CN117669691A

CN117669691A - Data processing method and device

Info

Publication number: CN117669691A
Application number: CN202311086784.XA
Authority: CN
Inventors: 卢冠松; 曾艺涵; 顾佳熙; 徐航; 许松岑; 张维
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2023-08-25
Filing date: 2023-08-25
Publication date: 2024-03-08

Abstract

A data processing method is applied to the field of artificial intelligence, and comprises the following steps: acquiring a first text and a first image; the first text is descriptive information of a person; the first image is an image obtained by generating a network on the condition of the first text, and the semantics of the first text comprise labels which are used for describing part of characteristics of the person; the first characteristic representation of the at least one body part associated with the tag is fused and the generation network is updated according to the fusion result. The method and the device can enable the trained generation network to have fine-grained data processing capability, and improve the effect of subsequent data generation.

Description

Data processing method and device

Technical Field

The present application relates to the field of artificial intelligence, and in particular, to a data processing method and apparatus thereof.

Background

Artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The goal of text-oriented generation tasks (e.g., 3D face generation) is to accomplish such things: taking 3D face generation as an example, given an input text, certain attributes of the face, such as color, skin tone, expression, etc., are described in the text, and the task is to generate a 3D face that conforms to the text description.

However, the two modalities of text and 3D information are very different, and how to accurately control 3D data generation with input text is a problem to be solved.

Disclosure of Invention

The application provides a data processing method, which utilizes labels contained in texts to fuse all local image features (related to the labels) obtained by a generating network, predicts the labels based on fusion results, enables the generating network after training to have fine-granularity data processing capability, and improves the effect of subsequent data generation.

In a first aspect, the present application provides a data processing method, the method comprising: acquiring a first text and a first image; the first text is descriptive information of a person; the first image is an image obtained by generating a network on the condition of the first text, the semantics of the first text comprise labels, and the labels comprise part of description features in the description information; respectively extracting features of at least one body part of a person contained in the first image to obtain at least one first feature representation; the tag is associated with the at least one body part; fusing the first characteristic representations of the at least one body part to obtain a third characteristic representation corresponding to the tag; and predicting corresponding labels according to the third characteristic representation, and updating the generated network according to the relation between the prediction result and the labels.

In the embodiment of the application, the labels contained in the text are utilized to fuse the local image features (related to the labels) obtained by the generating network, and the labels are predicted based on the fusion result, so that the generating network after training has fine-granularity data processing capability, and the effect of subsequent data generation is improved.

In one possible implementation, the method further comprises: extracting the characteristics of the label to obtain a second characteristic representation; said fusing of said first characteristic representation of said at least one said body part comprises: the first feature representation of the at least one body part is fused according to the similarity of the second feature representation and the at least one first feature representation.

In one possible implementation, the tag is used to describe a feature of the persona.

In one possible implementation, the feature extraction, according to the first image, by a first image encoder, is performed on a plurality of body parts of a person included in the first image, including: obtaining a segmentation map of each body part according to the first image; and respectively extracting the characteristics of the segmentation map of each body part through a first image encoder.

In one possible implementation, the segmentation map is obtained by masking the first image.

In one possible implementation, the generating network is configured to generate 3D information, where the first image is obtained by rendering the 3D information at a target viewing angle.

In a possible implementation, the predicting the corresponding tag according to the third feature representation, and updating the generating network according to the relationship between the prediction result and the tag, includes: and predicting corresponding labels according to the third characteristic representation, and updating the generating network and the first image encoder according to the relation between the prediction result and the labels.

In one possible implementation, the method further comprises: according to the first image, extracting the characteristics of the whole first image through a first image encoder to obtain a fourth characteristic representation; according to the first text, extracting features of the whole first text through a first text encoder to obtain a fifth feature representation; updating the generated network by contrast learning according to the fourth characteristic representation and the fifth characteristic representation.

In one possible implementation, the trained generation network can also have coarse-grained data processing capability through overall alignment of text and images, so that the effect of data generation is improved.

In one possible implementation, the method further comprises: acquiring a second text and a third text; the second text comprises descriptions of characters in the image to be generated and styles of the image to be generated; the third text does not carry the style information; respectively processing the second text and the third text according to the updated generation network to obtain a second image and a third image; updating the generated network according to the first association information and the second association information; the first association information indicates a relationship between the second text and the third text, and the second association information indicates a relationship between the second image and the third image.

By the method, the generation guide module based on the directional guide can enable the model to generate data of the style outside the training set.

In one possible implementation, the first association information is a direction vector between the second text and the third text, and the second association information indicates a direction vector between the second image and the third image.

In a second aspect, the present application provides a data processing apparatus, the apparatus comprising:

The acquisition module is used for acquiring a first text and a first image; the first text is descriptive information of a person; the first image is an image obtained by generating a network on the condition of the first text, the semantics of the first text comprise labels, and the labels comprise part of description features in the description information;

the processing module is used for respectively extracting the characteristics of at least one body part of the person contained in the first image to obtain at least one first characteristic representation; the tag is associated with the at least one body part; fusing the first characteristic representations of the at least one body part to obtain a third characteristic representation corresponding to the tag; and predicting corresponding labels according to the third characteristic representation, and updating the generated network according to the relation between the prediction result and the labels.

In one possible implementation, the processing module is further configured to:

extracting the characteristics of the label to obtain a second characteristic representation;

the processing module is specifically configured to:

the first feature representation of the at least one body part is fused according to the similarity of the second feature representation and the at least one first feature representation.

In one possible implementation, the processing module is specifically configured to:

obtaining a segmentation map of each body part according to the first image;

and respectively extracting the characteristics of the segmentation map of each body part.

and predicting corresponding labels according to the third characteristic representation, and updating the generating network and the first image encoder according to the relation between the prediction result and the labels.

In one possible implementation, the processing module is further configured to:

according to the first image, extracting the characteristics of the whole first image through a first image encoder to obtain a fourth characteristic representation;

according to the first text, extracting features of the whole first text through a first text encoder to obtain a fifth feature representation;

updating the generated network by contrast learning according to the fourth characteristic representation and the fifth characteristic representation.

In one possible implementation, the acquiring module is further configured to:

acquiring a second text and a third text; the second text comprises descriptions of characters in the image to be generated and styles of the image to be generated; the third text does not carry the style information;

the processing module is further configured to:

respectively processing the second text and the third text according to the updated generation network to obtain a second image and a third image;

updating the generated network according to the first association information and the second association information; the first association information indicates a relationship between the second text and the third text, and the second association information indicates a relationship between the second image and the third image.

In a third aspect, embodiments of the present application provide a data processing apparatus, which may include a memory, a processor, and a bus system, where the memory is configured to store a program, and the processor is configured to execute the program in the memory, so as to perform the method according to the first aspect and any optional method thereof.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, which when run on a computer causes the computer to perform the above-described first aspect and any of its optional methods.

In a fifth aspect, embodiments of the present application provide a computer program which, when run on a computer, causes the computer to perform the above first aspect and any of its alternative methods.

In a sixth aspect, the present application provides a chip system comprising a processor for supporting the execution of data processing means for performing the functions involved in the above aspects, e.g. for transmitting or processing data involved in the above methods; or, information. In one possible design, the chip system further includes a memory for holding program instructions and data necessary for the data processing apparatus. The chip system can be composed of chips, and can also comprise chips and other discrete devices.

Drawings

FIG. 1A is a schematic diagram of a structure of an artificial intelligence main body frame;

FIGS. 1B and 1C are illustrations of an application system framework of the present invention;

FIG. 1D is a schematic diagram of an alternative hardware architecture of a terminal;

FIG. 2 is a schematic diagram of a server;

FIG. 3 is a system architecture schematic of the present application;

FIG. 4A is a flow of a cloud service;

FIG. 4B is a schematic illustration of a network architecture;

FIG. 4C is a schematic representation of a network architecture;

FIG. 4D is a schematic representation of a network architecture;

FIG. 5 is a flowchart of a data processing method according to an embodiment of the present application;

FIG. 6 is a processing schematic of a data processing method according to an embodiment of the present application;

FIG. 7 is a processing schematic of a data processing method according to an embodiment of the present application;

FIG. 8 is a processing schematic of a data processing method according to an embodiment of the present application;

FIG. 9A is a processing schematic of a data processing method according to an embodiment of the present application;

FIG. 9B is a schematic illustration of the beneficial effects of an embodiment of the present application;

FIG. 10 is a schematic diagram of a data processing apparatus according to an embodiment of the present disclosure;

fig. 11 is a schematic structural diagram of an execution device according to an embodiment of the present application;

FIG. 12 is a schematic structural diagram of a training device according to an embodiment of the present disclosure;

fig. 13 is a schematic structural diagram of a chip according to an embodiment of the present application.

