WO2023207170A1 - 洗涤程序的推荐方法及装置、存储介质及电子装置 - Google Patents

洗涤程序的推荐方法及装置、存储介质及电子装置 Download PDF

Info

Publication number
WO2023207170A1
WO2023207170A1 PCT/CN2022/141689 CN2022141689W WO2023207170A1 WO 2023207170 A1 WO2023207170 A1 WO 2023207170A1 CN 2022141689 W CN2022141689 W CN 2022141689W WO 2023207170 A1 WO2023207170 A1 WO 2023207170A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
feature vector
washing machine
washing
recommended
Prior art date
Application number
PCT/CN2022/141689
Other languages
English (en)
French (fr)
Inventor
高扬
Original Assignee
青岛海尔科技有限公司
海尔智家股份有限公司
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 青岛海尔科技有限公司, 海尔智家股份有限公司 filed Critical 青岛海尔科技有限公司
Publication of WO2023207170A1 publication Critical patent/WO2023207170A1/zh

Links

Images

Classifications

    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F33/00—Control of operations performed in washing machines or washer-dryers 
    • D06F33/30—Control of washing machines characterised by the purpose or target of the control 
    • D06F33/32—Control of operational steps, e.g. optimisation or improvement of operational steps depending on the condition of the laundry
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
    • D06F34/04—Signal transfer or data transmission arrangements
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
    • D06F34/14—Arrangements for detecting or measuring specific parameters
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F2103/00—Parameters monitored or detected for the control of domestic laundry washing machines, washer-dryers or laundry dryers
    • D06F2103/02—Characteristics of laundry or load
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F2103/00—Parameters monitored or detected for the control of domestic laundry washing machines, washer-dryers or laundry dryers
    • D06F2103/02—Characteristics of laundry or load
    • D06F2103/04—Quantity, e.g. weight or variation of weight
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F2103/00—Parameters monitored or detected for the control of domestic laundry washing machines, washer-dryers or laundry dryers
    • D06F2103/28—Air properties
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F2103/00—Parameters monitored or detected for the control of domestic laundry washing machines, washer-dryers or laundry dryers
    • D06F2103/28—Air properties
    • D06F2103/32—Temperature
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F2103/00—Parameters monitored or detected for the control of domestic laundry washing machines, washer-dryers or laundry dryers
    • D06F2103/28—Air properties
    • D06F2103/34—Humidity

