CN112053343A - User picture data processing method and device, computer equipment and storage medium - Google Patents
User picture data processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112053343A CN112053343A CN202010908098.6A CN202010908098A CN112053343A CN 112053343 A CN112053343 A CN 112053343A CN 202010908098 A CN202010908098 A CN 202010908098A CN 112053343 A CN112053343 A CN 112053343A
- Authority
- CN
- China
- Prior art keywords
- picture data
- user
- data
- authenticity check
- user picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title description 9
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 36
- 238000013145 classification model Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 abstract description 5
- 230000004048 modification Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001156002 Anthonomus pomorum Species 0.000 description 1
- 241001292396 Cirrhitidae Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Abstract
The invention discloses a method and a device for processing user picture data, computer equipment and a storage medium, wherein the method comprises the following steps: preprocessing picture data uploaded by a user side to delete part of the picture data of which the definition does not meet preset conditions; sorting the preprocessed user picture data through the classifier to obtain M types of user picture data, and then carrying out authenticity check to obtain authenticity check results corresponding to each type; and storing the corresponding user picture data when the authenticity check result meets a preset condition, deleting the corresponding user picture data when the authenticity check result does not meet the preset condition, and sending a notification message to the user side. The embodiment of the invention can perform instant authentication on the picture data of the user and feed back the picture data to the user side for modification, thereby improving the efficiency of processing the user data of the user side at the service side. The invention also relates to the field of block chains, and is also suitable for the fields of intelligent medical treatment, intelligent government affairs, science and technology finance and the like.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for processing user picture data, computer equipment and a storage medium.
Background
With the development of the technology, when a user submits information to a network platform, the data is often converted into a picture by means of photographing, and then the picture is uploaded to a network platform server through a user terminal program, such as computer browser software or a mobile phone application program, so that the time for the user to submit the data is reduced, and the efficiency is increased to improve the user experience. However, the method reduces the time for the user to submit the data, but increases the workload of background auditing of the network platform, and if the data of the user is wrong, the information submitted by the user cannot be immediately audited and passed, and needs to be continuously modified and confirmed, so that the service acquisition timeliness of the user is prolonged, the user experience is reduced, and the method has a prominent problem particularly in some application scenarios with high requirements on service timeliness and data accuracy.
For example, in a medical health insurance claim settlement service scenario, in order to complete claims quickly and improve user experience, many insurance companies develop online acceptance and online claim settlement services. Generally, a user only needs to upload related materials such as personal information, cases, a charge list and the like to an online platform in a photographing mode to complete acceptance and payment, which is undoubtedly greatly convenient for the user. On the other hand, some users have limited mastery degree of knowledge of computers and mobile phones, or do not see that uploading requirements upload designated pictures according to regulations, for example, a platform requires that users upload identity card pictures, but users upload invoice pictures, and the platform requires that users upload invoice pictures, but users upload medical history pictures, and meanwhile, actual required necessary transmission materials are lost due to wrong image channel uploading. All the problems can increase the manpower of background manual processing, prolong the time effectiveness of claim settlement and examination, and often need to communicate with the client repeatedly to supplement submission materials, so that the experience effect of the client is poor.
Therefore, in order to solve the problems, a technical scheme is required to be provided to solve the problem that when a user uploads data to a platform server through a picture, a platform worker manually checks a large amount of picture data through a background, and the efficiency is low.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for processing user picture data, a computer device, and a storage medium, which can perform instant authentication on user picture data and feed back the user picture data to a user side for modification, thereby improving efficiency of processing user data at a user side by a service side.
First, in order to achieve the above object, the present invention provides a method for processing user picture data, where the method includes:
preprocessing picture data uploaded by a user side to delete part of the picture data of which the definition does not meet preset conditions;
sorting the preprocessed user picture data through the classifier to obtain M types of user picture data;
performing authenticity check on the M types of user picture data to obtain authenticity check results corresponding to each type of the sorted user picture data;
and storing the corresponding user picture data when the authenticity check result meets a preset condition, deleting the corresponding user picture data when the authenticity check result does not meet the preset condition, and sending a notification message to the user side.
Further, the preprocessing the picture data uploaded by the user side to delete the part of the picture data with the definition not meeting the preset condition further comprises:
and generating page data, and issuing the page data to the user side when receiving the user side request instruction so that the user side renders the page data to generate a user picture data submission page.
Further, the preprocessing the picture data uploaded by the user side to delete the part of the picture data of which the definition does not meet the preset condition includes:
randomly executing ROI fetching operation for N times on the picture data to obtain N slices;
respectively calculating the definition of the N slices to obtain N definition scores;
calculating the average value of the N definition scores to obtain a definition value L of the picture data;
and when the definition value L is not higher than the preset threshold value, deleting the picture data and sending the notification message to the user side.
Further, sorting the preprocessed user picture data by the classifier to obtain M types of user picture data includes:
collecting original pictures of different types, and pre-classifying the original pictures to obtain M types of picture training data of a preset classification model;
performing data enhancement calculation of a preset type on the M types of picture training data;
converting the M types of picture training data subjected to the data enhancement calculation into training pictures with preset sizes, and training the preset classification model through the training pictures;
and calculating the classification confidence probability of the preprocessed picture data through the preset classification model, and when the classification confidence probability is greater than the preset classification confidence, moving the preprocessed picture data to a channel position of a corresponding type in the pre-classification model to obtain the M types of user picture data.
Further, the performing the authenticity check on the user picture data after sorting the M types of user picture data to obtain the authenticity check result corresponding to each type of the sorted user picture data includes:
collecting multiple types of true and false pictures to perform two-class training on the deep learning network training classifier;
and carrying out authenticity check on the sorted user picture data through the deep learning network training classifier to obtain an authenticity check result.
Further, the training of the classifier through the deep learning network and the sorting of the preprocessed user image data through the classifier further include:
performing relevance checking on the sorted preset type of picture data to obtain a authenticity checking result;
and storing the corresponding user picture data when the authenticity check result meets a preset condition, deleting the corresponding user picture data when the authenticity check result does not meet the preset condition, and sending the notification message to the user side.
Further, after storing the corresponding user picture data when the authenticity check result meets the preset condition, the method further comprises:
and uploading the stored user picture data to a block chain.
In order to achieve the above object, the present invention further provides a device for processing user picture data, wherein the device for processing user picture data comprises:
the definition inspection module is used for preprocessing the picture data uploaded by the user side so as to delete part of the picture data of which the definition does not meet the preset condition; for
The intelligent sorting module is used for sorting the preprocessed user picture data through the classifier to obtain M types of user picture data;
the authenticity check module is used for carrying out authenticity check on the M types of user picture data to obtain authenticity check results corresponding to each type of the sorted user picture data;
and the result output module is used for storing the corresponding user picture data when the authenticity check result meets the preset condition, and deleting the corresponding user picture data and sending a notification message to the user side when the authenticity check result does not meet the preset condition.
To achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the above method.
Compared with the prior art, the user picture data processing method, the device, the computer equipment and the storage medium in the embodiment of the invention automatically classify the user picture data meeting the conditions by using machine learning, and then respectively carry out authenticity check on the classified pictures, so that the picture data of the user can be immediately identified and fed back to the user side for modification, and the efficiency of processing the user data of the user side by the service side is improved.
Drawings
FIG. 1 is a schematic diagram of an application environment of an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for processing user picture data according to a first embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating a process of preprocessing the image data uploaded by the user side in fig. 2;
FIG. 4 is a schematic view of the process of training a classifier through a deep learning network and sorting the preprocessed user image data through the classifier in FIG. 2;
fig. 5 is a schematic flow chart illustrating the authenticity check performed on the sorted user picture data in fig. 2 to obtain an authenticity check result;
fig. 6 is a flowchart illustrating a second method for processing user image data according to a first embodiment of the present invention;
FIG. 7 is a block diagram of a second embodiment of a processing apparatus for user image data according to the present invention;
FIG. 8 is a diagram of a hardware configuration of a third embodiment of a computer apparatus according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Referring to fig. 1, a schematic diagram of an implementation environment of the embodiment of the invention is shown. The implementation environment includes: a user terminal 10 and a server 12.
The user terminal 10 is an electronic device with network access function, and the device may be a smart phone, a tablet computer, a personal computer, or the like.
The user terminal 10 is installed with a program 11 that can access the server 12, and after the program 11 logs in to access the server 12 through an account and a password, the user can perform specific operations and inputs on the server 12.
The server 12 is a server, a server cluster formed by a plurality of servers, or a cloud computing center. The server 12 stores a program 13, the program 13 includes a front-end module and a back-end module, the front-end module and the back-end module can be called by an interface, and a user can perform specific operation and input on the program 13 after the program 11 logs in through an account and a password or accesses the program 13 of the server 12 through the account and the password.
