WO2021189896A1 - 车辆配件的分组方法、装置、电子设备及存储介质 - Google Patents
车辆配件的分组方法、装置、电子设备及存储介质 Download PDFInfo
- Publication number
- WO2021189896A1 WO2021189896A1 PCT/CN2020/131919 CN2020131919W WO2021189896A1 WO 2021189896 A1 WO2021189896 A1 WO 2021189896A1 CN 2020131919 W CN2020131919 W CN 2020131919W WO 2021189896 A1 WO2021189896 A1 WO 2021189896A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- coordinate
- accessory
- cluster center
- vehicle
- grouping
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Definitions
- This application relates to the field of image detection, and in particular to a method, device, electronic equipment, and computer-readable storage medium for grouping vehicle accessories.
- the inventor realizes that there are currently two methods for grouping vehicle parts based on text information and image information.
- the text information grouping method such as the user inputting the name of the vehicle part, calculates the name of the vehicle part and the original through the machine learning method.
- grouping errors are extremely prone to occur;
- the grouping of picture information due to the huge amount of picture information data, directly uses deep learning or machine learning methods to identify and group, it will take up a lot of computing resources, resulting in slow grouping speed and serious consumption of computer memory.
- a method for grouping vehicle accessories provided in this application includes:
- the present application also provides a device for grouping vehicle accessories, and the device includes:
- the vector conversion module is used to obtain a collection of vehicle accessory pictures and grouping criteria, divide the collection of accessory pictures according to the vehicle structure to obtain multiple accessory picture subsets, and transform the accessory picture subsets into vector to obtain the accessory vector set;
- the coordinate mapping module is used to map the accessory vector set to a pre-built coordinate system to obtain a vehicle accessory coordinate set
- An error calculation module configured to perform an initialization operation in the coordinate system according to the grouping standard to obtain a cluster center coordinate set, and sequentially calculate the error value between the cluster center coordinate set and the vehicle accessory coordinate set;
- the accessory grouping module is used to update the cluster center coordinate set using the error value, and calculate the updated error value, and until the error value meets the preset error requirement, use the vehicle accessory coordinate set to obtain the The grouping of vehicle accessories corresponding to the grouping standard.
- the present application also provides an electronic device, which includes: at least one processor; and,
- a memory communicatively connected with the at least one processor; wherein,
- the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the following method for grouping vehicle accessories:
- the present application also provides a computer-readable storage medium, including a storage data area and a storage program area, wherein the storage data area stores the created data, and the storage program area stores a computer program; wherein the computer program is
- the processor implements the grouping method of vehicle accessories as described below when executing:
- FIG. 1 is a schematic flowchart of a method for grouping vehicle accessories according to an embodiment of the application
- FIG. 2 is a detailed flowchart of S2 in the method for grouping vehicle accessories according to an embodiment of the application;
- FIG. 3 is a detailed flowchart of S4 in the method for grouping vehicle accessories according to an embodiment of the application;
- FIG. 5 is a schematic diagram of modules of a device for grouping vehicle accessories according to an embodiment of the application.
- FIG. 6 is a schematic diagram of the internal structure of an electronic device that implements a method for grouping vehicle accessories according to an embodiment of the application;
- the execution subject of the method for grouping vehicle accessories provided in the embodiments of the present application includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided in the embodiments of the present application, such as a server and a terminal.
- the grouping method of the vehicle accessories may be executed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform.
- the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.
- This application provides a method for grouping vehicle accessories.
- FIG. 1 it is a schematic flowchart of a method for grouping vehicle accessories according to an embodiment of this application.
- the method for grouping the vehicle accessories includes:
- the collection of photos of the accessories includes engine, throttle body, cylinder block, tensioner, drive train accessories, clutch, transmission, reducer, magnetic material, brake master cylinder, brake component Pictures of pumps, brake assemblies, brake pedal assemblies, compressors, brake discs, brake drums and other accessories. Due to the complexity of vehicle accessories and the endless emergence of vehicle accessories, it is necessary to efficiently group a large number of license plate accessories pictures according to the grouping criteria set by the user.
- the grouping standard includes the price of vehicle parts, the purchase channels of vehicle parts, etc.
- the collection of parts pictures includes engine, throttle body, cylinder block, tensioner, drive train parts, etc., where the grouping standard can be according to The repair price when the parts are damaged is divided into expensive parts, more expensive parts, ordinary parts and low-cost parts.
- the vehicle structure includes the external structure and internal structure of the vehicle.
- different vehicle accessories have specific vehicle application scenarios.
- C can only be applied to sports cars, and sedans, hatchbacks, and sports cars are the external structure of the vehicle.
- the internal structure of the vehicle includes the number of nuclear passengers, tire size, engine displacement, etc.
- accessory D can only be applied to vehicles with an engine displacement less than 1.0L
- accessory E can only be applied to an engine displacement of 1.6.
- Vehicles from L to 2.5L and accessory F can be applied to vehicles with an engine displacement above 4.0L.
- the collection of accessory pictures can be divided into a variety of accessory picture subsets.
- the S2 includes:
- the following convolution calculation formula is used to extract the accessory texture feature set in the accessory image subset:
- O y, u, v (x 1 , x 2 ) is the accessory texture feature set
- M(x 1 , x 2 ) is the pixel value coordinate of the accessory picture in the accessory picture subset
- ⁇ y, u, v (z) are the convolution function
- z is the convolution operator
- y, u, v represent the three components of the picture
- y is the brightness of the picture
- u, v are the chromaticity of the picture.
