Computing power implementation attribute reasoning method and device based on intelligent computing center

Abstract

The invention provides a computing power implementation attribute reasoning method and device based on an intelligent computing center, and relates to the technical field of computing power, and the method comprises the steps: S1, obtaining a to-be-evaluated image; s2, reasoning the to-be-evaluated image by adopting an attribute reasoning model running in the intelligent computing center to obtain attribute information of an object in the to-be-evaluated image; the inference of the attribute inference model on the to-be-evaluated image comprises the following steps: identifying an object in the to-be-evaluated image; extracting target features of an object in the to-be-evaluated image; and reasoning the attribute of the object according to the target feature to obtain the attribute information of the object in the to-be-evaluated image. According to the invention, through intelligent identification and reasoning of dominant and invisible attributes of the object, the accuracy and efficiency of reasoning of the attributes of the object in the image are improved, and quick-response image evaluation in a scene with a high real-time requirement is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent computing centers and computing power infrastructure of intelligent computing centers, and particularly relates to a method and device for realizing attribute reasoning based on the computing power of an intelligent computing center. Background Art

[0002] With the rapid development of artificial intelligence technology, "intelligent computing centers" and "intelligent computing centers" have emerged as the times require.

[0003] An "intelligent computing center" refers to a facility that provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios like artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, ASIC, etc.). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0004] The "intelligent computing center" includes, but is not limited to, the "intelligent computing center".

[0005] An "intelligent computing center", that is, an artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0006] "Computing power" is the ability of a computer device or a computing / data center to process information, is the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, is the computing ability to achieve the output of a target result by processing information data, is a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly provides services to society through computing power infrastructure.

[0007] With the continuous development of generative artificial intelligence technology, image generation and processing technologies have been widely applied in fields such as creative design, game development, and virtual reality. However, there is still a lack of a unified standard and an efficient implementation method for the evaluation method of generated pictures. When evaluating the attributes of a generated picture (such as color, shape, material, state, function, etc.), traditional image evaluation methods do not utilize intelligent computing centers and computing power. Limited by computing power and algorithm capabilities, it is difficult to meet the requirements of real-time performance and high precision when dealing with complex and multi-dimensional attribute reasoning tasks; and it usually relies on manual annotation or simple rule matching, resulting in problems such as low efficiency and strong subjectivity. Summary of the Invention

[0008] The present invention provides a method and device for realizing attribute reasoning based on the computing power of an intelligent computing center to solve the problem of the lack of an efficient attribute reasoning method in existing image evaluation.

[0009] To solve the above technical problems, the present invention is implemented as follows:

[0010] In a first aspect, the present invention provides a method for realizing attribute reasoning based on the computing power of an intelligent computing center, including:

[0011] Step S1: Obtain the image to be evaluated;

[0012] Step S2: Use the attribute reasoning model running on the intelligent computing center to reason about the image to be evaluated, and obtain the attribute information of the object in the image to be evaluated; wherein, the attribute reasoning model reasoning about the image to be evaluated includes: identifying the object in the image to be evaluated; extracting the target features of the object in the image to be evaluated; reasoning about the attributes of the object according to the target features, and obtaining the attribute information of the object in the image to be evaluated.

[0013] Optionally, the step S1 includes:

[0014] Step S11: Obtain the original image to be evaluated;

[0015] Step S12: Preprocess the original image to be evaluated to obtain the image to be evaluated, and the preprocessing includes at least one of the following: adjusting the size, normalization processing, data feature enhancement, and denoising.

[0016] The attribute information includes explicit attributes and implicit attributes, wherein the explicit attributes include at least one of the following: color, size, shape, material, texture, position, and quantity; the implicit attributes include at least one of the following: function, state, and emotional attributes.

[0017] Optionally, before the step S2, it further includes:

[0018] Step S0: Train the attribute reasoning model to be trained;

[0019] The step S0 includes:

[0020] Step S01: Obtain the training image and the true attribute information of the object in the training image;

[0021] Step S02: Use the attribute reasoning model to be trained to reason about the training image, and obtain the predicted attribute information of the object in the training image;

[0022] Step S03: Optimize the attribute reasoning model to be trained according to the predicted attribute information of the object in the training image and the true attribute information of the object in the training image, and obtain the trained attribute reasoning model.

