Image processing method and device, equipment, storage medium and program product

Abstract

The invention provides an image processing method which can be applied to the technical field of artificial intelligence. The image processing method comprises the steps that a target image is acquired and preprocessed to extract original byte data of the target image; inputting the original byte data into a target model to obtain target feature data conforming to a preset target character string system; based on a preset rule engine model, judging a coding type of the target feature data; according to the coding type of the target feature, inputting the target feature data into a corresponding decoding sandbox to obtain a decoded target result; extracting a target object of the target image based on the decoded target result; wherein the target model is a pre-trained adversarial network model. The invention further provides an image processing device, equipment, a storage medium and a program product.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and more particularly to an image processing method, device, equipment, storage medium and program product. BACKGROUND

[0002] In the current financial field, with the diversification of financial payment scenarios and the iterative evolution of processing technology, in the scenario of completing transactions by scanning with electronic devices, the quality of two-dimensional code images, the accuracy of decoding, and subsequent transaction processing are crucial to user experience and transaction security.

[0003] The existing two-dimensional code image decoding method often relies on simple image processing technology, which may fail or provide inaccurate information when faced with complex backgrounds or low-quality images. Therefore, a more intelligent and efficient image processing method is needed to improve the accuracy of two-dimensional code analysis and ensure the efficiency and security of transactions. SUMMARY

[0004] In view of the above problems, the present application provides an image processing method, device, equipment, storage medium and program product.

[0005] According to a first aspect of the present application, an image processing method is provided, comprising: obtaining a target image and preprocessing to extract original byte data of the target image; inputting the original byte data into a target model to obtain target feature data conforming to a preset target character string radix; determining the encoding type of the target feature data based on a preset rule engine model; inputting the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result; extracting a target object of the target image based on the decoded target result; wherein the target model is a pre-trained adversarial network model.

[0006] According to an embodiment of the present application, the method further comprises: when the decoded target result of any decoding sandbox does not conform to the decoding number of the preset result exceeds a preset threshold, triggering decoding fusing and switching decoding sandbox processing.

[0007] According to an embodiment of the present application, obtaining a target image and preprocessing to extract original byte data of the target image comprises: obtaining a target image and preprocessing to obtain initial data of the target image; extracting original byte data of the initial data based on a preset target decoder; wherein the initial data is image bitmap data of the target image, and the target decoder is a two-dimensional code image decoder.

[0008] According to an embodiment of the present application, the target model is a pre-trained adversarial network model, and the training process includes: obtaining training data and performing data structure processing, the training data being a data set conforming to a preset target string radix; and extracting target feature data of the training data based on an up-sampling layer or a transpose convolution layer of the target model.

[0009] According to an embodiment of the present application, the encoding type of the target feature data is determined based on a preset rule engine model, including: inputting the target feature data into the preset rule engine model to obtain the encoding type of the target feature data, the encoding type including a first encoding type and a second encoding type.

[0010] According to an embodiment of the present application, the target feature data is input into a corresponding decoding sandbox according to the encoding type of the target feature, including: when the encoding type is the first encoding type, inputting the target feature data into a first decoding sandbox, the first decoding sandbox including a custom verification rule or a decryption algorithm based on a preset first encoding format; and when the encoding type is the second encoding type, inputting the target feature data into a second decoding sandbox, the second decoding sandbox including a custom verification rule or a decryption algorithm based on a preset second encoding format.

[0011] According to an embodiment of the present application, the target object of the target image is extracted based on the decoded target result, including: analyzing the target result, the target result including a target string; and in response to obtaining a target intent, extracting a target object corresponding to the target intent from the target result.

[0012] The second aspect of the present application provides an image processing apparatus, including: a target image acquisition module configured to acquire a target image and perform preprocessing to extract original byte data of the target image; a target feature acquisition module configured to input the original byte data into a target model to obtain target feature data conforming to a preset target string radix; an encoding type determination module configured to determine an encoding type of the target feature data based on a preset rule engine model; a decoding module configured to input the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result; and a target object extraction module configured to extract a target object of the target image based on the decoded target result; wherein the target model is a pre-trained adversarial network model.

[0013] The third aspect of the present application provides an electronic device, including: one or more processors; a memory configured to store one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0014] The fourth aspect of the present application further provides a computer readable storage medium, having stored thereon a computer program or instructions, which, when executed by a processor, implement the steps of the above method.