- the dimensionality reduction operation includes using a sliding window with a fixed matrix dimension from left to right and top to bottom to sequentially sample the average value of specific steps on the accessory texture features in the accessory texture feature set,
- a sliding window with a matrix dimension of 2*2 and a specific step length of 3 can reduce the feature dimension of the accessory texture feature set to 1/4 of the original dimension, and sequentially combine the reduced features to obtain the accessory Vector set.
- the accessory coordinates of the vehicle accessory coordinate set can be represented by (x, y).
- the vehicle The accessory coordinates of the accessory coordinate set can be represented by (x, y, z).
- the vector about the throttle body in the accessory vector set is First, according to the form that each row in the vector represents a coordinate dimension, the corresponding value of (12...19) calculated by mathematical formula is 13, and (67...4) calculated by mathematical formula is 8, thus the throttle
- the vehicle accessory coordinates corresponding to the vector of the body are (13, 8)
- the accessory picture collection has been transformed into the vehicle accessory coordinate set through structural division, vector transformation and mapping, so the grouping of the vehicle accessory coordinate set is the grouping of the accessory picture collection.
- the performing an initialization operation in the coordinate system according to the grouping standard to obtain a cluster center coordinate set includes:
- S401 According to the grouping number in the grouping standard, randomly initialize in the coordinate system to obtain the same number of cluster center coordinates as the grouping number, and obtain the cluster center coordinate set.
- the parts are divided into four groups: expensive parts, more expensive parts, ordinary parts, and low-cost parts.
- the preset coordinate system is a three-dimensional coordinate system, in the three-dimensional coordinate system, you can Corresponding to random initialization, the four cluster center coordinates are (9,2,3), (0,1,7), (12,3,1), (72,12,34).
- the distance relationship between the cluster center coordinate set and the vehicle accessory coordinate set can be calculated, and the purpose of grouping the vehicle accessory coordinate set can be achieved through the distance relationship.
- the sequentially calculating the error values between the cluster center coordinate set and the vehicle accessory coordinate set includes:
- S402 Divide the vehicle accessory coordinate set according to the cluster center coordinate set, and obtain a vehicle accessory coordinate subset having the same number as the cluster center coordinate set.
- the cluster center coordinate set is also 4 cluster center coordinates.
- the vehicle accessory coordinate set can be divided into 4 groups of vehicle accessory coordinate subsets in the form of random division, such as (9,2,3) corresponding to the first group of vehicle accessory coordinate subsets, (0,1,7 )
- the second set of vehicle accessory coordinate subsets (12,3,1) corresponds to the third set of vehicle accessory coordinate subsets
- (72,12,34) corresponds to the fourth set of vehicle accessory coordinate subsets.
- the following formula is used to calculate the error value between each cluster center coordinate in the cluster center coordinate set and each vehicle accessory coordinate in the corresponding vehicle accessory coordinate subset:
- x t is the vehicle accessory coordinate in the vehicle accessory coordinate subset
- ⁇ i is the cluster center coordinate of the cluster center coordinate set
- K represents the number of the cluster center coordinate set
- c i represents the vehicle accessory
- the error value of each cluster center coordinate and the vehicle accessory coordinate in the corresponding vehicle accessory coordinate subset is sequentially calculated through the above calculation method.
- the S5 includes:
- (9,2,3) corresponds to the first set of vehicle accessories coordinate subsets
- (0,1,7) corresponds to the second set of vehicle accessories coordinate subsets
- (12,3,1) corresponds to the third set of vehicle accessories coordinates
- Subset (72,12,34) corresponds to the fourth set of vehicle accessory coordinate subsets.
- S52 Use the cluster center to update the coordinate set to adjust the vehicle accessory coordinate subset to obtain the adjusted vehicle accessory coordinate subset
- adjustments can be made according to the set of error values. If a part of the accessory coordinates and the corresponding cluster center coordinates in the first set of vehicle accessory coordinate subsets have too large an error, then this part of the accessory coordinates will be divided into parts To the second group of vehicle accessory coordinate subsets, the third group of vehicle accessory coordinate subsets, and the fourth group of vehicle accessory coordinate subsets to obtain a new vehicle accessory coordinate subset.
- S53 Calculate an error value between each cluster center update coordinate in the cluster center update coordinate set and each vehicle accessory coordinate in the adjusted vehicle accessory coordinate subset;
- the method for calculating the error value of each cluster center update coordinate in the cluster center update coordinate set and the adjusted vehicle accessory coordinate sub-set of each vehicle accessory coordinate is the same as in the above S403
- the method for calculating the error value between each cluster center coordinate in the cluster center coordinate set and each vehicle accessory coordinate in the corresponding vehicle accessory coordinate subset is the same, which will not be repeated here.
- the vehicle accessory coordinate subsets corresponding to the four sets of cluster center coordinates correspond to the grouping and comparison of expensive accessories. Expensive parts grouping, common parts grouping and low-cost parts grouping, thus completing the grouping of the collection of vehicle accessories pictures according to the user's grouping standard.
- the accessories are grouped based on the vehicle accessory pictures.
- the accessory pictures are first divided by structure, and vector transformation and coordinate mapping are performed on the accessory pictures after the structure is divided to obtain the vehicle accessory coordinate set, and use the vehicle accessory coordinate set to complete Grouping of vehicle accessories.
