the object language generating module generates an object language file according to the object language generating instruction and the event information;
the pushing module sends the object language file to the event pool module according to the pushing instruction;
and the event pool module sends the object language file to a user terminal.
According to the virtual character object language pushing method provided by the invention, the object language generating module comprises a novel generating sub-module, a voice synthesizing sub-module and a video generating sub-module;
the object language generating module generates an object language file according to the object language generating instruction and the event information, and the object language generating module comprises:
the novel generation sub-module calls the event information and a preset novel generation model according to the object language generation instruction to generate an object language text file;
the voice synthesis submodule generates a material language audio file according to the material language text file, a preset background music file and a preset audio synthesis model;
and the video generation sub-module generates a subject language video file according to the subject language audio file, preset expression information, preset action information and a preset video generation model.
According to the virtual character object language pushing method provided by the invention, the novel generation submodule calls the event information, the pre-stored writing state information and the preset novel generation model according to the object language generation instruction to generate an object language text file, and the method comprises the following steps:
the novel generation sub-module determines novel subject and novel main angle information according to the event information and pre-stored writing state information;
determining a novel quotation according to the novel theme and the novel main angle information;
and generating a material language text file according to the novel primer and a preset novel generation model.
According to the virtual character object language pushing method provided by the invention, the method for determining the novel quotation according to the novel theme and the novel main angle information comprises the following steps:
according to the novel subject, determining novel quotation templates in a plurality of preset novel quotation templates according to a preset mapping relation;
and determining the novel quotation according to the novel principal angle information and the novel quotation template.
According to the virtual character object language pushing method provided by the invention, the novel subject and novel main angle information are determined according to the event information and the pre-stored writing state information, and the method comprises the following steps:
determining continuous information according to the writing state information, wherein the continuous information comprises a continuous state and a historical object language text file theme;
under the condition that the continuous loading state is continuous loading, determining the theme of the historical object language text file as a novel theme, and determining the novel main angle information in the virtual character according to the novel theme and the event information;
and under the condition that the continuous loading state is not continuous loading, determining the novel subject according to the event information, and determining the novel principal angle information in the virtual character according to the event information corresponding to the novel subject.
According to the virtual character object language pushing method provided by the invention, the continuous information also comprises a historical object language text file;
and under the condition that the continuous loading state is continuous loading, generating a material language text file according to the novel quotation and a preset novel generation model, wherein the material language text file comprises the following steps:
and inputting the novel quotation and the historical material language text file into the preset novel generation model to generate the material language text file.
The invention also provides a virtual character object language pushing system, which comprises:
the event pool module is used for acquiring event information corresponding to the virtual character and sending a trigger instruction to the trigger module;
the triggering module is used for generating a pushing instruction and a material language generating instruction according to the triggering instruction;
the object language generation module is used for generating object language files according to the object language generation instruction and the event information;
the pushing module is used for sending the object language file to the event pool module according to the pushing instruction;
the event pool module is further configured to send the object language file to a user terminal.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps of any one of the virtual character object language pushing methods are realized when the processor executes the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the virtual character object pushing method as described in any one of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements the steps of the virtual character object language pushing method as described in any one of the above.
According to the virtual character object language pushing method, the virtual character object language pushing system and the electronic equipment, event information corresponding to a virtual character is obtained through the event pool module, and a trigger instruction is sent to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to the user terminal. The method and the device realize the generation of the characteristic object language based on the event corresponding to the virtual character, improve the richness and diversity of the object language, and improve the user experience when pushing the user.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a virtual character object language pushing method provided by the invention;
FIG. 2 is a schematic diagram of a virtual character object push system provided by the present invention;
FIG. 3 is a schematic diagram of a virtual character object pushing process provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a virtual character and object language pushing method which is applied to a character and object language pushing system. As shown in FIG. 1, the method includes S11-S15.
S11, the event pool module acquires event information corresponding to the virtual character and sends a trigger instruction to the trigger module.