[0015] The fifth aspect of the present application further provides a computer program product, comprising a computer program or instructions, which, when executed by a processor, implement the steps of the above method. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above content of the present application and other purposes, features and advantages will be more apparent through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:

[0017] Figure 1 An application scenario diagram of the image processing method according to the embodiments of the present application is schematically shown;

[0018] Figure 2 A flowchart of the image processing method according to the embodiments of the present application is schematically shown;

[0019] Figure 3 A flowchart of extracting original byte data of a target image according to the embodiments of the present application is schematically shown;

[0020] Figure 4 A flowchart of target model training according to the embodiments of the present application is schematically shown;

[0021] Figure 5 A flowchart of extracting a target object according to the embodiments of the present application is schematically shown;

[0022] Figure 6 A structural block diagram of the image processing apparatus according to the embodiments of the present application is schematically shown; and

[0023] Figure 7 A block diagram of an electronic device suitable for implementing the image processing method according to the embodiments of the present application is schematically shown. DETAILED DESCRIPTION

[0024] Hereinafter, the embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary, and are not intended to limit the scope of the present application. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that one or more embodiments can be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques have been omitted to avoid unnecessarily obscuring the concepts of the present application.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the terms "comprises", "comprising", "includes", "including" and the like are, where used, meant to be inclusive, but not limiting in any way.

[0026] All terms used herein including technical and scientific terms have the meanings commonly understood by one of ordinary skill in the art unless otherwise specified. It should be noted that the terms used herein are to be interpreted as having a meaning that is consistent with the understanding of those terms by those skilled in the art, and should not be interpreted in an idealized or overly formal sense.

[0027] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should generally be interpreted that the meaning of the expression is the same as that of "at least one of A or B; at least one of A or C; at least one of B or C; at least one of A, B, and C; etc.", unless otherwise specified.

[0028] In the technical solutions of the present application, the user information (including but not limited to user personal information, user image information, user equipment information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0029] In the scenario of using personal information for automated decision-making, the method, device and system provided by the embodiments of the present application all provide corresponding operation portal for the user to choose to agree or refuse the automated decision-making result; if the user chooses to refuse, the expert decision-making process is entered. The expression "automated decision-making" here refers to the activity of automatically analyzing, evaluating the behavior habits, interests and hobbies, or economic, health, credit status, etc. of an individual through a computer program, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by personnel who are engaged in a certain field of work, have specialized experience, knowledge and skills, and have reached a certain professional level.

[0030] Embodiments of the present application provide an image processing method, comprising: obtaining a target image and preprocessing the target image to extract original byte data of the target image; inputting the original byte data into a target model to obtain target feature data conforming to a preset target string radix; judging an encoding type of the target feature data based on a preset rule engine model; inputting the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result; and extracting a target object of the target image based on the decoded target result; wherein the target model is a pre-trained adversarial network model.

[0031] Through embodiments of the present application, the method extracts deep original byte features of an image through a pre-trained adversarial network model, significantly improving the feature recognition success rate in a real financial environment and also improving the decoding success rate and robustness in complex scenarios. In addition, the method can accurately judge the encoding type of the target feature data based on a preset rule engine model and a multi-decoding sandbox mechanism, and input the target feature data into the corresponding decoding sandbox. This intelligent processing method can quickly adapt to different formats of two-dimensional codes, greatly improving the decoding speed and accuracy, and thus ensuring the efficiency and security of transactions.

[0032] Figure 1 An application scenario diagram of the image processing method according to an embodiment of the present application is schematically shown.

[0033] As shown in Figure 1 The application scenario 100 according to the embodiment can include a first terminal device 101, a second terminal device 102, a third terminal device 103, and a server 105. A network 104 is used to provide a communication link medium between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0034] A user can use the first terminal device 101, the second terminal device 102, the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0035] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, laptop computers, and desktop computers, etc.

[0036] The server 105 can be a server providing various services, such as a background management server (for example only) providing support for a website browsed by a user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server can analyze and process received user requests and the like, and feed back the processing results (such as a webpage, information, or data generated or obtained according to a user request) to the terminal device.