[0023] Optionally, after the step S2, it further includes:

[0024] Step S3: Visualize and output the attribute information of the objects in the image to be evaluated in the form of image annotation or text.

[0025] Optionally, after step S2, it further includes:

[0026] Step S4: Match the attribute information of the objects in the image to be evaluated with the attribute information stored in advance when generating the image to be evaluated to obtain an image quality score.

[0027] In a second aspect, the present invention provides an attribute inference device based on the computing power of an intelligent computing center, including:

[0028] An acquisition module, configured to acquire an image to be evaluated;

[0029] A processing module, configured to perform inference on the image to be evaluated by using an attribute inference model running on the intelligent computing center to obtain the attribute information of the objects in the image to be evaluated; wherein, the attribute inference model performing inference on the image to be evaluated includes: identifying the objects in the image to be evaluated; extracting the target features of the objects in the image to be evaluated; and inferring the intrinsic attributes of the objects according to the target features to obtain the attribute information of the objects in the image to be evaluated.

[0030] Optionally, the acquisition module includes:

[0031] A first acquisition sub-module, configured to acquire the original image to be evaluated;

[0032] A preprocessing sub-module, configured to preprocess the original image to be evaluated to obtain the image to be evaluated, and the preprocessing includes at least one of the following: resizing, normalization, data feature enhancement, and denoising.

[0033] The attribute information includes explicit attributes and implicit attributes, wherein the explicit attributes include at least one of the following: color, size, shape, material, texture, position, and quantity; and the implicit attributes include at least one of the following: function, state, and emotional attributes.

[0034] Optionally, it further includes:

[0035] A model training module, configured to perform model training on the attribute inference model to be trained;

[0036] The model training module includes:

[0037] A first acquisition sub-module, configured to acquire training images and the true attribute information of the objects in the training images;

[0038] An inference sub-module, configured to perform inference on the training image by using an attribute inference model to be trained, and obtain the predicted attribute information of the object in the training image;

[0039] An optimization sub-module, configured to optimize the attribute inference model to be trained according to the predicted attribute information of the object in the training image and the true attribute information of the object in the training image, so as to obtain a trained attribute inference model.

[0040] Optionally, it further includes:

[0041] A visualization output module, configured to visually output the attribute information of the object in the image to be evaluated in the form of image annotation or text.

[0042] Optionally, it further includes:

[0043] A scoring module, configured to perform similarity matching on the attribute information of the object in the image to be evaluated and the attribute information stored in advance when generating the image to be evaluated, so as to obtain an image quality score.

[0044] In a third aspect, the present invention provides an electronic device, including a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps in the attribute inference method based on the computing power of the intelligent computing center described in any one of the first aspects are implemented.

[0045] In a fourth aspect, the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps in the attribute inference method based on the computing power of the intelligent computing center described in any one of the first aspects are implemented.

[0046] In a fifth aspect, the present invention provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps in the attribute inference method based on the computing power of the intelligent computing center described in any one of the first aspects are implemented.

[0047] In the present invention, a to-be-evaluated image is obtained; an attribute inference model running in the intelligent computing center is used to infer the to-be-evaluated image to obtain attribute information of an object in the to-be-evaluated image; wherein, the attribute inference model inferring the to-be-evaluated image includes: identifying the object in the to-be-evaluated image; extracting target features of the object in the to-be-evaluated image; and inferring the attributes of the object according to the target features to obtain the attribute information of the object in the to-be-evaluated image. In the present invention, by intelligently identifying and inferring the explicit and implicit attributes of an object, the accuracy and efficiency of object attribute inference in an image are improved, rapid response image evaluation in scenarios with high real-time requirements is realized, and the problem of the lack of an efficient attribute inference method in existing image evaluation is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0049] Figure 1 is a flowchart of a method for realizing attribute inference based on the computing power of an intelligent computing center provided by the present invention;

[0050] Figure 2 is a schematic structural diagram of a device for realizing attribute inference based on the computing power of an intelligent computing center provided by the present invention;

[0051] Figure 3 is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] The technical solutions in the present invention will be clearly and completely described below with reference to the drawings in the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0053] The "computing power" described in the present invention refers to the ability of a computer device or a computing / data center to process information, which is the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, is the computing ability to realize the output of a target result by processing information data, and is a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly provides services to society through computing power infrastructure.