Specifically, the event information of various events related to the virtual character in the network can be obtained through the event pool module, including but not limited to various events in weather, news, economy and the like. Optionally, to facilitate subsequent invocations, the obtained event information may be stored in an event store database. The event pool module may send a trigger instruction to the trigger module. The trigger instruction is used for transmitting an instruction of 'acquired event information, is ready for creation and generates a physical language' to the trigger module.
S12, the triggering module generates a pushing instruction and a subject generation instruction according to the triggering instruction.
Specifically, the triggering module receives the triggering instruction and can generate a pushing instruction and a material language generating instruction according to the triggering instruction. And instructing the related module to generate the object language through the object language generation instruction, and instructing the related module to call the generated object language to push through the pushing instruction. The push instruction includes, but is not limited to, information of a specified time of push, a push frequency, a push period, and the like.
S13, generating a material language file by the material language generation module according to the material language generation instruction and the event information.
Specifically, the object language generating module may call event information according to the object language generating instruction, and perform object language creation according to the event, so as to generate an object language file. The object files may include, but are not limited to, one or more of novice (i.e., text), audio, and video.
S14, the pushing module sends the object language file to the event pool module according to the pushing instruction.
S15, the event pool module sends the object language file to a user terminal.
Specifically, information such as the designated pushing time, pushing frequency, pushing period and the like can be determined through the pushing instruction, and the generated object language file is sent to the event pool module according to the information. And pushing the object language file to the user terminal through the event pool module.
In the embodiment of the invention, event information corresponding to the virtual character is obtained through the event pool module, and a trigger instruction is sent to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to the user terminal. The method and the device realize the generation of the characteristic object language based on the event corresponding to the virtual character, improve the richness and diversity of the object language, and improve the user experience when pushing the user.
According to the virtual character object language pushing method provided by the invention, the object language generating module comprises a novel generating sub-module, a voice synthesizing sub-module and a video generating sub-module;
step S13 includes S21-S23.
S21, the novel generation sub-module calls the event information and a preset novel generation model according to the object language generation instruction to generate an object language text file.
S22, the voice synthesis submodule generates a material language audio file according to the material language text file, the preset background music file and the preset audio synthesis model.
S23, the video generation sub-module generates a subject language video file according to the subject language audio file, preset expression information, preset action information and a preset video generation model.
Specifically, the novel generation sub-module can call event information and a preset novel generation model according to the object language generation instruction to generate an object language text file in a novel (text) form. The novel generation model can be obtained by training in advance according to actual needs, and can be a GPT2 deep learning network model. Optionally, the object text file can be stored in the object database according to a preset object text file path, so that storage management and subsequent calling are facilitated.
The voice synthesis submodule can generate an object language audio file in an audio form according to the object language text file, the preset background music file and the preset audio synthesis model. The audio synthesis model can be trained in advance according to actual needs, and can be a HIFI-GAN network model. Alternatively, the speech synthesis submodule may invoke the object text file in the object database according to the object text file path. Optionally, the number of the background music files may be multiple, the target background music file may be determined by matching the subject of the object text file with the multiple background music files, and the object audio file may be generated according to the object text file, the target background music file and a preset audio synthesis model. Optionally, the object language audio file can be stored in the object language database according to a preset object language audio file path, so that the storage management and the calling are convenient.
The video generation sub-module can generate the object language video file in a video form according to the object language audio file, the preset expression information, the preset action information and the preset video generation model. The video generation model can be obtained by training in advance according to actual needs. Alternatively, the video generation sub-module may invoke the object audio file in the object database according to the object audio file path.
In the embodiment of the invention, the novel generation sub-module calls event information and a preset novel generation model according to the object language generation instruction to generate the object language text file. The voice synthesis submodule generates a material language audio file according to the material language text file, a preset background music file and a preset audio synthesis model. The video generation submodule generates a subject language video file according to the subject language audio file, preset expression information, preset action information and a preset video generation model. The method and the device realize the generation of the object language files with multiple dimensions such as texts, audios, videos and the like based on the event information. And when the recommendation is performed later, object language files with multiple dimensions can be provided, so that the attraction and the user experience of the user are improved.
According to the virtual character object language pushing method provided by the invention, the step S21 comprises S31-S33.
