WO2021217340A1 - 基于ai的通用智能家居方案自动化设计方法及装置 - Google Patents

基于ai的通用智能家居方案自动化设计方法及装置 Download PDF

Info

Publication number
WO2021217340A1
WO2021217340A1 PCT/CN2020/087238 CN2020087238W WO2021217340A1 WO 2021217340 A1 WO2021217340 A1 WO 2021217340A1 CN 2020087238 W CN2020087238 W CN 2020087238W WO 2021217340 A1 WO2021217340 A1 WO 2021217340A1
Authority
WO
WIPO (PCT)
Prior art keywords
design
smart home
neural network
user
confirmation
Prior art date
Application number
PCT/CN2020/087238
Other languages
English (en)
French (fr)
Inventor
李建军
Original Assignee
Li Jianjun
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Li Jianjun filed Critical Li Jianjun
Priority to PCT/CN2020/087238 priority Critical patent/WO2021217340A1/zh
Publication of WO2021217340A1 publication Critical patent/WO2021217340A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Definitions

  • the present invention relates to the field of artificial intelligence technology, in particular to an AI-based general smart home solution automation design method, device and electronic equipment.
  • the embodiments of the present invention provide an AI-based general smart home solution automation design method, device, and electronic equipment, which at least partially solve the problems existing in the prior art.
  • an AI-based general smart home solution automation design method provided by an embodiment of the present invention includes:
  • Collect plane drawings related to intelligent design as valid image samples, so as to conduct deep learning of the image samples based on engine algorithms, train and verify the neural network system used by the engine, and pass hyperparameter debugging, regularization and optimization Methods to improve the neural network system;
  • the pooling layer is used to reduce the size of the model, increase the calculation speed, and at the same time improve the robustness of the extracted features, and gradually complete the full convolutional neural network Established the construction module of, and finally completed the target positioning, feature point detection, target detection related parameters required for the design;
  • the AI recognition content includes drawings or pictures of indoor floor plans.
  • AI automatically designs smart home solutions, including point design and pipeline design of smart home systems.
  • the automation design method uses AI to complete the number statistics and selection list output of the automation equipment of the smart home solution.
  • the automated design method uses AI to automatically generate orders.
  • the automated design method uses AI to complete the entire process from product selection to order completion to online user end, and provides online AI services.
  • the AI service includes, but is not limited to, completion of unique identification authentication, device status feedback, fault code prompt, remote reset, confirmation within and outside the warranty period, remote operation and maintenance, and super convenient after-sales service.
  • the generating a general intelligent home design scheme according to the confirmation of the user's selection at the client terminal includes:
  • Device status feedback The status detection of each device is divided into active detection and passive detection. Active detection is the remote time-sharing segment reading status, and passive detection is the status change, which is automatically uploaded to the system for update;
  • Fault code prompt establish a cluster of fault code numbers such as device failure, unstable connection, partial function failure, etc., for real-time update, upload, download, etc.;
  • Remote reset For faults that can be solved by reset, it can be solved by remote reset;
  • equipment traceability mechanism to compare whether the equipment in the database is out of warranty, to solve the problem of whether the warranty is charged or not;
  • Remote operation and maintenance according to the fault code, remote diagnosis, also online and offline consultation;
  • an AI-based general smart home solution automation design device including:
  • the acquisition module is used to collect plane drawings related to intelligent design as effective image samples, so as to conduct deep learning of the image samples based on engine algorithms, train and verify the neural network system used by the engine, and debug through hyperparameters , Regularization and optimization methods to improve the neural network system;
  • the establishment module is used to establish the parameter sharing and sparse connection of the convolutional layer for the neural network system, and then use the pooling layer to reduce the size of the model, increase the calculation speed, and improve the robustness of the extracted features, and gradually complete
  • the construction module of the full convolutional neural network is established, and the target positioning, feature point detection, and target detection related parameters required for the design are finally completed;
  • the generation module is used to realize the effective recognition of the plane drawings through Python language programming, intelligently add the candidate product icons of the database and scale them to a suitable size, generate the point design, and the system synchronously outputs the generated value of the marked device number, brand and model Format list
  • the execution module is used to obtain the input requirements set by the user at the client, and generate a general smart home design scheme according to the confirmation of the user's selection at the client.
  • an embodiment of the present invention 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 any of the foregoing first aspect or any implementation manner of the first aspect.
  • AI-based general smart home solution automation design method
  • embodiments of the present invention also provide a non-transitory computer-readable storage medium that stores computer instructions, and the computer instructions are used to make the computer execute the first aspect or the first aspect described above.
  • a non-transitory computer-readable storage medium that stores computer instructions, and the computer instructions are used to make the computer execute the first aspect or the first aspect described above.
  • an AI-based general smart home solution automation design method in any implementation manner.
  • the embodiments of the present invention also provide a computer program product.