Detailed Description

Embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention. The terminology used in the description of the embodiments of the invention herein is for the purpose of describing particular embodiments of the invention only and is not intended to be limiting of the invention.

Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can appreciate, with the development of technology and the appearance of new scenes, the technical solutions provided in the embodiments of the present application are applicable to similar technical problems.

The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which the embodiments of the application described herein have been described for objects of the same nature. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

The terms "basic," "about," and the like are used herein as approximate terms, rather than as degree terms, and are intended to take into account inherent deviations in measured or calculated values that would be known to one of ordinary skill in the art. Furthermore, the use of "may" in describing embodiments of the present invention refers to "one or more embodiments that may be possible". The terms "use", "used", and "used" as used herein may be regarded as synonymous with the terms "utilized", "utilizing", and "utilized", respectively. In addition, the term "exemplary" is intended to refer to an instance or illustration.

Referring to fig. 1A, fig. 1A shows a schematic structural diagram of an artificial intelligence main body framework, and the artificial intelligence main body framework is described below from two dimensions of "intelligent information chain" (horizontal axis) and "IT value chain" (vertical axis). Where the "intelligent information chain" reflects a list of processes from the acquisition of data to the processing. For example, there may be general procedures of intelligent information awareness, intelligent information representation and formation, intelligent reasoning, intelligent decision making, intelligent execution and output. In this process, the data undergoes a "data-information-knowledge-wisdom" gel process. The "IT value chain" reflects the value that artificial intelligence brings to the information technology industry from the underlying infrastructure of personal intelligence, information (provisioning and processing technology implementation), to the industrial ecological process of the system.

(1) Infrastructure of

The infrastructure provides computing capability support for the artificial intelligence system, realizes communication with the outside world, and realizes support through the base platform. Communicating with the outside through the sensor; the computing power is provided by a smart chip (CPU, NPU, GPU, ASIC, FPGA and other hardware acceleration chips); the basic platform comprises a distributed computing framework, a network and other relevant platform guarantees and supports, and can comprise cloud storage, computing, interconnection and interworking networks and the like. For example, the sensor and external communication obtains data that is provided to a smart chip in a distributed computing system provided by the base platform for computation.

(2) Data

The data of the upper layer of the infrastructure is used to represent the data source in the field of artificial intelligence. The data relate to graphics, images, voice and text, and also relate to the internet of things data of the traditional equipment, including service data of the existing system and sensing data such as force, displacement, liquid level, temperature, humidity and the like.

(3) Data processing

Data processing typically includes data training, machine learning, deep learning, searching, reasoning, decision making, and the like.

Wherein machine learning and deep learning can perform symbolized and formalized intelligent information modeling, extraction, preprocessing, training and the like on data.

Reasoning refers to the process of simulating human intelligent reasoning modes in a computer or an intelligent system, and carrying out machine thinking and problem solving by using formal information according to a reasoning control strategy, and typical functions are searching and matching.

Decision making refers to the process of making decisions after intelligent information is inferred, and generally provides functions of classification, sequencing, prediction and the like.

(4) General capability

After the data has been processed, some general-purpose capabilities can be formed based on the result of the data processing, such as algorithms or a general-purpose system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.

(5) Intelligent product and industry application

The intelligent product and industry application refers to products and applications of an artificial intelligent system in various fields, is encapsulation of an artificial intelligent overall solution, and realizes land application by making intelligent information decisions, and the application fields mainly comprise: intelligent terminal, intelligent transportation, intelligent medical treatment, autopilot, smart city etc.

The method and the device can be applied to the field of natural language processing in the field of artificial intelligence, and a plurality of application scenes falling to the product are introduced by taking natural language processing as an example.

First, an application scenario of the present application is described, which may be, but not limited to, an application program with a generating function, or a cloud service provided by a cloud server, or the like. The generation function includes, but is not limited to, a 3D face generation function, and the like.

The following description will be made separately:

1. generating class applications

The product form of the embodiments of the present application may be a generic application. The generation class application may run on a terminal device or a server on the cloud side.

In one possible implementation, the generation class application may implement a text-based generation task, resulting in a processing result.

In one possible implementation, the user may open a generating class application program installed on the terminal device and input text data, where the generating class application program may perform data generation based on the text through a model trained by a method provided by an embodiment of the present application, or may perform data generation based on the text through a method provided by an embodiment of the present application, and may present a processing result to the user (a presentation manner may be, but is not limited to, displaying, playing, saving, uploading to a cloud side, etc.).

In one possible implementation, a user may open a generating class application installed on the terminal device and input text data, where the generating class application may send the text data to a server on the cloud side, and the server on the cloud side performs data generation based on the text through a model trained by using the method provided by the embodiment of the present application and returns a processing result to the terminal device, and the terminal device may present the processing result to the user (a presentation manner may be, but is not limited to, displaying, playing, saving, uploading to the cloud side, and so on).

By way of example, the generation task may be specifically applied but is not limited to the following scenario:

scene 1, text-guided 3D face generation (text-guided 3D face generation)

The goal of the text-oriented 3D face generation task is to accomplish one of the following: given an input text, certain attributes of the face, such as color, skin tone, expression, etc., are described in the text, the task is to generate a 3D face that conforms to the text description. For example, the geometry of the generated 3D face may be represented by a 3D mesh (mesh) and the texture by a 2D rendering of multiple perspectives.

Scene 2, data enhancement:

in machine learning, more training data will generally facilitate training of the machine learning model. Then a plurality of texts can be designed to generate new 3D face data as new training data, so that the data acquisition cost is saved, and the performance of the machine learning model is improved.

The generation class application in the embodiments of the present application is next described separately from the functional architecture and the product architecture that implements the functionality.

Referring to fig. 1B, fig. 1B is a schematic functional architecture of a class application generated in an embodiment of the present application:

in one possible implementation, as shown in FIG. 1B, the generation class application 102 may receive input parameters 101 (e.g., text) and generate processing results 103 (e.g., generated data). The generation class application 102 is executable on at least one computer system, for example, and includes computer code that, when executed by one or more computers, causes the computers to execute models for performing training by the methods provided by embodiments of the present application.

Referring to fig. 1C, fig. 1C is a schematic diagram of an entity architecture of a generating class application running in an embodiment of the present application:

referring to fig. 1C, fig. 1C shows a schematic diagram of a system architecture. The system may include a terminal 100 and a server 200. Wherein the server 200 may include one or more servers (illustrated in fig. 1C as including one server as an example), the server 200 may provide the generation function for one or more terminals.

The terminal 100 may install a generation-type application program, or open a web page related to a generation function, where the application program and the web page may provide an interface, the terminal 100 may receive related parameters input by a user on the generation function interface and send the parameters to the server 200, and the server 200 may obtain a processing result based on the received parameters and return the processing result to the terminal 100.

It should be understood that, in some alternative implementations, the terminal 100 may also perform actions of obtaining the processing result based on the received parameters by itself, without requiring a server to cooperate with the implementation, which is not limited by the embodiments of the present application.

Next, the product form of the terminal 100 in fig. 1C will be described;

The terminal 100 in the embodiment of the present application may be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (personal digital assistant, PDA), or the like, which is not limited in any way.

Fig. 1D shows an alternative hardware architecture diagram of the terminal 100.

Referring to fig. 1D, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), a processor 170, an external interface 180, a power supply 190, and the like. Those skilled in the art will appreciate that fig. 1D is merely an example of a terminal or multifunction device and is not limiting of the terminal or multifunction device and may include more or fewer components than shown, or may combine certain components, or different components.

The input unit 130 may be used to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the portable multifunction device. In particular, the input unit 130 may comprise a touch screen 131 (optional) and/or other input devices 132. The touch screen 131 may collect touch operations on or near the user (e.g., operations of the user on or near the touch screen using any suitable object such as a finger, a joint, a stylus, etc.), and drive the corresponding connection means according to a preset program. The touch screen can detect the touch action of a user on the touch screen, convert the touch action into a touch signal, send the touch signal to the processor 170, and receive and execute a command sent by the processor 170; the touch signal includes at least touch point coordinate information. The touch screen 131 may provide an input interface and an output interface between the terminal 100 and a user. In addition, the touch screen may be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 130 may include other input devices in addition to the touch screen 131. In particular, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, mouse, joystick, etc.

Wherein other input devices 132 may receive input text data.

The display unit 140 may be used to display information input by a user or information provided to the user, various menus of the terminal 100, an interactive interface, file display, and/or play of any of the multimedia files. In the embodiment of the present application, the display unit 140 may be used to display an interface for generating a class application, a processing result, and the like.