S31, the novel generation sub-module determines novel subject and novel main angle information according to the event information and pre-stored writing state information.
S32, determining the novel quotation according to the novel theme and the novel principal angle information.
S33, generating a material language text file according to the novel primer and a preset novel generation model.
In particular, in order to generate a text file in a physical language with higher quality, a section of quotation is generally required for laying out basic information and main line context of the text in the physical language. In order to make the object text unique and more attractive to users, the novel text generation method can determine novel subjects and novel main angle information through the novel generation sub-module according to the event information and the pre-stored writing state information, and determine novel quotations according to the novel subjects and the novel main angle information, and is used for laying basic information and main line venation of the object text.
Wherein, a plurality of novel topics can be preset according to actual needs, including but not limited to, young campuses, magic poems, ancient moods, earthquakes, storm and welcome new people/residents and other event topics which are more relevant to the environment of the virtual people, selecting a novel theme from a plurality of preset novel themes according to the event information and the writing state information. And creating the novel quotation through a preset novel generation model to generate the object text file.
The writing status information may include, but is not limited to, a loading status (e.g., in-loading, non-loading, or completed) of a current novel (i.e., object text), a current loading period number, a total loading period number, a historical object text file theme, and the like. Optionally, the writing state information can be stored in a writing state database, and the writing state information is isolated from the object text file, the object audio file and the object video file, so that the writing state information is convenient to search and call.
In the embodiment of the invention, the novel generation sub-module determines novel subject and novel main angle information according to the event information and the pre-stored writing state information, so as to determine basic information required for creating the object text file, further determine novel quotation according to the novel subject and the novel main angle information, and lay the basic information and main line context of the object text through the novel quotation, thereby being convenient for obtaining high-quality object text subsequently. And creating a novel quotation through a preset novel generation model to generate a material language text file, so as to realize material language creation in a text form based on event information corresponding to the virtual character.
According to the virtual character object language pushing method provided by the invention, the step S32 comprises S41-S42.
S41, determining a novel quotation template from a plurality of preset novel quotation templates according to the novel subjects and the preset mapping relation.
S42, determining the novel quotation according to the novel principal angle information and the novel quotation template.
Specifically, corresponding novel quotation templates can be set according to a plurality of preset novel topics to form a mapping relationship. And determining a corresponding novel quotation template according to the determined novel theme and a preset mapping relation. And carrying out content completion on the novel quotation template according to the novel principal angle information to obtain the complete novel quotation.
In the embodiment of the invention, a plurality of novel quotation templates are preset, and the novel quotation templates are determined from the plurality of preset novel quotation templates according to a preset mapping relation according to novel subjects. Different novel quotation templates are determined according to different topics, so that the richness of the object language is improved, and the effect of content repetition is reduced. And carrying out content complement on the novel quotation template according to the novel main angle information, so as to obtain novel quotation, so that the novel quotation has stronger association with the virtual character, and the generated object file can enable the user to generate resonance, and the user experience is improved.
According to the virtual character object language pushing method provided by the invention, the step S31 comprises S51-S53.
S51, determining continuous information according to the writing state information, wherein the continuous information comprises continuous states and historical object text file subjects.
And S52, under the condition that the continuous loading state is continuous loading, determining the theme of the historical material language text file as a novel theme, and determining the novel principal angle information in the virtual character according to the novel theme and the event information.
And S53, determining the novel subject according to the event information under the condition that the continuous state is non-continuous, and determining the novel principal angle information in the virtual character according to the event information corresponding to the novel subject.
Specifically, the continuous loading state and the historical object text file theme can be determined according to the writing state information. And executing different determined novel subject and principal angle information strategies according to different loading states.
In the continuous state, the theme of the historical material language text file can be determined to be a novel theme, and novel principal angle information is determined in the virtual character according to the novel theme and the event information. The method and the device have the advantages that for the novel words in the continuous, the historical novel topics are determined to be the novel topics which are currently created, and then the novel main angle information is determined according to the novel topics, so that the consistency of the continuous topics is ensured, and the user experience is improved.