[0054] The "Computational Power (CP)" described in the present invention is a capability of a data center server to process data and output results, which is a comprehensive indicator for measuring the computing power of a data center and includes general computing power, supercomputing power, and intelligent computing power. The commonly used measurement unit is the number of floating-point operations per second (FLOPS, 1 EFLOPS = 10^18 FLOPS), and the larger the value, the stronger the comprehensive computing power. It is estimated that 1 EFLOPS is approximately the computing power output of 5 Tianhe-2A computers, or 500,000 mainstream server CPUs, or 2 million mainstream laptops. The calculation formula is: CP = CP_general + CP_intelligent + CP_super.

[0055] The "Network Power (NP)" described in the present invention is the manifestation of the data transmission capacity of computing power facilities, which is a comprehensive ability including network architecture, network bandwidth, transmission delay, intelligent management and scheduling, etc., and involves network transmission within and between data centers. It is a comprehensive indicator for measuring network transmission scheduling ability.

[0056] The "Storage Power (SP)" described in the present invention is the comprehensive ability of a data center in four aspects: data storage capacity, performance, security and reliability, and green and low-carbon. It is a comprehensive indicator for measuring the data storage capacity of a data center and includes external storage devices such as storage arrays and server-internal storage devices. The commonly used measurement unit for storage capacity is the exabyte (EB, 1 EB = 2^60 bytes), and the commonly used measurement unit for performance is the number of read / write operations per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB). The disaster recovery ratio is an important manifestation of security and reliability.

[0057] The "computing power infrastructure" described in the present invention refers to: a new type of information infrastructure that integrates information computing power, network carrying power, and data storage power, which can realize the centralized computing, storage, transmission, and application of information, presenting characteristics such as multi-modal ubiquitous, intelligent and agile, secure and reliable, green and low-carbon.

[0058] The "new type of information infrastructure" described in the present invention mainly includes network infrastructures such as 5G networks, fiber broadband networks, backbone networks, international communication networks, and satellite Internet, computing power infrastructures such as data centers, general computing power centers, intelligent computing centers, and supercomputing centers, and new technology facilities such as artificial intelligence, blockchain, and quantum computing. With the emergence and popularization of new general technologies, the form of the new type of information infrastructure will be more diverse.

[0059] The "computing power" described in the present invention includes: general computing power, intelligent computing power, and supercomputing power.

[0060] The "general computing power" described in the present invention refers to the computing power provided by servers based on CPU (Central Processing Unit) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0061] The "intelligent computing power" described in the present invention refers to a computing platform that is scaled for various artificial intelligence innovation applications and is based on dedicated chips such as GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and ASIC (Application Specific Integrated Circuit), such as natural language processing and machine vision.

[0062] The "super computing power" described in the present invention mainly refers to the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of multiple computer systems working in parallel and processes extremely complex or data-intensive problems through a dedicated operating system. It is mainly used for computing in cutting-edge scientific fields, such as planetary simulation, drug molecule design, and gene analysis.

[0063] The "intelligent computing center" described in the present invention refers to a facility that mainly provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios of artificial intelligence deep learning model development, model training, and model inference) by using large-scale heterogeneous computing power resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, ASIC, etc.). The intelligent computing center covers facilities, hardware, and software and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0064] The "intelligent computing center" described in the present invention includes but is not limited to the "intelligent computing center".

[0065] The "intelligent computing center" described in the present invention, that is, the artificial intelligence computing center, is a type of computing power infrastructure that provides computing power services, data services, and algorithm services required for artificial intelligence applications based on artificial intelligence theory and using an artificial intelligence computing architecture.

[0066] The "computing power center" described in the present invention refers to a facility mainly composed of infrastructure such as wind, fire, water, and electricity and IT software and hardware devices, and has computing power, carrying capacity, and storage capacity, including general data centers, intelligent computing centers, supercomputing centers, etc.

[0067] The "supercomputing center" described in the present invention refers to: namely, a supercomputing data center, which is a data center based on supercomputers or large-scale computing clusters and can provide functions such as large-scale computing, storage, and network services, and is widely used in application scenarios such as aerospace, national defense, oil exploration, climate modeling, and genome sequencing.

[0068] The "computing power resources" described in the present invention refers to: the technologies and facilities required for the development of the digital society with information computing, transmission, storage, and application capabilities, including but not limited to computing resources such as CPUs and GPUs, network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, and support and guarantee resources such as wind, fire, water, and electricity.