The memory 120 may be used to store instructions and data, and the memory 120 may mainly include a storage instruction area and a storage data area, and the storage data area may store various data, such as multimedia files, text, and the like; the store instruction area may store software elements such as operating systems, applications, instructions required for at least one function, or a subset, an extension set thereof. And may also include nonvolatile random access memory; providing processor 170 includes managing hardware, software, and data resources in the computing processing device, supporting control software and applications. And is also used for storing multimedia files and storing running programs and applications.

The processor 170 is a control center of the terminal 100, connects various parts of the entire terminal 100 using various interfaces and lines, and performs various functions of the terminal 100 and processes data by executing or executing instructions stored in the memory 120 and calling data stored in the memory 120, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor primarily handles operating systems, user interfaces, application programs, etc., and the modem processor primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 170. In some embodiments, the processor, memory, may be implemented on a single chip, or they may be implemented separately on separate chips in some embodiments. The processor 170 may be further configured to generate corresponding operation control signals to corresponding components of the computing processing device, and to read and process data in the software, and in particular, to read and process data and programs in the memory 120, so that each functional module therein performs a corresponding function, thereby controlling the corresponding components to act as required by the instructions.

The memory 120 may be used for storing software codes related to a data processing method, and the processor 170 may execute steps of the data processing method of the chip, or may schedule other units (such as the input unit 130 and the display unit 140) to implement corresponding functions.

The rf unit 110 (optional) may be configured to receive and send information or receive and send signals during a call, for example, after receiving downlink information of a base station, process the downlink information with the processor 170; in addition, the data of the design uplink is sent to the base station. Typically, RF circuitry includes, but is not limited to, antennas, at least one amplifier, transceivers, couplers, low noise amplifiers (Low Noise Amplifier, LNAs), diplexers, and the like. In addition, the radio frequency unit 110 may also communicate with network devices and other devices via wireless communications. The wireless communication may use any communication standard or protocol including, but not limited to, global system for mobile communications (Global System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), code division multiple access (Code Division Multiple Access, CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), long term evolution (Long Term Evolution, LTE), email, short message service (Short Messaging Service, SMS), and the like.

In this embodiment, the radio frequency unit 110 may send text data to the server 200 and receive a processing result sent by the server 200.

It should be appreciated that the radio unit 110 is optional and may be replaced with other communication interfaces, such as a portal.

The terminal 100 also includes a power supply 190 (e.g., a battery) for powering the various components, which may be logically connected to the processor 170 via a power management system, such as a power management system that performs functions such as charge, discharge, and power consumption management.

The terminal 100 further includes an external interface 180, which may be a standard Micro USB interface, or a multi-pin connector, which may be used to connect the terminal 100 to communicate with other devices, or may be used to connect a charger to charge the terminal 100.

Although not shown, the terminal 100 may further include a flash, a wireless fidelity (wireless fidelity, wiFi) module, a bluetooth module, sensors of different functions, etc., which will not be described herein. Some or all of the methods described below may be applied in the terminal 100 as shown in fig. 1D.

Next, the product form of the server 200 in fig. 1C will be described;

Fig. 2 provides a schematic structural diagram of a server 200, and as shown in fig. 2, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. Communication between processor 202, memory 204, and communication interface 203 is via bus 201.

Bus 201 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 2, but not only one bus or one type of bus.

The processor 202 may be any one or more of a central processing unit (central processing unit, CPU), a graphics processor (graphics processing unit, GPU), a Microprocessor (MP), or a digital signal processor (digital signal processor, DSP).

The memory 204 may include volatile memory (RAM), such as random access memory (random access memory). The memory 204 may also include a non-volatile memory (non-volatile memory), such as a read-only memory (ROM), a flash memory, a mechanical hard disk (HDD) or a solid state disk (solid state drive, SSD).

The memory 204 may be used for storing software codes related to a data processing method, and the processor 202 may execute steps of the data processing method of the chip, or may schedule other units to implement corresponding functions.

It should be appreciated that the terminal 100 and the server 200 may be centralized or distributed devices, and the processors (e.g., the processor 170 and the processor 202) in the terminal 100 and the server 200 may be hardware circuits (such as an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (field-programmable gate array, FPGA), a general purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor, or a microcontroller, etc.), or a combination of these hardware circuits, for example, the processor may be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the hardware system without an instruction execution function and a hardware system with an instruction execution function.

It should be understood that the steps related to the model reasoning process in the embodiments of the present application relate to AI-related operations, and the instruction execution architecture of the terminal device and the server is not limited to the architecture of the processor combined with the memory described above when performing AI operations. The system architecture provided in the embodiment of the present application is described in detail below with reference to fig. 3.

Fig. 3 is a schematic diagram of a system architecture according to an embodiment of the present application. As shown in fig. 3, the system architecture 500 includes an execution device 510, a training device 520, a database 530, a client device 540, a data storage system 550, and a data acquisition system 560.

The execution device 510 includes a computing module 511, an I/O interface 512, a preprocessing module 513, and a preprocessing module 514. The calculation module 511 may include a target model/rule 501 therein, with the preprocessing module 513 and preprocessing module 514 being optional.

The executing device 510 may be a terminal device or a server that generates a class application for the above operation.

The data acquisition device 560 is used to acquire training samples. The training samples may be text data, image data, etc. After the training samples are collected, the data collection device 560 stores the training samples in the database 530.

The training device 520 may maintain training samples based on the database 530 to obtain a target model/rule 501 for a neural network to be trained (e.g., a neural network model (e.g., including an image encoder, a text encoder, a data generation network, etc.) in embodiments of the present application).

It should be appreciated that the training device 520 may perform a pre-training process on the neural network to be trained based on maintaining training samples in the database 530, or fine-tuning of the model based on the pre-training.

It should be noted that, in practical applications, the training samples maintained in the database 530 are not necessarily all acquired by the data acquisition device 560, but may be received from other devices. It should be noted that the training device 520 is not necessarily completely based on the training samples maintained by the database 530 to perform training of the target model/rule 501, and it is also possible to obtain the training samples from the cloud or other places to perform model training, which should not be taken as a limitation of the embodiments of the present application.

The target model/rule 501 obtained by training according to the training device 520 may be applied to different systems or devices, such as the executing device 510 shown in fig. 3, where the executing device 510 may be a terminal, such as a mobile phone terminal, a tablet computer, a notebook computer, an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a vehicle-mounted terminal, or may be a server.

Specifically, the training device 520 may pass the trained model to the execution device 510.

In fig. 3, an execution device 510 configures an input/output (I/O) interface 512 for data interaction with an external device, and a user may input data (e.g., text data, image data, etc. in the embodiments of the present application) to the I/O interface 512 through a client device 540.

The preprocessing module 513 and the preprocessing module 514 are used for preprocessing according to the input data received by the I/O interface 512. It should be appreciated that there may be no pre-processing module 513 and pre-processing module 514 or only one pre-processing module. When the preprocessing module 513 and the preprocessing module 514 are not present, the calculation module 511 may be directly employed to process the input data.

In preprocessing input data by the execution device 510, or in performing processing related to computation or the like by the computation module 511 of the execution device 510, the execution device 510 may call data, codes or the like in the data storage system 550 for corresponding processing, or may store data, instructions or the like obtained by corresponding processing in the data storage system 550.

Finally, the I/O interface 512 provides the processing results to the client device 540, and thus to the user.

In the case shown in FIG. 3, the user may manually give input data, which may be manipulated through an interface provided by I/O interface 512. In another case, the client device 540 may automatically send the input data to the I/O interface 512, and if the client device 540 is required to automatically send the input data requiring authorization from the user, the user may set the corresponding permissions in the client device 540. The user may view the results output by the execution device 510 at the client device 540, and the specific presentation may be in the form of a display, a sound, an action, or the like. The client device 540 may also be used as a data collection terminal to collect input data from the input I/O interface 512 and output data from the output I/O interface 512 as new sample data, and store the new sample data in the database 530. Of course, instead of being collected by the client device 540, the I/O interface 512 may directly store the input data of the I/O interface 512 and the output result of the I/O interface 512 as new sample data into the database 530.

It should be noted that fig. 3 is only a schematic diagram of a system architecture provided in the embodiment of the present application, and the positional relationship among devices, apparatuses, modules, etc. shown in the drawing is not limited in any way, for example, in fig. 3, the data storage system 550 is an external memory with respect to the execution device 510, and in other cases, the data storage system 550 may be disposed in the execution device 510. It should be appreciated that the execution device 510 described above may be deployed in a client device 540.