  • the computer program product includes a calculation program stored on a non-transitory computer-readable storage medium.
  • the computer program includes program instructions. When executing, the computer is made to execute the AI-based general smart home solution automation design method in the foregoing first aspect or any implementation manner of the first aspect.
  • the AI-based general smart home solution automation design solution in the embodiment of the present invention includes collecting plan drawings related to smart design as valid image samples, so as to perform deep learning on the image samples based on engine algorithms, training and verifying the
  • the neural network system used by the engine is improved by hyperparameter debugging, regularization and optimization methods; for the neural network system, after establishing the parameter sharing and sparse connection of the convolutional layer, the pooling layer is used to reduce the size of the model, increase the calculation speed, and improve the robustness of the extracted features, gradually complete the construction of the full convolutional neural network, and finally complete the target positioning, feature point detection, and target detection related to the design.
  • FIG. 1 is a schematic diagram of an automated design process of an AI-based general smart home solution provided by an embodiment of the present invention
  • FIG. 2 is a schematic diagram of the design of an AI-based general smart home solution provided by an embodiment of the present invention
  • FIG. 3 is a schematic diagram of another AI-based general smart home solution design provided by an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of another AI-based general smart home solution automation design process provided by an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of an AI-based general smart home solution automation design device provided by an embodiment of the present invention.
  • Fig. 6 is a schematic diagram of an electronic device provided by an embodiment of the present invention.
  • the embodiments of the present disclosure provide an AI-based automation design method for a general smart home solution.
  • the AI-based general smart home solution automation design method provided in this embodiment can be executed by a computing device.
  • the computing device can be implemented as software, or as a combination of software and hardware, and the computing device can be integrated on a server and a terminal. Equipment and so on.
  • an AI-based general smart home solution automation design method provided by an embodiment of the present invention includes the following steps:
  • the pooling layer is used to reduce the size of the model, increase the calculation speed, and at the same time improve the robustness of the extracted features, and gradually complete the full convolution
  • the construction module of the neural network is established, and the target positioning, feature point detection, and target detection related parameters required for the design are finally completed;
  • S104 Obtain input requirements set by the user at the client, and generate a general intelligent home design scheme according to the user's confirmation of the type selection at the client.
  • step S101 to S104 it is possible to collect decorative plan drawings before and after the design of smart home systems on the market (or comparison pictures generated from plan drawings as content, hereinafter referred to as pictures), and continuously obtain valid data as samples.
  • Related algorithms carry out deep learning in CV (Computer Vision): input an effective smart home solution image, which can be a high-resolution jpg image, a PDF file generated by a decorative plan, or a CAD in DWG Documents, then output the index, and label; continuously train and verify the CNN (Convolutional Neural Network) neural network system used by this engine, and improve the deep neural network through hyperparameter debugging, regularization and optimization methods; CV edge detection (Edge detection example), convolution padding (padding), convolution step size (Strided convolutions), three-dimensional convolution (Convolutions over volumes), convolutional neural network fitting and "avoid overfitting", etc. process.
  • CV Computer Vision
  • the pooling layer is used to reduce the size of the model, increase the calculation speed, and at the same time improve the robustness of the extracted features, and gradually complete the construction of the full convolutional neural network. And finally complete the important parameters such as object localization, feature point detection (Landmark detection), and object detection (Object detection) required by the design;
  • the above practice process realizes the effective identification of drawings (or pictures) through Python language programming, and intelligently adds candidate product icons in the database and scales them to a suitable size, and generates point designs, etc.; the system synchronously outputs the number of marked devices, brands and models The generated formatted list;
  • the algorithm will be continuously optimized to reduce the calculation time and improve the user experience
  • the system will complete the order production according to the confirmation of the client's selection, and provide a series of follow-up services after the transaction is completed, mainly including:
  • Device status feedback The status detection of each device is divided into active detection and passive detection. Active detection is the remote time-sharing segment reading status, and passive detection is the status change, which is automatically uploaded to the system for update;
  • Fault code prompt Establish a cluster of fault code numbers such as equipment failure, unstable connection, partial function failure, etc., and perform real-time update, upload, download, etc.;
  • Remote reset If it is a fault that can be solved by reset, it can be solved by remote reset;
  • the equipment traceability mechanism is to compare whether the equipment in the database is out of warranty to solve the problem of whether the warranty is charged or not;
  • the AI recognition content includes drawings or pictures of indoor floor plans.
  • AI automatically designs smart home solutions, including point design and pipeline design of smart home systems.
  • the automation design method uses AI to complete the number statistics and selection list output of the automation equipment of the smart home solution.
  • the automated design method uses AI to automatically generate orders.
  • the automated design method uses AI to complete the entire process from product selection to order completion to online user end, and provides online AI services.
  • the AI service includes, but is not limited to, completion of unique identification authentication, device status feedback, fault code prompt, remote reset, confirmation within and outside the warranty period, remote operation and maintenance, and super convenient after-sales service.
  • the generating a general intelligent home design scheme according to the confirmation of the user's selection at the client terminal includes:
  • Device status feedback The status detection of each device is divided into active detection and passive detection. Active detection is the remote time-sharing segment reading status, and passive detection is the status change, which is automatically uploaded to the system for update;
  • Fault code prompt Establish a cluster of fault code numbers such as device failure, unstable connection, partial function failure, etc., for real-time update, upload, download, etc.;
  • Remote reset For faults that can be solved by reset, it can be solved by remote reset;
  • equipment traceability mechanism to compare whether the equipment in the database is out of warranty, to solve the problem of whether the warranty is charged or not;
  • Remote operation and maintenance according to the fault code, remote diagnosis, also online and offline consultation;
  • an embodiment of the present invention provides an AI-based general smart home solution automation design device 50, including:
  • the acquisition module 501 is used to collect plan drawings related to intelligent design as effective image samples, so as to perform deep learning on the image samples based on the engine algorithm, train and verify the neural network system used by the engine, and pass hyperparameters Debugging, regularization and optimization methods to improve the neural network system;
  • the establishment module 502 is used to establish the parameter sharing and sparse connection of the convolutional layer for the neural network system, and then use the pooling layer to reduce the size of the model, increase the calculation speed, and improve the robustness of the extracted features. Complete the establishment of the construction module of the full convolutional neural network, and finally complete the target positioning, feature point detection, and target detection related parameters required for the design;
  • the generation module 503 is used to realize the effective recognition of the plane drawings through Python language programming, intelligently add the candidate product icons of the database and scale them to a suitable size, generate a point design, and the system synchronously outputs the number of marked devices, brands and models. Formatted list;
  • the execution module 504 is used to obtain the input requirements set by the user at the client, and generate a general smart home design scheme according to the confirmation of the user's selection at the client.
  • an embodiment of the present invention also provides an electronic device 60, 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 AI-based general smart home solution automation design method in the foregoing method embodiment.
  • the embodiment of the present invention also provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to make the computer execute the foregoing method embodiments.
  • the embodiment of the present invention also provides a computer program product, the computer program product includes a calculation program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, The computer executes the AI-based general smart home solution automation design method in the foregoing method embodiment.
  • the device shown in Fig. 5 can execute the method of the embodiment shown in Figs. 1-4.
  • parts that are not described in detail in this embodiment please refer to the related description of the embodiment shown in Figs. 1-4. I won't repeat them here.
  • FIG. 6 shows a schematic structural diagram of an electronic device 60 suitable for implementing embodiments of the present disclosure.
  • Electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 60 may include a processing device (such as a central processing unit, a graphics processor, etc.) 601, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 602 or from a storage device 608.
  • the program in the memory (RAM) 603 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 60 are also stored.
  • the processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604.
  • the following devices can be connected to the I/O interface 605: including input devices 606 such as touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCD), speakers, An output device 607 such as a vibrator; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication device 609 may allow the electronic device 60 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 4 shows an electronic device 60 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may be implemented alternatively or provided with more or fewer devices.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602.
  • the processing device 601 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the electronic device When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains at least two Internet protocol addresses; A node evaluation request for an Internet Protocol address, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; wherein, the obtained The Internet Protocol address indicates the edge node in the content distribution network.
  • the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; Among the at least two Internet Protocol addresses, an Internet Protocol address is selected; the selected Internet Protocol address is returned; wherein the received Internet Protocol address indicates an edge node in the content distribution network.
  • the computer program code used to perform the operations of the present disclosure may be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include object-oriented programming languages-such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware. Wherein, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first obtaining unit can also be described as "a unit that obtains at least two Internet Protocol addresses.”

Abstract

一种基于AI的通用智能家居方案自动化设计方法、装置及电子设备,属于人工智能技术领域,该方法包括:采集与智能设计相关的平面图纸作为有效图像样本,针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小;通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计;获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案,能够提高智能家居方案设计的效率。

Description

基于AI的通用智能家居方案自动化设计方法及装置 技术领域
本发明涉及人工智能技术领域,尤其涉及一种基于AI的通用智能家居方案自动化设计方法、装置及电子设备。
背景技术
由于智能家居行业发展过程中,产生了服务商专业技术能力参差不齐,以及服务商对利润的追求导致的国内外良莠不齐的产品交叉应用等等行业怪相,目前已经从行业之初的百花齐放、百家争鸣到行业现状的鱼龙混杂、鱼目混珠,其直接后果是业主难于选择真正实用且有效的方案,甚至于被劣质产品所诱导,被服务商专业程度不足所伤害,间接的后果将导致大批用户对智能家居行业的信任度大幅下降直至行业发展受阻。
由于专业的智能家居产品有一定的门槛,对于相对业余的装饰设计师来说,设计出针对性的方案,成功率很低;由于门槛较高是个通病,业主的盲目或盲从选型,也是一种普遍现象,最后花了一定代价,并不了了之,也会对于智能家居行业的规范程度不够等现象失去原有的信心。
发明内容
有鉴于此,本发明实施例提供一种基于AI的通用智能家居方案自动化设计方法、装置及电子设备,至少部分解决现有技术中存在的问题。
第一方面,本发明实施例提供的一种基于AI的通用智能家居方案自动化设计方法,包括:
采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;
针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征 点检测、目标检测相关的参数;
通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案。
根据本公开实施例的一种具体实现方式,所述AI识别内容包括室内平面图的图纸或图片。
根据本公开实施例的一种具体实现方式,AI自动化设计智能家居方案,包括智能家居系统的点位设计、管线设计。
根据本公开实施例的一种具体实现方式,所述自动化设计方法利用AI完成智能家居方案的自动化设备数量统计、选型列表输出。
根据本公开实施例的一种具体实现方式,所述自动化设计方法利用AI自动化生成订单。
根据本公开实施例的一种具体实现方式,所述自动化设计方法利用AI完成从产品选型到订单完成直至用户端上线,全程溯源,并提供在线AI服务。
根据本公开实施例的一种具体实现方式,所述AI服务包括且不仅限于完成唯一标识认证、设备状态反馈、故障代码提示、远程复位、质保期内外确认、远程运维以及超级便利售后。
根据本公开实施例的一种具体实现方式,所述根据用户在客户端选型的确认,生成通用智能化家居设计方案,包括:
从产品选型、订单确认、交易完成、设备安装完成直到用户端上线,全程溯源机制建立;
完成唯一标识认证:根据设备联网的唯一标识,线上线下统一的数据库建立;
设备状态反馈:每个设备的状态检测,分主动检测和被动检测,其中主动检测为远程分时分段读取状态,被动检测为状态改变,自动上传至系统更新;
故障代码提示:建立设备无法连接、连接不稳定、部分功能失灵等等故障 代码编号集群,进行实时更新、上传、下载等等;
远程复位:对于属于复位可解决的故障问题,可以远程复位解决;
质保期内外确认:设备溯源机制,比对数据库中设备的是否过保问题,来解决保内保外是否收费的问题;
远程运维:根据故障代码,远程诊断,亦可线上线下会诊;
超级便利售后:可根据诊断结果实现一次维护或更换服务。
第二方面,本发明实施例提供了一种基于AI的通用智能家居方案自动化设计装置,包括:
获取模块,用于采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;
建立模块,用于针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征点检测、目标检测相关的参数;
生成模块,用于通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
执行模块,用于获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案。
第三方面,本发明实施例还提供了一种电子设备,该电子设备包括:
至少一个处理器;以及,
与该至少一个处理器通信连接的存储器;其中,
该存储器存储有可被该至少一个处理器执行的指令,该指令被该至少一个处理器执行,以使该至少一个处理器能够执行前述任第一方面或第一方面的任一实现方式中的基于AI的通用智能家居方案自动化设计方法。
第四方面,本发明实施例还提供了一种非暂态计算机可读存储介质,该非 暂态计算机可读存储介质存储计算机指令,该计算机指令用于使该计算机执行前述第一方面或第一方面的任一实现方式中的基于AI的通用智能家居方案自动化设计方法。
第五方面,本发明实施例还提供了一种计算机程序产品,该计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序,该计算机程序包括程序指令,当该程序指令被计算机执行时,使该计算机执行前述第一方面或第一方面的任一实现方式中的基于AI的通用智能家居方案自动化设计方法。
本发明实施例中的基于AI的通用智能家居方案自动化设计方案,包括采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征点检测、目标检测相关的参数;通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案,方案提供了智能家居自动化设计的效率。
附图说明
为了更清楚地说明本发明实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其它的附图。
图1为本发明实施例提供的一种基于AI的通用智能家居方案自动化设计流程示意图;
图2为本发明实施例提供的一种基于AI的通用智能家居方案设计示意图;
图3为本发明实施例提供的另一种基于AI的通用智能家居方案设计示意图;