[0037] It should be noted that the image processing method provided in the embodiments of the present application can generally be executed by the server 105. Correspondingly, the image processing apparatus provided in the embodiments of the present application can generally be arranged in the server 105. The image processing method provided in the embodiments of the present application can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the image processing apparatus provided in the embodiments of the present application can also be arranged in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the system is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks, and servers.

[0039] In the financial field, in some transaction scenarios, the background related system needs to perform image processing on the images collected by the related financial application, for example, when performing two-dimensional code image decoding processing, due to poor system compatibility, it is often encountered that image decoding is messy and cannot dynamically switch the encoding mode, thereby causing the accuracy of transaction data to be unable to be guaranteed, and there is a financial security risk. Therefore, the embodiments of the present application propose an image processing method.

[0040] The image processing method according to the embodiments of the present application will be described in detail below based on the scenario described above. Figure 1 Figures 2-5 The image processing method according to the embodiments of the present application will be described in detail below based on the scenario described above.

[0041] Figure 2 A flowchart of the image processing method according to the embodiments of the present application is schematically shown.

[0042] As shown in Figure 2 According to the embodiments of the present application, the image processing method specifically includes operations S210-S250.

[0043] In operation S210, a target image is acquired and preprocessed to extract original byte data of the target image. ​

[0044] Figure 3 A flowchart of extracting original byte data of a target image according to an embodiment of the present application is shown schematically.

[0045] As shown in Figure 3 According to an embodiment of the present application, a target image is acquired and preprocessed to extract original byte data of the target image, which specifically includes operations S310-S320.

[0046] In operation S310, the target image is acquired and preprocessed to obtain initial data of the target image.

[0047] In an embodiment of the present application, in some transaction scenarios in the financial field, the electronic device will capture relevant images (for example, images containing two-dimensional codes) through the financial application that generates the transaction, for example, some financial applications can capture images through scanning, and the images are target images.

[0048] Further, the images are subjected to grayscale, noise reduction, and binarization processing to generate initial data of the two-dimensional code image. It should be noted that the initial data here is image bitmap data of the target image, and the bitmap data here can be understood as binary bitmap.

[0049] In operation S320, the original byte data of the initial data is extracted based on a preset target decoder.

[0050] In an embodiment of the present application, the target decoder is a two-dimensional code image decoder. It can be understood that a general two-dimensional code decoder is used to initially decode the binary bitmap, and when the decoding is successful, the original byte array data is obtained, that is, the original byte data of the initial data is obtained.

[0051] Through the embodiments of the present application, the original byte data is extracted by preprocessing the target image, ensuring that clear image information can be obtained in various environments. This process greatly improves the decoding success rate of two-dimensional codes and reduces decoding failures caused by image quality problems.

[0052] In operation S220, the original byte data is input into the target model to obtain target feature data conforming to a preset target string radix.

[0053] In an embodiment of the present application, in order to determine the features of the original byte data initially decoded and extracted, the original byte data is input into a pre-trained target model, and the target model is a pre-trained adversarial network model. Next, the training process of the target model is described in detail.

[0054] Figure 4A flowchart of a target model training according to an embodiment of the present application is shown.

[0055] As shown in FIG. 4, according to an embodiment of the present application, the target model is a pre-trained adversarial network model, and the training process includes operation S410~operation S420. Figure 4

[0056] In operation S410, the training data is obtained and processed in a structured manner. The training data is a data set conforming to a preset target string radix.

[0057] In an embodiment of the present application, the radix of the preset target string is first defined, for example, binary, decimal or hexadecimal. Then, the training data set conforming to the radix form is extracted from the historical data source. For example, the string data extracted here is from a related transaction log file data source, including time stamp and operation type information, and can be matched by regular expression to the string conforming to the preset target format (for example, hexadecimal here), and then the strings are stored in a list to form a preliminary training data set.

[0058] Further, the extracted training data set is processed in a structured manner, and the data is converted into a format suitable for subsequent target model input. For example, each field in the string can be split and converted into numerical data to construct a feature matrix, where each row of the feature matrix corresponds to a sample, and each column corresponds to a feature, such as converting the time stamp into a numerical representation of the time series.

[0059] In operation S420, the target feature data of the training data is extracted based on the up-sampling layer or the transpose convolution layer of the target model.

[0060] In an embodiment of the present application, the above structured training data set is input into the constructed target model for training. The target model here is an adversarial network model, which is a system composed of two deep neural network models, and the target model includes a generator and a discriminator.