From the reasoning side of the model:

in this embodiment of the present application, the computing module 511 of the executing device 510 may obtain codes stored in the data storage system 550 to implement the steps related to the model reasoning process in this embodiment of the present application.

In this embodiment, the computing module 511 of the execution device 510 may include a hardware circuit (such as an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (field-programmable gate array, FPGA), a general purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor, or a microcontroller, etc.), or a combination of these hardware circuits, for example, the training device 520 may be a hardware system with an instruction execution function, such as a CPU, a DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above hardware systems without an instruction execution function and a hardware system with an instruction execution function.

Specifically, the computing module 511 of the executing device 510 may be a hardware system with an instruction executing function, the steps related to the model reasoning process provided in the embodiments of the present application may be software codes stored in a memory, and the computing module 511 of the executing device 510 may obtain the software codes from the memory and execute the obtained software codes to implement the steps related to the model reasoning process provided in the embodiments of the present application.

It should be understood that, the computing module 511 of the execution device 510 may be a combination of a hardware system that does not have an instruction execution function and a hardware system that has an instruction execution function, and some of the steps related to the model reasoning process provided in the embodiments of the present application may also be implemented by a hardware system that does not have an instruction execution function in the computing module 511 of the execution device 510, which is not limited herein.

From the training side of the model:

in this embodiment of the present application, the training device 520 may obtain codes stored in a memory (not shown in fig. 3, and may be integrated into the training device 520 or disposed separately from the training device 520) to implement the steps related to model training in this embodiment of the present application.

In this embodiment, the training device 520 may include hardware circuits (such as an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (field-programmable gate array, FPGA), a general purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor, or a microcontroller, etc.), or a combination of these hardware circuits, for example, the training device 520 may be a hardware system having an instruction execution function, such as a CPU, a DSP, etc., or a hardware system not having an instruction execution function, such as an ASIC, an FPGA, etc., or a combination of the above hardware systems not having an instruction execution function and a hardware system having an instruction execution function.

It should be understood that, the training device 520 may be a combination of a hardware system without an instruction execution function and a hardware system with an instruction execution function, and some steps related to training a model provided in the embodiment of the present application may also be implemented by a hardware system without an instruction execution function in the training device 520, which is not limited herein.

2. Generating a function cloud-like service provided by a server:

in one possible implementation, the server may provide the end side with a service that generates functionality through an application programming interface (application programming interface, API).

The terminal device may send relevant parameters (such as text and other data) to the server through an API provided by the cloud, where the server may obtain a processing result based on the received parameters, and return the processing result to the terminal.

The description of the terminal and the server may be described in the above embodiments, and will not be repeated here.

Fig. 4A illustrates a flow of generating a functional cloud-like service provided using a cloud platform.

1. And opening and purchasing the content auditing service.

2. The user can download a software development kit (software development kit, SDK) corresponding to the content auditing service, and generally the cloud platform provides a plurality of development versions of SDKs for the user to select according to requirements of a development environment, for example, a JAVA version of SDK, a python version of SDK, a PHP version of SDK, an Android version of SDK, and the like.

3. After downloading the SDK of the corresponding version to the local according to the requirement, the user imports the SDK project into the local development environment, configures and debugs the SDK project in the local development environment, and develops other functions by the local development environment, so that an application integrating the capability of generating the function class is formed.

4. The generating function class application can trigger the API call of the generating function when the generating function is needed in the process of being used. When the application triggers the generating function, an API request is initiated to an operating instance of the generating function class service in the cloud environment, wherein the API request carries text, and the operating instance in the cloud environment processes the text to obtain a processing result.

5. The cloud environment returns the processing result to the application, thereby completing one generation function call.

Since the embodiments of the present application relate to a large number of applications of neural networks, for ease of understanding, related terms and related concepts of the neural networks related to the embodiments of the present application will be described below.

(1) Neural network

The neural network may be composed of neural units, which may refer to an arithmetic unit with xs (i.e., input data) and intercept 1 as inputs, and the output of the arithmetic unit may be:

Where s=1, 2, … … n, n is a natural number greater than 1, ws is the weight of xs, and b is the bias of the neural unit. f is an activation function (activation functions) of the neural unit for introducing a nonlinear characteristic into the neural network to convert an input signal in the neural unit to an output signal. The output signal of the activation function may be used as an input to a next convolutional layer, and the activation function may be a sigmoid function. A neural network is a network formed by joining together a plurality of the above-described single neural units, i.e., the output of one neural unit may be the input of another neural unit. The input of each neural unit may be connected to a local receptive field of a previous layer to extract features of the local receptive field, which may be an area composed of several neural units.

(2) The convolutional neural network (convolutional neuron network, CNN) is a deep neural network with a convolutional structure. The convolutional neural network comprises a feature extractor consisting of a convolutional layer and a sub-sampling layer, which can be regarded as a filter. The convolution layer refers to a neuron layer in the convolution neural network, which performs convolution processing on an input signal. In the convolutional layer of the convolutional neural network, one neuron may be connected with only a part of adjacent layer neurons. A convolutional layer typically contains a number of feature planes, each of which may be composed of a number of neural elements arranged in a rectangular pattern. Neural elements of the same feature plane share weights, where the shared weights are convolution kernels. Sharing weights can be understood as the way features are extracted independent of location. The convolution kernel can be formed in a matrix with random size, and reasonable weight can be obtained through learning in the training process of the convolution neural network. In addition, the direct benefit of sharing weights is to reduce the connections between layers of the convolutional neural network, while reducing the risk of overfitting.

CNN is a very common neural network, and the structure of CNN is described in detail below with reference to fig. 4B. As described in the foregoing description of the basic concept, the convolutional neural network is a deep neural network with a convolutional structure, and is a deep learning architecture, where the deep learning architecture refers to learning at multiple levels at different abstraction levels through machine learning algorithms. As a deep learning architecture, CNN is a feed-forward artificial neural network in which individual neurons can respond to an image input thereto.

As shown in fig. 4B, convolutional Neural Network (CNN) 200 may include an input layer 210, a convolutional layer/pooling layer 220 (where the pooling layer is optional), and a fully-connected layer (fully connected layer) 230.

Convolution layer/pooling layer 220:

convolution layer:

the convolution/pooling layer 220 as shown in fig. 4B may include layers as examples 221-226, for example: in one implementation, layer 221 is a convolutional layer, layer 222 is a pooling layer, layer 223 is a convolutional layer, layer 224 is a pooling layer, layer 225 is a convolutional layer, and layer 226 is a pooling layer; in another implementation, 221, 222 are convolutional layers, 223 are pooling layers, 224, 225 are convolutional layers, and 226 are pooling layers. I.e. the output of the convolution layer may be used as input to a subsequent pooling layer or as input to another convolution layer to continue the convolution operation.

The internal principle of operation of one convolution layer will be described below using the convolution layer 221 as an example.

The convolution layer 221 may include a plurality of convolution operators, also known as kernels, which function in image processing as a filter to extract specific information from the input image matrix, which may be a weight matrix in nature, which is typically predefined, and which is typically processed on the input image in a horizontal direction, pixel by pixel (or two pixels by two pixels … …, depending on the value of the step size stride), to accomplish the task of extracting specific features from the image. The size of the weight matrix should be related to the size of the image, and it should be noted that the depth dimension (depth dimension) of the weight matrix is the same as the depth dimension of the input image, and the weight matrix extends to the entire depth of the input image during the convolution operation. Thus, convolving with a single weight matrix produces a convolved output of a single depth dimension, but in most cases does not use a single weight matrix, but instead applies multiple weight matrices of the same size (row by column), i.e., multiple homography matrices. The outputs of each weight matrix are stacked to form the depth dimension of the convolved image, where the dimension is understood to be determined by the "multiple" as described above. Different weight matrices may be used to extract different features in the image, e.g., one weight matrix is used to extract image edge information, another weight matrix is used to extract a particular color of the image, yet another weight matrix is used to blur unwanted noise in the image, etc. The plurality of weight matrixes have the same size (row and column), the feature images extracted by the plurality of weight matrixes with the same size have the same size, and the extracted feature images with the same size are combined to form the output of convolution operation.

The weight values in the weight matrices are required to be obtained through a large amount of training in practical application, and each weight matrix formed by the weight values obtained through training can be used for extracting information from an input image, so that the convolutional neural network 200 can perform correct prediction.

When convolutional neural network 200 has multiple convolutional layers, the initial convolutional layer (e.g., 221) tends to extract more general features, which may also be referred to as low-level features; as the depth of the convolutional neural network 200 increases, features extracted by the later convolutional layers (e.g., 226) become more complex, such as features of high level semantics, which are more suitable for the problem to be solved.