In the non-interlinked state, the novel subject can be determined according to the event information, and the novel principal angle information can be determined in the virtual character according to the novel subject and the event information. The method and the device have the advantages that for the non-carried and finished novel object, novel subjects are determined according to event information, so that the content of the generated object text has higher diversity.
Optionally, when determining the novel principal angle information, the virtual characters in the event information may be screened according to a preset limiting condition corresponding to the determined novel subject, for example, the novel subject is an love story, the limiting condition may be set to be that the principal angle is two people, the sex of the principal angle is a male or a female, and then the virtual characters are screened in the event information according to the limiting condition, so as to determine the novel principal angle information.
In the embodiment of the invention, the continuous loading state and the theme of the historical object text file are determined according to the writing state information, different novel theme determining strategies are executed according to different continuous loading states, and the main angle information is determined according to the novel theme. The method and the device have the advantages that the consistency of the subjects of the continuous load is ensured for the novel material words in the continuous load, and the user experience is improved. The method has the advantages that the content for generating new object language texts is more diversified for the non-carried novel object language.
According to the virtual character object language pushing method provided by the invention, the continuous information also comprises a historical object language text file;
in the case that the loading state is loading, step S33 specifically includes:
and inputting the novel quotation and the historical material language text file into the preset novel generation model to generate the material language text file.
In the embodiment of the invention, under the condition that the continuous loading state is continuous loading, the novel quotation and the historical object text file are input into the preset novel generation model, so that the continuous writing of the historical object text file is realized, the continuity of the object text file and the content of the historical object text file is ensured, and the user experience is improved.
The virtual character object pushing system provided by the invention is described below, and the virtual character object pushing system described below and the virtual character object pushing system described above can be correspondingly referred to each other. The modules of the virtual character and object pushing system described below may be software modules in a computer or may be physical modules independent of each other, which is not limited.
The invention also provides a virtual character object language pushing system, as shown in fig. 2, comprising:
the event pool module 21 is configured to obtain event information corresponding to the virtual character, and send a trigger instruction to the trigger module;
the trigger module 22 is configured to generate a push instruction and a idiom generation instruction according to the trigger instruction;
a material language generating module 23, configured to generate a material language file according to the material language generating instruction and the event information;
the pushing module 24 is configured to send the object document to the event pool module according to the pushing instruction;
the event pool module 21 is further configured to send the object file to a user terminal.
In the embodiment of the invention, event information corresponding to the virtual character is obtained through the event pool module, and a trigger instruction is sent to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to the user terminal. The method and the device realize the generation of the characteristic object language based on the event corresponding to the virtual character, improve the richness and diversity of the object language, and improve the user experience when pushing the user.
According to the virtual character object language pushing system provided by the invention, the object language generating module 23 comprises a novel generating sub-module, a voice synthesizing sub-module and a video generating sub-module;
the novel generation sub-module is used for calling the event information and a preset novel generation model according to the object language generation instruction to generate an object language text file;
the voice synthesis submodule is used for generating a material language audio file according to the material language text file, a preset background music file and a preset audio synthesis model;
and the video generation sub-module is used for generating the object language video file according to the object language audio file, the preset expression information, the preset action information and the preset video generation model.
According to the virtual character object language pushing system provided by the invention, the novel generation submodule is specifically used for:
determining novel subject and novel main angle information according to the event information and pre-stored writing state information;
determining a novel quotation according to the novel theme and the novel main angle information;
and generating a material language text file according to the novel primer and a preset novel generation model.
According to the virtual character object language pushing system provided by the invention, the novel generation submodule is specifically used for:
according to the novel subject, determining novel quotation templates in a plurality of preset novel quotation templates according to a preset mapping relation;
and determining the novel quotation according to the novel principal angle information and the novel quotation template.
According to the virtual character object language pushing system provided by the invention, the novel generation submodule is specifically used for:
determining continuous information according to the writing state information, wherein the continuous information comprises a continuous state and a historical object language text file theme;
under the condition that the continuous loading state is continuous loading, determining the theme of the historical object language text file as a novel theme, and determining the novel main angle information in the virtual character according to the novel theme and the event information;
and under the condition that the continuous loading state is not continuous loading, determining the novel subject according to the event information, and determining the novel principal angle information in the virtual character according to the event information corresponding to the novel subject.
