WO2023140580A1

WO2023140580A1 - Program, device and method for providing artificial intelligence-based vehicle as process management service

Info

Publication number: WO2023140580A1
Application number: PCT/KR2023/000739
Authority: WO
Inventors: 한보석; 이신우
Original assignee: 에피카 주식회사
Priority date: 2022-01-20
Filing date: 2023-01-16
Publication date: 2023-07-27
Also published as: KR102520846B1

Abstract

The present disclosure relates to a device for providing an artificial intelligence-based vehicle AS process management service, which can: on the basis of work information, determine a series of processes including at least one process for repair of a vehicle; assign a work bay and a worker for each process in the determined series of processes; calculate, for each determined process, wages, parts costs and predicted time required; and generate information on the present situation of the repair of the vehicle on the basis of a work initiation signal, a work stop signal or a work completion signal received from a terminal of the worker assigned to the vehicle and a stay time of the worker in the work bay.

Description

AI-based vehicle AS process management service provision method, device and program

The present disclosure relates to an AI-based vehicle AS process management service providing device.

Most vehicle after-sales service is carried out through reservations at the maintenance center, vehicle warehousing and shipping management, and general ERP functions for process completion and parts and labor for each process are mainly used.

For customer's convenience, notification of AS completion is being made through wired and wireless communication, but through this, the step-by-step situation of the customer's vehicle process or information that can be estimated about it is not provided.

In this way, there is a problem in that it is difficult to grasp the status of each process and efficiently allocate work bays (maintenance space) and technicians (workers, mechanics) from the standpoint of managing the maintenance center as well as from the customer's standpoint.

Currently, PUSH-based management, which proceeds to the next process according to the completion of work bays and technicians, which are the subject of each process step in the workshop, is in progress, which is a bottleneck between processes as well as hindering work efficiency in the operation of work bays and technicians.

Accordingly, it is necessary to provide a service capable of efficiently operating a workshop as well as customer convenience by solving the above problems, but a technology capable of implementing such a service has not been disclosed at present.

Embodiments disclosed in the present disclosure are aimed at providing an artificial intelligence-based vehicle AS process management service providing method.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

An artificial intelligence-based vehicle AS process management service providing apparatus according to an embodiment of the present disclosure for solving the above problems is a pre-learned artificial intelligence model, a process process for each maintenance item of a vehicle, a work bay in a repair shop, and a storage unit storing information about at least one worker in the repair shop; a receiving unit receiving job information for vehicle maintenance of a client; And based on the work information, determine a process including at least one process for servicing the vehicle, assign a workbay and a worker for each process in the determined process, calculate labor, parts cost, and expected required time for each of the determined processes, generate maintenance status information of the vehicle based on a work start signal, work stop signal, or work completion signal received from a terminal of a worker assigned to the vehicle and a stay time of the worker in the workbay, and generate maintenance status information of the vehicle through the communication unit to the terminal of the client and a processor controlling the current status information to be provided.

In addition, the processor may calculate an expected required time by inputting the determined process into the artificial intelligence model, calculate an expected required time and an estimated cost for vehicle maintenance of the client based on the determined process, a work schedule of a work bay in the repair shop, and a work schedule of the at least one worker, and provide the calculated estimated required time and estimated cost to the terminal of the client.

Also, the processor may allocate a workbay and an operator capable of performing the determined process based on a work schedule of the workbay in the repair shop and a work schedule of the at least one operator.

In addition, the receiving unit receives at least one image and symptom information about the vehicle from the client terminal when non-face-to-face counseling is conducted, and the processor inputs the at least one image and symptom information to the artificial intelligence model to generate the work information.

In addition, the artificial intelligence model determines a defect of the vehicle from at least one of an image and a sound of the at least one video, and the processor, when the determined defect is related to the symptom information, determines the determined defect as a definite defect and generates work information.

In addition, at least one identification device is installed in each workbay in the repair shop, and the processor can determine at least one of availability of each workbay, information on workers working in each workbay, work start time of each worker in the repair shop, work end time, and stay time in the workbay, based on information of a terminal identified through the identification device.

In addition, when a work start signal for the first process in the process is received from the worker's terminal and then a work completion signal is received from the worker's terminal, the processor may calculate a work success rate by inputting at least one image captured to include a work portion of the first process into the artificial intelligence model, and when the calculated work success rate satisfies a preset condition, provide work completion information of the first process to the client's terminal.

In addition, when a work completion signal for the second process in the process process is received, an actual required time for the second process is calculated based on the work start signal, work stop signal, and work completion signal received for the second process, and when calculating the expected required time, process efficiency points for the second process of the repair shop and the operator are calculated based on the calculated expected required time and the calculated actual required time, and the calculated actual required time and the process efficiency score are converted into the artificial intelligence model You can learn by entering.

In addition, a method for providing an artificial intelligence-based vehicle AS process management service according to an embodiment of the present disclosure for solving the above problems is a method performed by an apparatus, comprising the steps of receiving job information for vehicle maintenance of a client; determining a process including at least one process for servicing the vehicle based on the job information; allocating work bays and workers of each process in the determined process; Calculating labor, parts costs, and expected required time for each of the determined processes; Generating maintenance status information of the vehicle based on a work start signal, a work stop signal, or a work completion signal received from a terminal of a worker assigned to the vehicle and a stay time of the worker in the workbay; and providing the generated maintenance status information to a terminal of the client through the communication unit.