Pooling layer:

since it is often desirable to reduce the number of training parameters, the convolutional layers often require periodic introduction of pooling layers, one convolutional layer followed by one pooling layer, or multiple convolutional layers followed by one or more pooling layers, as illustrated by layers 221-226 in FIG. 4B 220. The only purpose of the pooling layer during image processing is to reduce the spatial size of the image. The pooling layer may include an average pooling operator and/or a maximum pooling operator for sampling the input image to obtain a smaller size image. The average pooling operator may calculate pixel values in the image over a particular range to produce an average as a result of the average pooling. The max pooling operator may take the pixel with the largest value in a particular range as the result of max pooling. In addition, just as the size of the weighting matrix used in the convolutional layer should be related to the image size, the operators in the pooling layer should also be related to the image size. The size of the image output after the processing by the pooling layer can be smaller than the size of the image input to the pooling layer, and each pixel point in the image output by the pooling layer represents the average value or the maximum value of the corresponding sub-region of the image input to the pooling layer.

Full connection layer 230:

after processing by the convolutional layer/pooling layer 220, the convolutional neural network 200 is not yet sufficient to output the desired output information. Because, as previously described, the convolution/pooling layer 220 will only extract features and reduce the parameters imposed by the input image. However, in order to process the final output information (the required class information or other related information), convolutional neural network 200 needs to utilize fully-connected layer 230 to process the output of one or a set of the required number of classes. Thus, multiple hidden layers (231, 232 to 23n as shown in fig. 4B) may be included in the fully-connected layer 230, and parameters included in the multiple hidden layers may be pre-trained according to relevant training data of a specific task type, e.g., the task type may include image recognition, image classification, image super-resolution reconstruction, etc. … …

After the hidden layers in the fully connected layer 230, i.e., the final layer of the overall convolutional neural network 200 is the output layer 240, the output layer 240 has a class-cross entropy-like loss function, specifically for calculating the prediction error, once the forward propagation of the overall convolutional neural network 200 (e.g., propagation in the direction from 210 to 240 in fig. 4B is forward propagation) is completed, the backward propagation (e.g., propagation in the direction from 240 to 210 in fig. 4B is backward propagation) will begin to update the weights and deviations of the aforementioned layers to reduce the loss of the convolutional neural network 200 and the error between the result output by the convolutional neural network 200 through the output layer and the ideal result.

It should be noted that the convolutional neural network 200 shown in fig. 4B is only an example of a convolutional neural network, and in a specific application, the convolutional neural network may also exist in the form of other network models, for example, only includes a part of the network structure shown in fig. 4B, for example, the convolutional neural network used in the embodiment of the present application may include only the input layer 210, the convolutional layer/pooling layer 220, and the output layer 240.

It should be noted that, the convolutional neural network 100 shown in fig. 4B is only an example of a convolutional neural network, and in a specific application, the convolutional neural network may also exist in the form of other network models, for example, a plurality of convolutional layers/pooling layers shown in fig. 4C are parallel, and the features extracted respectively are all input to the fully-connected layer 230 for processing.

(3) Deep neural network

Deep neural networks (Deep Neural Network, DNN), also known as multi-layer neural networks, can be understood as havingMany hidden layers of the neural network, there are no particular metrics for "many" here. From DNNs, which are divided by the location of the different layers, the neural networks inside the DNNs can be divided into three categories: input layer, hidden layer, output layer. Typically the first layer is the input layer, the last layer is the output layer, and the intermediate layers are all hidden layers. The layers are fully connected, that is, any neuron in the i-th layer must be connected to any neuron in the i+1-th layer. Although DNN appears to be complex, it is not really complex in terms of the work of each layer, simply the following linear relational expression: Wherein (1)>Is an input vector, +.>Is the output vector, +.>Is the offset vector, W is the weight matrix (also called coefficient), and α () is the activation function. Each layer is only for the input vector +.>The output vector is obtained by such simple operation>Since DNN has a large number of layers, the coefficient W and the offset vector +.>And thus a large number. The definition of these parameters in DNN is as follows: taking the coefficient W as an example: it is assumed that in DNN of one three layers, the linear coefficients of the 4 th neuron of the second layer to the 2 nd neuron of the third layer are defined as +.>The superscript 3 represents the number of layers in which the coefficient W is located, and the subscript corresponds to the output third layer index2 and the entered second layer index 4.

The summary is: the coefficients of the kth neuron of the L-1 th layer to the jth neuron of the L-1 th layer are defined as

It should be noted that the input layer is devoid of W parameters. In deep neural networks, more hidden layers make the network more capable of characterizing complex situations in the real world. Theoretically, the more parameters the higher the model complexity, the greater the "capacity", meaning that it can accomplish more complex learning tasks. The process of training the deep neural network, i.e. learning the weight matrix, has the final objective of obtaining a weight matrix (a weight matrix formed by a number of layers of vectors W) for all layers of the trained deep neural network.

(4) Transformer layer

Referring to fig. 4D, fig. 4D is an architecture schematic of a transducer layer, as shown in fig. 4D, the neural network includes an embedded layer and at least one transducer layer, which may be N transducer layers (N is an integer greater than 0), wherein each transducer layer includes an attention layer, a sum and normalization (add & norm) layer, a feed forward (feed forward) layer, and a sum and normalization layer, which are sequentially adjacent. At the embedding layer, embedding the current input to obtain a plurality of feature vectors; in the attention layer, P input vectors are obtained from the upper layer of the transducer layer, any first input vector in the P input vectors is taken as a center, and based on the association degree between each input vector and the first input vector in the preset attention window range, the intermediate vector corresponding to the first input vector is obtained, and the P intermediate vectors corresponding to the P input vectors are determined in this way; and merging the P intermediate vectors into Q output vectors at the pooling layer, wherein a plurality of output vectors obtained by the last transducer layer in at least one transducer layer are used as the characteristic representation of the current input.

Next, the steps described above are specifically described with reference to specific examples.

First, at the embedding layer, embedding processing is performed on the current input to obtain a plurality of feature vectors.

The embedding layer may be referred to as an input embedding (input embedding) layer. The current input may be a text input, for example, a text segment, or a sentence. The text can be Chinese text, english text, or other language text. After the embedding layer acquires the current input, the embedding layer can embed each word in the current input, and the feature vector of each word can be obtained. In some embodiments, as shown in fig. 4D, the embedded layers include an input embedded layer and a position-coding (positional encoding) layer. In the input embedding layer, word embedding processing can be performed on each word in the current input, so that word embedding vectors of each word are obtained. The position coding layer may obtain the position of each word in the current input, and then process the position vector for each word position. In some examples, the location of each word may be the absolute location of each word in the current input. Taking the current input of "several numbers should be also expressed as examples, the position of" several "may be expressed as a first position, and the position of" number "may be expressed as a second position, … …. In some examples, the location of the respective words may be a relative location between the respective words. Still taking the current input of "number payable" as an example, the position of "number" may be indicated before "number", and the position of "number" may be indicated after "number" and before "payable", … …. When the word embedding vector and the position vector of each word in the current input are obtained, the position vector of each word and the corresponding word embedding vector can be combined to obtain each word feature vector, and then a plurality of feature vectors corresponding to the current input are obtained. The plurality of feature vectors may be represented as an embedded matrix having a predetermined dimension. The number of feature vectors in the plurality of feature vectors may be set to be M, and the preset dimension may be set to be H, and the plurality of feature vectors may be represented as an m×h embedding matrix.

And secondly, acquiring P input vectors from the upper layer of the first transducer layer, taking any first input vector in the P input vectors as a center, and obtaining an intermediate vector corresponding to the first input vector based on the association degree between each input vector and the first input vector in a preset attention window range, so as to determine the P intermediate vectors corresponding to the P input vectors. The attention layer may also be referred to as a multi-head attention (multi-head attention) layer. In one example, the attention layer may be a fixed window multi-head attention (fixed window multi-head attention) layer.

In some embodiments, the first transducer layer may be a layer next to the embedded layer described above, and the P input vectors are the plurality of feature vectors derived from the embedded layer. In some embodiments, at least one transducer layer in the neural network provided by embodiments of the present disclosure further comprises a second transducer layer. The second transducer layer is the layer above the first self-attention, and the P input vectors are P output vectors output by the second transducer layer. At the last transducer layer in the neural network, the multiple output vectors from the above steps can be used as a representation of the characteristics of the current input. The feature representation is a representation of a feature suitable for computer processing for the current input.