Definitions

  • the present disclosure relates to the field of smart home technology, and specifically to a method and device for recommending a washing program, a storage medium and an electronic device.
  • a method for recommending a washing program including: when detecting that a washing machine is started, determining current feature data corresponding to the washing machine, wherein the current feature data is used to predict the washing machine.
  • the washing program of the washing machine determine a target feature vector through the current feature data, and determine a reference feature vector from the historical feature vector set of the washing machine based on the target feature vector; determine the washing machine's washing program based on the reference feature vector.
  • a washing program is recommended, and the recommended washing program is recommended to the target object through the washing machine.
  • a washing program recommendation device including: a first determination module configured to determine the current characteristic data corresponding to the washing machine when the startup of the washing machine is detected, Wherein, the current feature data is used to predict the washing program of the washing machine; the second determination module is configured to determine a target feature vector through the current feature data, and based on the target feature vector from the historical features of the washing machine A reference feature vector is determined in the vector set; a recommendation module is configured to determine the recommended washing program of the washing machine based on the reference feature vector, and recommend the recommended washing program to the target object through the washing machine.
  • a computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the above-mentioned washing program when running. Recommended method.
  • an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor performs the above-mentioned washing through the computer program. Recommended method of procedure.
  • Figure 1 is a schematic diagram of the hardware environment of an interaction method for smart devices according to an embodiment of the present disclosure
  • Figure 2 is a flow chart of a recommended method of a washing program according to an embodiment of the present disclosure
  • Figure 3 is a system framework diagram of a recommended method for a washing program according to an embodiment of the present disclosure
  • Figure 4 is a structural block diagram (1) of a recommended device for a washing program according to an embodiment of the present disclosure.
  • Figure 5 is a structural block diagram (2) of a recommended device for a washing program according to an embodiment of the present disclosure
  • Figure 6 is a structural block diagram of an optional electronic device according to an embodiment of the present disclosure.
  • an interaction method for smart home devices is provided.
  • the interaction method of smart home devices is widely used in whole-house intelligent digital control application scenarios such as smart home, smart home, smart home device ecology, and smart residence (Intelligence House) ecology.
  • the above smart home device interaction method can be applied to a hardware environment composed of a terminal device 102 and a server 104 as shown in FIG. 1 .
  • the server 104 is connected to the terminal device 102 through the network, and can be set to provide services (such as application services, etc.) for the terminal or the client installed on the terminal.
  • the database can be set up on the server or independently from the server. It is configured to provide data storage services for the server 104, cloud computing and/or edge computing services can be configured on the server or independently of the server, and it is configured to provide data computing services for the server 104.
  • the above-mentioned network may include but is not limited to at least one of the following: wired network, wireless network.
  • the above-mentioned wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, and local area network.
  • the above-mentioned wireless network may include at least one of the following: WIFI (Wireless Fidelity, Wireless Fidelity), Bluetooth.
  • the terminal device 102 may be, but is not limited to, a PC, a mobile phone, a tablet, a smart air conditioner, a smart hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing equipment, a smart dishwasher, or a smart projection device.
  • smart TV smart clothes drying rack, smart curtains, smart audio and video, smart sockets, smart audio, smart speakers, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, Smart air purification equipment, smart steamers, smart microwave ovens, smart kitchen appliances, smart purifiers, smart water dispensers, smart door locks, etc.
  • Figure 2 is a flow chart of a recommended method of washing procedures according to an embodiment of the present disclosure. The flow includes the following steps:
  • Step S202 when the startup of the washing machine is detected, determine the current characteristic data corresponding to the washing machine, where the current characteristic data is used to predict the washing program of the washing machine;
  • the technical solution of this embodiment can be applied in a cloud server (the cloud server includes the above-mentioned server 104).
  • the washing machine has an associated relationship with the cloud server. When the washing machine is started, it will report the current status to the cloud server. , such as usage time, geographical location, MAC address, etc.
  • determining the current characteristic data corresponding to the operating parameters of the washing machine can be achieved in the following manner:
  • Step S1 Determine the target time for starting the washing machine and the target geographical location of the washing machine
  • the cloud server can determine the time when the washing machine reports the current status as the target time.
  • the cloud server will save the corresponding relationship between the geographical location reported by the washing machine and the MAC address of the washing machine, and then the target geographical location of the washing machine can be determined based on the MAC address of the washing machine.
  • the target time is January 20, 2018, and the target geographical location is Beijing.
  • Step S2 Determine the climate parameters of the target geographical location at the target time, where the climate parameters include at least one of the following: temperature, humidity, and wind speed;
  • the cloud server can search the climate parameters at the target geographical location at the target time on the Internet. For example, search on the Internet for Beijing on January 20, 2018. climate parameters.
  • Step S3 Determine the laundry information of the laundry to be cleaned in the washing machine, where the laundry information includes at least one of the following: laundry type, laundry quantity.
  • Optional clothing types include but are not limited to: underwear, coats, sweaters, shirts, sweaters, etc.
  • determining the clothing information of the clothes to be cleaned in the washing machine can be achieved by: obtaining a target video sent by the washing machine; determining the information of the clothes to be cleaned in the washing machine through the target video. Clothing information.
  • the target video is a video collected by the image acquisition device of the washing machine when the target object is putting clothes into the washing machine.
  • the target object is a person, and the image collection device includes but is not limited to a camera.
  • the current characteristic data includes at least one of the following: the target time, the climate parameter, and the clothing information.
  • climate parameters also affect how clean your clothes are.
  • the above target time, climate parameters, and clothing information will affect the washing program of the washing machine to a certain extent.
  • Step S204 determine a target feature vector through the current feature data, and determine a reference feature vector from the historical feature vector set of the washing machine according to the target feature vector;
  • determining the target feature vector through the current feature data can be achieved in the following manner: normalizing the current feature data through preset rules to obtain normalized feature data. ; Determine a target feature vector through the normalized feature data, wherein the target feature vector is a one-dimensional vector, and the elements of the target feature vector are the normalized feature data.
  • the current characteristic data includes the target time and climate parameters, where the target time includes the month, week, and time; the climate parameters include temperature, humidity, and wind speed.
  • the working day converts Saturday and Sunday into 0, if it is an unknown state, convert it to 0.5; for the time, divide the hour by 24, if it is an unknown state, convert it to 0.5; for the month, divide the month by 12, if it is an unknown state, it is converted to 0.5; for the temperature, divide the temperature by 30, if it is an unknown state, it is converted to 0.5; for the humidity, it is converted to 0.5.
  • the humidity is divided by 100.
  • the target feature vector is (1, 0.3, 0.5, 1, 0.7, 0.5).
  • determining a reference feature vector from a historical feature vector set of the washing machine according to the target feature vector can be achieved in the following manner: determining the target feature vector and the historical feature vector set Target distance between each saved historical feature vector; historical feature vectors whose target distance is less than or equal to the preset distance are determined as reference feature vectors.
  • the distance between vectors can be determined using the Euclidean algorithm.
  • Step S206 Determine the recommended washing program of the washing machine according to the reference feature vector, and recommend the recommended washing program to the target object through the washing machine.
  • the recommended washing procedures include but are not limited to: standard washing, soaking washing, etc.
  • determining the recommended washing program of the washing machine based on the reference feature vector can be achieved in the following manner: when the reference feature vector includes a historical feature vector, the historical feature The historical washing program corresponding to the vector is determined as the recommended washing program of the washing machine; when the reference feature vector includes multiple historical feature vectors, the number of occurrences in the multiple historical washing programs corresponding to the multiple historical feature vectors is The most historical wash programs are used to determine the recommended wash program for the washing machine.
  • the feature data corresponding to the reference feature vector is relatively similar to the current feature data corresponding to the target feature vector, and the feature data corresponding to the reference feature vector can be used.
  • the selected washing program is used to predict the washing program that the user may choose based on the current characteristic data.
  • the historical washing program corresponding to the reference feature vector is determined as the recommended washing program. If there are multiple reference feature vectors, the historical washing program that appears the most frequently among the corresponding historical washing programs is selected as the recommended washing program. Washing program. Using the above technical solutions, the accuracy of prediction can be improved.
  • the current feature data corresponding to the washing machine is determined, the target feature vector is determined based on the current feature data, and the reference feature vector is determined from the historical feature vector set of the washing machine according to the target feature vector, and then the washing machine is determined based on the reference feature vector.
  • the recommended washing program that is to say, the washing program can be recommended to the user based on the user's historical usage, thereby improving the accuracy of the recommendation and solving the problem of low accuracy of the washing machine recommending washing programs to the user.
  • the target feature vector after recommending the recommended washing program to a target object through the washing machine, the target feature vector also needs to be added to the historical feature vector set; and a confirmation operation from the target object is received, wherein, The confirmation operation is used to confirm whether the washing machine executes the recommended washing program; when the target object confirms that the washing machine executes the recommended washing program, save the target feature vector and the recommended washing program. Correspondence; when the target object confirms that the washing machine does not execute the recommended washing program, receive the target washing program selected by the target object on the washing machine, and save the target feature vector and the target Correspondence between washing programs.
  • the recommended washing program is predicted by the cloud server based on the current feature data, and the user can determine whether to use the recommended washing program based on the actual situation. If the user selects the recommended washing program, the target feature vector is added to the history Feature vector collection, and establish the corresponding relationship between the target feature vector and the recommended washing program. If the user thinks that the cloud server's prediction is inaccurate, he can select the target washing program on the washing machine, and then the cloud server adds the target feature vector to the historical features. Vector collection, and establish the corresponding relationship between the target feature vector and the target washing program.
  • the user's real setting records will also be continuously recorded in the historical feature vector set. As the number of user uses continues to increase, the accuracy of the prediction through the target feature vector in the historical feature vector set will also increase. constant increase.
  • Figure 3 is a system framework diagram of a recommended method for a washing program according to an embodiment of the present disclosure.
  • the washing machine when the washing machine is turned on, it will report the current status to the cloud server, including but not Limited to using information such as time, location, MAC address, etc., while making recommendation requests.
  • the normalization module in the cloud server will normalize each necessary field after receiving the reported status data. Includes the following normalized content:
  • Week Convert working days to 1, Saturdays and Sundays to 0, and unknown status to 0.5.
  • Time hours/24, unknown status converted to 0.5.
  • Humidity Humidity/100, unknown status is converted to 0.5.
  • Wind speed Wind speed (level)/8, the unknown state is converted to 0.5.
  • the KNN search module searches for the above-mentioned vector v to be found in the historical vector library (equivalent to the above-mentioned historical feature vector set).
  • the specific search method is as follows:
  • Normalization Read out the usage records in the historical vector library, whose fields include week, time, month, temperature, humidity, wind speed, and usage program. Perform the same normalization process on the corresponding dimensions of week, time, month, temperature, humidity, and wind speed.
  • Voting Count all the found vectors and find the mode of the corresponding "user program”.
  • this embodiment uses features such as day of the week, time, month, temperature, humidity, wind speed, etc. that are used for preference recommendation, searches historical records in the KNN method, and recommends a recommendation method for personal preferences based on the majority. Then complex statistical machine learning problems are transformed into simple search problems. You can just reasonably normalize the input user description vector, and then search under the user index to get the maximum likelihood prediction value under a single prediction sample, thus greatly saving training time and reducing the amount of calculations. In the case of energy consumption, the user's personalized needs are modeled and predicted, so as to meet the personalized preference prediction of individual users in using the washing machine functions.
  • this embodiment abandons the use of classification algorithm models such as "decision tree” and “logistic regression” and instead uses the KNN search method to achieve prediction. Since no explicit training process is required, this method can achieve relatively accurate predictions with very limited consumption of computing resources. Moreover, in this process, the vector search function used is also an easy to implement method, so it has very obvious advantages in controlling landing risks and saving calculation costs.
  • the method according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is Better implementation.
  • the technical solution of the present disclosure can be embodied in the form of a software product in essence or that contributes to the existing technology.
  • the computer software product is stored in a storage medium (such as ROM/RAM, disk, CD), including several instructions to cause a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present disclosure.
  • This embodiment also provides a washing program recommendation device, which is configured to implement the above-mentioned embodiments and preferred implementations. What has already been described will not be described again.
  • the term "module” may be a combination of software and/or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
  • Figure 4 is a structural block diagram (1) of a recommended device for a washing program according to an embodiment of the present disclosure.
  • the device includes:
  • the first determination module 42 is configured to determine the current characteristic data corresponding to the washing machine when the startup of the washing machine is detected, wherein the current characteristic data is used to predict the washing program of the washing machine;
  • the second determination module 44 is configured to determine a target feature vector through the current feature data, and determine a reference feature vector from the historical feature vector set of the washing machine according to the target feature vector;
  • the recommendation module 46 is configured to determine the recommended washing program of the washing machine according to the reference feature vector, and recommend the recommended washing program to the target object through the washing machine.
  • the current feature data corresponding to the washing machine is determined, the target feature vector is determined based on the current feature data, and the reference feature vector is determined from the historical feature vector set of the washing machine according to the target feature vector, and then the washing machine is determined based on the reference feature vector.
  • the recommended washing program that is to say, the washing program can be recommended to the user based on the user's historical usage, thereby improving the accuracy of the recommendation and solving the problem of low accuracy of the washing machine recommending washing programs to the user.
  • the first determination module is further configured to determine the target time for starting the washing machine and the target geographical location of the washing machine; determine the climate parameters of the target geographical location at the target time, wherein, the climate parameters include at least one of the following: temperature, humidity, wind speed; and clothing information for determining the clothes to be cleaned in the washing machine, where the clothing information includes at least one of the following: clothing type, clothing quantity; wherein , the current feature data includes at least one of the following: the target time, the target geographical location, and the clothing information.
  • the first determination module is further configured to obtain a target video sent by the washing machine, wherein the target video is a target object in the process of putting clothes into the washing machine, and the washing machine
  • the video collected by the image acquisition device; the clothing information of the clothes to be cleaned in the washing machine is determined through the target video.
  • the second determination module is further configured to normalize the current feature data through preset rules to obtain normalized feature data;
  • the target feature vector is determined by the feature data, wherein the target feature vector is a one-dimensional vector, and the elements of the target feature vector are the normalized feature data.
  • the second determination module is further configured to determine a target distance between the target feature vector and each historical feature vector saved in the historical feature vector set; Historical feature vectors that are less than or equal to the preset distance are determined as reference feature vectors.
  • the recommendation module includes: a determining unit configured to determine the historical washing program corresponding to the historical feature vector as the washing machine when the reference feature vector includes a historical feature vector.
  • Recommended washing program in the case where the reference feature vector includes multiple historical feature vectors, the historical washing program with the most occurrences among the multiple historical washing programs corresponding to the multiple historical feature vectors is used to determine the washing machine's recommended washing program. Recommended washing program.
  • Figure 5 is a structural block diagram (2) of a washing program recommendation device according to an embodiment of the present disclosure.
  • the device further includes: a storage module 48 configured to add the target feature vector to to the historical feature vector set; receiving a confirmation operation from a target object, where the confirmation operation is used to confirm whether the washing machine executes the recommended washing program; confirming at the target object that the washing machine executes the recommended washing program In the case of , save the corresponding relationship between the target feature vector and the recommended washing program; when the target object confirms that the washing machine does not execute the recommended washing program, receive the target object on the washing machine Select the target washing program, and save the corresponding relationship between the target feature vector and the target washing program.
  • Embodiments of the present disclosure also provide a computer-readable storage medium that stores a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.
  • the above-mentioned storage medium may be configured to store a computer program configured to perform the following steps:
  • S3 Determine the recommended washing program of the washing machine according to the reference feature vector, and recommend the recommended washing program to the target object through the washing machine.
  • an electronic device configured to implement the recommended method of the above-mentioned washing program is also provided.
  • the electronic device includes a memory 602 and a processor 604 .
  • the memory 602 A computer program is stored, and the processor 604 is configured to execute the steps in any of the above method embodiments through the computer program.
  • the above-mentioned electronic device may be located in at least one network device among multiple network devices of the computer network.
  • the structure shown in Figure 6 is only illustrative, and the electronic device can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a mobile Internet device (Mobile Internet Devices, MID), PAD and other terminal equipment.
  • FIG. 6 does not limit the structure of the above-mentioned electronic device.
  • the electronic device may also include more or fewer components (such as network interfaces, etc.) than shown in FIG. 6 , or have a different configuration than that shown in FIG. 6 .
  • the memory 602 may be configured to store software programs and modules, such as program instructions/modules corresponding to the recommended methods and devices for washing programs in the embodiments of the present disclosure.
  • the processor 604 runs the software programs and modules stored in the memory 602 , thereby performing various functional applications and data processing, that is, the recommended method to implement the above-mentioned washing program.
  • Memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
  • the memory 602 may further include memory located remotely relative to the processor 604, and these remote memories may be connected to the terminal through a network.
  • the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.
  • the above-mentioned memory 602 may include, but is not limited to, the first determination module 42, the second determination module 44, and the recommendation module 46 in the recommendation device including the above-mentioned washing program as shown in FIG. 6 .
  • it may also include, but is not limited to, other modular units in the recommended device for the above-mentioned washing program, which will not be described again in this example.
  • the above-mentioned transmission device 606 is configured to receive or send data via a network.
  • Specific examples of the above-mentioned network may include wired networks and wireless networks.
  • the transmission device 606 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through network cables to communicate with the Internet or a local area network.
  • the transmission device 606 is a radio frequency (Radio Frequency, RF) module, which is configured to communicate with the Internet wirelessly.
  • RF Radio Frequency
  • the above-mentioned electronic device also includes: a display 608 and a connection bus 610.
  • the connection bus 610 is configured to connect various module components in the above-mentioned electronic device.
  • the computer-readable storage medium may include but is not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM) , mobile hard disk, magnetic disk or optical disk and other media that can store computer programs.
  • ROM read-only memory
  • RAM random access memory
  • mobile hard disk magnetic disk or optical disk and other media that can store computer programs.
  • Embodiments of the present disclosure also provide an electronic device, including a memory and a processor.
  • a computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.
  • the above-mentioned processor can be configured to perform the following steps through a computer program:
  • S3 Determine the recommended washing program of the washing machine according to the reference feature vector, and recommend the recommended washing program to the target object through the washing machine.
  • the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.
  • modules or steps of the present disclosure can be implemented using general-purpose computing devices, and they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices. They may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by the computing device, and in some cases may be executed in a sequence different from that shown herein. Or the described steps can be implemented by making them into individual integrated circuit modules respectively, or by making multiple modules or steps among them into a single integrated circuit module. As such, the present disclosure is not limited to any specific combination of hardware and software.

Landscapes

  • Engineering & Computer Science (AREA)
  • Textile Engineering (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Control Of Washing Machine And Dryer (AREA)

Abstract

一种洗涤程序的推荐方法及装置、存储介质及电子装置，涉及智慧家庭技术领域，该洗涤程序的推荐方法包括：在检测到洗衣机启动的情况下，确定洗衣机对应的当前特征数据，其中，当前特征数据用于预测洗衣机的洗涤程序；通过当前特征数据确定目标特征向量，并根据目标特征向量从洗衣机的历史特征向量集合中确定参考特征向量；根据参考特征向量确定洗衣机的推荐洗涤程序，并通过洗衣机向目标对象推荐推荐洗涤程序。

Description

洗涤程序的推荐方法及装置、存储介质及电子装置
本公开要求于2022年04月25日提交中国专利局、申请号为202210441587.4、发明名称“洗涤程序的推荐方法及装置、存储介质及电子装置”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及智慧家庭技术领域，具体而言，涉及一种洗涤程序的推荐方法及装置、存储介质及电子装置。
背景技术
目前，现有的洗衣机对于功能的预测都是使用“决策树”、“逻辑回归”等分类器来解决。但“决策树”、“逻辑回归”都是采用抽样的全局性的用户使用历史数据进行训练，进而可以保障在处理全局性问题时的准确率问题，即在相同情形下，表现与众数一致的用户的行为是容易被预测对的。
然而事实并非如此，有大量的用户在使用洗衣机的时候有着自己的个性化需求和理解，因此洗涤时呈现出来的彼此间的不同很明显，也就是说，单一用户对于洗衣机功能的偏好却相对集中，这使得单纯依赖预设功能设置默认值，或者根据全体用户的使用众数统计出来的功能不能有针对性地满足某个用户个体的偏好需求。
针对相关技术，洗衣机为用户推荐洗涤程序的准确率较低的问题，目前尚未提出有效的解决方案。
因此，有必要对相关技术予以改良以克服相关技术中的所述缺陷。
发明内容
根据本公开实施例的一方面，提供一种洗涤程序的推荐方法，包括：在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前 特征数据用于预测所述洗衣机的洗涤程序；通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
根据本公开实施例的另一方面，还提供了一种洗涤程序的推荐装置，包括：第一确定模块，被设置为在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；第二确定模块，被设置为通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；推荐模块，被设置为根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
根据本公开实施例的又一方面，还提供了一种计算机可读的存储介质，该计算机可读的存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述洗涤程序的推荐方法。
根据本公开实施例的又一方面，还提供了一种电子装置，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，上述处理器通过计算机程序执行上述洗涤程序的推荐方法。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是根据本公开实施例的一种智能设备的交互方法的硬件环境示意图；
图2是根据本公开实施例的洗涤程序的推荐方法的流程图；
图3是根据本公开实施例的洗涤程序的推荐方法的系统框架图；
图4是根据本公开实施例的洗涤程序的推荐装置的结构框图(一)。
图5是根据本公开实施例的洗涤程序的推荐装置的结构框图(二)；
图6是根据本公开实施例的一种可选的电子装置的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本公开方案，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分的实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本公开保护的范围。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
根据本公开实施例的一个方面，提供了一种智能家居设备的交互方法。该智能家居设备的交互方法广泛应用于智慧家庭(Smart Home)、智能家居、智能家用设备生态、智慧住宅(Intelligence House)生态等全屋智能数字化控制应用场景。可选地，在本实施例中，上述智能家居设备的交互方法可以应用于如图1所示的由终端设备102和服务器104所构成的硬件环境中。如图1所示，服务器104 通过网络与终端设备102进行连接，可被设置为为终端或终端上安装的客户端提供服务(如应用服务等)，可在服务器上或独立于服务器设置数据库，被设置为为服务器104提供数据存储服务，可在服务器上或独立于服务器配置云计算和/或边缘计算服务，被设置为为服务器104提供数据运算服务。
上述网络可以包括但不限于以下至少之一：有线网络，无线网络。上述有线网络可以包括但不限于以下至少之一：广域网，城域网，局域网，上述无线网络可以包括但不限于以下至少之一：WIFI(Wireless Fidelity，无线保真)，蓝牙。终端设备102可以并不限定于为PC、手机、平板电脑、智能空调、智能烟机、智能冰箱、智能烤箱、智能炉灶、智能洗衣机、智能热水器、智能洗涤设备、智能洗碗机、智能投影设备、智能电视、智能晾衣架、智能窗帘、智能影音、智能插座、智能音响、智能音箱、智能新风设备、智能厨卫设备、智能卫浴设备、智能扫地机器人、智能擦窗机器人、智能拖地机器人、智能空气净化设备、智能蒸箱、智能微波炉、智能厨宝、智能净化器、智能饮水机、智能门锁等。
为了解决上述问题，在本实施例中提供了一种洗涤程序的推荐方法，图2是根据本公开实施例的洗涤程序的推荐方法的流程图，该流程包括如下步骤：
步骤S202，在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；
作为一个可选的示例，本实施例的技术方案可以应用在云端服务器(云端服务器包括上述服务器104)中，洗衣机与云端服务器具有关联关系，进而洗衣机在启动的时候，会向云端服务器上报当前状态，例如使用时间，地理位置，MAC地址等。
在一个示例性的实施例中，确定所述洗衣机的运行参数所对应的当前特征数据，可以通过以下方式实现：
步骤S1：确定所述洗衣机启动的目标时刻与所述洗衣机的目标地理位置；
作为一个可选的示例，云端服务器可以将洗衣机上报当前状态的时间确定为目标时刻。由于洗衣机在注册时候，云端服务器会保存洗衣机上报的地理位置和 洗衣机的MAC地址对应的关系，进而可以根据洗衣机的MAC地址来确定洗衣机的目标地理位置。作为一个可选的示例，目标时刻为2018年1月20日，目标地理位置北京市。
步骤S2：确定所述目标地理位置在所述目标时刻的气候参数，其中，所述气候参数包括以下至少之一：温度、湿度、风速；
需要说明的是，由于知道了目标时刻和目标地理位置，进而云端服务器可以在互联网上搜索在目标地理位置在目标时刻的气候参数，例如，在互联网上搜索，北京市在2018年1月20日的气候参数。
步骤S3：确定所述洗衣机的待清洗衣物的衣物信息，其中，所述衣物信息包括以下至少之一：衣物类型，衣物数量。
可选的，衣物类型包括但不限于：内衣，外套，毛衣，衬衫，针织衫等。
在一个示例性的实施例中，确定所述洗衣机的待清洗衣物的衣物信息，可以通过以下方式实现：获取所述洗衣机发送的目标视频；通过所述目标视频确定所述洗衣机的待清洗衣物的衣物信息。需要说明的是，所述目标视频为目标对象在投放衣物至所述洗衣机的过程中，所述洗衣机的图像采集装置采集到的视频。可选的，所述目标对象为人，所述图像采集装置包括但不限于摄像头。
作为一个可选的示例，所述当前特征数据包括以下至少之一：所述目标时刻，所述气候参数，所述衣物信息。
需要说明的是，由于在工作日和非工作日，人们的生活习惯是不一样的，例如，在工作日的，用户的衣服相对干净，在非工作日，用户可能会外出出去玩，或者运动，进而衣物相对工作日而言相对脏一点。也就是说，目标时刻会影响衣服的干净程度。
进一步地，由于在温度高的时候，用户出汗可能会较多，湿度较大的情况下，衣服可能相对潮湿，风速较大的情况下，可能地面上的灰尘会被较多的吹到衣服上。也就是说，气候参数也会影响衣物的干净程度。
同时，由于衣物的不同，衣服对应的洗涤程序也是不相同的。
也就是说，上述目标时刻，气候参数，衣物信息会在一定程度在影响洗衣机对衣物的洗涤程序。
需要说明的是，作为一个可选的示例，上述S1-S2与上述步骤S3是异步执行的。
步骤S204，通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；
在一个示例性的实施例中，通过所述当前特征数据确定目标特征向量，可以通过以下方式实现：通过预设规则将所述当前特征数据进行归一化处理，得到归一化后的特征数据；通过所述归一化后的特征数据确定目标特征向量，其中，所述目标特征向量为一维向量，所述目标特征向量的元素为所述归一化后的特征数据。
为了更好的说明，以下进行具体说明，假设当前特征数据包括目标时刻与气候参数，其中，目标时刻包括月份，星期，时间；气候参数包括温度，湿度，风速。进而对于星期而言，将工作日转化为1，将周六日转化为0，如果是未知状态，则转化为0.5；对于时间而言，将小时除以24，如果是未知状态，则转化为0.5；对于月份而言，将月份除以12，如果是未知状态，则转化为0.5；对于温度而言，将温度除以30，如果是未知状态，则转化为0.5；对于湿度而言，将湿度除以100，如果是未知状态，则转化为0.5；对于风速：将风速的等级除以8，如果是未知状态，则转化为0.5，将上述六个维度归一化后作为一维向量的元素，得到目标特征向量。在一个示例性的实施例中，目标特征向量为(1，0.3，0.5，1，0.7，0.5)。
在一个示例性的实施例中，根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量，可以通过以下方式实现：确定所述目标特征向量与所述历史特征向量集合中保存的每个历史特征向量之间的目标距离；将所述目标距离小于或等于预设距离的历史特征向量确定为参考特征向量。
可选的，可以使用欧几里得算法来确定向量之间的距离。
步骤S206，根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
需要说明的是，推荐洗涤程序包括但不限于：标准洗，浸泡洗等。
在一个示例性的实施例中，根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，可以通过以下方式实现：在所述参考特征向量包括一个历史特征向量的情况下，将所述历史特征向量对应的历史洗涤程序确定为所述洗衣机的推荐洗涤程序；在所述参考特征向量包括多个历史特征向量的情况下，将所述多个历史特征向量对应的多个历史洗涤程序中出现次数最多的历史洗涤程序为确定所述洗衣机的推荐洗涤程序。
需要说明的是，由于参考特征向量与目标特征向量的距离较小，进而参考特征向量对应的特征数据与目标特征向量对应的当前特征数据较为相似，进而可以使用用户在参考特征向量对应的特征数据下选择的洗涤程序来预测用户在当前特征数据可能会选择的洗涤程序。
也就是说，如果参考特征向量只有一个，进而将参考特征向量对应的历史洗涤程序确定为推荐洗涤程序，如果有多个，那个就选取对应的历史洗涤程序中出现次数最多的历史洗涤程序作为推荐洗涤程序。采用上述技术方案，可以提高预测的准确度。
通过上述步骤，通过确定洗衣机对应的当前特征数据，并通过当前特征数据确定目标特征向量，并根据目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量，进而根据参考特征向量确定洗衣机的推荐洗涤程序，也就是说，可以通过用户的历史使用情况来为用户推荐洗涤程序，进而提高了推荐的准确率，解决了洗衣机为用户推荐洗涤程序的准确率较低的问题。
在一个示例性的实施例中，通过所述洗衣机向目标对象推荐所述推荐洗涤程序之后，还需要将所述目标特征向量添加至所述历史特征向量集合；接收目标对象的确认操作，其中，所述确认操作用于确认所述洗衣机是否执行所述推荐洗涤程序；在所述目标对象确认所述洗衣机执行所述推荐洗涤程序的情况下，保存所 述目标特征向量与所述推荐洗涤程序的对应关系；在所述目标对象确认所述洗衣机不执行所述推荐洗涤程序的情况下，接收所述目标对象在所述洗衣机上选择的目标洗涤程序，并保存所述目标特征向量与所述目标洗涤程序的对应关系。
需要说明的是，推荐洗涤程序是云端服务器根据当前特征数据预测的，进而用户可以根据实际情况来确定是否采用推荐洗涤程序，如果用户选择了推荐洗涤程序，则将目标特征向量添加至所述历史特征向量集合，并建立目标特征向量与推荐洗涤程序的对应关系，如果用户认为云端服务器预测的不准，则可以自己在洗衣机上选择目标的洗涤程序，进而云端服务器将目标特征向量添加至历史特征向量集合，并建立目标特征向量与目标洗涤程序的对应关系。采用上述技术方案，用户真实的设置记录也会被不断地记录在历史特征向量集合中，而随着用户使用的次数不断增加，通过目标特征向量在历史特征向量集合中查找预测的准确度也会不断上升。
显然，上述所描述的实施例仅仅是本公开一部分的实施例，而不是全部的实施例。为了更好的理解上述洗涤程序的推荐方法，以下结合实施例对上述过程进行说明，但不用于限定本公开实施例的技术方案，具体地：
在一个可选的实施例中，图3是根据本公开实施例的洗涤程序的推荐方法的系统框架图，如图3所示，洗衣机在开机时刻，会上报当前状态至云端服务器，包括但不限于使用时间、地点、MAC地址等信息，同时进行推荐请求。进而云端服务器中的归一化模块，会在收到上报状态的数据后对于其中的各必要字段进行归一化处理。包括以下归一化内容：
星期：将工作日转化为1，周六日转化为0，未知状态转化为0.5。
时间：小时/24，未知状态转化为0.5。
月份：月份/12，未知状态转化为0.5。
温度：温度/30，未知状态转化为0.5。
湿度：湿度/100，未知状态转化为0.5。
风速：风速(级)/8，未知状态转化为0.5。
并将上述6个维度归一化后的向量，作为待查找向量v(相当于上述实施例 中的目标特征向量)。
KNN搜索模块，对于上述待查找向量v，在历史向量库(相当于上述历史特征向量集合)中进行查找，具体查找方式如下：
归一化：将历史向量库中的使用记录读出，其字段包含星期、时间、月份、温度、湿度、风速、使用程序。将其中对应的星期、时间、月份、温度、湿度、风速这些维度进行相同的归一化处理。
查找：以待查找向量v为中心，在历史向量库中，以d为半径(例如，d＝0.52)，查找欧几里得距离小于等于d的所有向量。
投票：将查找出的所有向量进行统计，找出对应的“使用程序”的众数。
如果存在：则返回该使用程序的众数结果，如不存在则返回空值。
需要说明的是，用户真实的设置记录也会被不断地记录在历史向量库中，而随着用户使用的次数不断增加，KNN查找的准确度也会不断上升。
也就是说，本实施例将星期、时间、月份、温度、湿度、风速等用于偏好推荐的特征构成，以KNN方式查找历史记录，并根据众数推举个人使用偏好的推荐方法。进而将复杂的统计机器学习问题转化成为简单的查找问题。可以仅仅通过对于输入的用户描述向量进行合理的归一化，而后进行用户索引下的查找，得到某一次单一预测样本下的最大似然预测值，从而大大节省训练时间，并且在较低计算量能耗的情况下，对于用户的个性化需求进行建模和预测，从而满足个体用户在使用洗衣机功能上的个性化偏好预测。
此外，本实施例为了实现近似的预测目的，而摒弃使用“决策树”、“逻辑回归”之类的分类算法模型，转而使用KNN的查找方式来实现预测。由于不需要显式的训练过程，这种方式可以在非常有限的计算资源消耗的情况下，实现相对比较准确的预测目的。而且在这个过程中，所使用的向量查找功能也是一种易于实现的方式，因此对于落地风险的控制，计算成本的节省，有着非常明显的优点。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本公开的技术方 案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本公开各个实施例的方法。