[0069] The "attributes" described in the present invention refers to: multi-dimensional characteristics that can be parsed, described, and evaluated in the generated pictures. These attributes not only cover the explicit features in the images but also include some implicit information or high-level semantic information. For example: color, shape, material, state, function, and so on.

[0070] The "attribute reasoning" described in the present invention refers to: the process of automatically parsing and semantically understanding the multi-dimensional attributes (such as color, shape, material, state, function, etc.) of objects in pictures. By analyzing the explicit features and implicit information of pictures, combining factors such as scene context, spatial relationship, and time change, the true attributes of objects and their internal logic are inferred.

[0071] Please refer to Figure 1 , the present invention provides a method for realizing attribute reasoning based on the computing power of an intelligent computing center, including:

[0072] Step S1: Obtain the image to be evaluated;

[0073] In the present invention, optionally, the step S1 includes:

[0074] Step S11: Obtain the original image to be evaluated;

[0075] Step S12: Preprocess the original image to be evaluated to obtain the image to be evaluated, and the preprocessing includes at least one of the following: adjusting the size, normalizing, enhancing data features, and denoising.

[0076] In the present invention, preprocessing the original image to be evaluated provides clearer and more standardized image data for subsequent analysis and processing, improves the quality and consistency of image data, and thus enhances the effect of subsequent processing and analysis.

[0077] In the present invention, the image to be evaluated can be an image directly uploaded or an image generated by artificial intelligence. The image to be evaluated includes different objects or elements, and the attributes of different objects or elements in the image are multi-dimensional characteristics that can be analyzed, described, and evaluated. These attributes not only cover the explicit features in the image but also include some implicit information or high-level semantic information. For example: color, shape, material, state, function, etc.

[0078] Step S2: Use the attribute inference model running in the intelligent computing center to infer the image to be evaluated, and obtain the attribute information of the objects in the image to be evaluated. Among them, the attribute inference model inferring the image to be evaluated includes: identifying the objects in the image to be evaluated; extracting the target features of the objects in the image to be evaluated; inferring the attributes of the objects according to the target features to obtain the attribute information of the objects in the image to be evaluated.

[0079] In the present invention, optionally, before the step S2, it further includes:

[0080] Step S0: Train the attribute inference model to be trained.

[0081] The step S0 includes:

[0082] Step S01: Obtain the training images and the true attribute information of the objects in the training images.

[0083] Step S02: Use the attribute inference model to be trained to infer the training images, and obtain the predicted attribute information of the objects in the training images.

[0084] Step S03: Optimize the attribute inference model to be trained according to the predicted attribute information of the objects in the training images and the true attribute information of the objects in the training images, and obtain the trained attribute inference model.

[0085] In the present invention, a training image is used to train the attribute inference model, and the parameters of the model are adjusted to minimize the loss function. Among them, common optimization algorithms can be used but are not limited to gradient descent or Adaptive Moment Estimation (Adam), etc., and the performance of the model can be monitored, and the model can be updated regularly to cope with changes in data distribution or the introduction of new data. Among them, the attribute inference model can, but is not limited to, use a pre-trained visual model to extract the target features of the object in the image to be evaluated, and combine the target features and attribute inference to identify the inherent attributes of the object or element in the picture. Among them, the attribute inference is to automatically analyze and semantically understand the multi-dimensional attributes of the object in the picture (such as color, shape, material, state, function, etc.). By analyzing the explicit features and implicit information of the picture, combining factors such as scene context, spatial relationship, and time change, the true attributes and internal logic of the object are inferred, which improves the accuracy and efficiency of picture content analysis, and also provides a standardized and intelligent solution for the quality evaluation and practical application of generated pictures.

[0086] In the present invention, optionally, the attribute information includes explicit attributes and implicit attributes. Among them, the explicit attributes include at least one of the following: color, size, shape, material, texture, position, and quantity; the implicit attributes include at least one of the following: function, state, and emotional attribute.