(5) Attention mechanism (attention mechanism)

The attention mechanism mimics the internal process of biological observation behavior, i.e., a mechanism that aligns internal experience with external sensations to increase the observation finesse of a partial region, enabling rapid screening of high value information from a large amount of information with limited attention resources. Attention mechanisms can quickly extract important features of sparse data and are thus widely used for natural language processing tasks, particularly machine translation. While the self-attention mechanism (self-attention mechanism) is an improvement of the attention mechanism, which reduces reliance on external information, and is more adept at capturing internal dependencies of data or features. The essential idea of the attention mechanism can be rewritten as the following formula:

wherein lx= |source|represents the length of Source, the meaning of the formula is that the constituent elements in Source are imagined to be composed of a series of data pairs, at this time, given an element Query in a Target, the weight coefficient of Value corresponding to each Key is obtained by calculating the similarity or correlation of the Query and each Key, and then the Value is weighted and summed, thus obtaining the final Value. The attribute mechanism essentially performs weighted summation on the Value values of the elements in the Source, and Query and Key are used to calculate the weight coefficients for the corresponding values. Conceptually, attention is understood to mean that a small amount of important information is selectively screened out from a large amount of information and focused on the important information, and most of the unimportant information is ignored. The focusing process is embodied in the calculation of a weight coefficient, and the larger the weight is, the more focused on the Value corresponding to the weight is, namely the weight represents the importance of the information, and the Value is the information corresponding to the weight. The self-Attention mechanism is understood to be internal Attention (intra Attention), and the Attention mechanism occurs between the element Query of the Target and all elements in the Source, and the self-Attention mechanism is understood to be the Attention mechanism occurring between the elements in the Source or between the elements in the Target, or is understood to be the Attention computing mechanism in the special case of target=source, and the specific computing process is the same, except that the computing object changes.

(6) Loss function

In training the deep neural network, since the output of the deep neural network is expected to be as close to the value actually expected, the weight vector of each layer of the neural network can be updated by comparing the predicted value of the current network with the actually expected target value according to the difference between the predicted value of the current network and the actually expected target value (of course, there is usually an initialization process before the first update, that is, the pre-configuration parameters of each layer in the deep neural network), for example, if the predicted value of the network is higher, the weight vector is adjusted to be predicted to be lower, and the adjustment is continued until the deep neural network can predict the actually expected target value or the value very close to the actually expected target value. Thus, it is necessary to define in advance "how to compare the difference between the predicted value and the target value", which is a loss function (loss function) or an objective function (objective function), which are important equations for measuring the difference between the predicted value and the target value. Taking the loss function as an example, the higher the output value (loss) of the loss function is, the larger the difference is, and then the training of the deep neural network becomes a process of reducing the loss as much as possible.

(7) Back propagation algorithm

An error Back Propagation (BP) algorithm may be used to correct the magnitude of the parameters in the initial model during the training process, so that the error loss of the model is smaller and smaller. Specifically, the input signal is forward-transferred until output, and error loss occurs, and parameters in the initial model are updated by back-propagating the error loss information, so that the error loss converges. The back propagation algorithm is a back propagation motion that dominates the error loss, aiming at deriving optimal model parameters, such as a weight matrix.

The embodiment of the application mainly solves the problem of how to accurately control the attribute of the generated 3D face by using the input text and how to generate the 3D faces with different styles (such as Picks style, line drawing style and the like) in the text-oriented 3D face generation task.

The embodiment of the application provides a data processing method. The following describes the data processing method of the embodiment of the present application in detail with reference to the accompanying drawings.

Referring to fig. 5, fig. 5 is a flowchart of a data processing method provided in an embodiment of the present application, and as shown in fig. 5, the data processing method provided in the embodiment of the present application may include steps 501 to 504, and the steps are described in detail below respectively.

501. Acquiring a first text and a first image; the first text is descriptive information of a person; the first image is an image obtained by generating a network on the condition of the first text, the semantics of the first text comprise labels, and the labels comprise part of description features in the description information;

for example, the description information of the person may include a plurality of description features for the person, and the tag may be composed of a part of the description features among the plurality of description features.

Wherein the first text may be a natural language description indicating the generated image, the semantics of the text may indicate the generated image content. For example, in the generation of the data including the person, the first text may be descriptive information of the person included in the first image. For example, in a task of face generation, the first text may include features of the generated face.

The first image may be obtained by generating a network on the condition that the first text is used, for example, the first image may be processed by a text encoder to obtain a text feature representation, the generating network may process the text feature representation to obtain 3D information, and the first image may be a rendered image of the 3D information.

Taking a 3D face generation task as an example, when generating data based on text, referring to fig. 6, text s can be processed by a text encoder to obtain text features, a generation network (such as a Mapping network and a StyleGAN2 generator network shown in fig. 6) taking the text as conditions is used, camera parameters p, text features e and noise z are taken as inputs, a Tri-plane representation of a 3D face is generated through the Mapping network and the StyleGAN2 generator network, and then a 2D face image corresponding to camera parameters and text description is rendered through a Decoder network and a Neural Volume Rendering module.

In this embodiment of the present application, in order to enable the generating network to have fine-grained information processing capability when training the generating network, after obtaining the image obtained by the generating network, at least one tag including the tag may be determined according to the semantics of the text (or the tag is preset and stored in a training sample). Wherein each tag may be used to describe a feature of a person. In the face generation task, each tag may be used to describe an attribute feature of a part of the face.

For example, referring to fig. 7, one label may be used to describe color development ("black hair"), one label may be used to describe facial features ("musche"), one label may be used to describe skin tone ("skin"), and one label may be used to describe age ("young").

502. Respectively extracting features of at least one body part of a person contained in the first image to obtain at least one first feature representation; the tag is associated with the at least one body part;

in one possible implementation, the tag may also be feature extracted by a text encoder to obtain a second feature representation.

For example, a text encoder may be used to extract a corresponding feature representation (i.e., a second feature representation in embodiments of the present application, such as "Part-Level Text Features" h1 through hN shown in fig. 7) for each tag, including the tag.

Wherein the text encoder may be a pre-trained model.

In one possible implementation, the tag is associated with at least one body part of the person, where association is understood to mean that the characteristics of one or more parts affect the description of the corresponding tag. For example, a color label may be associated with a segmentation map of the hair region, a facial feature label may be associated with a segmentation map of the hair region, and a skin color label may be associated with a segmentation map of the eyebrow, face region.

In the face generation task, the body part may be a part on the face.

In one possible implementation, feature extraction may be performed by obtaining a body part associated with the tag from the first image.

For example, a segmentation map of the body part associated with the tag may be obtained from the first image; and respectively extracting the characteristics of the segmentation map of each body part through a first image encoder.

For example, "part-level image mask" shown in fig. 6 includes a hair segmentation map, an eye segmentation map, an eyebrow segmentation map, a face segmentation map, a nose segmentation map, and a mouth segmentation map.

As shown in fig. 6, a mask ("Part-Level Image mask") for each Part may be obtained for the Face Image x using a Face segmentation network ("Face segmentation") and then a first Image encoder ("Feature Extractor") may be used to obtain the Face local Image features (i.e., the first feature representation in the embodiment of the present application, such as "Part-Level Image Features" f1 through fM in fig. 6).

503. Fusing the first characteristic representations of the at least one body part to obtain a third characteristic representation corresponding to the tag;

In one possible implementation, the first feature representation of the at least one body part may be fused according to a similarity of the second feature representation and the at least one first feature representation.

In embodiments of the present application, a similarity may be calculated between the second characteristic representation of each of the tags, including the tag, and the first characteristic representation of the associated body part.

504. And predicting corresponding labels according to the third characteristic representation, and updating the generated network according to the relation between the prediction result and the labels.

For example, referring to fig. 7, in a face generating task, a similarity Score Map ("Score Map") between a face local image feature and a face local text feature may be calculated, and the face local image feature is aggregated according to the Score Map to obtain a fine-grained face image feature ("Aggregated Image Features"), so that attribute prediction is performed on the generated face image through a Classifier network "Classifier", and thus fine-grained text-face alignment is performed.

In one possible implementation, the image encoder may be updated in addition to the generation network, i.e. the corresponding tag may be predicted from the third characteristic representation and the generation network and the first image encoder may be updated according to the prediction result.

In the embodiment of the application, the local image features are fused by utilizing the similarity between the labels contained in the text and the local image features obtained by the generating network, and the labels are predicted based on the fusion result, so that the generating network after training has fine-granularity data processing capability, and the effect of subsequent data generation is improved.

In one possible implementation, the trained generation network can also have coarse-grained data processing capability through overall alignment of the text and the image, so that the effect of subsequent data generation is improved.