图4为本发明实施例提供的另一种基于AI的通用智能家居方案自动化设计流程示意图;
图5为本发明实施例提供的基于AI的通用智能家居方案自动化设计装置结构示意图;
图6为本发明实施例提供的电子设备示意图。
具体实施方式
下面结合附图对本发明实施例进行详细描述。
以下通过特定的具体实例说明本公开的实施方式,本领域技术人员可由本说明书所揭露的内容轻易地了解本公开的其他优点与功效。显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。本公开还可以通过另外不同的具体实施方式加以实施或应用,本说明书中的各项细节也可以基于不同观点与应用,在没有背离本公开的精神下进行各种修饰或改变。需说明的是,在不冲突的情况下,以下实施例及实施例中的特征可以相互组合。基于本公开中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。
需要说明的是,下文描述在所附权利要求书的范围内的实施例的各种方面。应显而易见,本文中所描述的方面可体现于广泛多种形式中,且本文中所描述的任何特定结构及/或功能仅为说明性的。基于本公开,所属领域的技术人员应了解,本文中所描述的一个方面可与任何其它方面独立地实施,且可以各种方式组合这些方面中的两者或两者以上。举例来说,可使用本文中所阐述的任何数目个方面来实施设备及/或实践方法。另外,可使用除了本文中所阐述的方面中的一或多者之外的其它结构及/或功能性实施此设备及/或实践此方法。
还需要说明的是,以下实施例中所提供的图示仅以示意方式说明本公开的基本构想,图式中仅显示与本公开中有关的组件而非按照实际实施时的组件数目、形状及尺寸绘制,其实际实施时各组件的型态、数量及比例可为一种随意 的改变,且其组件布局型态也可能更为复杂。
另外,在以下描述中,提供具体细节是为了便于透彻理解实例。然而,所属领域的技术人员将理解,可在没有这些特定细节的情况下实践所述方面。
本公开实施例提供一种基于AI的通用智能家居方案自动化设计方法。本实施例提供的基于AI的通用智能家居方案自动化设计方法可以由一计算装置来执行,该计算装置可以实现为软件,或者实现为软件和硬件的组合,该计算装置可以集成设置在服务器、终端设备等中。
参见图1、图2、图3及图4,本发明实施例提供的一种基于AI的通用智能家居方案自动化设计方法,包括如下步骤:
S101,采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;
S102,针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征点检测、目标检测相关的参数;
S103,通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
S104,获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案。
在实现步骤S101~S104的过程中,可以采集现有市场上智能家居系统设计前后的装饰平面图纸(或由平面图纸为内容生成的对照图片,下称图片),不断获得有效数据为样本,通过相关算法开展CV(计算机视觉,Computer vision)方面的深度学习:输入一个有效的智能家居方案图像,可以是较高分辨率jpg图片,也可以是装饰平面图生成的PDF文件,亦可为DWG的CAD文件,然后输出索引,并进行标签;不断训练和验证本引擎所采用的CNN(卷积,Convolutional Neural Network)神经网络系统,并通过超参数调试、正则化以及优化方法来改 善深层神经网络;经过CV边缘检测(Edge detection example)、卷积填充(padding)、卷积步长(Strided convolutions)、三维卷积(Convolutions over volumes)、卷积神经网络的拟合以及“避免过拟合”等等过程。
除了卷积层的参数共享和稀疏连接之外,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,并逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位(Object localization)、特征点检测(Landmark detection)、目标检测(Object detection)等重要参数;
上述实践过程通过Python语言编程实现图纸(或图片)的有效识别,并智能添加数据库的备选产品图标并缩放至合适大小,并生成点位设计等;系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
通过系统引擎将不断优化算法,减少计算时间,提升用户体验感;
系统将根据客户端选型的确认,随之完成订单生产,并给出交易完成后的一系列后续服务,主要包括:
(1)从产品选型、订单确认、交易完成、设备安装完成直到用户端上线,全程溯源机制建立;
(2)完成唯一标识认证:根据设备联网的的唯一标识,线上线下统一的数据库建立;
(3)设备状态反馈:每个设备的状态检测,分主动检测和被动检测,其中主动检测为远程分时分段读取状态,被动检测为状态改变,自动上传至系统更新;
(4)故障代码提示:建立设备无法连接、连接不稳定、部分功能失灵等等故障代码编号集群,进行实时更新、上传、下载等等;
(5)远程复位:若是属于复位可解决的故障问题,可以远程复位解决;
(6)质保期内外确认:设备溯源机制,比对数据库中设备的是否过保问题,来解决保内保外是否收费的问题;
(7)远程运维:根据故障代码,远程诊断,亦可线上线下会诊;
(8)超级便利售后:可根据诊断结果实现一次维护或更换服务。
根据本公开实施例的一种具体实现方式,所述AI识别内容包括室内平面图 的图纸或图片。
根据本公开实施例的一种具体实现方式,AI自动化设计智能家居方案,包括智能家居系统的点位设计、管线设计。
根据本公开实施例的一种具体实现方式,所述自动化设计方法利用AI完成智能家居方案的自动化设备数量统计、选型列表输出。
根据本公开实施例的一种具体实现方式,所述自动化设计方法利用AI自动化生成订单。
根据本公开实施例的一种具体实现方式,所述自动化设计方法利用AI完成从产品选型到订单完成直至用户端上线,全程溯源,并提供在线AI服务。
根据本公开实施例的一种具体实现方式,所述AI服务包括且不仅限于完成唯一标识认证、设备状态反馈、故障代码提示、远程复位、质保期内外确认、远程运维以及超级便利售后。
根据本公开实施例的一种具体实现方式,所述根据用户在客户端选型的确认,生成通用智能化家居设计方案,包括:
从产品选型、订单确认、交易完成、设备安装完成直到用户端上线,全程溯源机制建立;
完成唯一标识认证:根据设备联网的唯一标识,线上线下统一的数据库建立;
设备状态反馈:每个设备的状态检测,分主动检测和被动检测,其中主动检测为远程分时分段读取状态,被动检测为状态改变,自动上传至系统更新;
故障代码提示:建立设备无法连接、连接不稳定、部分功能失灵等等故障代码编号集群,进行实时更新、上传、下载等等;
远程复位:对于属于复位可解决的故障问题,可以远程复位解决;
质保期内外确认:设备溯源机制,比对数据库中设备的是否过保问题,来解决保内保外是否收费的问题;
远程运维:根据故障代码,远程诊断,亦可线上线下会诊;
超级便利售后:可根据诊断结果实现一次维护或更换服务。
与上述方法实施例相对应,参见图5,本发明实施例提供了一种基于AI的通用智能家居方案自动化设计装置50,包括:
获取模块501,用于采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;
建立模块502,用于针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征点检测、目标检测相关的参数;
生成模块503,用于通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
执行模块504,用于获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案。
参见图6,本发明实施例还提供了一种电子设备60,该电子设备包括:
至少一个处理器;以及,
与该至少一个处理器通信连接的存储器;其中,
该存储器存储有可被该至少一个处理器执行的指令,该指令被该至少一个处理器执行,以使该至少一个处理器能够执行前述方法实施例中基于AI的通用智能家居方案自动化设计方法。
本发明实施例还提供了一种非暂态计算机可读存储介质,该非暂态计算机可读存储介质存储计算机指令,该计算机指令用于使该计算机执行前述方法实施例中。
本发明实施例还提供了一种计算机程序产品,该计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序,该计算机程序包括程序指令,当该程序指令被计算机执行时,使该计算机执行前述方法实施例中的基于AI的通 用智能家居方案自动化设计方法。
图5所示装置可以执行图1-4所示实施例的方法,本实施例未详细描述的部分,可参考对图1-4所示实施例的相关说明。在此不再赘述。
下面参考图6,其示出了适于用来实现本公开实施例的电子设备60的结构示意图。本公开实施例中的电子设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图6所示,电子设备60可以包括处理装置(例如中央处理器、图形处理器等)601,其可以根据存储在只读存储器(ROM)602中的程序或者从存储装置608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中,还存储有电子设备60操作所需的各种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常,以下装置可以连接至I/O接口605:包括例如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等的输入装置606;包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607;包括例如磁带、硬盘等的存储装置608;以及通信装置609。通信装置609可以允许电子设备60与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的电子设备60,但是应理解的是,并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示 的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置609从网络上被下载和安装,或者从存储装置608被安装,或者从ROM 602被安装。在该计算机程序被处理装置601执行时,执行本公开实施例的方法中限定的上述功能。
需要说明的是,本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备:获取至少两个网际协议地址;向节点评价设备发送包括所述至少两个网际协议地址的节点评价请求,其中,所述节点评价设备从所述至少两个网际协议地址中,选取网际协议地址并返回;接收所述节点评价设备返回的网际协议地址;其中,所获取的网际协议地址指示内 容分发网络中的边缘节点。
或者,上述计算机可读介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备:接收包括至少两个网际协议地址的节点评价请求;从所述至少两个网际协议地址中,选取网际协议地址;返回选取出的网际协议地址;其中,接收到的网际协议地址指示内容分发网络中的边缘节点。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码,上述程序设计语言包括面向对象的程序设计语言-诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言-诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)-连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图,图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定,例如,第一获取单元还可以被描述为“获取至少两个网际协议地址 的单元”。
应当理解,本发明的各部分可以用硬件、软件、固件或它们的组合来实现。
以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到的变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应以权利要求的保护范围为准。

Claims (11)

  1. 一种基于AI的通用智能家居方案自动化设计方法,其特征在于,包括:
    采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;
    针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征点检测、目标检测相关的参数;
    通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
    获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案。
  2. 根据权利要求1所述的方法,其特征在于,所述AI识别内容包括室内平面图的图纸或图片。
  3. 根据权利要求1所述的方法,其特征在于,AI自动化设计智能家居方案,包括智能家居系统的点位设计、管线设计。
  4. 根据权利要求1所述的方法,其特征在于,所述自动化设计方法利用AI完成智能家居方案的自动化设备数量统计、选型列表输出。
  5. 根据权利要求1所述的方法,其特征在于,所述自动化设计方法利用AI自动化生成订单。
  6. 根据权利要求1所述的方法,其特征在于,所述自动化设计方法利用AI完成从产品选型到订单完成直至用户端上线,全程溯源,并提供在线AI服务。
  7. 根据权利要求1所述的方法,其特征在于,所述AI服务包括且不仅限于完成唯一标识认证、设备状态反馈、故障代码提示、远程复位、质保期内外确认、远程运维以及超级便利售后。
  8. 根据权利要求1所述的方法,其特征在于,所述根据用户在客户端选型的确认,生成通用智能化家居设计方案,包括:
    从产品选型、订单确认、交易完成、设备安装完成直到用户端上线,全程溯源机制建立;
    完成唯一标识认证:根据设备联网的唯一标识,线上线下统一的数据库建立;
    设备状态反馈:每个设备的状态检测,分主动检测和被动检测,其中主动检测为远程分时分段读取状态,被动检测为状态改变,自动上传至系统更新;
    故障代码提示:建立设备无法连接、连接不稳定、部分功能失灵等等故障代码编号集群,进行实时更新、上传、下载等等;
    远程复位:对于属于复位可解决的故障问题,可以远程复位解决;
    质保期内外确认:设备溯源机制,比对数据库中设备的是否过保问题,来解决保内保外是否收费的问题;
    远程运维:根据故障代码,远程诊断,亦可线上线下会诊;
    超级便利售后:可根据诊断结果实现一次维护或更换服务。
  9. 一种基于AI的通用智能家居方案自动化设计装置,其特征在于,包括:
    获取模块,用于采集与智能设计相关的平面图纸作为有效图像样本,以便于基于引擎算法对所述图像样本进行深度学习,训练和验证所述引擎所采用的神经网络系统,并通过超参数调试、正则化以及优化方法来改善所述神经网络系统;
    建立模块,用于针对所述神经网络系统,建立卷积层的参数共享和稀疏连接之后,使用池化层来缩减模型的大小,提高计算速度,同时提高所提取特征的鲁棒性,逐步完成全卷积神经网络的构造模块建立,并最终完成设计所需的目标定位、特征点检测、目标检测相关的参数;
    生成模块,用于通过Python语言编程实现针对平面图纸的有效识别,智能添加数据库的备选产品图标并缩放至合适大小,生成点位设计,系统同步输出标记的设备数量、品牌和型号所生成的格式化清单;
    执行模块,用于获取用户在客户端设置的输入需求,并根据用户在客户端选型的确认,生成通用智能化家居设计方案。
  10. 一种电子设备,其特征在于,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前述任一权利要求1-8所述的基于AI的通用智能家居方案自动化设计方法。
  11. 一种非暂态计算机可读存储介质,该非暂态计算机可读存储介质存储计算机指令,该计算机指令用于使该计算机执行前述任一权利要求1-8所述的基于AI的通用智能家居方案自动化设计方法。
PCT/CN2020/087238 2020-04-27 2020-04-27 基于ai的通用智能家居方案自动化设计方法及装置 WO2021217340A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/087238 WO2021217340A1 (zh) 2020-04-27 2020-04-27 基于ai的通用智能家居方案自动化设计方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/087238 WO2021217340A1 (zh) 2020-04-27 2020-04-27 基于ai的通用智能家居方案自动化设计方法及装置

Publications (1)

Publication Number Publication Date
WO2021217340A1 true WO2021217340A1 (zh) 2021-11-04

Family

ID=78373872

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/087238 WO2021217340A1 (zh) 2020-04-27 2020-04-27 基于ai的通用智能家居方案自动化设计方法及装置

Country Status (1)

Country Link
WO (1) WO2021217340A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081087A (zh) * 2022-07-22 2022-09-20 深圳装速配科技有限公司 基于物联网的装修云设计方法、装置、设备及存储介质
CN115221207A (zh) * 2022-06-21 2022-10-21 广州极点三维信息科技有限公司 一种智能家居方案设计方法、系统、装置及存储介质

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107330437A (zh) * 2017-07-03 2017-11-07 贵州大学 基于卷积神经网络目标实时检测模型的特征提取方法
CN108197632A (zh) * 2017-12-04 2018-06-22 马艺菲 基于卷积神经网络的分布式手绘画的识别系统及其方法
CN108710947A (zh) * 2018-04-10 2018-10-26 杭州善居科技有限公司 一种基于lstm的智能家居机器学习系统设计方法
CN108984904A (zh) * 2018-07-17 2018-12-11 北京理工大学 一种基于深度神经网络的家居设计方法
CN109299386A (zh) * 2018-11-12 2019-02-01 北京航天智造科技发展有限公司 一种家具行业设计师资源智能检索匹配方法和系统
CN110059690A (zh) * 2019-03-28 2019-07-26 广州智方信息科技有限公司 基于深度卷积神经网络的户型图语义自动分析方法及系统
CN110059750A (zh) * 2019-04-17 2019-07-26 广东三维家信息科技有限公司 户型形状识别方法、装置和设备
CN110175355A (zh) * 2019-04-19 2019-08-27 特斯联(北京)科技有限公司 一种基于机器学习的建筑匹配方法及装置
CN110197225A (zh) * 2019-05-28 2019-09-03 广东三维家信息科技有限公司 基于深度学习的户型空间匹配方法和系统
CN110826135A (zh) * 2019-11-05 2020-02-21 广东博智林机器人有限公司 家居排布方法、装置、神经网络构建方法及存储介质
CN110969137A (zh) * 2019-12-10 2020-04-07 杭州群核信息技术有限公司 家居图像描述生成方法、装置、系统及存储介质
US20200125945A1 (en) * 2018-10-18 2020-04-23 Drvision Technologies Llc Automated hyper-parameterization for image-based deep model learning

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107330437A (zh) * 2017-07-03 2017-11-07 贵州大学 基于卷积神经网络目标实时检测模型的特征提取方法
CN108197632A (zh) * 2017-12-04 2018-06-22 马艺菲 基于卷积神经网络的分布式手绘画的识别系统及其方法
CN108710947A (zh) * 2018-04-10 2018-10-26 杭州善居科技有限公司 一种基于lstm的智能家居机器学习系统设计方法
CN108984904A (zh) * 2018-07-17 2018-12-11 北京理工大学 一种基于深度神经网络的家居设计方法
US20200125945A1 (en) * 2018-10-18 2020-04-23 Drvision Technologies Llc Automated hyper-parameterization for image-based deep model learning
CN109299386A (zh) * 2018-11-12 2019-02-01 北京航天智造科技发展有限公司 一种家具行业设计师资源智能检索匹配方法和系统
CN110059690A (zh) * 2019-03-28 2019-07-26 广州智方信息科技有限公司 基于深度卷积神经网络的户型图语义自动分析方法及系统
CN110059750A (zh) * 2019-04-17 2019-07-26 广东三维家信息科技有限公司 户型形状识别方法、装置和设备
CN110175355A (zh) * 2019-04-19 2019-08-27 特斯联(北京)科技有限公司 一种基于机器学习的建筑匹配方法及装置
CN110197225A (zh) * 2019-05-28 2019-09-03 广东三维家信息科技有限公司 基于深度学习的户型空间匹配方法和系统
CN110826135A (zh) * 2019-11-05 2020-02-21 广东博智林机器人有限公司 家居排布方法、装置、神经网络构建方法及存储介质
CN110969137A (zh) * 2019-12-10 2020-04-07 杭州群核信息技术有限公司 家居图像描述生成方法、装置、系统及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115221207A (zh) * 2022-06-21 2022-10-21 广州极点三维信息科技有限公司 一种智能家居方案设计方法、系统、装置及存储介质
CN115081087A (zh) * 2022-07-22 2022-09-20 深圳装速配科技有限公司 基于物联网的装修云设计方法、装置、设备及存储介质

Similar Documents

Publication Publication Date Title
JP7043512B2 (ja) パイプ漏れを予測する新規な自律的人工知能システム
US11093370B1 (en) Impact analysis for software testing
US10938826B2 (en) Intelligent device security
WO2020143557A1 (zh) 用于显示信息的方法和装置
WO2021217340A1 (zh) 基于ai的通用智能家居方案自动化设计方法及装置
US11568242B2 (en) Optimization framework for real-time rendering of media using machine learning techniques
US20220004366A1 (en) Advanced software development application methods, systems, and computer readable medium
CN112597047A (zh) 测试方法、装置、电子设备和计算机可读介质
CN107885661A (zh) 移动应用的终端兼容性测试方法和系统、设备、介质
CN110765752B (zh) 试题的生成方法、装置、电子设备及计算机可读存储介质
CN111738316A (zh) 零样本学习的图像分类方法、装置及电子设备
CN111612135B (zh) 用于信息交互的方法和装置
CN113392018B (zh) 流量分发方法、装置、存储介质及电子设备
JP7216757B2 (ja) 情報を取得するための方法及び装置
KR102151756B1 (ko) 작업자 관리 및 중개 방법 및 장치
US10650415B2 (en) Method and system for registering link information to content
CN110069195B (zh) 图像拖拽变形方法和装置
WO2023179038A1 (zh) 数据标注的方法、ai开发平台、计算设备集群和存储介质
CN111562749A (zh) 基于ai的通用智能家居方案自动化设计方法及装置
CN116258911A (zh) 图像分类模型的训练方法、装置、设备及存储介质
CN113255819B (zh) 用于识别信息的方法和装置
US10180822B2 (en) Development environment for real-time application development
CN111680754B (zh) 图像分类方法、装置、电子设备及计算机可读存储介质
CN115310582A (zh) 用于训练神经网络模型的方法和装置
CN113808134A (zh) 油罐布局信息生成方法、装置、电子设备、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: 20933601

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: 20933601

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20933601

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 060623)

122 Ep: pct application non-entry in european phase

Ref document number: 20933601

Country of ref document: EP

Kind code of ref document: A1