[0061] In this training process, the structured feature matrix is first input into the up-sampling layer of the model generator. The role of this layer is to increase the dimension of the features, making them more recognizable. Subsequently, after processing by the transpose convolution layer, the model will generate higher-dimensional feature data, which can better express the complexity and diversity of the training data. Finally, after the above processing, the target model will output a set of target feature data corresponding to the training data set.

[0062] ​Further, after the training of the target model is completed, the original byte data is input into the trained target model to obtain target feature data conforming to a preset target string radix, and the target string radix is hexadecimal. It can be understood that the byte array data is converted into the hexadecimal target feature data.

[0063] Through the embodiments of the present application, the deep original byte features of the image are extracted by the pre-trained adversarial network model, which can better adapt to the two-dimensional code features in various complex environments, improve the learning ability and decoding accuracy of the model, and significantly improve the feature recognition success rate in the real financial environment, and also improve the decoding success rate and robustness in complex scenarios.

[0064] In operation S230, the encoding type of the target feature data is determined based on a preset rule engine model.

[0065] In the embodiments of the present application, the encoding type of the target feature data is determined based on a preset rule engine model, including: inputting the target feature data into the preset rule engine model to obtain the encoding type of the target feature data, and the encoding type includes a first encoding type and a second encoding type.

[0066] It can be understood that the target feature data is input into the preset rule engine model, which is composed of a series of pre-defined rules, and these rules are used to analyze the characteristics of the input data, and the rule engine can infer according to the features of the data.

[0067] For example, two key rules are defined in the rule engine, the first rule is to determine whether the hexadecimal string of the target feature data starts with 80 or 81, if yes, the encoding type of the target feature data is determined as the first encoding type. The second rule is to determine whether the hexadecimal string of the target feature data starts with 80 or 81, if not, the encoding type of the target feature data is determined as the second encoding type.

[0068] Specifically, after the target feature data is cleaned and standardized, such as removing invalid characters, filling missing values and the like, the target feature data is input into the above rule engine model for inference. If the input target feature data meets the first rule, the rule engine outputs "first encoding type". If the input target feature data meets the second rule, the rule engine outputs "second encoding type".

[0069] Through the embodiments of the present application, based on the preset rule engine model, the encoding type of the target feature data can be accurately determined and input into the corresponding decoding sandbox. This intelligent processing method can quickly adapt to two-dimensional codes of different formats, greatly improving the decoding speed and accuracy.

[0070] In operation S240, the target feature data is input into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result.

[0071] In the embodiments of the present application, inputting the target feature data into the corresponding decoding sandbox according to the encoding type of the target feature includes: when the encoding type is a first encoding type, inputting the target feature data into a first decoding sandbox, the first decoding sandbox including a self-defined check rule or decryption algorithm based on a preset first encoding format; and when the encoding type is a second encoding type, inputting the target feature data into a second decoding sandbox, the second decoding sandbox including a self-defined check rule or decryption algorithm based on a preset second encoding format.

[0072] For example, the first decoding sandbox herein can be a login code special decoding sandbox, which is configured with decoding algorithms and rules for login codes. In this sandbox, the decoding engine reads the input login code data and performs decoding operation according to its internal logic to obtain a decoded result, such as extracting corresponding text information or numerical information.

[0073] For example, the second decoding sandbox herein can be a transaction code decoding sandbox. The sandbox is configured with relevant rules and algorithms for transaction code decoding, and the decoding engine processes the input transaction code data to output a decoded target result.

[0074] Further, the target feature data is input into the corresponding decoding sandbox according to its encoding type, the target feature data of the first encoding type is input into the first decoding sandbox, and the target feature data of the second encoding type is input into the second decoding sandbox. For example, taking the login code as an example, after inputting the data, the decoding sandbox starts decoding, parses the actual meaning of the data, and generates a decoded target result such as "instruction". For the transaction code, the decoding sandbox executes the corresponding decoding algorithm to output the corresponding decoded target result such as "website information".

[0075] It should be noted that when the number of decoding results of any decoding sandbox that does not conform to the preset result exceeds the preset threshold, decoding fusing is triggered and the decoding sandbox is switched.

