WO2020172767A1

WO2020172767A1 - Electronic purchase order recognition method and apparatus, and terminal device.

Info

Publication number: WO2020172767A1
Application number: PCT/CN2019/076042
Authority: WO
Inventors: 武泽; 张俊; 黄利庆; 吴松
Original assignee: 深圳盒子信息科技有限公司
Priority date: 2019-02-25
Filing date: 2019-02-25
Publication date: 2020-09-03
Also published as: CN113474786A

Abstract

Disclosed in the present application are an electronic purchase order recognition method and an apparatus, and a terminal device, the electronic purchase order recognition method comprising: acquiring an electronic purchase order image, the electronic purchase order image containing an electronic signature; and by means of a pre-trained Alexnet convolutional neural network model, performing recognition on the electronic purchase order image and determining whether the electronic signature on the electronic purchase order image is legitimate to obtain a determination result. The technical solution provided in the present application is able to automatically recognize and determine the legitimacy of an electronic signature on an electronic purchase order, thus compensating for gaps in manual checking.

Description

Method, device and terminal equipment for identifying electronic purchase order

Technical field

This application relates to the technical field of e-commerce, and in particular to an electronic purchase order recognition method, device, terminal equipment and computer-readable storage medium.

Background technique

In traditional credit card consumption, consumers need to pay at POS (Point of sales) The paper purchase form printed out by the terminal is signed as the cardholder's proof of confirmation of this purchase. Due to the waste of paper and cumbersome storage and management of paper purchase orders, more and more merchants use electronic purchase orders to replace traditional paper purchase orders. After the transaction is completed, consumers use the touch screen to electronically sign the electronic purchase order. After the signature is completed, the POS terminal will automatically upload the electronic purchase order to the system for storage, which is environmentally friendly and easy to manage.

However, in busy work, the cashier usually does not carefully identify whether the electronic signature on the electronic purchase order is clear and legal. If the consumer just clicks or swipes randomly on the touch screen, the cashier will not necessarily find out , Resulting in the failure to determine what is signed on the electronic purchase order as a voucher during later review, resulting in potential risks.

technical problem

In view of this, this application provides an electronic purchase order identification method, device, terminal device, and computer readable storage medium to solve the problem of how to automatically identify and judge the electronic signature in the electronic purchase order.

Technical solutions

The first aspect of this application provides an electronic purchase order identification method, including:

Obtaining a picture of an electronic purchase order, where the picture of the electronic purchase order includes an electronic signature;

The pre-trained Alexnet convolutional neural network model is used to identify the electronic purchase order picture, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain the determination result.

The second aspect of the present application provides an electronic purchase order recognition device, including:

The first obtaining unit is configured to obtain a picture of an electronic purchase order, wherein the picture of the electronic purchase order includes an electronic signature;

The recognition unit is configured to recognize the electronic purchase order picture through the pre-trained Alexnet convolutional neural network model, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain the determination result.

A third aspect of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and running on the processor. The processor implements the first aspect or the first aspect when the computer program is executed by the processor. The electronic purchase order identification method mentioned in any of the possible implementations.

A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and the computer program implements the first aspect or any possible implementation manner of the first aspect when executed by a processor The electronic purchase order identification method mentioned in.

Beneficial effect

In the embodiment of the present invention, since the pre-trained Alexnet convolutional neural network model is used to identify and judge the electronic purchase order containing the electronic signature, the legality of the electronic signature on the electronic purchase order can be accurately and efficiently checked in time. Automatically identify and judge to make up for manual inspection omissions.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

Figure 1 is a schematic diagram of the implementation process of the first method for identifying electronic purchase orders provided by this application;

Figures 2a-2c are example diagrams of positive sample pictures provided by this application;

Figures 3a-3c are example diagrams of negative sample pictures provided by this application;

Figure 4 is a schematic diagram of the implementation process of the second method for identifying electronic purchase orders provided by this application;

Fig. 5 is a schematic diagram of the electronic purchase order recognition device provided by this application;

Figure 6 is a schematic structural diagram of an embodiment of a terminal device provided by this application.

Embodiments of the invention

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of the present invention.

In order to illustrate the technical solution of the present invention, specific embodiments are used for description below.

It should be understood that when used in this specification and appended claims, the term "comprising" indicates the existence of the described features, wholes, steps, operations, elements and/or components, but does not exclude one or more other features Existence or addition of, whole, step, operation, element, component and/or its collection.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "once" or "in response to determination" or "in response to detection" depending on the context . Similarly, the phrase "if determined" or "if detected [described condition or event]" can be interpreted as meaning "once determined" or "response to determination" or "once detected [described condition or event]" depending on the context ]" or "in response to detection of [condition or event described]".