[0087] In the present invention, the explicit attribute is an attribute that can be directly obtained through visual observation or measurement, and is usually easy to identify and describe, including but not limited to: color, that is, the color feature of the object (such as red, blue, etc.); shape, that is, the geometric shape of the object (such as round, square, etc.); size, that is, the size of the object (such as large, small, etc.); material, that is, the material of the object (such as wood, metal, etc.); texture, that is, the details of the object surface (such as smooth, rough, etc.); quantity, that is, the number of objects in the image (such as one, multiple, etc.); position, that is, the specific position of the object in the image (such as left, right, etc.); the implicit attribute is an attribute that is not easy to directly observe or measure, and usually requires reasoning or background knowledge to understand, including but not limited to: function, that is, the use or function of the object (such as a chair is for sitting); state, that is, the state or condition of the object (such as whether an object is new or old, intact or damaged); emotional attribute, that is, the emotion or atmosphere related to the object (such as warm, cold, etc.); history or background, that is, the history or cultural background of the object (such as the origin or usage history of a certain object); context, that is, the meaning of the object in a specific situation (such as the symbolic meaning of an object in a specific occasion); mutual relationship, that is, the relationship between the object and other objects (such as dependence, contrast, etc.); Understanding the difference between explicit attributes and implicit attributes helps to more comprehensively analyze and reason the information in the image.

[0088] In the present invention, for example, by automatically reasoning about the multi-dimensional attributes of elements in a picture (such as a melting snowman), including color (white, translucent), shape (irregular edges), material (granularity of snow), state (melting), and function (decoration or role). The reasoning process combines high-performance computing, deep learning models, and task decomposition techniques, enabling accurate parsing of picture content and intelligent evaluation of multiple attributes, effectively solving the problems of strong subjectivity, low efficiency, and inconsistent standards in the process of evaluating generated pictures. Through the high-performance computing power and advanced algorithms of the intelligent computing center, the accuracy and real-time performance of attribute reasoning are significantly improved; users can quickly obtain multi-dimensional attribute evaluation results of picture content without cumbersome manual intervention, providing strong technical support for creative design, content generation optimization, and virtual reality scene construction.

[0089] In the present invention, a to-be-evaluated image is obtained; an attribute reasoning model running in the intelligent computing center is used to reason about the to-be-evaluated image to obtain attribute information of an object in the to-be-evaluated image; wherein, the attribute reasoning model reasoning about the to-be-evaluated image includes: identifying the object in the to-be-evaluated image; extracting target features of the object in the to-be-evaluated image; reasoning about the attributes of the object according to the target features to obtain attribute information of the object in the to-be-evaluated image. In the present invention, by intelligently identifying and reasoning about the explicit and implicit attributes of an object, the accuracy and efficiency of object attribute reasoning in an image are improved, realizing fast-response image evaluation in scenarios with high real-time requirements, and solving the problem of the lack of an efficient attribute reasoning method in existing image evaluation.

[0090] In the present invention, optionally, after step S2, the following is further included:

[0091] Step S3: Visually output the attribute information of the object in the to-be-evaluated image in the form of image annotation or text.

[0092] In the present invention, the reasoning result, that is, the attribute information of the object in the to-be-evaluated image, is visually output, including an image annotating the attribute information of the object, or describing the attribute information of the object in text form or chart form, improving the transparency and usability of the model, and being able to more clearly display the evaluation result of the to-be-evaluated image, facilitating further evaluation by subsequent manual or system, thereby promoting better business results.

[0093] In the present invention, optionally, after step S2, the following is further included:

[0094] Step S4: Perform similarity matching between the attribute information of the object in the to-be-evaluated image and the attribute information stored in advance when generating the to-be-evaluated image to obtain an image quality score.

[0095] In the present invention, the attribute inference model can, but is not limited to, use a reward model to perform similarity matching between the attribute information of the objects in the image to be evaluated and the attribute information stored in advance when generating the image to be evaluated, so as to obtain an image quality score;

[0096] In some embodiments, taking the image to be evaluated as coming from an Artificial Intelligence Generated Content (AIGC) generation model as an example, the reward model optimizes the framework of the output of the generation model through a reward signal. That is, in the evaluation task of the image to be evaluated generated by AIGC, the goal of the reward model is to automatically measure the quality of the image to be evaluated and provide meaningful feedback to guide the generation model (such as a diffusion model) to generate higher-quality pictures. Specifically, the quality evaluation here is mainly based on the reasoning ability of the attributes of the objects or elements in the picture. In other words, the task of the reward model is to analyze whether the attribute information of the objects in the generated picture meets the expectations and score or reward based on this.