According to the virtual character object language pushing system provided by the invention, the continuous information also comprises a historical object language text file;
the novel generation sub-module is specifically used for inputting the novel quotation and the historical object text file into the preset novel generation model to generate the object text file.
In one example based on the above embodiments, a virtual character object pushing flow is shown in fig. 3. The event pool module acquires event information corresponding to the virtual character, stores the event information into the event storage database and sends a trigger instruction to the trigger module. The triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction, sends the pushing instruction to the pushing module, and sends the material language generating instruction to the material language generating module. The novel method comprises the steps that a novel generation sub-module in a material language generation module calls event information in an event storage database according to a material language generation instruction, calls writing state information in a writing state information base, generates a material language text file according to the event information, the writing state information and a preset novel generation model, and updates the material language text file to the material language database. The voice synthesis sub-module invokes the object text file in the object database, generates an object audio file according to the object text file, and updates the object audio file to the object database. The video generation sub-module invokes the object language audio file in the object language database, generates the object language video file according to the object language audio file, and updates the object language video file to the object language database. The pushing module calls object language files (object language text files, object language audio files and object language video files) in the object language database according to the pushing instruction, and sends the object language files to the event pool module. And the time pool module sends the object language file to the user terminal to finish the pushing of the virtual character object language.
Fig. 4 illustrates a physical schematic diagram of an electronic device, as shown in fig. 4, which may include: processor 410, communication interface (Communications Interface) 420, memory 430 and communication bus 440, wherein processor 410, communication interface 420 and memory 430 communicate with each other via communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to execute a virtual character object pushing method applied to a character object pushing system, where the character object pushing system includes an event pool module, a trigger module, an object generating module, and a pushing module, the method includes: the event pool module acquires event information corresponding to the virtual character and sends a trigger instruction to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to a user terminal.
Further, the logic instructions in the memory 430 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, where the computer program product includes a computer program, where the computer program may be stored on a non-transitory computer readable storage medium, where the computer program when executed by a processor is capable of executing the virtual character object pushing method provided by the methods above, where the virtual character object pushing method is applied to a character object pushing system, where the character object pushing system includes an event pool module, a trigger module, an object generating module, and a pushing module, and the method includes: the event pool module acquires event information corresponding to the virtual character and sends a trigger instruction to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to a user terminal.
In still another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the methods described above to provide a virtual character object pushing method, applied to a character object pushing system, where the character object pushing system includes an event pool module, a trigger module, an object generating module, and a pushing module, the method includes: the event pool module acquires event information corresponding to the virtual character and sends a trigger instruction to the trigger module; the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction; the object language generating module generates an object language file according to the object language generating instruction and the event information; the pushing module sends the object language file to the event pool module according to the pushing instruction; and the event pool module sends the object language file to a user terminal.
The embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. The virtual character object language pushing method is characterized by being applied to a character object language pushing system, wherein the character object language pushing system comprises an event pool module, a triggering module, an object language generating module and a pushing module, and the method comprises the following steps:
the event pool module acquires event information corresponding to the virtual character and sends a trigger instruction to the trigger module;
the triggering module generates a pushing instruction and a material language generating instruction according to the triggering instruction;
the object language generating module generates an object language file according to the object language generating instruction and the event information;
the pushing module sends the object language file to the event pool module according to the pushing instruction;
the event pool module sends the object language file to a user terminal;
the object language generation module comprises a novel generation sub-module, a voice synthesis sub-module and a video generation sub-module;
the object language generating module generates an object language file according to the object language generating instruction and the event information, and the object language generating module comprises: the novel generation sub-module calls the event information and a preset novel generation model according to the object language generation instruction to generate an object language text file; the voice synthesis submodule generates a material language audio file according to the material language text file, a preset background music file and a preset audio synthesis model; the video generation sub-module generates a subject language video file according to the subject language audio file, preset expression information, preset action information and a preset video generation model;
the novel generation sub-module calls the event information, the pre-stored writing state information and a preset novel generation model according to the object language generation instruction to generate an object language text file, and the novel generation sub-module comprises the following steps: the novel generation sub-module determines novel subject and novel main angle information according to the event information and pre-stored writing state information; determining a novel quotation according to the novel theme and the novel main angle information; generating a material language text file according to the novel primer and a preset novel generation model;
said determining a novel quotation based on said novel subject and said novel principal angle information, comprising: according to the novel subject, determining novel quotation templates in a plurality of preset novel quotation templates according to a preset mapping relation; determining the novel quotation according to the novel principal angle information and the novel quotation template;
according to the event information and the pre-stored writing state information, the novel theme and novel main angle information are determined, and the method comprises the following steps: determining continuous information according to the writing state information, wherein the continuous information comprises a continuous state and a historical object language text file theme; under the condition that the continuous loading state is continuous loading, determining the theme of the historical object language text file as a novel theme, and determining the novel main angle information in the virtual character according to the novel theme and the event information; under the condition that the continuous loading state is non-continuous loading, determining the novel subject according to the event information, and determining the novel principal angle information in the virtual character according to the event information corresponding to the novel subject;
the continuous information also comprises a historical object language text file;
and under the condition that the continuous loading state is continuous loading, generating a material language text file according to the novel quotation and a preset novel generation model, wherein the material language text file comprises the following steps: and inputting the novel quotation and the historical material language text file into the preset novel generation model to generate the material language text file.
2. A virtual character object pushing system, comprising:
the event pool module is used for acquiring event information corresponding to the virtual character and sending a trigger instruction to the trigger module;
the triggering module is used for generating a pushing instruction and a material language generating instruction according to the triggering instruction;
the object language generation module is used for generating object language files according to the object language generation instruction and the event information;
the pushing module is used for sending the object language file to the event pool module according to the pushing instruction;
the event pool module is further used for sending the object language file to a user terminal;
the object language generation module comprises a novel generation sub-module, a voice synthesis sub-module and a video generation sub-module;
the novel generation sub-module is used for calling the event information and a preset novel generation model according to the object language generation instruction to generate an object language text file;
the voice synthesis submodule is used for generating a material language audio file according to the material language text file, a preset background music file and a preset audio synthesis model;
the video generation sub-module is used for generating a subject language video file according to the subject language audio file, preset expression information, preset action information and a preset video generation model;
the novel generation submodule is specifically used for: determining novel subject and novel main angle information according to the event information and pre-stored writing state information; determining a novel quotation according to the novel theme and the novel main angle information; generating a material language text file according to the novel primer and a preset novel generation model;
the novel generation submodule is specifically used for: according to the novel subject, determining novel quotation templates in a plurality of preset novel quotation templates according to a preset mapping relation; determining the novel quotation according to the novel principal angle information and the novel quotation template;
the novel generation submodule is specifically used for: determining continuous information according to the writing state information, wherein the continuous information comprises a continuous state and a historical object language text file theme; under the condition that the continuous loading state is continuous loading, determining the theme of the historical object language text file as a novel theme, and determining the novel main angle information in the virtual character according to the novel theme and the event information; under the condition that the continuous loading state is non-continuous loading, determining the novel subject according to the event information, and determining the novel principal angle information in the virtual character according to the event information corresponding to the novel subject;
the continuous information also comprises a historical object language text file;
the novel generation sub-module is specifically used for inputting the novel quotation and the historical object text file into the preset novel generation model to generate the object text file.
3. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the virtual character object pushing method of claim 1 when the program is executed.
4. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the virtual character object pushing method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310032652.2A CN115914366B (en) | 2023-01-10 | 2023-01-10 | Virtual character object language pushing method, system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310032652.2A CN115914366B (en) | 2023-01-10 | 2023-01-10 | Virtual character object language pushing method, system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115914366A CN115914366A (en) | 2023-04-04 |
| CN115914366B true CN115914366B (en) | 2023-06-30 |
Family
ID=86491530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310032652.2A Active CN115914366B (en) | 2023-01-10 | 2023-01-10 | Virtual character object language pushing method, system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115914366B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408786A (en) * | 2018-09-27 | 2019-03-01 | 武汉旖旎科技有限公司 | Intelligent novel assists authoring system |
| CN111383346A (en) * | 2020-03-03 | 2020-07-07 | 深圳创维－Rgb电子有限公司 | Interaction method and system based on intelligent voice, intelligent terminal and storage medium |
| CN114898746A (en) * | 2022-04-12 | 2022-08-12 | 青岛海尔科技有限公司 | Interaction method and device, storage medium and electronic device |
| CN114968459A (en) * | 2022-05-27 | 2022-08-30 | 重庆长安汽车股份有限公司 | Event processing method based on automobile AI intelligent assistant |
| CN114995636A (en) * | 2022-05-09 | 2022-09-02 | 阿里巴巴（中国）有限公司 | Multi-modal interaction method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160147383A1 (en) * | 2014-11-25 | 2016-05-26 | Mark C. Kneece | System for virtual event planning |
-
2023
- 2023-01-10 CN CN202310032652.2A patent/CN115914366B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408786A (en) * | 2018-09-27 | 2019-03-01 | 武汉旖旎科技有限公司 | Intelligent novel assists authoring system |
| CN111383346A (en) * | 2020-03-03 | 2020-07-07 | 深圳创维－Rgb电子有限公司 | Interaction method and system based on intelligent voice, intelligent terminal and storage medium |
| CN114898746A (en) * | 2022-04-12 | 2022-08-12 | 青岛海尔科技有限公司 | Interaction method and device, storage medium and electronic device |
| CN114995636A (en) * | 2022-05-09 | 2022-09-02 | 阿里巴巴（中国）有限公司 | Multi-modal interaction method and device |
| CN114968459A (en) * | 2022-05-27 | 2022-08-30 | 重庆长安汽车股份有限公司 | Event processing method based on automobile AI intelligent assistant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115914366A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10152965B2 (en) | Learning personalized entity pronunciations | |
| US8738375B2 (en) | System and method for optimizing speech recognition and natural language parameters with user feedback | |
| CN110751943A (en) | Voice emotion recognition method and device and related equipment | |
| US20170316775A1 (en) | Dialog device with dialog support generated using a mixture of language models combined using a recurrent neural network | |
| CN112259072A (en) | Voice conversion method and device and electronic equipment | |
| US9984679B2 (en) | System and method for optimizing speech recognition and natural language parameters with user feedback | |
| CN110046230B (en) | Method for generating recommended speaking collection, and recommended speaking method and device | |
| JP5834291B2 (en) | Voice recognition device, automatic response method, and automatic response program | |
| CN109377979B (en) | Method and system for updating welcome language | |
| JP6333329B2 (en) | Information processing apparatus, information processing method, and program | |
| JP2018129068A (en) | Information processing device, information processing method, and program | |
| CN109545203A (en) | Audio recognition method, device, equipment and storage medium | |
| CN111128175B (en) | Spoken language dialogue management method and system | |
| JPWO2018043138A1 (en) | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM | |
| CN115914366B (en) | Virtual character object language pushing method, system and electronic equipment | |
| CN117424956A (en) | Setting item processing method and device, electronic equipment and storage medium | |
| CN109272999A (en) | Information processing unit, its interactive method and storage medium | |
| CN117122927A (en) | NPC interaction method, device and storage medium | |
| CN107808662B (en) | Method and device for updating grammar rule base for speech recognition | |
| CN116312456A (en) | Voice dialogue script generation method and device and electronic equipment | |
| CN105118507B (en) | Voice activated control and its control method | |
| CN110349563B (en) | Dialogue personnel configuration method and system for voice dialogue platform | |
| KR102120936B1 (en) | System for providing customized character doll including smart phone | |
| CN108989589A (en) | A kind of intelligent call semantics recognition communication method and intelligent conversational system | |
| CN116633909B (en) | Conference management method and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |