CN115661439A

CN115661439A - Bill identification method and device, electronic equipment and medium

Info

Publication number: CN115661439A
Application number: CN202211312581.3A
Authority: CN
Inventors: 王赛; 王臻; 刘龙; 石文鹏; 李辉芳
Original assignee: Agricultural Bank of China
Current assignee: Agricultural Bank of China
Priority date: 2022-10-25
Filing date: 2022-10-25
Publication date: 2023-01-31

Abstract

The embodiment of the application discloses a bill identification method, a bill identification device, electronic equipment and a medium. Wherein, the method comprises the following steps: determining a target bill from the sample bills, and determining a target area of the target bill; performing model training according to the target bill and the target area, and determining an area detection model; detecting the sample bill based on the area detection model, and determining a content area in the sample bill; and intercepting a content area in the sample bill, performing model training according to the content area in the sample bill and the text content in the content area, determining a text recognition model, and recognizing the text in the bill to be recognized based on the text recognition model. According to the technical scheme, the bill recognition model is trained automatically by utilizing an automatic deep learning technology, so that the amount of labeled data is reduced, and the training efficiency and accuracy are improved greatly.

Description

Bill identification method and device, electronic equipment and medium

Technical Field

The present application relates to the field of bill identification technologies, and in particular, to a bill identification method and apparatus, an electronic device, and a medium.

Background

The existing bank system has more difficulty in bill identification. Firstly, the bill is various in type, relates to the bill of multiple type, multiple version, and the content of waiting to discern of every kind of bill is not fixed, needs to customize independent OCR detection and recognition model to every type of version. Secondly, the bill identification difficulty is high. The bill usually contains types of characters such as numbers, english, chinese and the like, and has the problems of illegible handwriting, adhesion between characters and the like. Thirdly, note marking cost is high. The position and the characters of the content to be recognized need to be marked at the same time, the marking time of a single bill is long, and the recognition effect of the OCR model is poor due to the fact that the marked data quantity is too small.

The existing bill identification methods are mainly divided into two types, one type is detection and identification, automatic training cannot be realized, and hyper-parameters need to be manually set according to the types of bills. The other type directly outputs the identification result in an end-to-end identification mode without detection. However, a separate recognition model needs to be trained according to each content to be recognized, and the whole process is complex.

Disclosure of Invention

The application provides a bill identification method, a bill identification device, an electronic device and a medium, which can automatically train a bill identification model by utilizing an automatic deep learning technology and solve the problems that bill identification depends on manual work and the process is complex.

According to an aspect of the present application, there is provided a bill identifying method, the method including:

determining a target bill from sample bills, and determining a target area of the target bill;

performing model training according to the target bill and the target area, and determining an area detection model;

detecting the sample bill based on the area detection model, and determining a content area in the sample bill;

and intercepting a content area in the sample bill, performing model training according to the content area in the sample bill and the text content in the content area, determining a text recognition model, and recognizing the text in the bill to be recognized based on the text recognition model.

According to another aspect of the present application, there is provided a bill identifying apparatus including:

the target area determining module is used for determining a target bill from the sample bills and determining a target area of the target bill;

the model training module is used for carrying out model training according to the target bill and the target area and determining an area detection model;

the content area determining module is used for detecting the sample bill based on the area detection model and determining a content area in the sample bill;

and the character recognition module is used for intercepting the content area in the sample bill, performing model training according to the content area in the sample bill and the character content in the content area, determining a character recognition model, and recognizing characters in the bill to be recognized based on the character recognition model.

According to another aspect of the present application, there is provided a ticket recognition electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a method of ticket identification as described in any embodiment of the present application.

According to another aspect of the present application, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement a method for ticket identification according to any one of the embodiments of the present application when executed.

According to the technical scheme, the bill recognition model is trained automatically by utilizing an automatic deep learning technology, so that the amount of labeled data is reduced, and the training efficiency and accuracy are improved greatly.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow chart of a method for identifying a bill according to an embodiment of the present application;

FIG. 2 is a schematic diagram illustrating basic steps of a method for identifying a bill according to an embodiment of the present application;

FIG. 3 is a flow chart of a bill identification method according to the second embodiment of the present application;

FIG. 4 is a schematic diagram of the basic steps of a bill identification method according to the second embodiment of the present application;

fig. 5 is a schematic structural diagram of a bill identifying device according to the fourth embodiment of the present application;

fig. 6 is a schematic structural diagram of an electronic device implementing a ticket identification method according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. 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 application.