In addition, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

Example one

The following describes the first electronic purchase order identification method provided by the embodiment of the present application. Please refer to FIG. 1. The electronic purchase order identification method in the embodiment of the present application includes:

In S101, an electronic purchase order picture is obtained, where the electronic purchase order picture includes an electronic signature.

The electronic purchase order is a consumption certificate generated by the consumer after swiping the card. In addition to basic information such as the store name, product name, consumption amount, consumption time, and serial number, the complete electronic purchase order also contains the consumer's approval Handwritten electronic signature of electronic equipment on electronic purchase order.

To obtain the picture of the electronic purchase order, the electronic purchase order can be converted into a picture format such as jpg through the format conversion program, or the picture of the electronic purchase order can be obtained through automatic screenshot when the electronic purchase order is displayed. The picture of the electronic purchase order includes at least an area where the electronic signature is displayed, that is, the electronic purchase order needs to include electronic signature information. Preferably, the electronic purchase order picture only includes an area where the electronic signature is displayed, excluding the area where other redundant basic information is displayed.

In S102, the pre-trained Alexnet convolutional neural network model is used to identify the electronic purchase order picture, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain a determination result.

Load the pre-trained Alexnet convolutional neural network model into the running memory, identify the image of the electronic purchase order, and determine whether the electronic signature on the electronic purchase order image is legal, that is, determine whether the signature on the electronic purchase order is clear Recognizable and get the judgment result. Optionally, the judgment result can be fed back to the user in the form of text or patterns displayed on the screen, for example, by displaying texts such as "legal" or "illegal", or by displaying a green icon to feed back the electronic purchase order The electronic signature on the e-signature is legal, and the red icon is displayed to feedback that the electronic signature on the e-signature is illegal.

Optionally, before the step S102, the method further includes:

Preprocessing the picture of the electronic purchase order.

The preprocessing can include grayscale processing and vector conversion processing.

When judging the legality of the electronic signature on the electronic purchase order picture, there is no need to obtain the specific color information of the electronic purchase order picture. Therefore, if the electronic purchase order picture is an RGB picture, the electronic purchase order picture can be Gray-scale processing obtains an electronic purchase order picture with only one color channel information, thereby reducing the amount of calculation for the subsequent recognition and judgment of the Alexnet convolutional neural network model.

Because the Alexnet convolutional neural network model specifically performs a series of convolution and transformation operations on the input matrix data, the vector conversion of the electronic purchase order picture is carried out, and the vector corresponding to the converted electronic purchase order picture is input to Alexnet Convolutional neural network model.

Specifically, the pre-trained Alexnet convolutional neural network model includes Batch Normalization layer and softmax classifier.

The pre-trained Alexnet convolutional neural network model is an 8-layer deep neural network, including 5 layers of convolutional layers and 3 layers of fully connected layers, and finally includes a softmax classifier, which is described as follows:

Convolutional layer 1: Since the electronic purchase order pictures are usually black and white pictures or have been grayscale processed, the input data matrix is different from the usual 227*227*3, but 227*227*1; linear rectification function is used (Rectified Linear Unit, ReLU) as the activation function, the size of the convolution kernel is 11*11, the number is 96, the step size is 4*4, the filling pixel is 0, and the data is obtained after this layer of convolution (227-11)/4+1 =55, so the output is 55*55*96. After the first layer of convolutional layer, there is a local response normalization layer (Local Response Normalization, LRN) and max_pooling pooling layer. The LRN layer creates a competition mechanism for the activity of local neurons, making the response larger. It is relatively larger and inhibits other neurons with smaller feedback, which enhances the generalization ability of the model. The core size of max_pooling pooling layer is 3*3, the step size is 2*2, and the data is transformed (55-3)/2+1=27, so after all the processing of the first layer, the data becomes 27*27 *96.

Convolutional layer 2: The input data matrix is 27*27*96, using RELU as the activation function, the size of the convolution kernel is 5*5, the number is 256, the step size is 1*1, the filling pixel is 2, and the data passes through this layer After convolution, we get (27-5+2*2)/1+1=27, so the output is 27*27*256. Convolutional layer 2 is the same as layer 1, with the same LRN layer and max_pooling pooling layer. After the pooling layer (27-3)/2+1=13, the final output is 13*13*256.

Convolutional layer 3: The input data matrix is 13*13*256, using RELU as the activation function, the size of the convolution kernel is 3*3, the number is 384, the step size is 1*1, the filling pixel is 1, and the data passes through this layer After convolution, we get (13-3+2*1)/1+1=13, so the output is 13*13*384. Convolutional layer 3 has no LRN layer and pooling layer.

Convolutional layer 4: The input data matrix is 13*13*384, using RELU as the activation function, the size of the convolution kernel is 3*3, the number is 384, the step size is 1*1, the filling pixel is 1, and the data passes through this layer After convolution, we get (13-3+2*1)/1+1=13, so the output is 13*13*384. Convolutional layer 4 also has no LRN layer and pooling layer.

Convolutional layer 5: The input data matrix is 13*13*384, using RELU as the activation function, the size of the convolution kernel is 3*3, the number is 256, the step size is 1*1, the filling pixel is 1, and the data passes through this layer After convolution, we get (13-3+2*1)/1+1=13, so the output is 13*13*256. This layer also has a max_pooling pooling layer, the core size of the pooling layer is 3*3, the step size is 2*2, after transformation, it is (13-3)/2+1=6, and the output is 6*6*256 .

Fully connected layer 1: The input data is 6*6*256, and RELU is used as the activation function. This layer uses Batch Normalization is the dropout layer, and the data becomes 4096*1 after the change.

Using Batch Normalization as the dropout layer can prevent overfitting and speed up model training.

Fully connected layer 2: Fully connected layer 2 is similar to fully connected layer 1, the input is 4096*1, and the output is also 4096*1.

Fully connected layer 3: Input data is 4096*1, output is 1000*1.

Softmax classifier: The softmax classifier here specifically includes two classifications, the classification label 0 means legal, and the classification label 1 means illegal.

Optionally, before the step S102, the method further includes:

Acquiring a preset number of training pictures, the training pictures carrying judgment label information;

Set the batch size parameter batch_size of the Alexnet convolutional neural network, the training round parameter epochs, and the validation set ratio parameter validation_split, and input the training picture to obtain the pre-trained Alexnet convolutional neural network model.

The training picture is a picture that contains an electronic signature and carries determination tag information. A determination tag of 0 indicates that the electronic signature contained in the training picture is legal, and a determination tag of 1 indicates that the electronic signature contained in the training picture is illegal. The judgment label information carried in the training picture may be a label marked by the staff through manual judgment in advance. Obtain a preset number of training pictures, for example, 97150 pictures containing electronic signatures are obtained as training pictures. The training pictures contain positive sample pictures (legitimate pictures with a judgment label of 0 carried, as shown in Figure 2a, Figure 2b, and Figure 2c) ) And negative sample pictures (carrying illegal pictures with a judgment label of 1, as shown in Figure 3a, Figure 3b, and Figure 3c), and the ratio of positive sample pictures and negative sample pictures is balanced. For example, in 97150 training pictures, The number of positive samples is 56,600, and the number of negative samples is 40,550. After obtaining a preset number of training pictures, vector conversion processing is performed on the training pictures.

Set the hyperparameters of the Alexnet convolutional neural network. The hyperparameters include the batch size parameter batch_size, the training round parameter epochs, and the validation set scale parameter validation_split. For example, set batch_size to 128, epochs to 100, and validation_split to 0.2 (It means that there are 0.2 ratio pictures in the training pictures as the validation set). Input the above vector-transformed training images into the Alexnet convolutional neural network with hyperparameters set for training. During the training process, the Alexnet convolutional neural network automatically adjusts other parameters, and finally a trained Alexnet convolutional neural network model is obtained. This training A good Alexnet convolutional neural network model is used as a pre-trained Alexnet convolutional neural network model.

In the embodiments of this application, since the pre-trained Alexnet convolutional neural network model is used to identify and judge the electronic purchase order containing the electronic signature, it is possible to accurately and efficiently check the legality of the electronic signature on the electronic purchase order in time. Automatically identify and judge to make up for manual inspection omissions.

Example two

Fig. 4 shows a schematic flow chart of a second method for identifying electronic purchase orders provided by an embodiment of the present application. The execution subject of the example of the present invention is a terminal device, such as a POS machine. The details are as follows:

In S401, a picture of an electronic purchase order is obtained, where the picture of the electronic purchase order includes an electronic signature.

S401 in this embodiment is the same as S101 in the previous embodiment. For details, please refer to the related description of S101 in the previous embodiment, which will not be repeated here.

Optionally, before the S401, it further includes:

Obtain the sliding track, and generate an electronic signature on the electronic purchase order according to the sliding track.