[0076] For example, when the number of decoding results of the first decoding sandbox that does not conform to the preset result exceeds 3 times, the first decoding sandbox is subjected to decoding fusing processing, and the target feature data of the first encoding type is input into the second decoding sandbox.

[0077] Through the embodiments of the present application, by using the multi-decoding sandbox and combining the "decoding fusing" mechanism, when the number of decoding failures of a certain sandbox exceeds the limit, automatic switching can be realized, which not only avoids the waste of resources caused by infinite circulation, but also effectively prevents the impact on transaction security caused by continuous decoding failures, and enhances the robustness and reliability of the system.

[0078] In operation S250, the target object of the target image is extracted based on the decoded target result.

[0079] Figure 5 A flowchart for extracting the target object according to an embodiment of the present application is schematically shown.

[0080] As Figure 5 shown, according to an embodiment of the present application, the target object of the target image is extracted based on the decoded target result, and this process specifically includes operation S510~operation S520.

[0081] In operation S510, the target result is parsed, and the target result includes a target string.

[0082] Exemplarily, the target result string is parsed to extract the key information. Using a string processing method (such as segmentation, regular expression, etc.), the target result can be split into multiple parts, and after parsing, a structured data object is obtained, which is convenient for subsequent processing.

[0083] In operation S520, the target object corresponding to the target intent is extracted from the target result in response to obtaining the target intent.

[0084] Specifically, in this operation, the target intent currently obtained needs to be determined first. For example, it is assumed that the target intent of the user is "to make a payment". According to this target intent, the target object related to it is extracted from the parsed result. For example, the target object can be a data object corresponding to the "payment code", and the specific extraction process can be realized by conditional judgment, checking whether the target intent matches the image type in the parsed result, and if it matches, the corresponding target object is stored to be sent to the background server to complete the corresponding transaction processing.

[0085] Through the embodiments of the present application, by parsing the decoded target result, the system can respond to the target intent of the user and extract the related transaction information, such as payment amount, merchant information, etc. The user experience is improved, and the efficiency and safety of the transaction process are ensured.

[0086] Based on the above image processing method, the present application further provides an image processing device. The device will be described in detail below. Figure 6

[0087] Figure 6 ​A structural block diagram of an image processing apparatus according to an embodiment of the present application is shown schematically.

[0088] As shown in Figure 6 The image processing apparatus 600 of this embodiment includes a target image acquisition module 610, a target feature acquisition module 620, an encoding type judgment module 630, a decoding module 640, and a target object extraction module 650.

[0089] The target image acquisition module 610 is configured to acquire a target image and perform preprocessing to extract original byte data of the target image. In an embodiment, the target image acquisition module 610 can be configured to perform the operation S210 described above, and thus repeated details are not provided herein.

[0090] The target feature acquisition module 620 is configured to input the original byte data into a target model to obtain target feature data conforming to a preset target string radix. In an embodiment, the target feature acquisition module 620 can be configured to perform the operation S220 described above, and thus repeated details are not provided herein.

[0091] The encoding type judgment module 630 is configured to judge the encoding type of the target feature data based on a preset rule engine model. In an embodiment, the encoding type judgment module 630 can be configured to perform the operation S230 described above, and thus repeated details are not provided herein.

[0092] The decoding module 640 is configured to input the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result. In an embodiment, the decoding module 640 can be configured to perform the operation S240 described above, and thus repeated details are not provided herein.

[0093] The target object extraction module 650 is configured to extract a target object of the target image based on the decoded target result. In an embodiment, the target object extraction module 650 can be configured to perform the operation S250 described above, and thus repeated details are not provided herein.

[0094] According to an embodiment of the present application, the target model is a pre-trained adversarial network model.

[0095] According to an embodiment of the present application, the target image acquisition module 610 includes an image acquisition sub-module and an original byte data extraction sub-module.

[0096] The image acquisition sub-module is configured to acquire a target image and perform preprocessing to obtain initial data of the target image. In an embodiment, the image acquisition sub-module can be configured to perform the operation S310 described above, and thus repeated details are not provided herein.

[0097] The original byte data extraction submodule is configured to extract original byte data of the initial data based on a preset target decoder. In an embodiment, the original byte data extraction submodule can be configured to perform the operation S320 described above, and details are not repeated here.

[0098] According to an embodiment of the present application, the target feature acquisition module 620 comprises a training submodule, which comprises a to-be-trained data acquisition subunit and a target feature extraction subunit.