- the vehicle accessory coordinate set is more concise than the accessory picture set, and the grouping can be completed without too much calculation, which can solve the problem of consuming too much computing resources when the vehicle accessories are grouped.
- FIG. 5 it is a schematic diagram of the module of the grouping device of the vehicle accessories of the present application.
- the device 100 for grouping vehicle accessories described in this application can be installed in an electronic device.
- the device 100 for grouping vehicle accessories may include a vector transformation module 101, a coordinate mapping module 102, an error calculation module 103, and an accessory grouping module 104.
- the module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.
- each module/unit is as follows:
- the vector conversion module 101 is used to obtain a collection of vehicle accessory pictures and grouping criteria, divide the collection of accessory pictures according to the vehicle structure, obtain multiple accessory picture subsets, and perform vector conversion on the accessory picture subsets, Get the accessory vector set;
- the coordinate mapping module 102 is configured to map the accessory vector set to a pre-built coordinate system to obtain a vehicle accessory coordinate set;
- the error calculation module 103 is configured to perform an initialization operation in the coordinate system according to the grouping standard to obtain a cluster center coordinate set, and sequentially calculate the error value between the cluster center coordinate set and the vehicle accessory coordinate set;
- the accessory grouping module 104 is configured to update the cluster center coordinate set using the error value, and calculate the updated error value, and until the error value meets the preset error requirement, use the vehicle accessory coordinate set to obtain The vehicle accessories grouping corresponding to the grouping standard.
- the modules in the device provided in this application can be used based on the same grouping method as the above-mentioned vehicle accessories.
- the vehicle accessories coordinate set can be obtained by structural division, vector transformation and mapping operations on the collection of accessory pictures, and use the vehicle accessory coordinates
- the set is grouped, which can solve the problem of occupying too much computing resources when the vehicle parts are grouped.
- FIG. 6 it is a schematic diagram of the structure of an electronic device that implements the method for grouping vehicle accessories in the present application.
- the electronic device 1 may include a processor 10, a memory 11, and a bus, and may also include a computer program stored in the memory 11 and run on the processor 10, such as a grouping program 12 of vehicle accessories.
- the memory 11 includes at least one type of readable storage medium, and the readable storage medium may be volatile or nonvolatile.
- the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc.
- the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, for example, a mobile hard disk of the electronic device 1.
- the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SmartMediaCard, SMC), and a secure digital (SecureDigital, SD) equipped on the electronic device 1. Card, flash card (FlashCard), etc.
- the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
- the memory 11 can be used not only to store application software and various data installed in the electronic device 1, such as the code of the grouping program 12 of vehicle accessories, etc., but also to temporarily store data that has been output or will be output.
- the processor 10 may be composed of integrated circuits in some embodiments, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more Central Processing Unit (CPU), microprocessor, digital processing chip, graphics processor and a combination of various control chips, etc.
- the processor 10 is the control core (ControlUnit) of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and runs or executes programs or modules stored in the memory 11 (such as executing a vehicle). Grouping programs of accessories, etc.), and call data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
- ControlUnit ControlUnit
- the bus may be a peripheral component interconnection standard (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like.
- PCI peripheral component interconnection standard
- EISA extended industry standard architecture
- the bus can be divided into address bus, data bus, control bus and so on.
- the bus is configured to implement connection and communication between the memory 11 and at least one processor 10 and the like.
- FIG. 6 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 6 does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure. Components, or a combination of certain components, or different component arrangements.
- the electronic device 1 may also include a power source (such as a battery) for supplying power to various components.
- the power source may be logically connected to the at least one processor 10 through a power management device, thereby controlling power
- the device implements functions such as charge management, discharge management, and power consumption management.
- the power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators.
- the electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
- the electronic device 1 may also include a network interface.
- the network interface may include a wired interface and/or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
- the electronic device 1 may also include a user interface.
- the user interface may be a display (Display) and an input unit (such as a keyboard (Keyboard)).
- the user interface may also be a standard wired interface or a wireless interface.
- the display may be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light emitting diode) touch device, etc.
- the display can also be appropriately called a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visualized user interface.
- the grouping program 12 of vehicle accessories stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can realize:
- the integrated module/unit of the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
- the computer-readable storage medium may be volatile or non-volatile.
- the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read -OnlyMemory).
- the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function, etc.; the storage data area may store a block chain node Use the created data, etc.
- modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
- the functional modules in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
- the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional modules.
- the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
- Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种车辆配件的分组方法、装置、电子设备及存储介质,涉及图像检测领域,该方法包括:按照车辆结构划分配件图片总集得到多个配件图片子集(S1),将所述配件图片子集进行向量转化得到配件向量集(S2),将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集(S3),根据分组标准在所述坐标系中初始化得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值(S4),利用所述误差值更新所述簇心坐标集,直至误差值满足预设误差要求时,得到与所述分组标准对应的车辆配件分组(S5),所述配件图片总集可以存储在区块链节点中。该方法可以解决车辆配件分组时,占用过多计算资源的问题。
Description
本申请要求于2020年09月02日提交中国专利局、申请号为202010911998.6,发明名称为“车辆配件的分组方法、装置、电子设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及图像检测领域,尤其涉及一种车辆配件的分组方法、装置、电子设备及计算机可读存储介质。
当前,随着汽车领域的快速发展,新能源车辆、智能驾驶类车辆等层出不求,随之而来的是车辆配件如雨后春笋般涌现,因此如何快速的对车辆配件进行分组,以分组后的汽车配件进行工作安排是极其重要的。
发明人意识到,目前关于车辆配件的分组,主要有基于文本信息和基于图片信息两种方法,其中文本信息的分组方法,如用户输入车辆配件名称,通过机器学习方法,计算车辆配件名称与原有数据库内的车辆配件名词的相似度,并根据相似度结果完成车辆配件的分组,但由于用户与原有数据库关于对车牌配件的命名缺乏统一标准,因此极其容易发生分组错误的现象;而关于图片信息的分组,由于图片信息数据量庞大,直接通过深度学习或机器学习方法进行识别分组时,会占用大量的计算资源,导致分组速度慢,计算机内存等消耗严重。
发明内容
本申请提供的一种车辆配件的分组方法,包括:
获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集;
将所述配件图片子集进行向量转化,得到配件向量集;
将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;
根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;
利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
本申请还提供一种车辆配件的分组装置,所述装置包括:
向量转化模块,用于获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集,将所述配件图片子集进行向量转化,得到配件向量集;
坐标映射模块,用于将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;
误差计算模块,用于根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;
配件分组模块,用于利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
本申请还提供一种电子设备,所述电子设备包括:至少一个处理器;以及,
与所述至少一个处理器通信连接的存储器;其中,
所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的车辆配件的分组方法:
获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集;
将所述配件图片子集进行向量转化,得到配件向量集;
将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;
根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;
利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
本申请还提供一种计算机可读存储介质,包括存储数据区和存储程序区,其中,所述存储数据区存储创建的数据,所述存储程序区存储有计算机程序;其中,所述计算机程序被处理器执行时实现如下所述的车辆配件的分组方法:
获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集;
将所述配件图片子集进行向量转化,得到配件向量集;
将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;
根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;
利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
图1为本申请一实施例提供的车辆配件的分组方法的流程示意图;
图2为本申请一实施例提供的车辆配件的分组方法中S2的详细流程示意图;
图3为本申请一实施例提供的车辆配件的分组方法中S4的详细流程示意图;
图4为本申请一实施例提供的车辆配件的分组方法中S5的详细流程示意图;
图5为本申请一实施例提供的车辆配件的分组装置的模块示意图;
图6为本申请一实施例提供的实现车辆配件的分组方法的电子设备的内部结构示意图;
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供的车辆配件的分组方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述车辆配件的分组方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
本申请提供一种车辆配件的分组方法。参照图1所示,为本申请一实施例提供的车辆配件的分组方法的流程示意图。在本实施例中,所述车辆配件的分组方法包括:
S1、获取配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集。
本申请较佳实施例中,所述配件图片总集包括发动机、节气门体、气缸体、涨紧轮、传动系配件、离合器、变速器、减速器、磁性材料、制动总泵、制动分泵、制动器总成、制动踏板总成、压缩机、刹车盘、刹车鼓等配件图片。由于车辆配件复杂,且车辆配件层出不穷推陈出新,因此需要根据用户设定的分组标准,对大量的车牌配件图片进行高效分组。
进一步地,所述分组标准包括车辆配件的价格、车辆配件的购买渠道等,如配件图片总集包括发动机、节气门体、气缸体、涨紧轮、传动系配件等,其中分组标准可以是按照配件损坏时的维修价格,将配件分为昂贵配件、较贵配件、普通配件及低廉配件。
详细地,所述车辆结构包括车辆的外部结构和内部结构,如不同的车辆配件具有特定的车辆应用场景,配件A只能应用在三厢车内,配件B只能应用在两厢轿车上,配件C只能应用在跑车上,而三厢车、两厢轿车、跑车即为车辆外部结构。相比于车辆外部结构,车辆内部结构包括核载人数、轮胎尺寸、发动机排量等,如配件D只能应用于发动机排量小于1.0L的车辆、配件E只能应用于发动机排量在1.6L至2.5L的车辆、配件F可应用在发动机排量在4.0L以上的车辆。由此可将配件图片总集划分出多种配件图片子集。