In one possible implementation, the feature extraction may be performed on the whole first image by a first image encoder according to the first image, so as to obtain a fourth feature representation; according to the first text, extracting features of the whole first text through a first text encoder to obtain a fifth feature representation; updating the generated network by contrast learning according to the fourth characteristic representation and the fifth characteristic representation.

For example, reference may be made to Text-to-face alignment module (Text-to-Face Cross Modal Alignment) in fig. 7. Which is further divided into a coarse-Grained Text-to-Face Alignment module ("Global Text-to-Face Contrastive Learning") and a Fine-Grained Text-to-Face Alignment module ("Fine-Grained Text-to-Face Alignment").

In the coarse-granularity text-face alignment module, the generated 2D image is subjected to a CLIP image encoder to obtain image features, and semantic similarity is calculated with the text features, namely, the inner product between two feature vectors. The following contrast learning loss function is further adopted in the training process to calculate contrast learning loss:

aiming at the task of generating a text-oriented 3D face, how to accurately control the attribute of the generated 3D face by using an input text, the embodiment of the application provides a new text-oriented 3D face generation method, wherein a text-face alignment module with decoupled coarse and fine granularity is designed to improve the semantic matching degree of the generated 3D face and text description.

In addition, GAN loss functions can be constructed to update the model. For example, the Text-Conditional Discriminator network in fig. 7 may calculate the GAN loss function to provide a training gradient for the 101 module shown in fig. 9B. The method takes a 2D face image, a camera parameter p and a text feature e in a 2D face image/training data set generated by a 101 module as inputs to predict the reality degree of the 2D face image.

In one possible implementation, the second text and the third text may also be obtained; the second text comprises descriptions of characters in an image to be generated and styles of the image; the third text does not carry the style information; respectively processing the second text and the third text according to the updated generation network to obtain a second image and a third image; updating the data generation network according to the first association information and the second association information; the first association information indicates a relationship between the second text and the third text, and the second association information indicates a relationship between the second image and the third image.

By the method, the generation guide module based on the directional guide can enable the model to generate the 3D face of the style outside the training set.

Because the model is often trained by using real 2D face pictures, 3D faces which cannot be generated in other styles, such as Picks styles, line drawing styles and the like, are directly generated. For this purpose, the embodiment of the application adopts the generation guiding module based on the directional guide to guide the generator network to carry out fine adjustment so as to generate the 3D face of the corresponding style. By way of example, the following steps may be included:

1. the direction vector between the face image generated by the target style model to be fine-tuned (the upper row of images in fig. 8) and the face image generated by the real style model (the lower row of images in fig. 8) is calculated:

2. calculating a direction vector between a target style face text description ("Input text") and a neutral text description ("Photo"):

V _T ＝E _T (s ^★ )-E _T (s _o ).

3. the directional guide loss function is calculated so that the two vector directions are consistent to guide the generation of the target style 3D face.

Referring to fig. 9A, fig. 9A is a schematic illustration of the reasoning process of the model, and steps 2 and 3 correspond to steps 101 and 102 in fig. 9B, respectively, and include:

step 1 the user designates the input text. Random noise is input.

And 2, generating a corresponding 3D face according to the input text, and simultaneously rendering 2D face pictures with a plurality of different visual angles.

And 3, calculating the semantic matching degree between the 3D faces generated in the step 2 and the input text, sequencing the semantic matching degree, and returning a result with the highest semantic matching degree.

And 4, based on the result of the step 3, generating a corresponding 3D object by using the generating guide module and the guide model.

Referring to fig. 9B, fig. 9B is a schematic diagram of an overall training process of a model, and firstly, text is input to a module 101 to generate a 3D face and render 2D face images with different viewing angles; the resulting calculation is the following loss function: gan loss function: the invention employs a framework for generating a countermeasure network, wherein there is a network of generators, a network of discriminators, the generators generating results, the discriminators calculating GAN loss functions for the generated results, providing gradients to train the network of generators. The text-to-3D face generation module 101 in fig. 7 corresponds to a generator network, and a discriminator network is included in the GAN loss function. 2. And calculating a coarse grain alignment loss function and a fine grain alignment loss function through a text-face alignment module. Finally, the several loss functions are weighted and summed to form the final loss function, a gradient reverse return gradient is calculated, and the text is trained to the 3D face generation module 101.

Next, the beneficial effects of the present application are described, and the examples of the present application are tested and compared with existing algorithms on two published data sets (Multi-model CelebA-HQ, celebAText-HQ).

First, the method is compared with a text-oriented 3D face generation method Latent 3D. The embodiment of the application adopts a numerical index MVIC (multi-view identity consistency) which calculates the consistency between different visual angles of the generated 3D face, and the higher the value is, the better the consistency is. As shown in table 1, the results of the examples of the present application were better than latex 3D on both data sets.

TABLE 1

In addition, the embodiment of the application is compared with a plurality of text-2D face generation methods to measure the texture quality of the 3D face generated by the embodiment of the application. Two indexes are adopted: FID, which measures the quality of the generated image, and CLIP Score, which measures the semantic consistency between the generated image and the input text. As shown in tables 2 and 3, the method of the embodiments of the present application achieves better results on both public data sets than existing text-2D face generation methods.

TABLE 2

TABLE 3 Table 3

/>

Finally, the generating and guiding module based on the directional guide provided by the embodiment of the application can guide the model to generate 3D faces in different styles on the basis of the generated 3D faces in the real style.

Referring to fig. 10, fig. 10 is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application, and as shown in fig. 10, in the data processing apparatus provided in the embodiment of the present application, the apparatus 1000 includes:

an acquiring module 1001, configured to acquire a first text and a first image; the first text is descriptive information of a person; the first image is an image obtained by generating a network on the condition of the first text, the semantics of the first text comprise labels, and the labels comprise part of description features in the description information;

for a specific description of the obtaining module 1001, reference may be made to the description of step 501 in the above embodiment, which is not repeated here.

A processing module 1002, configured to perform feature extraction on at least one body part of the person included in the first image, to obtain at least one first feature representation; the tag is associated with the at least one body part; fusing the first characteristic representations of the at least one body part to obtain a third characteristic representation corresponding to the tag; and predicting corresponding labels according to the third characteristic representation, and updating the generated network according to the relation between the prediction result and the labels.

For a specific description of the processing module 1002, reference may be made to the descriptions of steps 502 to 504 in the above embodiments, which are not repeated here.

In one possible implementation, the processing module 1002 is further configured to:

the processing module 1002 is specifically configured to:

The processing module 1002 is specifically configured to:

obtaining a segmentation map of each body part according to the first image;

and respectively extracting the characteristics of the segmentation map of each body part through a first image encoder.

In one possible implementation, the processing module 1002 is specifically configured to:

In one possible implementation, the obtaining module 1001 is further configured to:

the processing module 1002 is further configured to:

Next, referring to fig. 11, fig. 11 is a schematic structural diagram of a terminal device provided in the embodiment of the present application, where the terminal device 1100 may specifically be represented by a virtual reality VR device, a mobile phone, a tablet, a notebook, an intelligent wearable device, etc., which is not limited herein. Specifically, the terminal apparatus 1100 includes: a receiver 1101, a transmitter 1102, a processor 1103 and a memory 1104 (where the number of processors 1103 in the terminal device 1100 may be one or more, one processor is exemplified in fig. 11), wherein the processor 1103 may include an application processor 11031 and a communication processor 11032. In some embodiments of the present application, the receiver 1101, transmitter 1102, processor 1103 and memory 1104 may be connected by a bus or other means.

The memory 1104 may include read-only memory and random access memory and provides instructions and data to the processor 1103. A portion of the memory 1104 may also include non-volatile random access memory (non-volatile random access memory, NVRAM). The memory 1104 stores a processor and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations.

The processor 1103 controls the operation of the execution device. In a specific application, the individual components of the execution device are coupled together by a bus system, which may include, in addition to a data bus, a power bus, a control bus, a status signal bus, etc. For clarity of illustration, however, the various buses are referred to in the figures as bus systems.

The method disclosed in the embodiments of the present application may be applied to the processor 1103 or implemented by the processor 1103. The processor 1103 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the method described above may be performed by integrated logic circuitry in hardware or instructions in software in the processor 1103. The processor 1103 may be a general purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and may further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The processor 1103 may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present application. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 1104, and the processor 1103 reads the information in the memory 1104, and in combination with its hardware, performs the steps of the above method that involve model training or model reasoning.

The receiver 1101 is operable to receive input numeric or character information and to generate signal inputs related to performing relevant settings and function control of the device. The transmitter 1102 may be used to output numeric or character information through a first interface; the transmitter 1102 may also be configured to send instructions to the disk stack via the first interface to modify data in the disk stack; the transmitter 1102 may also include a display device such as a display screen.