The user terminal 10 and the server 12 are connected via a network, which may include a plurality of network nodes, and the network may be the internet, a local area network, or a block chain network.
The processing method of the user picture data according to the embodiment of the present invention can be applied to the program 11 or the program 13 alone, can be applied to the program 11 and the program 13 in a distributed manner, or can be stored in a plurality of nodes of the network in a block chain manner.
Example one
According to the processing method of the user picture data, the characteristic screening is performed by utilizing the specificity information of the data and the existing characteristic generation method or the automatic characteristic generation process of the tool, so that the transmission and accumulation of errors in the characteristic generation process are reduced, and the quality and the precision of machine learning output data are improved.
Referring to fig. 2, a method for processing front-end and back-end user picture data in this embodiment includes the following steps:
step S100, generating page data, and issuing the page data to the user side when receiving the user side request instruction, so that the user side renders the page data to generate a user picture data submission page.
Specifically, in this embodiment, first, page data is generated, and when a user-side request is received, the page data is sent to the user side, where the page data generates a user page at the user side through rendering, and is used for a user to submit user data;
step S200, preprocessing the picture data uploaded by the user side to delete part of the picture data of which the definition does not meet the preset condition.
The preprocessing is to detect the definition of the picture so as to prevent the indistinguishable fuzzy picture from being uploaded and incapable of subsequent classification operation.
Specifically, referring to fig. 3, step S200 includes:
step S210: the ROI (region of interest) operation is performed N times on the picture at random to obtain N slices.
The ROI is a region to be processed, which is defined as a region of interest from a processed image in a manner of a square frame, a circle, an ellipse, an irregular polygon, etc. in machine vision and image processing, the ROI is calculated by using various operators (operators) and functions commonly used in machine vision software such as Halcon, OpenCV, Matlab, etc. through a specific tool, and the image is processed in the next step.
Step S220: respectively calculating the definition of the N slices to obtain N definition scores;
in this embodiment, by performing different sharpness detection algorithms for different slices, in other embodiments, only one detection algorithm may be used.
Step S230: calculating the average value of the N definition scores to obtain a definition value L of the picture;
step S240, when the definition value L is higher than a preset threshold value, the picture is saved, and when the definition value L is lower than the preset threshold value, the picture is deleted and a prompt notice is sent to a user side;
specifically, in this embodiment, by inputting one picture submitted by the user, the ROI region is randomly selected for the input image, and the operation is performed 10 times, so that 10 ROI small slices are generated in total. The sharpness score was then calculated for each slice using the Brenner, Tenengrad, Variance, Laplacian, Vollath algorithms, respectively. Each algorithm can generate 10 scores on 10 slices, the median of the 10 scores is taken as the final score of the algorithm, if the final score is higher than the definition threshold of the algorithm, the image is considered to be clear, otherwise, the image is considered to be fuzzy.
The threshold may be self-defined, or may be obtained by taking a median value from results obtained according to default thresholds corresponding to different picture sharpness quality algorithms, for example, in 5 algorithms in total, if 3 or more than 3 methods consider that the image is sharp, the image is determined to be sharp, otherwise, the image is determined to be fuzzy.
S300: and sorting the preprocessed user picture data through the classifier to obtain M types of user picture data.
The preprocessed pictures are all pictures with the definition meeting preset conditions, the pictures are stored in preset positions of a platform server, and the pictures are classified and trained through machine learning to realize automatic sorting of the pictures.
Specifically, referring to fig. 4, step S300 includes:
step S310: and collecting a plurality of different types of pictures and pre-classifying the pictures to obtain M types of picture training data of a preset classification model.
Specifically, a deep learning network resnet50 is used to train the classifier. In the training phase, we collected 4 kinds of pictures, identification card, invoice, medical history, and others. The identity card pictures comprise front and back sides, and other pictures are some of the first three types of pictures which are open, and are formed by combining natural scenes and open source data sets. Correspondingly, the final output channel number 1000 of the original resnet50 is set to 4.
Step S320: performing data enhancement calculation of a preset type on the M types of picture training data;
specifically, data enhancement is performed on pictures of a training set, and the data enhancement mode is formed by randomly combining five data enhancement modes, wherein the five data enhancement modes comprise random small-angle rotation in a range, random mirror image overturning in the horizontal direction and the vertical direction, image blurring, random brightness adjustment in a range and random saturation adjustment in a range.