[0097] Specifically, by calculating the similarity between the attribute information A of the objects in the image to be evaluated and the attribute information B stored in advance when generating the image to be evaluated: Rattr = Sim(A, B); where Sim(·) can adopt cosine similarity, Euclidean distance or other feature comparison methods;

[0098] Then, use the semantic similarity score between the text and the picture to obtain a multimodal consistency reward: Rtext-img = Sim(CLIPimg(image), CLIPtext(input)); where CLIPimg(image) is the first feature vector obtained by inputting the image image into the image encoder of the multimodal pre-training model (Contrastive Language-Image Pre-training, CLIP), representing the semantic information of the picture; CLIPtext(input) is the second feature vector obtained by inputting the text input into the text encoder of CLIP, representing the semantic information of the text.

[0099] Traditional image quality assessment metrics can be introduced, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM), or a dedicated network can be trained to predict the subjective quality score of the picture, so as to integrate various evaluation metrics to calculate the final reward score. In the subsequent reinforcement learning stage, the loss function for guiding the improvement of the generation model is obtained through the score in the reward model: LossRL = -Epolicy[R(image)], where Epolicy[R(image)] is the reward score obtained for the image generated by the model under the current policy.

[0100] In the present invention, by designing a reward function, the quality of pictures is comprehensively evaluated from aspects such as the matching degree of attribute information, multimodal consistency, and visual quality dimension. The reward model is trained through supervised learning, the reward model is combined with the generation model, and reinforcement learning is used to optimize the generation process to improve the quality, attribute consistency, and diversity of picture generation.

[0101] Please refer to Figure 2 , an attribute inference device based on the computing power of an intelligent computing center provided by an embodiment of the present invention includes:

[0102] An acquisition module 21, configured to acquire an image to be evaluated;

[0103] A processing module 22, configured to perform inference on the image to be evaluated by using an attribute inference model running on the intelligent computing center to obtain attribute information of an object in the image to be evaluated; wherein, the attribute inference model performing inference on the image to be evaluated includes: identifying an object in the image to be evaluated; extracting target features of the object in the image to be evaluated; and inferring the inherent attributes of the object according to the target features to obtain the attribute information of the object in the image to be evaluated.

[0104] In the present invention, optionally, the acquisition module includes:

[0105] A first acquisition sub-module, configured to acquire an original image to be evaluated;

[0106] A preprocessing sub-module, configured to perform preprocessing on the original image to be evaluated to obtain the image to be evaluated, and the preprocessing includes at least one of the following: adjusting the size, normalizing, enhancing data features, and denoising.

[0107] The attribute information includes explicit attributes and implicit attributes, wherein the explicit attributes include at least one of the following: color, size, shape, material, texture, position, and quantity; and the implicit attributes include at least one of the following: function, state, and emotional attributes.

[0108] Optionally, the present invention further includes:

[0109] A model training module for training an attribute inference model to be trained;

[0110] The model training module includes:

[0111] A first acquisition sub-module for acquiring training images and the true attribute information of the objects in the training images;

[0112] An inference sub-module for inferring the training images using the attribute inference model to be trained to obtain the predicted attribute information of the objects in the training images;

[0113] An optimization sub-module for optimizing the attribute inference model to be trained according to the predicted attribute information of the objects in the training images and the true attribute information of the objects in the training images to obtain a trained attribute inference model.

[0114] Optionally, the present invention further includes:

[0115] A visualization output module for visually outputting the attribute information of the objects in the image to be evaluated in the form of image annotation or text.

[0116] Optionally, the present invention further includes:

[0117] A scoring module for performing similarity matching between the attribute information of the objects in the image to be evaluated and the attribute information stored in advance when generating the image to be evaluated to obtain an image quality score.

[0118] The attribute inference based on the computing power of the intelligent computing center provided by the embodiments of the present invention can implement Figure 1 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, details are not described here again.

[0119] The embodiments of the present invention provide an electronic device 30. Refer to Figure 3 as shown. Figure 3 is a schematic block diagram of the electronic device 30 according to the embodiments of the present invention, including a processor 31, a memory 32, and a program or instruction stored in the memory 32 and executable on the processor 31. When the program or instruction is executed by the processor, the steps in any one of the attribute inference methods based on the computing power of the intelligent computing center of the present invention are implemented.