Referring to fig. 12, fig. 12 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 1200 may have a relatively large difference due to different configurations or performances, and may include one or more central processing units (central processing units, CPU) 1212 (e.g., one or more processors) and a memory 1232, one or more storage media 1230 (e.g., one or more mass storage devices) storing application programs 1242 or data 1244. Wherein memory 1232 and storage medium 1230 can be transitory or persistent. The program stored on the storage medium 1230 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, a central processor 1212 may be provided in communication with the storage medium 1230, executing a series of instruction operations on the server 1200 in the storage medium 1230.

The server 1200 may also include one or more power sources 1226, one or more wired or wireless network interfaces 1250, one or more input/output interfaces 1258; or one or more operating systems 1241, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.

In this embodiment, the central processor 1212 is configured to perform the actions related to model training or model reasoning in the above embodiment.

Embodiments of the present application also provide a computer program product that, when run on a computer, causes the computer to perform the steps performed by the aforementioned performing device, or causes the computer to perform the steps performed by the aforementioned training device.

There is also provided in an embodiment of the present application a computer-readable storage medium having stored therein a program for performing signal processing, which when run on a computer, causes the computer to perform the steps performed by the aforementioned performing device or causes the computer to perform the steps performed by the aforementioned training device.

The execution device, training device or terminal device provided in the embodiment of the present application may specifically be a chip, where the chip includes: a processing unit, which may be, for example, a processor, and a communication unit, which may be, for example, an input/output interface, pins or circuitry, etc. The processing unit may execute the computer-executable instructions stored in the storage unit to cause the chip in the execution device to perform the data processing method described in the above embodiment, or to cause the chip in the training device to perform the data processing method described in the above embodiment. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit may also be a storage unit in the wireless access device side located outside the chip, such as a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a random access memory (random access memory, RAM), etc.

Specifically, referring to fig. 13, fig. 13 is a schematic structural diagram of a chip provided in an embodiment of the present application, where the chip may be represented as a neural network processor NPU 1300, and the NPU 1300 is mounted as a coprocessor on a main CPU (Host CPU), and the Host CPU distributes tasks. The core part of the NPU is an arithmetic circuit 1303, and the controller 1304 controls the arithmetic circuit 1303 to extract matrix data in the memory and perform multiplication.

In some implementations, the arithmetic circuit 1303 includes a plurality of processing units (PEs) inside. In some implementations, the operation circuit 1303 is a two-dimensional systolic array. The arithmetic circuit 1303 may also be a one-dimensional systolic array or other electronic circuit capable of performing mathematical operations such as multiplication and addition. In some implementations, the operation circuit 1303 is a general-purpose matrix processor.

For example, assume that there is an input matrix a, a weight matrix B, and an output matrix C. The arithmetic circuit fetches the data corresponding to the matrix B from the weight memory 1302 and buffers the data on each PE in the arithmetic circuit. The arithmetic circuit takes matrix a data from the input memory 1301 and performs matrix operation with matrix B, and the partial result or the final result of the matrix obtained is stored in an accumulator (accumulator) 1308.

Unified memory 1306 is used to store input data and output data. The weight data is directly transferred to the weight memory 1302 through the memory cell access controller (Direct Memory Access Controller, DMAC) 1305. The input data is also carried into the unified memory 1306 through the DMAC.

BIU is Bus Interface Unit, bus interface unit 1310 for interaction of the AXI bus with the DMAC and instruction fetch memory (Instruction Fetch Buffer, IFB) 1309.

The bus interface unit 1310 (Bus Interface Unit, abbreviated as BIU) is configured to obtain an instruction from the external memory by the instruction fetch memory 1309, and further configured to obtain raw data of the input matrix a or the weight matrix B from the external memory by the memory unit access controller 1305.

The DMAC is mainly used to transfer input data in the external memory DDR to the unified memory 1306 or to transfer weight data to the weight memory 1302 or to transfer input data to the input memory 1301.

The vector calculation unit 1307 includes a plurality of operation processing units that perform further processing, such as vector multiplication, vector addition, exponential operation, logarithmic operation, size comparison, and the like, on the output of the operation circuit 1303, if necessary. The method is mainly used for non-convolution/full-connection layer network calculation in the neural network, such as Batch Normalization (batch normalization), pixel-level summation, up-sampling of a characteristic plane and the like.

In some implementations, the vector computation unit 1307 can store the vector of processed outputs to the unified memory 1306. For example, the vector calculation unit 1307 may perform a linear function; alternatively, a nonlinear function is applied to the output of the arithmetic circuit 1303, for example, to linearly interpolate the feature plane extracted by the convolution layer, and then, for example, to accumulate a vector of values for processing the activation value. In some implementations, vector computation unit 1307 processes the normalized values, the pixel-level summed values, or both. In some implementations, the vector of processed outputs can be used as an activation input to the arithmetic circuit 1303, for example for use in subsequent layers in a neural network.

An instruction fetch memory (instruction fetch buffer) 1309 connected to the controller 1304 for storing instructions used by the controller 1304;

the unified memory 1306, the input memory 1301, the weight memory 1302, and the finger memory 1309 are all On-Chip memories. The external memory is proprietary to the NPU hardware architecture.

The processor mentioned in any of the above may be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the above-mentioned programs.

It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection therebetween, and can be specifically implemented as one or more communication buses or signal lines.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course may be implemented by dedicated hardware including application specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment in many cases for the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., including several instructions for causing a computer device (which may be a personal computer, a training device, or a network device, etc.) to perform the method described in the embodiments of the present application.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

Claims

1. A method of data processing, the method comprising:

acquiring a first text and a first image; the first text is descriptive information of a person; the first image is an image obtained by generating a network on the condition of the first text, the semantics of the first text comprise labels, and the labels comprise part of description features in the description information;

respectively extracting features of at least one body part of a person contained in the first image to obtain at least one first feature representation; the tag is associated with the at least one body part;

fusing the first characteristic representations of the at least one body part to obtain a third characteristic representation corresponding to the tag;

and predicting corresponding labels according to the third characteristic representation, and updating the generated network according to the relation between the prediction result and the labels.

2. The method according to claim 1, wherein the method further comprises:

said fusing of said first characteristic representation of said at least one said body part comprises:

3. The method of claim 1 or 2, wherein the tag is used to describe a feature of the character.

4. A method according to any one of claims 1 to 3, wherein the feature extraction of at least one body part of the person contained in the first image comprises:

obtaining a segmentation map of each body part according to the first image;

5. The method according to any one of claims 1 to 4, wherein the generating network is configured to generate 3D information, and the first image is obtained by rendering the 3D information at a target viewing angle.

6. The method according to any one of claims 1 to 5, wherein predicting the corresponding label according to the third feature representation and updating the generated network according to the relation between the prediction result and the label comprises:

7. The method according to any one of claims 1 to 5, further comprising:

Extracting features of the whole first image to obtain a fourth feature representation;

extracting features of the whole first text to obtain a fifth feature representation;

8. The method according to any one of claims 1 to 7, further comprising:

9. The method of claim 8, wherein the first association information is a direction vector between the second text and the third text, the second association information indicating a direction vector between the second image and the third image.

10. A data processing apparatus, the apparatus comprising:

11. The apparatus of claim 10, wherein the processing module is further configured to:

the processing module is specifically configured to:

12. The apparatus according to claim 10 or 11, characterized in that the processing module is specifically configured to:

obtaining a segmentation map of each body part according to the first image;

13. The apparatus according to any one of claims 10 to 12, wherein the generating network is configured to generate 3D information, and the first image is obtained by rendering the 3D information at a target viewing angle.

14. The apparatus according to any one of claims 10 to 13, wherein the processing module is specifically configured to:

15. The apparatus of any one of claims 10 to 14, wherein the processing module is further configured to:

16. The apparatus of any one of claims 10 to 15, wherein the acquisition module is further configured to:

the processing module is further configured to:

17. The apparatus of claim 16, wherein the first association information is a direction vector between the second text and the third text, the second association information indicating a direction vector between the second image and the third image.

18. A computer storage medium storing one or more instructions which, when executed by one or more computers, cause the one or more computers to perform the operations of the method of any one of claims 1 to 9.

19. A computer program product comprising computer readable instructions which, when run on a computer device, cause the computer device to perform the method of any of claims 1 to 9.

20. A system comprising at least one processor, at least one memory; the processor and the memory are connected through a communication bus and complete communication with each other;

the at least one memory is used for storing codes;

the at least one processor is configured to execute the code to perform the method of any of claims 1 to 9.

21. A chip comprising a processor for supporting a data processing apparatus to implement a method as claimed in any one of claims 1 to 9.