After the consumer completes a consumption by swiping the card, an electronic purchase order is generated and displayed on the terminal device. At this time, the terminal device obtains the consumer's sliding operation, and the consumer can use a touch pen or finger to display the electronic display on the terminal device's touch screen. Perform a sliding operation on the signature bar of the purchase order to obtain the sliding track. After the consumer's sliding operation ends, the terminal device generates an electronic signature on the electronic purchase order according to the sliding track.

In S402, the pre-trained Alexnet convolutional neural network model is used to identify the electronic purchase order picture, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain the determination result.

S402 in this embodiment is the same as S102 in the previous embodiment. For details, please refer to the related description of S102 in the previous embodiment, which will not be repeated here.

Optionally, after the S402, it further includes:

Store the picture of the electronic purchase order and the corresponding determination result.

Store the picture of the electronic purchase order and the corresponding judgment result to facilitate subsequent query and historical information traceability. Optionally, the serial number of the electronic purchase order corresponding to the picture of the electronic purchase order can be extracted, and the serial number, the picture of the electronic purchase order and the corresponding determination result can be stored in the database, and then the user only needs to enter the serial number. Check the legal information of the electronic purchase order.

In S403, if the determination result is illegal, a prompt to re-signature is issued.

If the electronic signature on the current electronic purchase order picture is judged to be illegal, it means that the current consumer's electronic signature on the electronic purchase order is not clear, and a re-signature prompt is issued at this time. The consumer can be prompted to re-sign the electronic signature on the electronic purchase order by playing voice and/or displaying text on the display screen.

In the embodiments of this application, since the pre-trained Alexnet convolutional neural network model is used to identify and judge the electronic purchase order containing the electronic signature, it is possible to accurately and efficiently check the legality of the electronic signature on the electronic purchase order in time. Automatically identify and judge, so as to make up for manual inspection omissions; at the same time, when the judgment result is illegal, a re-signature prompt is issued to automatically guide consumers to re-sign, which further reduces the workload of staff and improves work efficiency.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

Example three

The embodiment of the present application also provides an electronic purchase order recognition device. As shown in FIG. 5, for ease of description, only the parts related to the embodiment of the present application are shown:

The device for identifying electronic purchase orders includes: a first acquiring unit 51 and an identifying unit 52. among them:

The first acquiring unit 51 is configured to acquire a picture of an electronic purchase order, wherein the picture of the electronic purchase order includes an electronic signature.

The recognition unit 52 is configured to recognize the electronic purchase order picture through the pre-trained Alexnet convolutional neural network model, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain the determination result.

Convolutional layer 1: Since the electronic purchase order picture is usually black and white or gray-scale processed, the input data matrix is different from the usual 227*227*3, but 227*227*1; linear rectification function is used (Rectified Linear Unit, ReLU) as the activation function, the size of the convolution kernel is 11*11, the number is 96, the step size is 4*4, the filling pixel is 0, and the data is obtained after this layer of convolution (227-11)/4+1 =55, so the output is 55*55*96. After the first layer of convolutional layer, there is a local response normalization layer (Local Response Normalization, LRN) and max_pooling pooling layer. The LRN layer creates a competition mechanism for the activity of local neurons, making the response larger. It is relatively larger and inhibits other neurons with smaller feedback, which enhances the generalization ability of the model. The core size of max_pooling pooling layer is 3*3, the step size is 2*2, and the data is transformed (55-3)/2+1=27, so after all the processing of the first layer, the data becomes 27*27 *96.

Convolutional layer 5: The input data matrix is 13*13*384, using RELU as the activation function, the size of the convolution kernel is 3*3, the number is 256, the step size is 1*1, the filling pixel is 1, and the data passes through this layer After convolution, we get (13-3+2*1)/1+1=13, so the output is 13*13*256. This layer also has a max_pooling pooling layer, the core size of the pooling layer is 3*3, the step size is 2*2, after transformation, it is (13-3)/2+1=6 and the output is 6*6*256 .

Fully connected layer 3: Input data is 4096*1, output is 1000*1.

Optionally, the electronic purchase order recognition device further includes:

The training unit is used to obtain a preset number of training pictures, the training pictures carry judgment label information; set the batch size parameter batch_size of the Alexnet convolutional neural network, the training round parameter epochs, and the validation set ratio parameter validation_split, and Input the training picture to obtain the pre-trained Alexnet convolutional neural network model.

Optionally, the electronic purchase order recognition device further includes:

The electronic signature generating unit is used to obtain the sliding track, and generate an electronic signature on the electronic purchase order according to the sliding track.

Optionally, the electronic purchase order recognition device further includes:

The preprocessing unit is used to preprocess the picture of the electronic purchase order.

Optionally, the electronic purchase order recognition device further includes:

The prompt unit is used to send out a prompt to re-sign if the result of the determination is illegal.