[0099] The to-be-trained data acquisition subunit is configured to acquire to-be-trained data and perform data structure processing, the to-be-trained data being a data set conforming to a preset target string radix. In an embodiment, the to-be-trained data acquisition subunit can be configured to perform the operation S410 described above.

[0100] The target feature extraction subunit is configured to extract target feature data of the to-be-trained data based on an up-sampling and transpose convolution layer of the target model. In an embodiment, the target feature extraction subunit can be configured to perform the operation S420 described above.

[0101] According to an embodiment of the present application, the decoding module 640 comprises a first decoding submodule and a second decoding submodule.

[0102] The first decoding submodule is configured to input the target feature data into a first decoding sandbox to obtain a decoded target result when the encoding type is a first encoding type. The first decoding sandbox comprises a custom verification rule or decryption algorithm based on a preset first encoding format.

[0103] The second decoding submodule is configured to input the target feature data into a second decoding sandbox to obtain a decoded target result when the encoding type is a second encoding type. The second decoding sandbox comprises a custom verification rule or decryption algorithm based on a preset second encoding format.

[0104] According to an embodiment of the present application, the target object extraction module 650 comprises a target result analysis submodule and a target object extraction submodule.

[0105] The target result analysis submodule is configured to analyze the target result, the target result comprising a target string. In an embodiment, the target result analysis submodule can be configured to perform the operation S510 described above.

[0106] The target object extraction submodule is configured to extract a target object corresponding to a target intent from the target result in response to acquiring the target intent. In an embodiment, the target object extraction submodule can be configured to perform the operation S520 described above.

[0107] According to an embodiment of the present application, any one or more of the target image obtaining module 610, the target feature obtaining module 620, the encoding type judging module 630, the decoding module 640 and the target object extracting module 650 can be combined in one module, or any one of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. According to an embodiment of the present application, at least one of the target image obtaining module 610, the target feature obtaining module 620, the encoding type judging module 630, the decoding module 640 and the target object extracting module 650 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware that can be integrated or packaged with a circuit, or implemented in any one of software, hardware and firmware or in a proper combination of any of them. Alternatively, at least one of the target image obtaining module 610, the target feature obtaining module 620, the encoding type judging module 630, the decoding module 640 and the target object extracting module 650 can be at least partially implemented as a computer program module that can perform corresponding functions when it is run.

[0108] Figure 7 A block diagram of an electronic device suitable for implementing the image processing method according to an embodiment of the present application is schematically shown.

[0109] As shown in Figure 7 The electronic device 700 according to an embodiment of the present application includes a processor 701 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 702 or loaded from a storage portion 708 into a random access memory (RAM) 703. The processor 701 can include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset, and / or a special-purpose microprocessor (e.g., an application specific integrated circuit (ASIC)), etc. The processor 701 can also include an on-board memory for cache use. The processor 701 can include a single processing unit or multiple processing units for performing different actions of the method processes according to embodiments of the present application.

[0110] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via the bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present application by executing the programs in the ROM 702 and / or the RAM 703. It should be noted that the programs can also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 can also perform various operations of the method flow according to the embodiments of the present application by executing the programs stored in the one or more memories.

[0111] According to the embodiments of the present application, the electronic device 700 can further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 can further include one or more of the following components connected to the input / output (I / O) interface 705: an input part 706 including a keyboard, a mouse, and the like; an output part 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage part 708 including a hard disk, and the like; and a communication part 709 including a network interface card such as a LAN card, a modem, and the like. The communication part 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as necessary. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is installed in the storage part 708 as necessary.

[0112] The present application also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, when the one or more programs are executed, the method according to the embodiments of the present application is implemented.

[0113] According to an embodiment of the present application, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, can include but is not limited to: a portable computer diskette, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), a portable compact disc read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this application, a computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, the computer readable storage medium can include one or more of the above-described ROM 702 and / or RAM 703 and / or one or more memories other than the ROM 702 and the RAM 703.

[0114] Embodiments of the present application also include a computer program product, which includes a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the image processing method provided by the embodiments of the present application.

[0115] The above-described functions defined in the system / device / apparatus of the embodiments of the present application are performed when the computer program is executed by the processor 701. According to an embodiment of the present application, the above-described system, device, module, unit, etc. can be implemented by computer program modules.