Step S330: and converting the M types of picture training data into training pictures with preset sizes and training the preset classification model.
Specifically, the input size of the resnet50 trained classifier is set to 224 × 224. When the arbitrary size picture is transformed to 224 x 224, we first scale the long edge to 224 size and record the scale of the long edge. Then, we multiply the short edge of the input image by the scaling of the long edge to get the new short edge output. At this time, the obtained new short side length is definitely less than or equal to 224 lengths, we fill in the short side direction with fixed pixel values of the specified length, the fixed pixel values are obtained by calculating the average value of all image RGB channels of the training set, for example, [155,155,155], and finally the short side length also reaches 224. The specific filling method is as follows: taking an image with the current height H of 224 and the width W (W <224) as an example, the width W1 filled on the left side of the current image is int ((224-W)/2), int represents the rounding operation, and the width W2 filled on the right side of the image is 224-W1. Finally, after left and right fill, the short side also reaches a length output of 224. A similar approach is done for an image with a height H (H <224) for a scaled width of 224.
Step S340: and calculating the classification confidence probability of the preprocessed picture data through the preset classification model, and when the classification confidence probability is greater than the preset classification confidence, moving the preprocessed picture data to a channel position of a corresponding type in the pre-classification model to obtain the M types of user picture data.
Specifically, inputting a preprocessed picture, we obtain an array with a length of 4, where the number of ith (i ═ 0, 1, 2, 3) positions indicates the probability of being classified into ith class. We set the classification confidence 0.95. If the final classification score is larger than the classification confidence and the obtained channel type is not in accordance with the original input channel type, the picture channel uploaded by the user is considered to be wrong, and the system moves the picture to the corresponding channel.
And step S400, performing authenticity check on the M types of user picture data to obtain authenticity check results corresponding to each type of the sorted user picture data.
Specifically, referring to fig. 5, in step S400, performing a authenticity check on the M types of user picture data to obtain an authenticity check result corresponding to each type of the sorted user picture data includes:
step S410, collecting multiple types of true and false pictures to perform two-class training on the deep learning network training classifier;
and step S420, collecting multiple types of true and false pictures to perform two-class training on the deep learning network training classifier.
Step S500, storing the corresponding user picture data when the authenticity check result meets the preset condition, deleting the corresponding user picture data and sending a notification message to the user terminal when the authenticity check result does not meet the preset condition.
When processing user picture data, for a specific type of picture, it is necessary to perform an authenticity check, such as invoice data, to verify the authenticity of an invoice, and for some specific types of pictures, it is necessary to verify whether an original is an original, but not a copy or a print, such as an identification card picture.
Specifically, in the invoice verification stage, the uploaded invoice must be an original image, but not a copied or printed image. Whether the shot picture meets the requirements or not is judged by training a two-classification classifier. Wherein, a classifier is trained by adopting a deep learning network resnet50, and the number of output channels 1000 of resnet50 is changed into 2. During training, data enhancement is carried out on a training set, wherein the data enhancement comprises random small-angle rotation in a range, image blurring, random brightness adjustment in a range, random saturation adjustment in a range and RGB channel disturbance recombination, the five methods are combined randomly, the input size of a model is set to be 224 × 224, and the mode of converting images with any sizes into 224 × 224 is similar to that of automatic sorting. And if the image uploaded by the user is judged to be not a valid image, prompting the user to upload again.
Specifically, please refer to fig. 6, which is a flowchart illustrating a second method for processing user image data according to a first embodiment of the present invention, in this embodiment, the following steps are further included, and in other embodiments, the following steps may not be included:
step S600: and storing the corresponding user picture data when the authenticity check result meets a preset condition.
And step S700, deleting the corresponding user picture data and sending the notification message to the user side when the authenticity check result does not meet the preset condition.
Specifically, for classified pictures of special types, correlation verification needs to be performed to further verify whether picture data uploaded by a user is wrong, for example, for an invoice and a medical history image uploaded by the user, a deep learning technology is adopted to detect a date area on the image, then, a model is identified to identify the date, if the date difference between the two places is within 7 days, the two places are judged to meet correlation conditions, and if the date difference exceeds 7 days, the two places are judged not to meet the correlation conditions, and the user is prompted to upload again.
The notification message can be a prompt for uniformly prompting the user that the picture uploading fails, and can also be a notification message content which is not customized according to different error types, for example, the definition is not enough, the authenticity verification is not passed, the association verification is not passed, the picture channel uploading errors are wrong, and the like, so that the work can be carried out for 24 hours, the feedback is timely carried out, and compared with the manual work, the service volume can be greatly improved, the service efficiency is improved, the user experience can be improved, and the user quality is obtained.
And S800, uploading the stored user picture data to a block chain.
And obtaining corresponding summary information based on the stored user picture data, specifically, obtaining the summary information by performing hash processing on the stored user picture data, for example, by using a sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user equipment may download the summary information from the blockchain to verify whether the stored user picture data is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
According to the user data processing method, the user picture data meeting the conditions are automatically classified by using machine learning, and then the classified pictures are subjected to authenticity verification respectively, so that the picture data of the user can be immediately identified and fed back to the user side for modification, and the efficiency of processing the user data of the user side by the service side is improved.
Specifically, in the quality detection stage, the samples with good quality are accepted through algorithm intervention, the samples with poor quality are eliminated, the quality of the images can be checked at the source, and meanwhile, the waiting caused by returning the unqualified quality to the user for resubmission in later-stage arrangement is avoided. In the sorting stage, the images input by the user can be classified in the background, the input images can be classified into correct channels, the process avoids complex and tedious manual intervention, a large amount of labor cost is saved, and meanwhile user experience is improved. In the invoice true-checking stage, whether the invoice meets the conditions or not can be automatically judged through the modeling, so that the manual verification work is omitted, the labor cost is saved, and the risk of false data is avoided. In the material correlation stage, the accuracy of claim material can be further improved through algorithm identification, and the labor burden is reduced. Because the algorithm reasoning speed is fast, the accuracy rate is high, and the operation can be carried out for 24 hours, compared with the manual work, the service volume can be greatly improved undoubtedly, the service efficiency is improved, and meanwhile, the user experience can also be improved.
Example two
Referring to fig. 7, a program module diagram of the apparatus for processing user picture data according to the present invention is shown. In this embodiment, the processing apparatus 20 for user picture data may include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors to implement the present invention and implement the processing method for user picture data. The program module referred to in the embodiments of the present invention refers to a series of computer program instruction segments capable of performing specific functions, and is more suitable for describing the execution process of the processing apparatus 20 of user picture data in a storage medium than the program itself. The following description will specifically describe the functions of the program modules of the present embodiment:
the definition inspection module 202 is configured to pre-process the picture data uploaded by the user side to delete part of the picture data whose definition does not meet a preset condition; for
The intelligent sorting module 204 is configured to sort the preprocessed user picture data through the classifier to obtain M types of user picture data;
the authenticity check module 206 is configured to perform authenticity check on the M types of user picture data to obtain an authenticity check result corresponding to each type of the sorted user picture data;
and the result output module 208 is configured to store the corresponding user picture data when the authenticity check result meets a preset condition, and delete the corresponding user picture data and send a notification message to the user terminal when the authenticity check result does not meet the preset condition.
EXAMPLE III
Fig. 8 is a schematic diagram of a hardware architecture of a computer device according to a third embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown in fig. 8, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a processing device 20 for user picture data, which are communicatively connected to each other through a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used for storing an operating system installed in the computer device 2 and various types of application software, such as the program codes of the processing apparatus 20 for user picture data described in the above embodiments. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 8 only shows the computer device 2 with components 20-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the processing device 20 of the user picture data stored in the memory 21 can be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
Example four
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer readable storage medium of the present embodiment is used for the processing device 20 storing the user picture data, and when being executed by the processor, the processing device implements the processing method of the user picture data according to the foregoing embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for processing user picture data, the method comprising:
preprocessing picture data uploaded by a user side to delete part of the picture data of which the definition does not meet preset conditions;
sorting the preprocessed user picture data through a classifier to obtain M types of user picture data;
performing authenticity check on the M types of user picture data to obtain authenticity check results corresponding to each type of the sorted user picture data;
and storing the corresponding user picture data when the authenticity check result meets a preset condition, deleting the corresponding user picture data when the authenticity check result does not meet the preset condition, and sending a notification message to the user side.
2. The method for processing user picture data according to claim 1, wherein before the preprocessing the picture data uploaded by the user side to delete the part of the picture data whose definition does not satisfy the preset condition, the method further comprises:
and generating page data, and issuing the page data to the user side when receiving the user side request instruction so that the user side renders the page data to generate a user picture data submission page.