S2、将所述配件图片子集进行向量转化,得到配件向量集。
由于图片内像素点众多且特征不明显,若直接利用图片对车辆配件进行分组,不仅消耗大量计算资源,同时分组准确率不高,因此需先将图片转化为向量。
详细地,参阅图2所示,所述S2包括:
S21、利用卷积操作提取所述配件图片子集内的配件纹理特征集;
S22、将所述配件纹理特征集进行降维操作并组合,得到所述配件向量集。
本申请较佳实施例中,采用如下卷积计算公式,提取所述配件图片子集内的配件纹理特征集:
O
y,u,v(x
1,x
2)=M(x
1,x
2)*φ
y,u,v(z)
其中,O
y,u,v(x
1,x
2)为所述配件纹理特征集,M(x
1,x
2)为所述配件图片子集内的配件图片的像素值坐标,φ
y,u,v(z)为卷积函数,z为卷积算子,y,u,v代表图片的三个分量,其中y为图片明亮度、u,v为图片的色度。
由于卷积操作后的配件纹理特征集依然数据量庞大,因此需要进一步地通过降维操作,缩小配件纹理特征集的数据量。
优选地,所述降维操作包括利用矩阵维度固定的滑动窗口从左到右、从上到下,依次在所述配件纹理特征集内的配件纹理特征上,进行特定步长的平均值采样,如矩阵维度为2*2的滑动窗口,特定步长为3时,可将配件纹理特征集的特征维数降至原先维度的1/4,并依次将降维后的特征组合得到所述配件向量集。
S3、将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集。
本申请较佳实施例,若坐标系为二维平面坐标系,则所述车辆配件坐标集的配件坐标可用(x,y)表示,当所述坐标系为三维平面坐标系,则所述车辆配件坐标集的配件坐标可用(x,y,z)表示。
优选地,所述映射的方法较多,如配件向量集中关于节气门体的向量为
先按照向量中每行代表一个坐标维度的形式,将(12…19)利用数学公式计算得到对应的数值为13,(67…4)利用数学公式计算得到对应的数值为8,由此节气门体的向量对应的车辆配件坐标则为(13,8)
S4、根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计 算所述簇心坐标集与所述车辆配件坐标集的误差值。
根据上述S1至S3可知,配件图片总集通过结构划分、向量转化和映射已转变为车辆配件坐标集,因此对车辆配件坐标集的分组,即为对配件图片总集的分组。
进一步地,参阅图3所示,所述根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集包括:
S401、根据所述分组标准中的分组数,在所述坐标系中,随机初始化得到与所述分组数相同数量的簇心坐标,得到所述簇心坐标集。
如以车辆配件的价格为分组标准,将配件分为昂贵配件、较贵配件、普通配件及低廉配件4个分组数,若预设的坐标系为三维坐标系,则在三维坐标系中,可对应随机初始化得到4个簇心坐标分别为(9,2,3)、(0,1,7)、(12,3,1)、(72,12,34)。
当得到簇心坐标集后,可计算簇心坐标集与车辆配件坐标集之间的距离关系,通过该距离关系可达到对车辆配件坐标集进行分组的目的。
进一步地,所述依次计算所述簇心坐标集与所述车辆配件坐标集的误差值,包括:
S402、根据所述簇心坐标集划分所述车辆配件坐标集,得到与所述簇心坐标集的数量相同的车辆配件坐标子集。
如上述以车辆配件的价格为分组标准,将配件分为昂贵配件、较贵配件、普通配件及低廉配件4个分组数,因此簇心坐标集也为4个簇心坐标,通过该4个簇心坐标,可先通过随机划分的形式,将车辆配件坐标集划分为4组车辆配件坐标子集,如(9,2,3)对应第一组车辆配件坐标子集、(0,1,7)对应第二组车辆配件坐标子集、(12,3,1)对应第三组车辆配件坐标子集、(72,12,34)对应第四组车辆配件坐标子集。
S403、计算所述簇心坐标集内每个簇心坐标与对应的所述车辆配件坐标子集内每个车辆配件坐标的误差值。
本申请较佳实施例中,采用下述公式计算所述簇心坐标集内每个簇心坐标与对应的所述车辆配件坐标子集内每个车辆配件坐标的误差值:
其中,x
t为所述车辆配件坐标子集内的车辆配件坐标,μ
i为所述簇心坐标集的簇心坐标,K表示所述簇心坐标集的数量,c
i表示所述车辆配件坐标子集,通过上述计算方法,依次计算得到每个簇心坐标和对应的车辆配件坐标子集内的车辆配件坐标的误差值。
S5、利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
当计算出每个簇心坐标和对应的车辆配件坐标子集内的车辆配件坐标的误差值后,需要根据误差值对所述车辆配件坐标集分组,故详细地,参阅图4所示,所述S5包括:
S51、汇总所述簇心坐标集内每个簇心坐标与对应车辆配件坐标子集的误差值,得到误差值集,根据所述误差值集更新所述簇心坐标集的坐标位置,得到簇心更新坐标集;
如上述(9,2,3)对应第一组车辆配件坐标子集、(0,1,7)对应第二组车辆配件坐标子集、(12,3,1)对应第三组车辆配件坐标子集、(72,12,34)对应第四组车辆配件坐标子集,通过计算出(9,2,3)和第一组车辆配件坐标子集所计算出的误差值集,调整(9,2,3)的坐标为(16,21,23),依次类推得到4组更新后的簇心更新坐标集。
S52、利用簇心更新坐标集调整所述车辆配件坐标子集,得到调整后的车辆配件坐标子集;
本申请较佳实施例中,可根据所述误差值集进行调整,如第一组车辆配件坐标子集中有一部分配件坐标与对应的簇心坐标误差太大,则将该一部分配件坐标分部划分至第二组 车辆配件坐标子集、第三组车辆配件坐标子集及第四组车辆配件坐标子集,从而得到新的车辆配件坐标子集。
S53、计算所述簇心更新坐标集内每个簇心更新坐标与调整后的所述车辆配件坐标子集内每个车辆配件坐标的误差值;
本申请实施例中,所述计算所述簇心更新坐标集内每个簇心更新坐标与调整后的所述车辆配件坐标子集内每个车辆配件坐标的误差值的方法与上述的S403中计算所述簇心坐标集内每个簇心坐标与对应的所述车辆配件坐标子集内每个车辆配件坐标的误差值的方法相同,这里不在赘述。
S54、统计出误差值大于所述预设误差的数量,与误差值小于或等于所述预设误差的数量,计算大于所述预设误差的数量与小于或等于所述预设误差的数量的比值;
S55、判断所述比值与预设比例的大小关系,所述比值大于预设比例,则返回S51;
S56、若所述比值小于或等于所述预设比例,将对应的车辆配件坐标子集作为与所述分组标准对应的车辆配件分组。
如经过上述的循环、更新等步骤,得到4组簇心坐标均满足比值小于或等于所述预设比例,则该4组簇心坐标对应的车辆配件坐标子集即分别对应昂贵配件分组、较贵配件分组、普通配件分组及低廉配件分组,从而完成了根据用户的分组标准,对车辆的配件图片总集的分组。
本申请实施例基于车辆配件图片对配件进行分组,先通过结构划分配件图片,并依次对结构划分后的配件图片进行向量转化和坐标映射,得到车辆配件坐标集,并利用该车辆配件坐标集完成车辆配件的分组。车辆配件坐标集相比于配件图片集来说更简洁,不需要过多的计算即可完成分组,可以解决车辆配件分组时,占用过多计算资源的问题。
如图5所示,是本申请车辆配件的分组装置的模块示意图。
本申请所述车辆配件的分组装置100可以安装于电子设备中。根据实现的功能,所述车辆配件的分组装置100可以包括向量转化模块101、坐标映射模块102、误差计算模块103及配件分组模块104。本发所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述向量转化模块101,用于获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集,将所述配件图片子集进行向量转化,得到配件向量集;
所述坐标映射模块102,用于将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;
所述误差计算模块103,用于根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;
所述配件分组模块104,用于利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
本申请所提供的装置中的模块能够在使用时基于与上述的车辆配件的分组方法相同,通过对配件图片总集进行结构划分、向量转化及映射操作得到车辆配件坐标集,并利用车辆配件坐标集进行分组,从而可以解决车辆配件分组时,占用过多计算资源的问题。
如图6所示,是本申请实现车辆配件的分组方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如车辆配件的分组程序12。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质可以是易失性的,也可以是非易失性的。具体的,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(SmartMediaCard,SMC)、安全数字(SecureDigital,SD)卡、闪存卡(FlashCard)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如车辆配件的分组程序12的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(CentralProcessingunit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(ControlUnit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如执行车辆配件的分组程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheralcomponentinterconnect,简称PCI)总线或扩展工业标准结构(extendedindustrystandardarchitecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图6仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图6示出的结构并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(OrganicLight-EmittingDiode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的车辆配件的分组程序12是多个指令的组合,在所述处理器10中运行时,可以实现:
获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多 个配件图片子集;
将所述配件图片子集进行向量转化,得到配件向量集;
将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;
根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;
利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。所述计算机可读存储介质可以是易失性的,也可以是非易失性的。具体的,所述计算机可读存储介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-OnlyMemory)。
进一步地,所述计算机可用存储介质可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序等;存储数据区可存储根据区块链节点的使用所创建的数据等。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图表记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。
Claims (20)
- 一种车辆配件的分组方法,其中,所述方法包括:获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集;将所述配件图片子集进行向量转化,得到配件向量集;将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
- 如权利要求1所述的车辆配件的分组方法,其中,所述根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,包括:根据所述分组标准中的分组数,在所述坐标系中,随机初始化得到与所述分组数相同数量的簇心坐标,得到所述簇心坐标集。
- 如权利要求2所述的车辆配件的分组方法,其中,所述计算所述簇心坐标集与所述车辆配件坐标集的误差值,包括:根据所述簇心坐标集划分所述车辆配件坐标集,得到与所述簇心坐标集数量相同的车辆配件坐标子集;计算所述簇心坐标集内每个簇心坐标与对应的所述车辆配件坐标子集内每个车辆配件坐标的误差值。
- 如权利要求3中所述的车辆配件的分组方法,其中,所述利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组,包括:汇总所述簇心坐标集内每个簇心坐标与对应车辆配件坐标子集的误差值,得到误差值集,根据所述误差值集更新所述簇心坐标集的坐标位置,得到簇心更新坐标集;利用簇心更新坐标集调整所述车辆配件坐标子集,得到调整后的车辆配件坐标子集;计算所述簇心更新坐标集内每个簇心坐标与调整后的所述车辆配件坐标子集内每个车辆配件坐标的误差值;统计出误差值大于所述预设误差的数量,与误差值小于或等于所述预设误差的数量,计算大于所述预设误差的数量与小于或等于所述预设误差的数量的比值;判断所述比值与预设比例的大小关系,当所述比值大于所述预设比例时,重新更新所述簇心坐标集的坐标位置;当所述比值小于或等于所述预设比例时,将对应的车辆配件坐标子集作为与所述分组标准对应的车辆配件分组。
- 如权利要求1至5中任意一项所述的车辆配件的分组方法,其中,所述将所述配件图片子集进行向量转化,得到配件向量集,包括:利用卷积操作提取所述配件图片子集内的配件纹理特征集;将所述配件纹理特征集进行降维操作并组合,得到所述配件向量集。
- 如权利要求6所述的车辆配件的分组方法,其中,所述卷积操作提取所述配件图片子集内的配件纹理特征集,包括:采用如下卷积计算公式提取所述配件图片子集内的配件纹理特征集:O y,u,v(x 1,x 2)=M(x 1,x 2)*φ y,u,v(z)其中,O y,u,v(x 1,x 2)为所述配件纹理特征集,M(x 1,x 2)为所述配件图片子集内的配件图片的像素值坐标,φ y,u,v(z)为卷积函数,z为卷积算子,y为配件图片明亮度、u,v为配件图片的色度。
- 一种车辆配件的分组装置,其中,所述装置包括:向量转化模块,用于获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集,将所述配件图片子集进行向量转化,得到配件向量集;坐标映射模块,用于将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;误差计算模块,用于根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;配件分组模块,用于利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
- 一种电子设备,其中,所述电子设备包括:至少一个处理器;以及,与所述至少一个处理器通信连接的存储器;其中,所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的车辆配件的分组方法:获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集;将所述配件图片子集进行向量转化,得到配件向量集;将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
- 如权利要求9所述的电子设备,其中,所述根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,包括:根据所述分组标准中的分组数,在所述坐标系中,随机初始化得到与所述分组数相同数量的簇心坐标,得到所述簇心坐标集。
- 如权利要求10所述的电子设备,其中,所述计算所述簇心坐标集与所述车辆配件坐标集的误差值,包括:根据所述簇心坐标集划分所述车辆配件坐标集,得到与所述簇心坐标集数量相同的车辆配件坐标子集;计算所述簇心坐标集内每个簇心坐标与对应的所述车辆配件坐标子集内每个车辆配件坐标的误差值。
- 如权利要求11中所述的电子设备,其中,所述利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标 集,得到与所述分组标准对应的车辆配件分组,包括:汇总所述簇心坐标集内每个簇心坐标与对应车辆配件坐标子集的误差值,得到误差值集,根据所述误差值集更新所述簇心坐标集的坐标位置,得到簇心更新坐标集;利用簇心更新坐标集调整所述车辆配件坐标子集,得到调整后的车辆配件坐标子集;计算所述簇心更新坐标集内每个簇心坐标与调整后的所述车辆配件坐标子集内每个车辆配件坐标的误差值;统计出误差值大于所述预设误差的数量,与误差值小于或等于所述预设误差的数量,计算大于所述预设误差的数量与小于或等于所述预设误差的数量的比值;判断所述比值与预设比例的大小关系,当所述比值大于所述预设比例时,重新更新所述簇心坐标集的坐标位置;当所述比值小于或等于所述预设比例时,将对应的车辆配件坐标子集作为与所述分组标准对应的车辆配件分组。
- 如权利要求9至13中任意一项所述的电子设备,其中,所述将所述配件图片子集进行向量转化,得到配件向量集,包括:利用卷积操作提取所述配件图片子集内的配件纹理特征集;将所述配件纹理特征集进行降维操作并组合,得到所述配件向量集。
- 一种计算机可读存储介质,包括存储数据区和存储程序区,其中,所述存储数据区存储创建的数据,所述存储程序区存储有计算机程序;其中,所述计算机程序被处理器执行时实现如下所述的车辆配件的分组方法:获取车辆的配件图片总集及分组标准,按照车辆结构划分所述配件图片总集,得到多个配件图片子集;将所述配件图片子集进行向量转化,得到配件向量集;将所述配件向量集映射至预构建的坐标系中,得到车辆配件坐标集;根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,依次计算所述簇心坐标集与所述车辆配件坐标集的误差值;利用所述误差值更新所述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组。
- 如权利要求15所述的计算机可读存储介质,其中,所述根据所述分组标准,在所述坐标系中执行初始化操作,得到簇心坐标集,包括:根据所述分组标准中的分组数,在所述坐标系中,随机初始化得到与所述分组数相同数量的簇心坐标,得到所述簇心坐标集。
- 如权利要求16所述的计算机可读存储介质,其中,所述计算所述簇心坐标集与所述车辆配件坐标集的误差值,包括:根据所述簇心坐标集划分所述车辆配件坐标集,得到与所述簇心坐标集数量相同的车辆配件坐标子集;计算所述簇心坐标集内每个簇心坐标与对应的所述车辆配件坐标子集内每个车辆配件坐标的误差值。
- 如权利要求17中所述的计算机可读存储介质,其中,所述利用所述误差值更新所 述簇心坐标集,并计算更新后的误差值,且直至误差值满足预设误差要求时,利用所述车辆配件坐标集,得到与所述分组标准对应的车辆配件分组,包括:汇总所述簇心坐标集内每个簇心坐标与对应车辆配件坐标子集的误差值,得到误差值集,根据所述误差值集更新所述簇心坐标集的坐标位置,得到簇心更新坐标集;利用簇心更新坐标集调整所述车辆配件坐标子集,得到调整后的车辆配件坐标子集;计算所述簇心更新坐标集内每个簇心坐标与调整后的所述车辆配件坐标子集内每个车辆配件坐标的误差值;统计出误差值大于所述预设误差的数量,与误差值小于或等于所述预设误差的数量,计算大于所述预设误差的数量与小于或等于所述预设误差的数量的比值;判断所述比值与预设比例的大小关系,当所述比值大于所述预设比例时,重新更新所述簇心坐标集的坐标位置;当所述比值小于或等于所述预设比例时,将对应的车辆配件坐标子集作为与所述分组标准对应的车辆配件分组。
- 如权利要求15至19中任意一项所述的计算机可读存储介质,其中,所述将所述配件图片子集进行向量转化,得到配件向量集,包括:利用卷积操作提取所述配件图片子集内的配件纹理特征集;将所述配件纹理特征集进行降维操作并组合,得到所述配件向量集。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010911998.6 | 2020-09-02 | ||
| CN202010911998.6A CN112070142B (zh) | 2020-09-02 | 2020-09-02 | 车辆配件的分组方法、装置、电子设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021189896A1 true WO2021189896A1 (zh) | 2021-09-30 |
Family
ID=73666241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/131919 Ceased WO2021189896A1 (zh) | 2020-09-02 | 2020-11-26 | 车辆配件的分组方法、装置、电子设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112070142B (zh) |
| WO (1) | WO2021189896A1 (zh) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070106409A1 (en) * | 2005-11-08 | 2007-05-10 | The Boeing Company | Attribute-based item information grouping, such as for use in generating manufacturing instructions |
| CN108288076A (zh) * | 2018-02-12 | 2018-07-17 | 深圳开思时代科技有限公司 | 汽车配件聚类方法、装置、电子设备及存储介质 |
| CN110555470A (zh) * | 2019-08-19 | 2019-12-10 | 一汽解放汽车有限公司 | 一种喷油器分组方法 |
| US20200134496A1 (en) * | 2018-10-29 | 2020-04-30 | Hewlett Packard Enterprise Development Lp | Classifying parts via machine learning |
| CN111475541A (zh) * | 2020-03-17 | 2020-07-31 | 中国平安人寿保险股份有限公司 | 数据决策方法、装置、电子设备及存储介质 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8443278B2 (en) * | 2009-01-02 | 2013-05-14 | Apple Inc. | Identification of tables in an unstructured document |
| CN106845519A (zh) * | 2016-12-20 | 2017-06-13 | 南京信息工程大学 | 一种分布式实现的稀疏子空间聚类方法 |
| CN111354038B (zh) * | 2018-12-21 | 2023-10-13 | 广东美的白色家电技术创新中心有限公司 | 锚定物检测方法及装置、电子设备及存储介质 |
-
2020
- 2020-09-02 CN CN202010911998.6A patent/CN112070142B/zh active Active
- 2020-11-26 WO PCT/CN2020/131919 patent/WO2021189896A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070106409A1 (en) * | 2005-11-08 | 2007-05-10 | The Boeing Company | Attribute-based item information grouping, such as for use in generating manufacturing instructions |
| CN108288076A (zh) * | 2018-02-12 | 2018-07-17 | 深圳开思时代科技有限公司 | 汽车配件聚类方法、装置、电子设备及存储介质 |
| US20200134496A1 (en) * | 2018-10-29 | 2020-04-30 | Hewlett Packard Enterprise Development Lp | Classifying parts via machine learning |
| CN110555470A (zh) * | 2019-08-19 | 2019-12-10 | 一汽解放汽车有限公司 | 一种喷油器分组方法 |
| CN111475541A (zh) * | 2020-03-17 | 2020-07-31 | 中国平安人寿保险股份有限公司 | 数据决策方法、装置、电子设备及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112070142A (zh) | 2020-12-11 |
| CN112070142B (zh) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932534B (zh) | 医学影像图片分析方法、装置、电子设备及可读存储介质 | |
| US20210216871A1 (en) | Fast Convolution over Sparse and Quantization Neural Network | |
| CN111738212B (zh) | 基于人工智能的交通信号灯识别方法、装置、设备及介质 | |
| CN111476225B (zh) | 基于人工智能的车内人脸识别方法、装置、设备及介质 | |
| CN114913371B (zh) | 多任务学习模型训练方法、装置、电子设备及存储介质 | |
| CN114708461B (zh) | 基于多模态学习模型的分类方法、装置、设备及存储介质 | |
| WO2021189856A1 (zh) | 证件校验方法、装置、电子设备及介质 | |
| JP7085600B2 (ja) | 画像間の類似度を利用した類似領域強調方法およびシステム | |
| CN112347042A (zh) | 文件上传方法、装置、电子设备及存储介质 | |
| US20210209473A1 (en) | Generalized Activations Function for Machine Learning | |
| CN111652226B (zh) | 基于图片的目标识别方法、装置及可读存储介质 | |
| CN111985449A (zh) | 救援现场图像的识别方法、装置、设备及计算机介质 | |
| CN111932595A (zh) | 图像配准方法、装置、电子设备及存储介质 | |
| CN111651292A (zh) | 数据校验方法、装置、电子设备及计算机可读存储介质 | |
| CN111931729B (zh) | 基于人工智能的行人检测方法、装置、设备及介质 | |
| CN113869455B (zh) | 无监督聚类方法、装置、电子设备及介质 | |
| WO2021189896A1 (zh) | 车辆配件的分组方法、装置、电子设备及存储介质 | |
| CN115346095A (zh) | 视觉问答方法、装置、设备及存储介质 | |
| CN114943989A (zh) | 基于人工智能的狗脸关键点检测方法及相关设备 | |
| CN112233194B (zh) | 医学图片优化方法、装置、设备及计算机可读存储介质 | |
| CN112132140B (zh) | 基于人工智能的车品牌识别方法、装置、设备及介质 | |
| CN115098685A (zh) | 局部聚类方法、装置、设备及存储介质 | |
| WO2022198786A1 (zh) | 目标物检测方法、装置、电子设备及存储介质 | |
| WO2021056134A1 (en) | Scene retrieval for computer vision | |
| WO2022227191A1 (zh) | 非主动活体检测方法、装置、电子设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20927999 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20927999 Country of ref document: EP Kind code of ref document: A1 |