Optionally, the electronic purchase order recognition device further includes:

The storage unit is used to store the picture of the electronic purchase order and the corresponding determination result.

Example four

Fig. 6 is a schematic diagram of a terminal device provided by an embodiment of the present invention. As shown in FIG. 6, the terminal device 6 of this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and running on the processor 60, such as electronic purchase order recognition program. When the processor 60 executes the computer program 62, the steps in the above embodiments of the electronic purchase order recognition method are implemented, for example, steps S101 to S102 shown in FIG. 1. Alternatively, when the processor 60 executes the computer program 62, the functions of the modules/units in the foregoing device embodiments, such as the functions of the modules 51 to 52 shown in FIG. 5, are realized.

Exemplarily, the computer program 62 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 61 and executed by the processor 60 to complete this invention. The one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the terminal device 6. For example, the computer program 62 may be divided into a first acquisition unit and an identification unit, and the specific functions of each unit are as follows:

The first obtaining unit is configured to obtain a picture of an electronic purchase order, wherein the picture of the electronic purchase order includes an electronic signature.

The terminal device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The terminal device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that FIG. 6 is only an example of the terminal device 6 and does not constitute a limitation on the terminal device 6. It may include more or less components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

The so-called processor 60 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 61 may be an internal storage unit of the terminal device 6, such as a hard disk or memory of the terminal device 6. The memory 61 may also be an external storage device of the terminal device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), or a secure digital (Secure Digital, SD) equipped on the terminal device 6. Flash memory card Card) etc. Further, the memory 61 may also include both an internal storage unit of the terminal device 6 and an external storage device. The memory 61 is used to store the computer program and other programs and data required by the terminal device. The memory 61 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and conciseness of the description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units, Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above-mentioned integrated units can be hardware-based Formal realization can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only used to facilitate distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, which is not repeated here.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

A person of ordinary skill in the art may be aware that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed device/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units. Or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal, and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in Within the protection scope of the present invention.

Claims

An electronic purchase order recognition method, characterized in that it comprises:

Obtaining a picture of an electronic purchase order, where the picture of the electronic purchase order includes an electronic signature;

The pre-trained Alexnet convolutional neural network model is used to identify the electronic purchase order picture, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain the determination result.
The method for identifying an electronic purchase order according to claim 1, wherein before said obtaining the picture of the electronic purchase order, the method further comprises:

Obtain the sliding track, and generate an electronic signature on the electronic purchase order according to the sliding track.
The method for identifying an electronic purchase order according to claim 1, wherein after said obtaining the picture of the electronic purchase order, the method further comprises:

Preprocessing the picture of the electronic purchase order.
The electronic purchase order recognition method according to claim 1, wherein the pre-trained Alexnet convolutional neural network model includes a Batch Normalization layer and a softmax classifier.
The electronic purchase order recognition method according to claim 1, characterized in that, in the pre-trained Alexnet convolutional neural network model, the electronic purchase order picture is recognized, and the electronic purchase order is determined Whether the electronic signature on the picture of the purchase order is legal, before the judgment result is obtained, it also includes:

Acquiring a preset number of training pictures, the training pictures carrying judgment label information;

Set the batch size parameter batch_size of the Alexnet convolutional neural network, the training round parameter epochs, and the validation set ratio parameter validation_split, and input the training picture to obtain the pre-trained Alexnet convolutional neural network model.
The electronic purchase order identification method according to any one of claims 1 to 5, wherein the pre-trained Alexnet convolutional neural network model is used to identify the electronic purchase order picture, and determine the Whether the electronic signature on the picture of the electronic purchase order is legal, after the judgment result is obtained, it also includes:

If the result of the determination is illegal, a prompt to re-signature is issued.
The electronic purchase order identification method according to any one of claims 1 to 5, wherein the pre-trained Alexnet convolutional neural network model is used to identify the electronic purchase order picture, and determine the Whether the electronic signature on the picture of the electronic purchase order is legal, after the judgment result is obtained, it also includes:

Store the picture of the electronic purchase order and the corresponding determination result.
An electronic purchase order recognition device, characterized in that it comprises:

The first obtaining unit is configured to obtain a picture of an electronic purchase order, wherein the picture of the electronic purchase order includes an electronic signature;

The recognition unit is configured to recognize the electronic purchase order picture through the pre-trained Alexnet convolutional neural network model, determine whether the electronic signature on the electronic purchase order picture is legal, and obtain the determination result.
A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program as claimed in claims 1 to 7 Steps of any of the methods.
A computer-readable storage medium storing a computer program, wherein the computer program implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by a processor.