[0120] An embodiment of the present invention provides a readable storage medium, on which a program or instructions are stored. When the program or instructions are executed by a processor, each process of the embodiment of the method for realizing attribute reasoning based on the computing power of an intelligent computing center as described in any one of the above is realized, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0121] An embodiment of the present invention further provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, each process of the method embodiment described above is realized, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here. Figure 1 When the computer instructions are executed by a processor, each process of the method embodiment described above is realized, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0122] Computer-readable media include both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined in the present invention, computer-readable media do not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0123] It should be noted that in the technical solution of the present invention, in terms of the collection, gathering, updating, analysis, processing, use, transmission, storage, etc. of the user's personal information, it complies with the provisions of relevant laws and regulations, is used for legal purposes, and does not violate public order and good customs. Necessary measures are taken for the user's personal information to prevent illegal access to the user's personal information data and to maintain the security of the user's personal information and network security.

[0124] It should be noted that in the present invention, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including that element.

[0125] The serial numbers of the embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments.

[0126] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that makes a contribution to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a service classification device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0127] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A method for implementing attribute reasoning based on the computing power of an intelligent computing center, characterized in that: include: Step S1: Obtain an image to be evaluated; Step S2: Use the attribute reasoning model running in the intelligent computing center to reason about the image to be evaluated, and obtain the attribute information of the object in the image to be evaluated; wherein the attribute reasoning model reasoning about the image to be evaluated includes: identifying the object in the image to be evaluated; extracting the target features of the object in the image to be evaluated; and reasoning about the attributes of the object according to the target features to obtain the attribute information of the object in the image to be evaluated.

2. The attribute reasoning method based on the computing power of the intelligent computing center according to claim 1 is characterized in that: The step S1 comprises: Step S11: obtaining the original image to be evaluated; Step S12: preprocessing the original image to be evaluated to obtain the image to be evaluated, wherein the preprocessing includes at least one of the following: resizing, normalization, data feature enhancement, and denoising.

3. The attribute reasoning method based on the computing power of the intelligent computing center according to claim 1 is characterized in that: The attribute information includes explicit attributes and invisible attributes, wherein the explicit attributes include at least one of the following: color, size, shape, material, texture, position and quantity; the invisible attributes include at least one of the following: function, state and emotional attributes.

4. The attribute reasoning method based on the computing power of the intelligent computing center according to claim 1 is characterized in that: Before step S2, the method further includes: Step S0: Perform model training on the attribute reasoning model to be trained; The step S0 comprises: Step S01: obtaining a training image and real attribute information of an object in the training image; Step S02: using the attribute inference model to be trained to infer the training image to obtain predicted attribute information of the object in the training image; Step S03: optimizing the attribute reasoning model to be trained according to the predicted attribute information of the object in the training image and the real attribute information of the object in the training image to obtain a trained attribute reasoning model.

5. The method for realizing attribute reasoning based on the computing power of an intelligent computing center according to claim 1 is characterized in that: The step S2 further includes: Step S3: Visually output the attribute information of the object in the image to be evaluated in the form of image annotation or text.

6. The method for realizing attribute reasoning based on the computing power of an intelligent computing center according to claim 1 is characterized in that: The step S2 further includes: Step S4: performing similarity matching on the attribute information of the object in the image to be evaluated with the pre-stored attribute information stored when the image to be evaluated is generated, to obtain an image quality score.

7. A device for implementing attribute reasoning based on the computing power of an intelligent computing center, characterized in that: include: An acquisition module, used for acquiring an image to be evaluated; A processing module is used to use the attribute reasoning model running in the intelligent computing center to reason about the image to be evaluated, so as to obtain the attribute information of the object in the image to be evaluated; wherein the attribute reasoning model reasoning about the image to be evaluated includes: identifying the object in the image to be evaluated; extracting the target features of the object in the image to be evaluated; and reasoning about the intrinsic attributes of the object according to the target features to obtain the attribute information of the object in the image to be evaluated.

8. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps in the attribute reasoning method based on the computing power of an intelligent computing center as described in any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps in the attribute reasoning method based on the computing power of the intelligent computing center as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that It includes computer instructions, which, when executed by a processor, implement the steps in the attribute reasoning method based on the computing power of an intelligent computing center as described in any one of claims 1 to 6.

Images