[0116] In one embodiment, the computer program can rely on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of a signal on a network medium, and be downloaded and installed through the communication part 709, and / or be installed from the detachable medium 711. The program codes contained in the computer program can be transmitted by any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

[0117] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or be installed from the detachable medium 711. When the computer program is executed by the processor 701, the above-described functions defined in the system of the embodiments of the present application are performed. According to an embodiment of the present application, the above-described system, device, apparatus, module, unit, etc. can be implemented by computer program modules.

[0118] According to embodiments of the present application, program code for implementing the computer programs provided by embodiments of the present application can be written in any combination of one or more programming languages, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. Programming languages include, but are not limited to, Java, C++, python, "C", or the like. Program code can execute entirely on a user's computing device, partly on the user's device, as a stand-alone software package, partly on a remote computing device, or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0119] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0120] Those skilled in the art will appreciate that features recited in the various embodiments of the present application can be combined and / or integrated in various combinations, even if such combinations have not been explicitly recited in the present application. In particular, the features recited in the various embodiments of the present application can be combined and / or integrated in various combinations, without departing from the spirit and teachings of the present application. All such combinations are within the scope of the present application.

Claims

1. An image processing method, characterized by, The method comprises: acquiring a target image and preprocessing the target image to extract original byte data of the target image; inputting the original byte data into a target model to obtain target feature data conforming to a preset target string radix; judging an encoding type of the target feature data based on a preset rule engine model; inputting the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result; extracting a target object of the target image based on the decoded target result. The target model is a pre-trained adversarial network model.

2. The image processing method of claim 1, wherein, The method further comprises: when the number of decoding results of any decoding sandbox that does not conform to a preset result exceeds a preset threshold, triggering decoding fusing and switching decoding sandboxes.

3. The image processing method of claim 1, wherein, The method of acquiring a target image and preprocessing the target image to extract original byte data of the target image comprises: acquiring a target image and preprocessing the target image to obtain initial data of the target image; extracting original byte data of the initial data based on a preset target decoder. The initial data is image bitmap data of the target image, and the target decoder is a two-dimensional code image decoder.

4. The image processing method of claim 1, wherein, The target model is a pre-trained adversarial network model, and the training process comprises: acquiring training data and performing data structure processing, wherein the training data is a data set conforming to a preset target string radix; extracting target feature data of the training data based on an up-sampling layer or a transpose convolution layer of the target model.

5. The image processing method of claim 1, wherein, The method of judging an encoding type of the target feature data based on a preset rule engine model comprises: inputting the target feature data into a preset rule engine model to obtain the encoding type of the target feature data, wherein the encoding type comprises a first encoding type and a second encoding type.

6. The image processing method of claim 1 or 5, wherein, The method of inputting the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature comprises: when the encoding type is the first encoding type, inputting the target feature data into a first decoding sandbox, wherein the first decoding sandbox comprises a custom verification rule or a decryption algorithm based on a preset first encoding format; when the encoding type is the second encoding type, inputting the target feature data into a second decoding sandbox, wherein the second decoding sandbox comprises a custom verification rule or a decryption algorithm based on a preset second encoding format.

7. The image processing method of claim 1, wherein, The method of extracting a target object of the target image based on the decoded target result comprises: parsing the target result, wherein the target result comprises a target string; in response to acquiring a target intent, extracting a target object corresponding to the target intent from the target result.

8. An image processing apparatus characterized by comprising: The apparatus comprises: a target image acquisition module configured to acquire a target image and preprocess the target image to extract original byte data of the target image; a target feature acquisition module configured to input the original byte data into a target model to obtain target feature data conforming to a preset target string radix; The encoding type judgment module is configured to judge the encoding type of the target feature data based on a preset rule engine model. The decoding module is configured to input the target feature data into a corresponding decoding sandbox according to the encoding type of the target feature to obtain a decoded target result. The target object extraction module is configured to extract a target object of the target image based on the decoded target result. The target model is a pre-trained adversarial network model. 9.An electronic device comprising: one or more processors; memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, The computer program or instruction is executed by the processor to implement the steps of the method according to any one of claims 1-7.

11. A computer program product comprising computer programs or instructions, characterized in that, The computer program or instruction is executed by the processor to implement the steps of the method according to any one of claims 1-7.

Images