在本实施例中还提供了一种洗涤程序的推荐装置，该装置被设置为实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的设备较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图4是根据本公开实施例的洗涤程序的推荐装置的结构框图(一)，该装置包括：
第一确定模块42，被设置为在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；
第二确定模块44，被设置为通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；
推荐模块46，被设置为根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
通过上述装置，通过确定洗衣机对应的当前特征数据，并通过当前特征数据确定目标特征向量，并根据目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量，进而根据参考特征向量确定洗衣机的推荐洗涤程序，也就是说，可以通过用户的历史使用情况来为用户推荐洗涤程序，进而提高了推荐的准确率，解决了洗衣机为用户推荐洗涤程序的准确率较低的问题。
在一个可选的实施例中，第一确定模块，还被设置为确定所述洗衣机启动的目标时刻与所述洗衣机的目标地理位置；确定所述目标地理位置在所述目标时刻的气候参数，其中，所述气候参数包括以下至少之一：温度、湿度、风速；以及确定所述洗衣机的待清洗衣物的衣物信息，其中，所述衣物信息包括以下至少之 一：衣物类型，衣物数量；其中，所述当前特征数据包括以下至少之一：所述目标时刻，所述目标地理位置，所述衣物信息。
在一个示例性的实施例中，第一确定模块，还被设置为获取所述洗衣机发送的目标视频，其中，所述目标视频为目标对象在投放衣物至所述洗衣机的过程中，所述洗衣机的图像采集装置采集到的视频；通过所述目标视频确定所述洗衣机的待清洗衣物的衣物信息。
在一个示例性的实施例中，第二确定模块，还被设置为通过预设规则将所述当前特征数据进行归一化处理，得到归一化后的特征数据；通过所述归一化后的特征数据确定目标特征向量，其中，所述目标特征向量为一维向量，所述目标特征向量的元素为所述归一化后的特征数据。
在一个示例性的实施例中，第二确定模块，还被设置为确定所述目标特征向量与所述历史特征向量集合中保存的每个历史特征向量之间的目标距离；将所述目标距离小于或等于预设距离的历史特征向量确定为参考特征向量。
在一个示例性的实施例中，推荐模块包括：确定单元，被设置为在所述参考特征向量包括一个历史特征向量的情况下，将所述历史特征向量对应的历史洗涤程序确定为所述洗衣机的推荐洗涤程序；在所述参考特征向量包括多个历史特征向量的情况下，将所述多个历史特征向量对应的多个历史洗涤程序中出现次数最多的历史洗涤程序为确定所述洗衣机的推荐洗涤程序。
图5是根据本公开实施例的洗涤程序的推荐装置的结构框图(二)，在一个示例性的实施例中，所述装置还包括：存储模块48，被设置为将所述目标特征向量添加至所述历史特征向量集合；接收目标对象的确认操作，其中，所述确认操作用于确认所述洗衣机是否执行所述推荐洗涤程序；在所述目标对象确认所述洗衣机执行所述推荐洗涤程序的情况下，保存所述目标特征向量与所述推荐洗涤程序的对应关系；在所述目标对象确认所述洗衣机不执行所述推荐洗涤程序的情况下，接收所述目标对象在所述洗衣机上选择的目标洗涤程序，并保存所述目标特征向量与所述目标洗涤程序的对应关系。
本公开的实施例还提供了一种计算机可读存储介质，该计算机可读存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
可选地，在本实施例中，上述存储介质可以被设置为存储被设置为执行以下步骤的计算机程序：
S1，在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；
S2，通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；
S3，根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
根据本公开实施例的又一个方面，还提供了一种被设置为实施上述洗涤程序的推荐方法的电子装置，如图6所示，该电子装置包括存储器602和处理器604，该存储器602中存储有计算机程序，该处理器604被设置为通过计算机程序执行上述任一项方法实施例中的步骤。
可选地，在本实施例中，上述电子装置可以位于计算机网络的多个网络设备中的至少一个网络设备。
可选地，本领域普通技术人员可以理解，图6所示的结构仅为示意，电子装置也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。图6其并不对上述电子装置的结构造成限定。例如，电子装置还可包括比图6中所示更多或者更少的组件(如网络接口等)，或者具有与图6所示不同的配置。
其中，存储器602可被设置为存储软件程序以及模块，如本公开实施例中的洗涤程序的推荐方法和装置对应的程序指令/模块，处理器604通过运行存储在存储器602内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的洗涤程序的推荐方法。存储器602可包括高速随机存储器，还可以包括非 易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器602可进一步包括相对于处理器604远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。作为一种示例，上述存储器602可以如图6所示的包括但不限于包括上述洗涤程序的推荐装置中的第一确定模块42、第二确定模块44，推荐模块46。
此外，还可以包括但不限于上述洗涤程序的推荐装置中的其他模块单元，本示例中不再赘述。
可选地，上述的传输装置606被设置为经由一个网络接收或者发送数据。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置606包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置606为射频(Radio Frequency，RF)模块，其被设置为通过无线方式与互联网进行通讯。
此外，上述电子装置还包括：显示器608和连接总线610，所述连接总线610被设置为连接上述电子装置中的各个模块部件。
在一个示例性实施例中，上述计算机可读存储介质可以包括但不限于：U盘、只读存储器(Read-Only Memory，简称为ROM)、随机存取存储器(Random Access Memory，简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的介质。
本实施例中的具体示例可以参考上述实施例及示例性实施方式中所描述的示例，本实施例在此不再赘述。
本公开的实施例还提供了一种电子装置，包括存储器和处理器，该存储器中存储有计算机程序，该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
可选地，在本实施例中，上述处理器可以被设置为通过计算机程序执行以下 步骤：
S1，在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；
S2，通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；
S3，根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
在一个示例性实施例中，上述电子装置还可以包括传输设备以及输入输出设备，其中，该传输设备和上述处理器连接，该输入输出设备和上述处理器连接。
本实施例中的具体示例可以参考上述实施例及示例性实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本公开的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本公开不限制于任何特定的硬件和软件结合。
以上所述仅是本公开的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本公开原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本公开的保护范围。

Claims (16)

  1. 一种洗涤程序的推荐方法，包括：
    在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；
    通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；
    根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
  2. 根据权利要求1所述的方法，其中，确定所述洗衣机的运行参数所对应的当前特征数据，包括：
    确定所述洗衣机启动的目标时刻与所述洗衣机的目标地理位置；
    确定所述目标地理位置在所述目标时刻的气候参数，其中，所述气候参数包括以下至少之一：温度、湿度、风速；以及
    确定所述洗衣机的待清洗衣物的衣物信息，其中，所述衣物信息包括以下至少之一：衣物类型，衣物数量；
    其中，所述当前特征数据包括以下至少之一：所述目标时刻，所述气候参数，所述衣物信息。
  3. 根据权利要求2所述的方法，其中，确定所述洗衣机的待清洗衣物的衣物信息，包括：
    获取所述洗衣机发送的目标视频，其中，所述目标视频为目标对象在投放衣物至所述洗衣机的过程中，所述洗衣机的图像采集装置采集到的视频；
    通过所述目标视频确定所述洗衣机的待清洗衣物的衣物信息。
  4. 根据权利要求1所述的方法，其中，通过所述当前特征数据确定目标特征向量， 包括：
    通过预设规则将所述当前特征数据进行归一化处理，得到归一化后的特征数据；
    通过所述归一化后的特征数据确定目标特征向量，其中，所述目标特征向量为一维向量，所述目标特征向量的元素为所述归一化后的特征数据。
  5. 根据权利要求1所述的方法，其中，根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量，包括：
    确定所述目标特征向量与所述历史特征向量集合中保存的每个历史特征向量之间的目标距离；
    将所述目标距离小于或等于预设距离的历史特征向量确定为参考特征向量。
  6. 根据权利要求1所述的方法，其中，根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，包括：
    在所述参考特征向量包括一个历史特征向量的情况下，将所述历史特征向量对应的历史洗涤程序确定为所述洗衣机的推荐洗涤程序；
    在所述参考特征向量包括多个历史特征向量的情况下，将所述多个历史特征向量对应的多个历史洗涤程序中出现次数最多的历史洗涤程序为确定所述洗衣机的推荐洗涤程序。
  7. 根据权利要求1所述的方法，其中，通过所述洗衣机向目标对象推荐所述推荐洗涤程序之后，所述方法还包括：
    将所述目标特征向量添加至所述历史特征向量集合；
    接收目标对象的确认操作，其中，所述确认操作用于确认所述洗衣机是否执行所述推荐洗涤程序；
    在所述目标对象确认所述洗衣机执行所述推荐洗涤程序的情况下，保存所 述目标特征向量与所述推荐洗涤程序的对应关系；
    在所述目标对象确认所述洗衣机不执行所述推荐洗涤程序的情况下，接收所述目标对象在所述洗衣机上选择的目标洗涤程序，并保存所述目标特征向量与所述目标洗涤程序的对应关系。
  8. 一种洗涤程序的推荐装置，包括：
    第一确定模块，被设置为在检测到洗衣机启动的情况下，确定所述洗衣机对应的当前特征数据，其中，所述当前特征数据用于预测所述洗衣机的洗涤程序；
    第二确定模块，被设置为通过所述当前特征数据确定目标特征向量，并根据所述目标特征向量从所述洗衣机的历史特征向量集合中确定参考特征向量；推荐模块，被设置为根据所述参考特征向量确定所述洗衣机的推荐洗涤程序，并通过所述洗衣机向目标对象推荐所述推荐洗涤程序。
  9. 根据权利要求8所述的装置，其中，所述第一确定模块，还被设置为确定所述洗衣机启动的目标时刻与所述洗衣机的目标地理位置；确定所述目标地理位置在所述目标时刻的气候参数，其中，所述气候参数包括以下至少之一：温度、湿度、风速；以及确定所述洗衣机的待清洗衣物的衣物信息，其中，所述衣物信息包括以下至少之一：衣物类型，衣物数量；其中，所述当前特征数据包括以下至少之一：所述目标时刻，所述目标地理位置，所述衣物信息。
  10. 根据权利要求9所述的装置，其中，所述第一确定模块，还被设置为获取所述洗衣机发送的目标视频，其中，所述目标视频为目标对象在投放衣物至所述洗衣机的过程中，所述洗衣机的图像采集装置采集到的视频；通过所述目标视频确定所述洗衣机的待清洗衣物的衣物信息。
  11. 根据权利要求8所述的装置，其中，所述第二确定模块，还被设置为通过预设规则将所述当前特征数据进行归一化处理，得到归一化后的特征数据；通过所述归一化后的特征数据确定目标特征向量，其中，所述目标特征向量为一维向量，所述目标特征向量的元素为所述归一化后的特征数据。
  12. 根据权利要求8所述的装置，其中，所述第二确定模块，还被设置为确定所述目标特征向量与所述历史特征向量集合中保存的每个历史特征向量之间的目标距离；将所述目标距离小于或等于预设距离的历史特征向量确定为参考特征向量。
  13. 根据权利要求8所述的装置，其中，所述推荐模块包括：确定单元，被设置为在所述参考特征向量包括一个历史特征向量的情况下，将所述历史特征向量对应的历史洗涤程序确定为所述洗衣机的推荐洗涤程序；在所述参考特征向量包括多个历史特征向量的情况下，将所述多个历史特征向量对应的多个历史洗涤程序中出现次数最多的历史洗涤程序为确定所述洗衣机的推荐洗涤程序。
  14. 根据权利要求8所述的装置，其中，所述装置还包括：存储模块，被设置为将所述目标特征向量添加至所述历史特征向量集合；接收目标对象的确认操作，其中，所述确认操作用于确认所述洗衣机是否执行所述推荐洗涤程序；在所述目标对象确认所述洗衣机执行所述推荐洗涤程序的情况下，保存所述目标特征向量与所述推荐洗涤程序的对应关系；在所述目标对象确认所述洗衣机不执行所述推荐洗涤程序的情况下，接收所述目标对象在所述洗衣机上选择的目标洗涤程序，并保存所述目标特征向量与所述目标洗涤程序的对应关系。
  15. 一种计算机可读的存储介质，所述计算机可读的存储介质存储有计算机程序，其中，所述计算机程序被设置为运行时执行权利要求1至7中任一项所述的方法。
  16. 一种电子装置，包括存储器和处理器，所述存储器中存储有计算机程序，所述处理器被设置为通过所述计算机程序执行权利要求1至7中任一项所述的方法。
PCT/CN2022/141689 2022-04-25 2022-12-23 洗涤程序的推荐方法及装置、存储介质及电子装置 WO2023207170A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210441587.4A CN114855416B (zh) 2022-04-25 2022-04-25 洗涤程序的推荐方法及装置、存储介质及电子装置
CN202210441587.4 2022-04-25

Publications (1)

Publication Number Publication Date
WO2023207170A1 true WO2023207170A1 (zh) 2023-11-02

Family

ID=82633876

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/141689 WO2023207170A1 (zh) 2022-04-25 2022-12-23 洗涤程序的推荐方法及装置、存储介质及电子装置