In addition to this, a computer program stored in a computer readable recording medium for execution to implement the present disclosure may be further provided.

In addition to this, a computer readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

According to the above-described problem solving means of the present disclosure, an artificial intelligence-based vehicle AS process management service is provided.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a schematic diagram of an AI-based vehicle AS process management service providing system according to an embodiment of the present disclosure.

2 is providing an artificial intelligence-based vehicle AS process management service according to an embodiment of the present disclosure

3 is a block diagram of an AI-based vehicle AS process management service providing apparatus according to an embodiment of the present disclosure.

4 to 6 are flowcharts of a method for providing an AI-based vehicle AS process management service according to an embodiment of the present disclosure.

7 is a diagram illustrating that an artificial intelligence model calculates a process efficiency score.

8 is a diagram illustrating a user interface of a worker terminal.

9 is a diagram illustrating that when a process within a process is completed, an artificial intelligence model analyzes an image of a process part to calculate a work success rate.

10 is a diagram illustrating learning of an artificial intelligence model by configuring a photographed image of a learning target vehicle as a learning dataset.

11 is a diagram illustrating a video analysis (CNN) and post-processing model for predicting a work process.

12 is a diagram illustrating a work process efficiency (text-based) learning model Bi-LSTM.

Like reference numbers designate like elements throughout this disclosure. The present disclosure does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present disclosure belongs is omitted. The term 'unit, module, member, or block' used in the specification may be implemented in software or hardware, and according to embodiments, a plurality of 'units, modules, members, or blocks' may be implemented as a single component, or a single 'unit, module, member, or block' may include a plurality of components.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case of being directly connected but also the case of being indirectly connected, and the indirect connection includes being connected through a wireless communication network.

In addition, when a part "includes" a certain component, it means that it may further include other components without excluding other components unless otherwise stated.

Throughout the specification, when a member is said to be located “on” another member, this includes not only a case where a member is in contact with another member, but also a case where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

Expressions in the singular number include plural expressions unless the context clearly dictates otherwise.

In each step, the identification code is used for convenience of explanation, and the identification code does not describe the order of each step, and each step may be performed in a different order from the specified order unless a specific order is clearly described in context.

Hereinafter, the working principle and embodiments of the present disclosure will be described with reference to the accompanying drawings.

In this specification, the 'vehicle AS process management service providing device according to the present disclosure' includes all various devices capable of providing results to users by performing calculation processing. For example, an apparatus for providing a vehicle AS process management service according to the present disclosure may include a computer, a server device, and a portable terminal, or may be in any one form.

Here, the computer may include, for example, a laptop computer, a desktop computer, a laptop computer, a tablet PC, a slate PC, and the like equipped with a web browser.

The server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

The portable terminal is, for example, a wireless communication device that ensures portability and mobility, and includes Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT)-2000, Code Division Multiple Access (CDMA)-2000, W-Code Division Multiple Access (W-CDMA), and WiBro (Wi-Bro). All types of handheld-based wireless communication devices such as reless Broadband Internet terminals and smart phones, and wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted-devices (HMDs).

Functions related to artificial intelligence according to the present disclosure are operated through a processor and a memory. A processor may consist of one or a plurality of processors. In this case, the one or more processors may be a general-purpose processor such as a CPU, an AP, or a digital signal processor (DSP), a graphics-only processor such as a GPU or a vision processing unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control input data to be processed according to predefined operating rules or artificial intelligence models stored in a memory. Alternatively, when one or more processors are processors dedicated to artificial intelligence, the processors dedicated to artificial intelligence may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

A predefined action rule or an artificial intelligence model is characterized in that it is created through learning. Here, being made through learning means that a basic artificial intelligence model is learned using a plurality of learning data by a learning algorithm, so that a predefined action rule or artificial intelligence model set to perform a desired characteristic (or purpose) is created. Such learning may be performed in the device itself in which artificial intelligence according to the present disclosure is performed, or through a separate server and/or system. Examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the above examples.

An artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and a neural network operation is performed through an operation between an operation result of a previous layer and a plurality of weight values. A plurality of weights possessed by a plurality of neural network layers may be optimized by a learning result of an artificial intelligence model. For example, a plurality of weights may be updated so that a loss value or a cost value obtained from an artificial intelligence model is reduced or minimized during a learning process. The artificial neural network may include a deep neural network (DNN), for example, a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a Restricted Boltzmann Machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q-network, but is not limited to the above examples.

According to an exemplary embodiment of the present disclosure, a processor may implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network in which a machine learns by mimicking a human's biological neuron. The methodology of artificial intelligence includes supervised learning in which the answer (output data) of the problem (output data) is provided by providing both input data and output data as training data according to the learning method, unsupervised learning in which only input data is provided without output data and the answer (output data) to the problem (output data) is not determined, and reward is given in the external environment whenever an action is taken in the current state. It can be classified as reinforcement learning. In addition, the methodology of artificial intelligence may be classified according to the architecture, which is the structure of the learning model. The widely used architecture of deep learning technology is a Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Transformer, and generative adversarial networks (GAN).