3. The method for processing user picture data according to claim 1 or 2, wherein the preprocessing the picture data uploaded by the user side to delete the part of the picture data whose definition does not satisfy the preset condition comprises:
randomly executing ROI fetching operation for N times on the picture data to obtain N slices;
respectively calculating the definition of the N slices to obtain N definition scores;
calculating the average value of the N definition scores to obtain a definition value L of the picture data;
and when the definition value L is not higher than the preset threshold value, deleting the picture data and sending the notification message to the user side.
4. The method as claimed in claim 3, wherein the sorting the pre-processed user picture data by the classifier to obtain M types of user picture data comprises:
collecting original pictures of different types, and pre-classifying the original pictures to obtain M types of picture training data of a preset classification model;
performing data enhancement calculation of a preset type on the M types of picture training data;
converting the M types of picture training data subjected to the data enhancement calculation into training pictures with preset sizes, and training the preset classification model through the training pictures;
and calculating the classification confidence probability of the preprocessed picture data through the preset classification model, and when the classification confidence probability is greater than the preset classification confidence, moving the preprocessed picture data to a channel position of a corresponding type in the pre-classification model to obtain the M types of user picture data.
5. The method as claimed in claim 4, wherein the performing the authenticity check on the M types of user picture data to obtain the authenticity check result corresponding to each type of the sorted user picture data comprises:
collecting multiple types of true and false pictures to perform two-class training on the deep learning network training classifier;
and carrying out authenticity check on the sorted user picture data through the deep learning network training classifier to obtain an authenticity check result.
6. The method as claimed in claim 5, wherein the training of the classifier by the deep learning network and the sorting of the pre-processed user picture data by the classifier further comprises:
performing relevance checking on the sorted preset type of picture data to obtain a authenticity checking result;
and storing the corresponding user picture data when the authenticity check result meets a preset condition, deleting the corresponding user picture data when the authenticity check result does not meet the preset condition, and sending the notification message to the user side.
7. The method as claimed in claim 6, wherein the step of storing the corresponding user picture data when the authenticity check result satisfies a predetermined condition further comprises:
and uploading the stored user picture data to a block chain.
8. A device for processing user picture data, the device comprising:
the definition inspection module is used for preprocessing the picture data uploaded by the user side so as to delete part of the picture data of which the definition does not meet the preset condition; for
The intelligent sorting module is used for sorting the preprocessed user picture data through the classifier to obtain M types of user picture data;
the authenticity check module is used for carrying out authenticity check on the M types of user picture data to obtain authenticity check results corresponding to each type of the sorted user picture data;
and the result output module is used for storing the corresponding user picture data when the authenticity check result meets the preset condition, and deleting the corresponding user picture data and sending a notification message to the user side when the authenticity check result does not meet the preset condition.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method for processing user picture data according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when being executed by a processor, realizes the steps of the method for processing user picture data according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010908098.6A CN112053343A (en) | 2020-09-02 | 2020-09-02 | User picture data processing method and device, computer equipment and storage medium |
| PCT/CN2020/122784 WO2021174869A1 (en) | 2020-09-02 | 2020-10-22 | User image data processing method, apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010908098.6A CN112053343A (en) | 2020-09-02 | 2020-09-02 | User picture data processing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112053343A true CN112053343A (en) | 2020-12-08 |
Family
ID=73608097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010908098.6A Pending CN112053343A (en) | 2020-09-02 | 2020-09-02 | User picture data processing method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112053343A (en) |
| WO (1) | WO2021174869A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992496B (en) * | 2023-09-28 | 2023-12-29 | 武汉彤新科技有限公司 | Data resource safety supervision system for enterprise service management |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657694A (en) * | 2018-10-26 | 2019-04-19 | 平安科技（深圳）有限公司 | Picture automatic classification method, device and computer readable storage medium |