Country Status (2)

Country Link
CN (1) CN114855416B (zh)
WO (1) WO2023207170A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114855416B (zh) * 2022-04-25 2024-03-22 青岛海尔科技有限公司 洗涤程序的推荐方法及装置、存储介质及电子装置
CN117492379B (zh) * 2023-12-25 2024-04-26 珠海格力电器股份有限公司 一种电器设备功能推荐方法、装置和电子设备及电器设备

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109162065A (zh) * 2018-11-08 2019-01-08 珠海格力电器股份有限公司 洗衣机的控制方法、系统和洗衣机
WO2020082982A1 (zh) * 2018-10-23 2020-04-30 青岛海尔洗衣机有限公司 家用电器的程序推荐控制方法
EP3666954A1 (en) * 2018-12-14 2020-06-17 LG Electronics Inc. -1- Washing machine
CN111401306A (zh) * 2020-04-08 2020-07-10 青岛海尔智能技术研发有限公司 用于衣物穿搭推荐的方法及装置、设备
WO2020164424A1 (zh) * 2019-02-12 2020-08-20 青岛海尔洗衣机有限公司 家电的控制方法
CN111663294A (zh) * 2019-03-08 2020-09-15 Lg电子株式会社 人工智能设备及其动作方法
US20210363680A1 (en) * 2019-06-28 2021-11-25 Lg Electronics Inc. Ai-based laundry course recommending apparatus and method of controlling the same
CN114855416A (zh) * 2022-04-25 2022-08-05 青岛海尔科技有限公司 洗涤程序的推荐方法及装置、存储介质及电子装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016064077A (ja) * 2014-09-25 2016-04-28 大日本印刷株式会社 洗濯日推奨システム，洗濯日推奨装置および物干し器具
US11004135B1 (en) * 2017-08-18 2021-05-11 Amazon Technologies, Inc. Artificial intelligence system for balancing relevance and diversity of network-accessible content
CN109957910B (zh) * 2017-12-25 2022-08-05 青岛胶南海尔洗衣机有限公司 基于大数据分析的衣物洗涤管理方法
KR20210096072A (ko) * 2018-12-26 2021-08-04 엘지전자 주식회사 세탁물 처리 장치 및 그의 세탁 코스 결정 방법
US11048976B2 (en) * 2019-11-11 2021-06-29 Midea Group Co., Ltd. Method and system for controlling machines based on object recognition
KR20210067605A (ko) * 2019-11-29 2021-06-08 엘지전자 주식회사 인공 지능을 이용한 상업용 세탁기의 제어 방법 및 그 시스템
CN113699739A (zh) * 2020-05-20 2021-11-26 青岛海尔洗衣机有限公司 洗涤控制方法、装置、洗衣机控制设备、及存储介质
JP7428897B2 (ja) * 2020-07-22 2024-02-07 株式会社ノーリツ 浴槽洗浄装置
CN111967380A (zh) * 2020-08-16 2020-11-20 云知声智能科技股份有限公司 内容推荐方法及系统
CN114108227A (zh) * 2020-08-27 2022-03-01 青岛海尔洗衣机有限公司 洗衣机的控制方法、装置、洗衣机及存储介质
CN113265830B (zh) * 2021-04-30 2023-09-19 青岛海尔科技有限公司 智能洗衣机洗涤模式的推送方法和装置及电子装置
CN113987343A (zh) * 2021-10-26 2022-01-28 浙江中烟工业有限责任公司 基于强化学习的多样化推荐方法、系统及存储介质

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020082982A1 (zh) * 2018-10-23 2020-04-30 青岛海尔洗衣机有限公司 家用电器的程序推荐控制方法
CN109162065A (zh) * 2018-11-08 2019-01-08 珠海格力电器股份有限公司 洗衣机的控制方法、系统和洗衣机
EP3666954A1 (en) * 2018-12-14 2020-06-17 LG Electronics Inc. -1- Washing machine
WO2020164424A1 (zh) * 2019-02-12 2020-08-20 青岛海尔洗衣机有限公司 家电的控制方法
CN111560730A (zh) * 2019-02-12 2020-08-21 青岛海尔洗衣机有限公司 家电的控制方法
CN111663294A (zh) * 2019-03-08 2020-09-15 Lg电子株式会社 人工智能设备及其动作方法
US20210363680A1 (en) * 2019-06-28 2021-11-25 Lg Electronics Inc. Ai-based laundry course recommending apparatus and method of controlling the same
CN111401306A (zh) * 2020-04-08 2020-07-10 青岛海尔智能技术研发有限公司 用于衣物穿搭推荐的方法及装置、设备
CN114855416A (zh) * 2022-04-25 2022-08-05 青岛海尔科技有限公司 洗涤程序的推荐方法及装置、存储介质及电子装置

Also Published As

Publication number Publication date
CN114855416B (zh) 2024-03-22
CN114855416A (zh) 2022-08-05

Similar Documents

Publication Publication Date Title
WO2023207170A1 (zh) 洗涤程序的推荐方法及装置、存储介质及电子装置
US20180305851A1 (en) Laundry treating apparatus, control method of the laundry treating apparatus and online system including the same
CN109112774B (zh) 洗衣机的控制方法、装置、存储介质及洗衣机
CN108070978B (zh) 一种智能化的物联网洗衣机及其控制方法
CN110308661B (zh) 基于机器学习的智能设备控制方法及装置
CN107888458A (zh) 智能设备状态处理方法及装置
WO2024036694A1 (zh) 控制指令的发送方法、控制装置、存储介质及电子装置
CN115167164A (zh) 设备场景的确定方法和装置、存储介质及电子装置
CN115202228A (zh) 智能家电设备的控制方法、装置、遥控器及存储介质
CN114880560A (zh) 内容的推荐方法和装置、存储介质及电子装置
WO2024001189A1 (zh) 食物存储信息的确定方法及装置、存储介质及电子装置
WO2024001196A1 (zh) 家电设备的控制方法、装置、存储介质及电子装置
CN113194155A (zh) 一种物联网中场景智能推荐的方法及装置
CN116540556A (zh) 基于用户习惯的设备控制方法及装置
WO2024066089A1 (zh) 烹饪计划的确定方法及装置、存储介质及电子装置
WO2023165051A1 (zh) 身份确定方法、存储介质及电子装置
WO2023168853A1 (zh) 使用意图的预测方法和装置、存储介质及电子装置
CN114815645A (zh) 物联网设备的控制方法和装置、存储介质和电子装置
CN114691731A (zh) 使用偏好的确定方法和装置、存储介质及电子装置
CN115345225A (zh) 推荐场景的确定方法及装置、存储介质及电子装置
CN113622134A (zh) 一种洗衣控制方法、装置、设备及存储介质
CN113961804A (zh) 设备推荐方法、装置、设备及存储介质
WO2024036804A1 (zh) 意图指令的确定方法及装置、存储介质及电子装置
WO2024040824A1 (zh) 行为习惯的识别方法和装置、存储介质及电子装置
CN110830339A (zh) 一种基于家庭大脑的智慧家庭服务系统

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: 22939979

Country of ref document: EP

Kind code of ref document: A1