The device may include an artificial intelligence model. The artificial intelligence model may be one artificial intelligence model or may be implemented as a plurality of artificial intelligence models. Artificial intelligence models may be composed of neural networks (or artificial neural networks), and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to an overall model having a problem-solving ability by changing synaptic coupling strength through learning of artificial neurons (nodes) formed in a network by synaptic coupling. Neurons in a neural network may contain a combination of weights or biases. A neural network may include one or more layers composed of one or more neurons or nodes. Illustratively, the device may include an input layer, a hidden layer, and an output layer. A neural network constituting the device can infer a result (output) to be predicted from an arbitrary input (input) by changing the weight of a neuron through learning.

The processor may generate a neural network, train or learn the neural network, perform an operation based on received input data, generate an information signal based on the result of the operation, or retrain the neural network. Models of the neural network include a Convolution Neural Network (CNN) such as GoogleNet, AlexNet, and VGG Network, a Region with Convolution Neural Network (R-CNN), a Region Proposal Network (RPN), Various types of models may include, but are not limited to, Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, etc. The processor is one for performing calculations according to the models of the neural network. The above processors may be included, for example, the neural network may include a deep neural network.

Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto Encoder) , DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), It will be appreciated by those skilled in the art that it may include any neural network, which may include, but is not limited to, Liquid State Machine (LSM), Extreme Learning Machine (ELM), Echo State Network (ESN), Deep Residual Network (DRN), Differentiable Neural Computer (DNC), Neural Turning Machine (NTM), Capsule Network (CN), Kohonen Network (KN), and Attention Network (AN).

According to an exemplary embodiment of the present disclosure, the processor may include a Convolution Neural Network (CNN), a Region with Convolution Neural Network (R-CNN), a Region Proposal Network (RPN), a Recurrent Neural Network (RNN), a Stacking-based deep Neural Network (S-DNN), a State-Space Dynamic Neural Network (S-SDNN), a Deconvolution Network, a Deep Belief Network (DBN), a Restructcted Boltzman Machine), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT for natural language processing, SP-BERT, MRC/QA, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet Anomaly Detection for data intelligence, Predi Various AI structures and algorithms can be used, such as action, time-series forecasting, optimization, recommendation, and data creation, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

1 is a schematic diagram of an AI-based vehicle AS process management service providing system 10 according to an embodiment of the present disclosure.

An AI-based vehicle AS process management service providing system 10 according to an embodiment of the present disclosure includes a vehicle AS process management service providing device 100 , a worker terminal 200 and a client terminal 300 .

The AI-based vehicle AS process management service providing system 10 according to an embodiment of the present disclosure may mean a Digital Workshop system (DWS).

In an embodiment of the present disclosure, the system 10 may further include an Annotation Component Server, and the apparatus 100 periodically transmits process work management and vehicle images collected or collected in real time to the annotation component server. After detecting and diagnosing an abnormal part through image processing, the process work information (time, labor, parts, work history) according to the WIP (RO) of the vehicle can be mapped and set as metadata.

The identification device 50 may communicate with the device 100 and the operator's terminal 200, and at least one may be installed in a repair shop (workshop) where the AS process of the vehicle is performed.

The identification device 50 plays a role as an identification means by identifying a terminal possessed by a worker performing process work in the workbay and calculating the worker's stay time in the workbay, and the number of installations and installation location can be determined according to the situation of the repair shop.

In one embodiment, one or more identification devices 50 may be installed in each workbay to improve identification accuracy, but is not limited thereto.

In addition, the identification device 50 may receive a work start signal, a work stop signal, or a work completion signal from the operator's terminal 200 and transmit it to the device 100, and the identification device 50 may not necessarily perform the function.

In one embodiment, when a job start signal, a job stop signal, or a job completion signal is input through a service application installed in the operator terminal 200, the input signal may be provided to the device 100 through the communication unit 120.

In an embodiment of the present disclosure, the vehicle AS process management service providing device 100 is configured to include the server device 100 and may be implemented in the form of a server.

In an embodiment of the present disclosure, the vehicle AS process management service providing apparatus 100 may further include an annotation component server. In addition, the annotation component server may configure a learning model based on received data (image, metadata) and learn the model in an online batch method.

In an embodiment of the present disclosure, the vehicle AS process management service providing apparatus 100 can provide various information to the client by checking the status of the process step, process status, etc. of the client's vehicle through the above-described configuration, and can efficiently schedule work by recognizing the schedule of the work bay and the worker in real time.

Hereinafter, the vehicle AS process management service providing system 10, apparatus 100, and method according to an embodiment of the present disclosure will be described in more detail with reference to other drawings.

2 is a block diagram of an AI-based vehicle AS process management service providing apparatus 100 according to an embodiment of the present disclosure.

3 is a block diagram of an AI-based vehicle AS process management service providing apparatus 100 according to an embodiment of the present disclosure.

Referring to FIG. 2 , an artificial intelligence-based vehicle AS process management service providing apparatus 100 according to an embodiment of the present disclosure includes an identification device 50, a processor 110, a communication unit 120, a storage unit 130, a management unit 140, a calculating unit 150, and a learning unit 160.

However, in some embodiments, the system 10 and device 100 may include fewer or more components than those shown in FIGS. 1 to 3 .

The identification device 50 communicates with the worker terminal 200 and the communication unit 120 .

The identification device 50 includes a communication means, and in one embodiment, the identification device 50 may include a short-range communication means for communicating with the operator terminal 200 and a long-distance communication means for communicating with the device 100.

In one embodiment, the identification device 50 may communicate with the worker terminal 200 using a communication means such as Bluetooth or Wi-Fi.

Since the communication means included in the identification device 50 and the communication method are general contents, a detailed description thereof will be omitted.

In one embodiment, the identification device 50 may include at least one camera or at least one LIDAR, and may identify a worker in the workbay based on a sensing result sensed through the camera or LIDAR.

A camera processes an image frame such as a still image or a moving image obtained by an image sensor in a photographing mode. The processed image frame may be displayed on a display unit or stored in a memory.

The communication unit 120 may include one or more modules that connect the vehicle AS process management service providing apparatus 100 to one or more networks.

The processor 110 may be implemented with at least one processor 110 that performs the above-described operations using a memory for storing an algorithm for controlling the operation of components in the device 100 or data for a program that reproduces the algorithm, and data stored in the memory. In this case, the memory and the processor 110 may be implemented as separate chips. Alternatively, the memory and the processor 110 may be implemented as a single chip.

In addition, the processor 110 may control any one or a combination of a plurality of components described above in order to implement various embodiments according to the present disclosure described in the following drawings on the device 100.

The processor 110 may control general operations of the device 100 in addition to operations related to the application program. The processor 110 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the components described above or by driving an application program stored in a memory.

In addition, the processor 110 may control at least some of the components of the device 100 in order to drive an application program stored in memory. Furthermore, the processor 110 may combine and operate at least two or more of the components included in the device 100 to drive the application program.

The communication unit 120 may include one or more components that enable communication with the external device 100, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-distance communication module, and a location information module.

The wired communication module may include not only various wired communication modules such as a local area network (LAN) module, a wide area network (WAN) module, or a value added network (VAN) module, but also various cable communication modules such as universal serial bus (USB), high definition multimedia interface (HDMI), digital visual interface (DVI), recommended standard 232 (RS-232), power line communication, or plain old telephone service (POTS).

In addition to a WiFi module and a wireless broadband module, the wireless communication module may include a wireless communication module supporting various wireless communication schemes such as global system for mobile communication (GSM), code division multiple access (CDMA), wideband code division multiple access (WCDMA), universal mobile telecommunications system (UMTS), time division multiple access (TDMA), long term evolution (LTE), 4G, 5G, and 6G.

The wireless communication module may include a wireless communication interface including an antenna and a transmitter for transmitting signals. In addition, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor 110 through a wireless communication interface into an analog type wireless signal under the control of the processor 110 .

The short -range communication module is for short range communication, Bluetooth (RFID), Radio Frequency Identification (RFID), Infrared Data Association (IRDA), UWB (UWB) A Wideband), Zigbee, NEAR FIELD Communication (NFC), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, Wireless USB (Wireless Universal Serial Bus) techniques to close communication using at least one. You can apply.

The storage unit 130 may store information about a pre-learned artificial intelligence model, a process for each maintenance item of a vehicle, a workbay in a repair shop, and at least one operator in the repair shop in order to execute a vehicle AS process management service providing method.

In addition, the storage unit 130 may store various information generated by the operation of the processor 110 and various information calculated by the operation of the calculation unit 150 .

The storage unit 130 may store data supporting various functions of the device 100 . The storage unit 130 may store a plurality of application programs (application programs or applications) running in the device 100, data for operation of the device 100, and commands. At least some of these application programs may exist for basic functions of the device 100 . Meanwhile, the application program may be stored in memory, installed in the device 100, and driven by the processor 110 to perform an operation (or function).

The storage unit 130 may store data supporting various functions of the device 100 and programs for operating the processor 110, input/output data (e.g., music files, still images, videos, etc.) may be stored, and may store a plurality of application programs (applications) running in the device 100, data for operating the device 100, and commands. At least some of these application programs may be downloaded from an external server through wireless communication.

The storage unit 130 is a flash memory type, a hard disk type, a solid state disk type (SSD type), a silicon disk drive type (SDD type), a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), and electrically erasable programm (EEPROM). Able read-only memory), programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. In addition, the storage unit 130 is separated from the apparatus 100, but may be a database connected by wire or wirelessly.

In one embodiment, cloud storage may be applied to at least a portion of the storage space of the storage unit 130 .

In addition, the storage unit 130 may include a plurality of processes for the vehicle AS process management service providing apparatus 100 and method.

3 is an example of matters managed by the management unit 140, and individual modules may be configured for each management matter. In addition, information and data stored in the storage unit 130 are exemplified, and these information and data can also be configured as individual storage spaces and stored and managed separately.

The calculation unit 150 may perform a calculation operation according to a control signal of the processor 110 .

As an embodiment, the calculation unit 150 may calculate labor for each process, parts cost, and expected required time for each process.

The learning unit 160 may learn the artificial intelligence model, and learn and re-learn the artificial intelligence model by generating various data, information, etc. generated by the operation of the vehicle AS process management service providing device 100 as a learning dataset.

Below, the operation of the apparatus 100 will be described in more detail with reference to a flowchart and various exemplary drawings of a method for providing an AI-based vehicle AS process management service according to an embodiment of the present disclosure.

The artificial intelligence-based vehicle AS process management service providing method according to an embodiment of the present disclosure may be performed in the same process as shown in FIG. 4, and FIG. 5 illustrates that the process proceeds by a client making an AS reservation and consultation with a service advisor, and FIG.

5 and 6 have some differences in whether or not the artificial intelligence model is used, so the drawings are referred to with reference to this.

The processor 110 generates job information based on the image and symptom information of the client's vehicle. (S100)

The processor 110 receives job information for vehicle maintenance. (S200)

As shown in FIG. 5 , when a consultation between a client and a service advisor is in progress, the service advisor may photograph the client's vehicle and create inspection items for the vehicle.

The processor 110 may generate task information based on the received image of the vehicle and at least one input inspection item.

In the case of non-face-to-face counseling as shown in FIG. 6 , the device 100 may receive at least one captured image of the vehicle and symptom information from the client terminal 300 .

At this time, the symptom information can be directly input by the client through the service application of the terminal, and the processor 110 provides at least one inspection item so that the client does not have difficulty in inputting the symptom information, so that the client can self-inspect the vehicle and input the symptom information.

At this time, when the information on the symptoms of the vehicle is received from the client terminal 300, the processor 110 derives at least one inspection item based on this, and provides the derived at least one inspection item to the client terminal 300 to request inspection of the vehicle.

As an embodiment, the processor 110 may also provide a guide on how to photograph a vehicle when providing a guide on inspection items to the terminal 300 of a client.

In one embodiment, the processor 110 may request recording of sound or recording of an image including sound according to symptoms of the vehicle.

The artificial intelligence model may determine a defect of the vehicle from at least one of an image and a sound of at least one captured image, and the processor 110 may generate work information by determining the determined defect as a definitive defect when the defect determined through the artificial intelligence model is related to symptom information.

As an embodiment, if there is a defect unrelated to the symptom information among the determined defects, the processor 110 may provide the client terminal 300 with information that a face-to-face inspection is required for accurate calculation of the estimated required time and estimated cost.

As an embodiment, if there is a defect unrelated to the symptom information among the determined defects, the processor 110 may provide accurate guidance of the estimated required time and estimated cost after the vehicle is put in and a face-to-face inspection is performed. Information can be provided.

At this time, the processor 110 may calculate the degree of relevance in order to determine whether or not there is relevance, and if the pre-set relevance is satisfied, it is determined to be related, and if the pre-set relevance is not satisfied, it is determined to be unrelated.

In addition, when the client inspects the inspection item and inputs the inspection result, the processor 110 may generate at least one symptom information about the vehicle by inputting the inspection result to the artificial intelligence model. That is, in the embodiment of the present disclosure, the symptom information may be directly input by the client, or after providing the client terminal 300 with a guide for self-inspection of the vehicle as described above, the artificial intelligence model may generate symptom information based on the inspection result received from the client terminal 300.

Thereafter, the processor 110 may generate work information for a vehicle AS process by inputting the vehicle photographed image and symptom information received from the client terminal 300 into an artificial intelligence model.

At this time, the work information is somewhat different from the detailed process determined in S300, and means information on necessary tasks such as what part is abnormal in the vehicle to be repaired (client's vehicle) and what parts need to be replaced or repaired.

The processor 110 determines a process for AS of the vehicle based on the job information. (S300)

The processor 110 allocates work bays and workers for each process. (S400)

The processor 110 calculates labor, parts cost, and expected required time for each process. (S500)

The processor 110 determines a process including at least one process for vehicle maintenance by inputting job information to the artificial intelligence model.

The processor 110 may schedule the workbay and the worker's schedule based on the data collected through the identification device 50, the workbay, and the worker's schedule for a certain time in the future.

In addition, the identification device 50 may monitor the operating state of the workbay, and based on this, it is possible to determine whether each workbay is operating or available.

In one embodiment, the processor 110 confirms that the workbay is operating through the identification device 50, but when a work stop signal is input to the terminal 200 of a worker working in the workbay, the worker terminal 200 can be requested to resume work.

In one embodiment, the processor 110 based on the workbay operating time collected through the identification device 50 and the work start signal, work stop signal, work resume signal, and work completion time received from the worker terminal 200, It is possible to determine whether the workbay operating time and the required work time of the worker match.

The processor 110 checks a workbay required for each process and a schedule of a worker capable of performing each process, and allocates a workbay and a worker for each process included in the process based on the checked result.

In one embodiment, the processor 110 may assign a worker for each process based on the process efficiency score for each process of the worker. Since each worker may have a difference in skill level and processing speed for each process, the processor 110 may allocate the process to the worker in consideration of this.

However, processes are not necessarily allocated based on proficiency and processing speed for each process, and can be allocated according to the urgency of the AS process of the vehicle. In this case, the vehicle's AS process urgency means the vehicle's AS process urgency, and the urgency may be determined according to the vehicle's condition or the client's request.

The processor 110 calculates an expected required time for the process by inputting the determined process to the artificial intelligence model, and calculates an expected required time and estimated cost for servicing the client's vehicle based on the determined process, the work schedule of the work bay in the repair shop, and the work schedule of the at least one worker.

The processor 110 may provide the calculated estimated required time and estimated cost to the client terminal 300 .

In one embodiment, the processor 110 may calculate and store the process efficiency score and the required time range of each worker in the storage unit 130 based on the details of each worker's work time for each process.

In the case of a process performed by a person, since the work speed and required time may vary each time, the processor 110 may calculate a range of expected task required time in addition to calculating the expected task required time as described above.

Then, the processor 110 calculates the expected required time based on the required work time range for each process of each worker assigned to each process and provides it to the client terminal 300, but applies the expected required time range to provide information.

For example, the vehicle may provide the client terminal 300 with a range of expected required time in which process A and B are performed, and the range of expected required time for process A of worker A and the range of expected required time for process B of worker B are added together.

Based on the estimated required time, the processor 110 can reassign work bays and workers when a new vehicle to be serviced (the second vehicle) is received, as long as the estimated time required for the vehicle to be repaired (the first vehicle) that has been previously stored is not exceeded.

As an embodiment, in a situation in which a workbay for the first vehicle and a worker are already assigned, when a situation arises in which workbays and workers are required to be input to the first vehicle for process efficiency of a newly stocked second vehicle, the processor 110 may change at least a part of the workbay and worker assignment of the first vehicle to assign the workbay and the worker of the second vehicle to the extent that the estimated time required for the first vehicle is not exceeded.

The processor 110 generates vehicle maintenance status information according to the start of vehicle maintenance work. (S600)

The processor 110 provides maintenance status information to the client. (S700)

The processor 110 may generate vehicle maintenance status information based on a work start signal, a work stop signal, or a work completion signal received from the terminal 200 of a worker assigned to the vehicle and the worker's stay time in the workbay.

The processor 110 may provide vehicle maintenance status information to the client terminal 300 at predetermined time intervals.

When vehicle maintenance status information is requested from the client terminal 300 , the processor 110 may provide the vehicle maintenance status information generated with respect to a corresponding point in time to the client terminal 300 .

The processor 110 may generate vehicle maintenance status information and provide it to the client terminal 300 whenever one process for the vehicle is completed.

Referring to FIG. 7 , the processor 110 may calculate an actual required time for each process based on a workbay operation time and a worker's working time, and may calculate a process efficiency score based on the calculated actual required time and the estimated required time calculated in S500.

The processor 110 may input the calculated process efficiency score into an artificial intelligence model to learn the work efficiency score for each process of the workbay and each worker.

In one embodiment, the artificial intelligence model may calculate the expected range of requirements for each process of each worker described above based on these learning results.

As an embodiment, the processor 110 calculates a process efficiency score trend for the workbay and each worker, and when the trend of the process efficiency score calculated for a specific workbay or a specific worker for a predetermined time period falls below a reference value, a signal requesting an inspection of the corresponding workbay or the corresponding worker may be generated.

8 is a diagram illustrating a user interface of the worker terminal 200 .

Referring to FIG. 8 , a user interface provided by the apparatus 100 to the operator's terminal 200 is exemplified, and the operator can check the type of vehicle and work assigned to him/her, and through this user interface, the start of the process for the vehicle, work stop, work completion, etc. can be input.

Referring to FIG. 9 , the processor 110 receives a work start signal for the first process in the process from the worker's terminal 200 and then receives a work completion signal from the worker's terminal 200. The artificial intelligence model may input and analyze at least one image captured to include the work part of the first process to calculate a work success rate.

When the calculated job success rate satisfies a preset condition, the processor 110 may provide job completion information of the first process to the terminal 300 of the client.

In one embodiment, the processor 110 may provide a first process reconfirmation request signal to the operator's terminal 200 when the calculated job success rate does not satisfy a preset condition.

As an embodiment, when the calculated job success rate does not satisfy a preset condition, the processor 110 derives a job shortage area or a job failure area through an artificial intelligence model, and provides the derived information to the operator's terminal 200. And, when it is received from the operator's terminal 200 that the artificial intelligence model has an error in judgment, the artificial intelligence model can learn about the error by controlling the learning unit 160 .

As an embodiment, when a task shortage area or a task failure area is derived through an artificial intelligence model, and when it is confirmed from the worker terminal 200 that the task is insufficient or the task has failed, the processor 110 calculates an additional task required time for the task insufficient area or task failed area, adds the calculated task required time to the expected required time, and provides information that the expected required time may be delayed to the client terminal 300.

Referring to FIG. 10 , the device 100 receives at least one image of a learning target vehicle.

The processor 110 may analyze the received image to recognize images of vehicle parts included in the learning target vehicle, locations of the vehicle components in the vehicle, and connection relationships among a plurality of vehicle components.

The processor 110 may generate a learning data set by inputting the recognized result together with the vehicle type and basic vehicle specifications to the artificial intelligence model.

In this case, the processor 110 may receive a plurality of images received from different angles for more detailed and accurate analysis.

In addition, when the processor 110 receives an image of the exterior of the vehicle as well as individual images of all detachable parts such as the bonnet, headlight, rearview mirror, wheel, body, trunk, etc., the processor 110 separates or combines them and stores them in the storage unit 130.

The processor 110 builds big data using the information stored in the storage unit 130, and inputs it as learning data to learn an artificial intelligence model, so that when an image of an accident vehicle or a vehicle in which a breakdown has occurred is received, it is possible to determine the required AS only by analyzing the image.

Referring to FIG. 11, it is exemplified that an artificial intelligence model performs image analysis and post-processing for prediction of a work process.

The artificial intelligence model can detect the characteristics of the work process (accidents, repair parts) by analyzing the captured images, and can classify the work process.

In addition, the artificial intelligence model can measure work state efficiency in the post-processing stage, and by performing state estimation for each process, it is possible to calculate cost (time, labor, etc.) for each process according to the process prediction.

In addition, the artificial intelligence model can calculate the shortest distance for each process using the Dijkstra Algorithm.

Process A can proceed in the order of Process 1, Process 2, Process 3, Process 1 can be assigned to Technician A, Workbay A, 5h/5FRU, Process 2 can be assigned to Technician B, Workbay B, 5h/4FRU, and Process 3 can be assigned to Technician C, Workbay C, 3h/2FRY.

Process B can proceed in the order of process 1, process 2, process 1, and process 3. Process 1 can be assigned to technician A, workbay A, 3h/3FRU, next process 2 can be assigned to technician B, workbay B, 5h/4FRU, next process 1 can be assigned to technician A, workbay A, 3h/2FRY, and next process 3 can be assigned to technician C, workbay C, 3h/2FRY.

Process C can proceed in the order of process 3, process 1, process 2, process 3 can be assigned to technician C, workbay C, 1h/2FRU, next process 1 to technician A, workbay A, 2h/5FRU, and next process 2 to technician B, workbay A, 1h/1FRY.

In the case of the existing LSTM, there is an information loss problem as the length of the sequence increases, which is the biggest disadvantage of the RNN model.

In an embodiment of the present disclosure, the artificial intelligence model learns process efficiency through Bi-LSTM to solve this disadvantage.

The input parameters of LSTM are {X0, X1, X2 ~ Xn01}, but the input parameters of Bi-LSTM are {X0, X1, X2 ~ Xn-1} and {Xn-1... X2, X1, X0}.

Through this configuration, the artificial intelligence model can complement/consider variables that can result in high process efficiency (value) in the lower priority of work.

The method according to an embodiment of the present disclosure described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The above-described program may include a code coded in a computer language such as C, C++, JAVA, or machine language that can be read by a processor (CPU) of the computer through a device interface of the computer so that the computer reads the program and executes the methods implemented as a program. These codes may include functional codes related to functions defining necessary functions for executing the methods, and control codes related to execution procedures necessary for the processor of the computer to execute the functions according to a predetermined procedure. In addition, these codes may further include memory reference related code indicating where additional information or media necessary for the processor of the computer to execute the functions should be referenced from which location (address address) of the computer's internal or external memory. In addition, when the processor of the computer needs to communicate with any other remote computer or server in order to execute the functions, the code may further include communication-related codes for how to communicate with any other remote computer or server using a communication module of the computer, and what information or media should be transmitted and received during communication.

The storage medium is not a medium that stores data for a short moment, such as a register, cache, or memory, but a medium that stores data semi-permanently and is readable by a device. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers accessible by the computer or various recording media on the user's computer. In addition, the medium may be distributed to computer systems connected through a network, and computer readable codes may be stored in a distributed manner.

Steps of a method or algorithm described in connection with an embodiment of the present disclosure may be implemented directly in hardware, implemented in a software module executed by hardware, or a combination thereof. A software module may reside in random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art.

Although the embodiments of the present disclosure have been described with reference to the accompanying drawings, those skilled in the art to which the present disclosure pertains may understand that the present disclosure may be implemented in other specific forms without changing the technical spirit or essential features. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

[Description of code]

10: AI-based vehicle AS process management service provision system

50: identification device 100: vehicle AS process management service providing device

110: processor 120: communication unit

130: storage unit 140: management unit

150: calculation unit 160: learning unit

200: worker terminal 300: client terminal

Claims

a storage unit storing information about a pre-learned artificial intelligence model, a process for each maintenance item of a vehicle, a workbay in a garage, and at least one operator in the garage;

a receiving unit receiving job information for vehicle maintenance of a client; and

Based on the operation information, determining a process including at least one process for servicing the vehicle;

Allocate work bays and workers for each process in the determined process,

Calculate the labor, parts cost, and expected time required for each process determined above,

Generating maintenance status information of the vehicle based on a work start signal, a work stop signal, or a work completion signal received from a terminal of a worker assigned to the vehicle and a stay time of the worker in the workbay;

Including a processor for controlling the generated maintenance status information to be provided to the terminal of the client through a communication unit,

Vehicle AS process management service provision device.
According to claim 1,

the processor,

Calculate the expected required time by inputting the determined process into the artificial intelligence model,

Based on the determined process, the work schedule of the work bay in the repair shop, and the work schedule of the at least one operator, an estimated required time and estimated cost for servicing the vehicle of the client are calculated,

Characterized in that the calculated estimated required time and estimated cost are provided to the terminal of the client,

Vehicle AS process management service provision device.
According to claim 2,

the processor,

Characterized in that, based on the work schedule of the work bay in the maintenance shop and the work schedule of the at least one operator, a work bay and an operator capable of performing the determined process are assigned.

Vehicle AS process management service provision device.
According to claim 2,

The receiving unit receives at least one image and symptom information about the vehicle from the client terminal when non-face-to-face counseling is conducted,

Characterized in that the processor generates the task information by inputting the at least one image and the symptom information to the artificial intelligence model,

Vehicle AS process management service provision device.
According to claim 4,

The artificial intelligence model,

Determining a defect of the vehicle from at least one of an image and a sound of the at least one image;

the processor,

When the determined defect is related to the symptom information, determining the determined defect as a definite defect and generating work information.

Vehicle AS process management service provision device.
According to claim 2,

At least one identification device is installed in each workbay in the workshop,

the processor,

Based on the information of the terminal identified through the identification device,

At least one of the availability of each workbay, information of workers working in each workbay, work start time and work end time of each worker in the repair shop, and a stay time in the workbay Characterized in that,

Vehicle AS process management service provision device.
According to claim 6,

the processor,

When the work completion signal is received from the worker's terminal after the work start signal for the first process in the process is received from the worker's terminal,

Calculating a work success rate by inputting at least one image captured to include a working part of the first process into the artificial intelligence model;

Characterized in that, when the calculated job success rate satisfies a preset condition, job completion information of the first process is provided to the terminal of the client.

Vehicle AS process management service provision device.
According to claim 6,

When a work completion signal for the second process in the process process is received, based on the work start signal, work stop signal, and work completion signal received for the second process, an actual required time for the second process is calculated,

When calculating the estimated required time, based on the estimated required time calculated for the second process and the calculated actual required time, process efficiency scores for the second process of the workshop and the operator are calculated;

Characterized in that the calculated actual required time and the process efficiency score are input to the artificial intelligence model for learning.

Vehicle AS process management service provision device.
In a method performed by the device,

Receiving work information for vehicle maintenance of a client;

determining a process including at least one process for servicing the vehicle based on the job information;

allocating work bays and workers of each process in the determined process;

Calculating labor, parts costs, and expected required time for each of the determined processes;

Generating maintenance status information of the vehicle based on a work start signal, a work stop signal, or a work completion signal received from a terminal of a worker assigned to the vehicle and a stay time of the worker in the workbay; and

Providing the generated maintenance status information to the terminal of the client,

The apparatus includes a pre-learned artificial intelligence model, a process process for each maintenance item of a vehicle, a workbay in a workshop, and a storage unit in which information about at least one operator in the workshop is stored.

How to provide vehicle after-sales service process management services.
According to claim 9,

The device,

Calculate the expected required time by inputting the determined process into the artificial intelligence model,

Based on the determined process, the work schedule of the work bay in the repair shop, and the work schedule of the at least one operator, an estimated required time and estimated cost for servicing the vehicle of the client are calculated,

Characterized in that the calculated estimated required time and estimated cost are provided to the terminal of the client,

How to provide vehicle after-sales service process management services.
According to claim 10,

The device,

Characterized in that, based on the work schedule of the work bay in the maintenance shop and the work schedule of the at least one operator, a work bay and an operator capable of performing the determined process are assigned.

How to provide vehicle after-sales service process management services.
According to claim 10,

The device,

Receiving at least one image and symptom information about the vehicle from the client terminal when non-face-to-face counseling is conducted;

Characterized in that the work information is generated by inputting the at least one image and the symptom information to the artificial intelligence model.

How to provide vehicle after-sales service process management services.
According to claim 12,

The artificial intelligence model,

Determining a defect of the vehicle from at least one of an image and a sound of the at least one image;

The device,

When the determined defect is related to the symptom information, determining the determined defect as a definite defect and generating work information.

How to provide vehicle after-sales service process management services.
According to claim 10,

At least one identification device is installed in each workbay in the workshop,

The device,

Based on the information of the terminal identified through the identification device, at least one of the availability of each workbay, information of workers working in each workbay, work start time of each worker in the workshop, work end time and stay time in the workbay is determined.

How to provide vehicle after-sales service process management services.
A computer-readable recording medium in which a program for executing the method of claim 9 is stored in combination with a computer, which is hardware.