It should be noted that the terms "first," "second," "target," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a bill identification method according to an embodiment of the present application, where the present embodiment is applicable to a case where a bill generated in a bank flow is identified, and the method may be executed by a bill identification device, where the bill identification device may be implemented in a form of hardware and/or software, and the bill identification device may be configured in an electronic device with data processing capability. As shown in fig. 1, the method includes:

s110, determining a target bill from the sample bills and determining a target area of the target bill.

Wherein, the sample bill can be a bill issued by a bank or paid by the bank, comprising: examples of the bill include a bill of a bank, a draft bill of a bank, and a check issued by a bank, and the type of the sample bill is not limited herein.

Optionally, the number of the target tickets is smaller than the number of the sample tickets.

The user can select a part of the sample bills as the target bills. For example, if the number of the sample tickets is 100, the user may select 10 of the sample tickets as the target tickets, and the application does not limit the number of the sample tickets and the number of the target tickets.

After the target bills are determined, the user can manually mark the target area in each target bill to serve as a label of a training sample of the detection model, and input the marked target bills into electronic equipment for subsequent processing, wherein the electronic equipment can be a mobile phone, a computer and the like, and the application does not limit the target bills.

The target area can be an area needing to be identified in the bill, and particularly can be an area with characters.

And S120, performing model training according to the target bill and the target area, and determining an area detection model.

Specifically, an automatic Deep learning technology can be adopted for model training, the Deep learning (Deep learning, DL) algorithm (structure) for automatic Deep learning is used for replacing manual operation in Deep learning, and neural network structure design and super-parameter optimization in automatic Deep learning can be automatically carried out without depending on manual adjustment of model parameters.

In the actual processing process, a bill which is input into the electronic device and is marked with a target region can be input into a basic Neural network model for training, the Neural network model can be a Convolutional Neural network, and the Convolutional Neural Network (CNN) is a feed-forward Neural network (fed Neural network) which contains Convolutional calculation and has a deep structure, and can also be other Neural Networks.

S130, detecting the sample bill based on the area detection model, and determining a content area in the sample bill.

And inputting the sample bills into the trained area detection model, and determining the content areas in all the sample bills.

S140, intercepting the content area in the sample bill, performing model training according to the content area in the sample bill and the text content in the content area, determining a text recognition model, and recognizing the text in the bill to be recognized based on the text recognition model.

Specifically, the text information of the content to be identified of the bill in the service flow is extracted and used as a label of a training sample of the identification model. And detecting the position of each content to be recognized in the bill by using the trained detection model, and cutting a corresponding area according to a detection result to be used as a training sample of the recognition model.

And training a bill recognition model by using an automatic deep learning technology, wherein the bill recognition model is used for recognizing the text information of each content to be recognized in the bill.

FIG. 2 is a schematic diagram illustrating basic steps of a method for identifying a bill according to an embodiment of the present application; as shown in fig. 2, the steps include:

and S1, starting.

And S2, manually marking the position area of the content to be identified.

And S3, extracting the text information of the content to be identified in the service flow.

Step S3 and step S2 may be performed synchronously.

And S4, training the detection model by using an automatic deep learning technology.

And S5, detecting and cutting various content areas to be recognized in the bill by using the detection model.

The content to be identified may be classified into different categories according to keywords, including but not limited to: a user name field, a money amount field, etc.

And S6, training the recognition model by using automatic deep learning.

The recognition model is used for recognizing characters on the bill.

And S7, ending.

According to the technical scheme of the embodiment of the application, the target bill is determined from the sample bills, and the target area of the target bill is determined; performing model training according to the target bill and the target area, and determining an area detection model; detecting the sample bill based on the area detection model, and determining a content area in the sample bill; and intercepting a content area in the sample bill, performing model training according to the content area in the sample bill and the character content in the content area, determining a character recognition model, and recognizing characters in the bill to be recognized based on the character recognition model. According to the technical scheme, the bill recognition model is trained automatically by utilizing an automatic deep learning technology, so that the amount of labeled data is reduced, and the training efficiency and accuracy are improved greatly.

Example two

Fig. 3 is a flowchart of a bill identifying method according to a second embodiment of the present application, and the present embodiment is optimized based on the second embodiment. As shown in fig. 3, the method of this embodiment specifically includes the following steps:

s210, loading a preset training configuration file to perform model training according to the preset training configuration file to determine an area detection model and a character recognition model;

the preset training configuration file comprises at least one of a basic detection model name, a basic identification model name, a sample bill path, parameters of a basic detection model and parameters of a basic identification model.

The underlying detection model may be stored in a neural network model library with a corresponding name, and the sample ticket path may be a physical path of the sample ticket stored locally. The parameters of the basic detection model and the parameters of the basic identification model can be parameters which need to be input by the basic model, and the input parameters can be the number of layers of the basic network, the size of a convolution kernel, the sliding step length and the like by taking the basic model as a convolution neural network model as an example.

S220, loading the sample bill configuration file to determine the key fields to be identified and/or the number of the key fields according to the sample bill configuration file.

The key fields may be the name of the item filled in on the sample ticket form, for example a transfer check, and include: date of drawing the ticket, the name of the bank of transfer, the recipient, and the account number of the drawer, etc.

S230, loading at least one group of preset hyper-parameters to perform iterative optimization on the region detection model and the character recognition model according to the preset hyper-parameters;

the preset hyper-parameter comprises at least one of a learning rate, a training iteration number and whether a test enhancing technology is used.

Learning rate (Learning rate) is an important hyper-parameter in supervised Learning and deep Learning, which determines whether and when the objective function can converge to a local minimum. Setting an appropriate learning rate enables the objective function to converge to a local minimum value in an appropriate time.

During Test Time Augmentation (TTA), multiple input source pictures are generated and respectively sent to a model, and then all inference results are comprehensively integrated.

The number of training iterations may include: epoch, batch _ size, and iteration.

epoch means that all training data sets were trained once at the time of training.

The batch _ size refers to selecting a group of samples in the training set to update the weights.

The iteration means that 1 batch training image is trained once through a network, once forward propagation and once backward propagation are carried out, and the weight is updated once every iteration.

S240, determining a target bill from the sample bills and determining a target area of the target bill.

And S250, performing model training according to the target bill and the target area, and determining an area detection model.

S260, detecting the sample bill based on the area detection model, and determining a content area in the sample bill.

S270, intercepting a content area in the sample bill, performing model training according to the content area in the sample bill and the text content in the content area, determining a text recognition model, and recognizing the text in the bill to be recognized based on the text recognition model.

S280, converting the region detection model and the character recognition model into an open neural network exchange format.

ONNX (Open Neural Network Exchange), which is a standard for representing deep learning models, can make models transferred between different frameworks and is used for storing trained models.

And S290, storing the area detection model and the character recognition model in the open neural network exchange format.

It should be noted that, in the embodiment of the present application, the execution sequence of S210, S220, S230, and S240 is not limited.

On the basis of the foregoing embodiment, optionally, after storing the area detection model and the character recognition model in the open neural network exchange format, the method further includes:

and determining an inference code according to the storage paths of the region detection model and the character recognition model in the open neural network exchange format, and calling the region detection model and the character recognition model according to the storage paths in the inference code to process the bill to be detected.

The storage paths of the region detection model and the character recognition model may be physical paths stored locally.

Fig. 4 is a schematic diagram of basic steps of a bill identification method according to the second embodiment of the present application.

As shown in fig. 4, the steps include:

n1, start.

And N2, loading a basic training configuration file.

And N3, loading a bill related parameter configuration file.

And N4, presetting a plurality of groups of hyper-parameters.

In actual operation, multiple sets of hyper-parameters can be preset, and the hyper-parameters with the highest accuracy and robustness are selected as the finally selected hyper-parameters through training.

And N5, training a basic detection model.

And N6, training a basic recognition model.

N7, ONNX model conversion.

And N8, compiling the inference code.

And N9, ending.

According to the technical scheme, a preset training configuration file is loaded, a region detection model and a character recognition model are determined through model training according to the preset training configuration file, a sample bill configuration file is loaded, the number of key fields and/or key fields to be recognized is determined according to the sample bill configuration file, at least one group of preset super parameters is loaded, iterative optimization is conducted on the region detection model and the character recognition model according to the preset super parameters, the region detection model and the character recognition model are converted into an open neural network exchange format, the region detection model and the character recognition model of the open neural network exchange format are stored, inference codes are determined according to storage paths of the region detection model and the character recognition model of the open neural network exchange format, the region detection model and the character recognition model are called according to the storage paths in the inference codes, the models and the inference codes which can be deployed on-line are automatically constructed, systematization and automation of a bank bill recognition process are improved, labor cost is saved, errors caused by relying on manual detection recognition are avoided, and bill detection recognition is more accurate.

EXAMPLE III

Fig. 5 is a schematic structural diagram of a bill identifying device provided in the third embodiment of the present application, where the device is capable of executing the bill identifying method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the executing method. As shown in fig. 5, the apparatus includes:

a target area determining module 310, configured to determine a target bill from the sample bills, and determine a target area of the target bill;

the model training module 320 is used for performing model training according to the target bill and the target area to determine an area detection model;

a content area determining module 330, configured to detect the sample ticket based on the area detection model, and determine a content area in the sample ticket;

the character recognition module 340 is configured to intercept the content area in the sample ticket, perform model training according to the content area in the sample ticket and the content of the character in the content area, determine a character recognition model, and recognize the character in the ticket to be recognized based on the character recognition model.

On the basis of the above embodiment, optionally, the number of the target tickets is smaller than the number of the sample tickets.

On the basis of the foregoing embodiment, optionally, the apparatus further includes:

the training configuration file loading module is used for loading a preset training configuration file so as to carry out model training according to the preset training configuration file to determine an area detection model and a character recognition model;

and the bill configuration file loading module is used for loading the sample bill configuration file so as to determine the key fields to be identified and/or the number of the key fields according to the sample bill configuration file.

the device comprises a preset hyper-parameter loading module, a character recognition module and a region detection module, wherein the preset hyper-parameter loading module is used for loading at least one group of preset hyper-parameters so as to carry out iterative optimization on a region detection model and a character recognition model according to the preset hyper-parameters; the preset hyper-parameters comprise at least one of learning rate, training iteration times and whether a test enhancing technology is used or not.

and the model conversion module is used for converting the region detection model and the character recognition model into an open neural network exchange format.

and the model storage module is used for storing the region detection model and the character recognition model in the open neural network exchange format.

and the inference code determining module is used for determining the inference code according to the storage paths of the area detection model and the character recognition model in the open neural network exchange format so as to call the area detection model and the character recognition model according to the storage paths in the inference code to process the bill to be detected.

The bill identification device provided by the embodiment of the application can execute the bill identification method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.

EXAMPLE five

FIG. 6 shows a schematic structural diagram of an electronic device 10 that may be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the ticket recognition method.

In some embodiments, the ticket identification method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the ticket recognition method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the ticket recognition method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of this application, a computer readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of the present application can be achieved, and the present invention is not limited thereto.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of bill identification, the method comprising:

determining a target bill from the sample bills, and determining a target area of the target bill;

2. The method of claim 1 wherein the number of target documents is less than the number of sample documents.

3. The method of claim 1, wherein prior to model training based on the target document and the target area, the method further comprises:

loading a preset training configuration file to perform model training according to the preset training configuration file to determine an area detection model and a character recognition model;

4. The method of claim 1, wherein prior to performing model training based on the target document and the target area, the method further comprises:

and loading the sample bill configuration file to determine the key fields to be identified and/or the number of the key fields according to the sample bill configuration file.

5. The method of claim 1, wherein prior to performing model training based on the target document and the target area, the method further comprises:

loading at least one group of preset hyper-parameters to perform iterative optimization on the region detection model and the character recognition model according to the preset hyper-parameters; the preset hyper-parameter comprises at least one of a learning rate, a training iteration number and whether a test enhancing technology is used.

6. The method of claim 5, wherein after determining the text recognition model, the method further comprises:

converting the region detection model and the character recognition model into an open neural network exchange format;

and storing the area detection model and the character recognition model of the open neural network exchange format.

7. The method of claim 1, wherein after storing the region detection model and the text recognition model in an open neural network switched format, the method further comprises:

8. A bill identifying apparatus, comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of any of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a processor to perform the method of any one of claims 1-7 when executed.