| CN109726783A (en) * | 2018-12-28 | 2019-05-07 | 大象慧云信息技术有限公司 | A kind of invoice acquisition management system and method based on OCR image recognition technology |
| CN110175980A (en) * | 2019-04-11 | 2019-08-27 | 平安科技（深圳）有限公司 | Image definition recognition methods, image definition identification device and terminal device |
| CN110288755A (en) * | 2019-05-21 | 2019-09-27 | 平安银行股份有限公司 | The invoice method of inspection, server and storage medium based on text identification |
| CN111178345A (en) * | 2019-05-20 | 2020-05-19 | 京东方科技集团股份有限公司 | Bill analysis method, bill analysis device, computer equipment and medium |
| CN111191539A (en) * | 2019-12-20 | 2020-05-22 | 江苏常熟农村商业银行股份有限公司 | Certificate authenticity verification method and device, computer equipment and storage medium |
| CN111324874A (en) * | 2020-01-21 | 2020-06-23 | 支付宝实验室(新加坡)有限公司 | Certificate authenticity identification method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107862785A (en) * | 2017-10-16 | 2018-03-30 | 深圳市中钞信达金融科技有限公司 | Bill authentication method and device |
| CN108288073A (en) * | 2018-01-30 | 2018-07-17 | 北京小米移动软件有限公司 | Picture authenticity identification method and device, computer readable storage medium |
-
2020
- 2020-09-02 CN CN202010908098.6A patent/CN112053343A/en active Pending
- 2020-10-22 WO PCT/CN2020/122784 patent/WO2021174869A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657694A (en) * | 2018-10-26 | 2019-04-19 | 平安科技（深圳）有限公司 | Picture automatic classification method, device and computer readable storage medium |
| CN109726783A (en) * | 2018-12-28 | 2019-05-07 | 大象慧云信息技术有限公司 | A kind of invoice acquisition management system and method based on OCR image recognition technology |
| CN110175980A (en) * | 2019-04-11 | 2019-08-27 | 平安科技（深圳）有限公司 | Image definition recognition methods, image definition identification device and terminal device |
| CN111178345A (en) * | 2019-05-20 | 2020-05-19 | 京东方科技集团股份有限公司 | Bill analysis method, bill analysis device, computer equipment and medium |
| CN110288755A (en) * | 2019-05-21 | 2019-09-27 | 平安银行股份有限公司 | The invoice method of inspection, server and storage medium based on text identification |
| CN111191539A (en) * | 2019-12-20 | 2020-05-22 | 江苏常熟农村商业银行股份有限公司 | Certificate authenticity verification method and device, computer equipment and storage medium |
| CN111324874A (en) * | 2020-01-21 | 2020-06-23 | 支付宝实验室(新加坡)有限公司 | Certificate authenticity identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021174869A1 (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287971B (en) | Data verification method, device, computer equipment and storage medium | |
| CN108256591B (en) | Method and apparatus for outputting information | |
| CN107066844B (en) | Method and device for safety control and traceability tracking of paper documents | |
| CN112861648B (en) | Character recognition method, character recognition device, electronic equipment and storage medium | |
| CN109783781B (en) | Image recognition-based policy entry method and related device | |
| CN109840469B (en) | Image recognition-based policy entry method and related device | |
| CN112861906A (en) | Method and device for detecting picture abnormity | |
| CN114550051A (en) | Vehicle loss detection method and device, computer equipment and storage medium | |
| CN113673439A (en) | Pet dog identification method, device, equipment and storage medium based on artificial intelligence | |
| CN113111880A (en) | Certificate image correction method and device, electronic equipment and storage medium | |
| CN110458184B (en) | Optical character recognition assistance method, device, computer equipment and storage medium | |
| CN112036488A (en) | Event identification method, device and equipment based on image identification and storage medium | |
| CN111680181A (en) | Abnormal object identification method and terminal equipment | |
| CN111192106A (en) | Information acquisition method and device based on picture identification and computer equipment | |
| CN112053343A (en) | User picture data processing method and device, computer equipment and storage medium | |
| US11887392B2 (en) | Systems and methods for digitized document image text contouring | |
| CN113657318A (en) | Pet classification method, device, equipment and storage medium based on artificial intelligence | |
| CN111950562A (en) | Picture processing method and device, terminal equipment and storage medium | |
| CN113239910B (en) | Certificate identification method, device, equipment and storage medium | |
| CN111709404B (en) | Machine room legacy identification method, system and equipment | |
| CN114329030A (en) | Information processing method and device, computer equipment and storage medium | |
| CN113066223A (en) | Automatic invoice verification method and device | |
| CN113807256A (en) | Bill data processing method and device, electronic equipment and storage medium | |
| CN113505780A (en) | Two-dimensional code-based intelligent detection maintenance method and equipment | |
| CN114077994A (en) | Electronic evidence processing method and device based on evidence chain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |