WO2022227526A1 - 物品查找方法、装置、空调设备和存储介质 - Google Patents

物品查找方法、装置、空调设备和存储介质 Download PDF

Info

Publication number
WO2022227526A1
WO2022227526A1 PCT/CN2021/132758 CN2021132758W WO2022227526A1 WO 2022227526 A1 WO2022227526 A1 WO 2022227526A1 CN 2021132758 W CN2021132758 W CN 2021132758W WO 2022227526 A1 WO2022227526 A1 WO 2022227526A1
Authority
WO
WIPO (PCT)
Prior art keywords
item
information
image
candidate
items
Prior art date
Application number
PCT/CN2021/132758
Other languages
English (en)
French (fr)
Inventor
郭蕾
郝本华
刘庆赟
李红
罗欢
Original Assignee
青岛海尔空调器有限总公司
青岛海尔空调电子有限公司
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 青岛海尔空调器有限总公司, 青岛海尔空调电子有限公司, 海尔智家股份有限公司 filed Critical 青岛海尔空调器有限总公司
Publication of WO2022227526A1 publication Critical patent/WO2022227526A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present application relates to the technical field of home appliances, and in particular, to a method, device, air conditioner and storage medium for finding items.
  • multi-functional lockers are often used to store items.
  • the multi-functional lockers adopt a layered design. When items are placed in them, the items can be classified and placed neatly.
  • the multi-functional lockers are set There is a control box, the control box is connected to the external power supply, and the control box is connected to the actuator.
  • the manager can input the position of the item to be taken in the control box according to the requirements.
  • the control box sends the control command to the actuator, and the actuator receives the control. After the command, grab the item at the input position, saving the time of rummaging for items.
  • the storage space of the multifunctional locker is limited, and there are too many items, and it is often difficult for people to remember where the items are, so the multifunctional locker still has shortcomings in storing items and making it easier for people to find them. Therefore, How to improve the current situation has become an urgent problem to be solved.
  • the present application provides an item search method, device, air conditioner and storage medium, which are used to solve the defect in the prior art that searching for items is limited by knowing the location of the item, realizes fast and accurate search for items, and searches for items for users Saved a lot of time.
  • This application provides a method for finding items, including:
  • the location information of the target item is determined, the item information library includes attribute information and position information of a plurality of candidate items, and the attribute information of the target item matches the item description information , the item information database is determined by performing target detection on the image of the monitoring area;
  • An article searching method is provided according to the present application, further comprising:
  • a list of discarded items is generated and sent.
  • the determining the usage information of each candidate item in the item information database includes:
  • the usage information of any candidate item is updated.
  • an item search method wherein based on the position information of the person in the image and the position information of any candidate item, the usage relationship between the person and the any candidate item is detected, including: :
  • the relationship detection model is obtained by training using relationship labels based on the sample images and the location information of sample persons and sample items therein.
  • the article information database is determined based on the following steps:
  • the image is input to the target detection model, and the attribute information and position information of each detected item output by the target detection model are obtained, and the target detection model is based on the sample image and the attribute information of each sample item in the sample image and The location information is obtained by training;
  • the item information database is updated based on attribute information and location information of each detected item.
  • the updating of the item information database based on the attribute information and location information of each detected item includes:
  • the attribute information and location information of any detected item are stored in the item information database.
  • the application also provides an article searching device, comprising:
  • a receiving unit for receiving an item search request
  • a determining unit configured to determine the item description information in the item search request; further configured to determine the location information of the target item based on the item description information and the item information base, the item information base including attributes of a plurality of candidate items information and location information, the attribute information of the target item matches the item description information,
  • a detection unit configured to perform target detection on the image of the monitoring area, and determine the item information database
  • the returning unit is used to return the location information of the target item.
  • the present application also provides an air conditioner, including an image acquisition device, where the image acquisition device is used to acquire an image of a monitoring area, and transmit the image to an item finding device.
  • the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of any one of the above-mentioned methods for finding an item.
  • the article searching method, device, air conditioner and storage medium construct an article information database by performing target detection on the image of the monitoring area; match the article description information with the article information database, and determine the position of the article according to the matching result It solves the problem that finding items is limited by knowing the location of the items, realizes fast and accurate search for items, and saves a lot of time for users to find items.
  • Fig. 1 is the schematic flow chart of the article search method provided by the application
  • Fig. 2 is the structural representation of the article searching device provided by the present application.
  • Fig. 3 is the structural representation of the air-conditioning equipment provided by the present application.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by the present application. .
  • Fig. 1 is a schematic flowchart of a method for finding items provided by the present application.
  • the execution body of the method can be a built-in processor of an air-conditioning device under the indoor intelligent networking, or a server that directly controls each smart device .
  • the air-conditioning equipment here may be a wall-mounted air conditioner, a vertical cabinet type air conditioner, a window type air conditioner, a ceiling type air conditioner, etc.
  • the following takes the processor as an example for description, and the method includes:
  • an item search request is a request sent by a user to search for an item through a client device, where the client device may be a smart phone, a tablet computer, or other smart digital products, which are not specifically described in this embodiment of the application limited.
  • the item description information is the user's description of the item to be searched.
  • the item search request includes the relevant information of the item to be searched, that is, the item description information.
  • the item description information is the attribute information of the item.
  • the attribute information of the item can be the name and category of the item, or the size and shape of the item, or the color and purpose of the item, which are not specifically limited in the embodiments of the present application.
  • the processor After receiving the item search request sent by the client device, the processor determines the item description information of the item to be searched from the item search request. After determining the item description information carried in the item search request, step 120 is performed.
  • Step 120 Determine the position information of the target item based on the item description information and the item information base, the item information base includes attribute information and position information of a plurality of candidate items, the attribute information of the target item and the item description
  • the object information database is determined by object detection on the image of the monitoring area.
  • the monitoring area here is the area where image collection needs to be performed, and may specifically be a living room, a kitchen, or a bedroom or a storage room, which is not specifically limited in this embodiment of the present application.
  • the installation position of the image acquisition device may be on the wall of the monitoring area, or may be on the ceiling of the monitoring area, which is not specifically limited in this embodiment of the present application.
  • the monitoring area may be one or multiple, and in the case of multiple control areas, image acquisition needs to be performed on each monitoring area.
  • the user can log in to the software through the user terminal device, and enable the anti-forgetting function on the software.
  • the image acquisition device can perform image acquisition for the monitoring area.
  • the processor performs target detection on the collected image and obtains the detection result. That is, each item in the image is detected, the attribute information and position information of each item in the image are obtained, and an item information database is constructed according to the attribute information and position information of each item.
  • the item information base includes attribute information and position information of multiple candidate items, which are each item in the image.
  • the user can also log in to the software through the user terminal device to enable the special memory function. After the special memory function is turned on, special images can be collected for the important items in the monitoring area.
  • the processor determines whether there is attribute information matching the item description information in the item search request in the item information base according to the item description information and the item information base.
  • the candidate item corresponding to the attribute information is used as the target item, that is, the attribute information of the target item matches the item description information carried in the item search request. Then, the position information of the candidate item, that is, the position information of the target item, is determined from the item information database. After the location information of the target item is determined, step 130 is executed.
  • the item description information carried in the item search request sent by the user can be that the name of the item to be searched is thermos cup, the color of the item to be searched is blue, and the shape of the item to be searched is cylindrical. Items to be searched are classified as daily necessities.
  • Each candidate item in the item information database may include books, pens, tissues, boxes, clothes, thermos cups, and the like.
  • the attribute information of the book can be the name of advanced mathematics, the color is red and white, the shape is a cuboid, and it is classified as a book;
  • the attribute information of the paper towel can be the name of the handkerchief paper, the color is blue, the shape is a cuboid, and the classification is life Supplies;
  • the name of the thermos cup is thermos cup, the color is blue, the shape is cylindrical, and it is classified as a daily necessities.
  • the processor After receiving the item search request with item description information, the processor matches the attribute information of each candidate item in the item information base with the item description information, and determines that the attribute information of the thermos cup in the item information base matches the item description information, That is, it is determined that the thermos cup in the item information base is the item to be searched, and then the position information of the thermos cup is determined from the item information base.
  • the item to be searched corresponding to the item description information is determined to be a new item, and the item description information is stored in the item information database for subsequent monitoring.
  • the image of the area is subjected to target detection, and when it is detected that there is attribute information matching the item description information in the image, the item corresponding to the attribute information is determined as the item to be searched.
  • the location information of the item to be found is obtained from the image, and the location information is stored in the item information database, which together with the item description information constitutes the complete information of the item to be found.
  • Step 130 returning the location information of the target item.
  • the processor After determining the location information of the target item, the processor returns the location information of the target item to the client device that sent the item search request, so that the user can know the location information of the item to be searched through the client device. After knowing the location information of the item to be found, the user can directly find the item to be found from the location described by the location information.
  • the article search method provided by the present application constructs an article information database by performing target detection on the image of the monitoring area; matches the article description information with the article information database, and determines the location information of the article according to the matching result, which solves the problem of limited article search. Due to the problem of knowing the location of the item, the fast and accurate search for the item is realized, which saves a lot of time for the user to find the item.
  • the method further includes: determining usage information of each candidate item in the item information database, where the usage information is obtained by detecting the relationship between the item and the person in the image;
  • a list of discarded items is generated and sent.
  • the usage information of the item here is the information recorded by the processor when it is determined that the item is used.
  • the usage information of the item may be the previous usage time of the item or the usage frequency of the item, which is not specifically limited in this embodiment of the present application.
  • the usage information of each candidate item in the item information base needs to be recorded.
  • the process of recording the use information of each candidate item includes detecting the relationship between any item in the image of the monitoring area and the person, and judging whether the item is used according to the detection result; if it is judged that the item is used, then update the item. usage information.
  • the usage information of the item will not be updated, or the usage information of the item may be cleared after a preset time period from the last use of the item.
  • a list of disconnected items is generated according to the usage information of each candidate item, and the generated list of disconnected items is sent to the client device for the user to pass through.
  • the client device confirms whether to discard each item in the disconnection list.
  • the discarding list here is a list of candidate items that can be discarded determined by the processor according to the usage information of each candidate item in the item information base. According to the usage information of each candidate item, there are various ways to generate a list of items to be discarded.
  • each candidate item in the item information database it is determined whether each candidate item has been used within the preset time, and if any item has not been used within the preset time, it indicates that the user has not used the item for a period of time , the item can be included in the cut-off list, and the cut-off list can be sent to the client device, so that the user can confirm through the client device whether to discard each item in the cut-off list.
  • the preset time is the time preset by the user through the client device according to the user's own situation, or the default time when the processor is manufactured.
  • the preset time may be three months, four months, or six months or one year, which is not specifically limited in this embodiment of the present application.
  • the usage times of each candidate item within a preset time is determined. Use this item, the item is used less frequently, the item can be included in the disconnection list, and the disconnection list is sent to the client device, so that the user can confirm whether to discard the disconnection list through the client device items inside.
  • the number of times of use of any item within the preset time period is greater than or equal to the preset number of times, it indicates that the user frequently uses the item, the item is used frequently, and the item does not need to be included in the disconnection list.
  • the preset number of times is the number of times preset by the user through the user terminal device and the preset time according to the user's own situation, or the number of times the processor matches the preset time by default when the processor is manufactured.
  • the preset number of times may be two or three, or five or ten, which is not specifically limited in this embodiment of the present application.
  • a list of items to be separated and discarded is generated and sent, and further includes:
  • the user receives the disconnection list sent by the processor, and confirms each item in the disconnection list according to his own needs, item value and occupied space, and confirms whether to discard each item in the disconnection list. If the user confirms to discard any item in the disconnection list, the user can return to the disconnection list to confirm the item to be disconnected through the user terminal device.
  • the user can return the instruction of not needing to discard the items in the drop-off list through the client device, or remove the items in the drop-off list from the drop-off list through the client device .
  • the processor After receiving the confirmed items to be cut off based on the confirmation returned by the user based on the cut-off list, the processor generates a cut-off plan according to information such as the value and occupied space of the items confirmed to be cut and cut, and generates the generated cut-off plan.
  • the disconnection plan is sent to the client device, so that the user can select and confirm the disconnection plan for the disconnection through the client device.
  • the determining the usage information of each candidate item in the item information database includes:
  • the usage information of the candidate item is updated.
  • personnel detection is performed on the image of the monitoring area to detect whether there is a person in the image of the monitoring area. If it is detected that there is a person in the image of the monitoring area, the location information of the person is obtained from the image. According to the position information of the person in the image and the position information of any candidate item in the item information database, the usage relationship between the person and the candidate item is detected, and the usage relationship result is obtained.
  • the usage relationship detection here is to detect whether the candidate uses the candidate item, and if the candidate item is confirmed to be used, the usage information of the candidate item is recorded.
  • the recording usage information of the candidate item it is judged whether there is recorded usage information in the usage information of the candidate item in the item information database, if not, then the item information database
  • the usage information of the candidate item is updated, that is, the recorded usage information of the candidate item is added to the usage information of the candidate item in the item information database.
  • the detection of the usage relationship between the person and the candidate item based on the position information of the person in the image and the position information of any candidate item includes:
  • the relationship detection model is obtained by training using relationship labels based on the sample images and the location information of sample persons and sample items therein.
  • sample image collection is performed on the monitoring area, target detection and person detection are performed on the sample image, and location information of the sample person and location information of the sample item in the sample image are obtained.
  • the usage relationship label here is the known usage relationship between people and candidate items in the image.
  • the training process of the relationship detection model is as follows: input the sample image, the position information of the sample person in the sample image, and the position information of the sample item in the sample image into the relationship detection model, obtain the usage relationship result output by the relationship detection model, and output the output Compare the usage relationship results with the usage relationship labels, and adjust the parameters of the relationship detection model for the first time according to the comparison results; then input the sample image, the location information of the sample person in the sample image, and the location information of the sample item in the sample image to The relationship detection model after adjusting the parameters for the first time, obtain the usage relationship results output by the relationship detection model after adjusting the parameters for the first time, compare the output usage relationship results with the usage relationship labels, and adjust the relationship for the second time according to the comparison results Detect the parameters of the model; repeat the above process until the usage relationship result output by the relationship detection model is consistent with the usage relationship label, end the training, and obtain the trained relationship detection model.
  • the item information base is determined based on the following steps:
  • the image is input to the target detection model, and the attribute information and position information of each detected item output by the target detection model are obtained, and the target detection model is based on the sample image and the attribute information of each sample item in the sample image and The location information is obtained by training;
  • the item information database is updated based on attribute information and location information of each detected item.
  • the training process of the target detection model is as follows: input the sample image into the target detection model, obtain the attribute information and position information of each detected item output by the target detection model, and compare the output attribute information and position information of each detected item with The attribute information and position information of each sample item in the sample image are compared, and the parameters of the target detection model are adjusted for the first time according to the comparison results; then the sample image is input into the target detection model after the first adjustment of parameters, and the first adjustment is obtained.
  • the parameterized target detection model outputs the attribute information and position information of each detection item, and compares the output attribute information and position information of each detection item with the attribute information and position information of each sample item in the sample image.
  • Adjust the parameters of the target detection model for the second time repeat the above process until the attribute information and position information of each detection item output by the target detection model are consistent with the attribute information and position information of each sample item in the sample image, end the training, and get the trained object detection model.
  • the item information database is updated according to the attribute information and position information of each detected item output by the relationship detection model.
  • the updating of the item information database based on the attribute information and location information of each detected item includes:
  • the position of the candidate item that matches the attribute information of the detected item is updated information
  • the attribute information and position information of the detected item are stored in the item information base.
  • the attribute information and position information of each detected item output by the relationship detection model it is determined whether there is a candidate item matching the attribute information of any detected item in the item information database. If there is a candidate item that matches the attribute information of the detected item, that is, the candidate item and the detected item are the same item, then determine whether the location information of the candidate item is the same as the location information of the detected item, that is, determine the item information database Whether the position of the candidate item has changed in If the position information of the candidate item in the library is updated, the position information of the candidate item in the item information library is updated to the position information of the detected item.
  • the position information of the candidate item is the same as the position information of the detected item, that is, the attribute information and position information of the detected item are respectively the same as the item information. If the attribute information and position information of the candidate item in the library are the same, there is no need to update the position information of the candidate item in the item information library.
  • the attribute information and location information of the detected item can be stored in the Item repository.
  • the image is captured based on the image acquisition device built in the air conditioner.
  • the image acquisition device is arranged inside the air conditioner, and the image acquisition device performs image acquisition on the monitoring area. It should be noted that the period of image acquisition performed by the image acquisition device on the monitoring area may be fixed or may be variable.
  • the user can set the cycle of capturing images by the image acquisition device through the user terminal device according to their own needs.
  • the image acquisition device here may be a camera or a scanner, which is not specifically limited in this embodiment of the present application.
  • FIG. 2 is a schematic structural diagram of an air conditioning control device provided by the present application. As shown in Figure 2, the device includes:
  • a receiving unit 210 configured to receive an item search request
  • the determining unit 220 is configured to determine the item description information in the item search request; it is also configured to determine the location information of the target item based on the item description information and the item information database, and the item information database includes multiple candidate items. attribute information and location information, the attribute information of the target item matches the item description information,
  • a detection unit 230 configured to perform target detection on the image of the monitoring area, and determine the item information database
  • the returning unit 240 is configured to return the location information of the target item.
  • the article finding device constructs an article information database by performing target detection on the image of the monitoring area; matches the article description information with the article information database, and determines the location information of the article according to the matching result, which solves the problem of limited article search. Due to the problem of knowing the location of the item, the fast and accurate search for the item is realized, which saves a lot of time for the user to find the item.
  • the determining unit 220 is used for:
  • a list of discarded items is generated and sent.
  • the detection unit 230 is used for:
  • the usage information of the candidate item is updated.
  • the detection unit 230 is used for:
  • the relationship detection model is obtained by training using relationship labels based on the sample images and the location information of sample persons and sample items therein.
  • the detection unit 230 is used for:
  • the image is input to the target detection model, and the attribute information and position information of each detected item output by the target detection model are obtained, and the target detection model is based on the sample image and the attribute information of each sample item in the sample image and The location information is obtained by training;
  • the item information database is updated based on attribute information and location information of each detected item.
  • the device further includes an update unit for:
  • the position of the candidate item that matches the attribute information of the detected item is updated information
  • the attribute information and position information of the detected item are stored in the item information base.
  • the image is captured based on the image acquisition device built in the air conditioner.
  • FIG. 3 is a schematic structural diagram of the air conditioning equipment provided by the present application. As shown in FIG. 3 , the equipment includes an image acquisition device 310 , which is used to collect images of the monitoring area and transmit them to an item finding device.
  • image acquisition device 310 which is used to collect images of the monitoring area and transmit them to an item finding device.
  • FIG. 4 illustrates a schematic diagram of the physical structure of an electronic device.
  • the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440,
  • the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 .
  • the processor 410 may invoke the logic instructions in the memory 430 to execute an item search method, the method comprising: receiving an item search request, determining item description information in the item search request; based on the item description information and the item information database, Determine the position information of the target item, the item information base includes attribute information and position information of a plurality of candidate items, the attribute information of the target item matches the item description information, and the item information base is for the monitoring area.
  • the image is determined by target detection; the position information of the target item is returned.
  • the above-mentioned logic instructions in the memory 430 may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as an independent product.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .
  • the present application also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer
  • the computer can execute the item search method provided by the above methods, the method includes: receiving an item search request, determining item description information in the item search request; determining a target based on the item description information and the item information database
  • the position information of the item, the item information library includes attribute information and position information of a plurality of candidate items, the attribute information of the target item matches the item description information, and the item information base is the image of the monitoring area. Determined by target detection; return the location information of the target item.
  • the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the computer program is implemented to execute the above-mentioned methods for finding items provided, the method comprising: receiving an item search request, determine the item description information in the item search request; determine the location information of the target item based on the item description information and the item information base, the item information base includes attribute information and position information of multiple candidate items , the attribute information of the target item matches the item description information, the item information base is determined by performing target detection on the image of the monitoring area; and the position information of the target item is returned.
  • the device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.
  • each embodiment can be implemented by means of software plus a necessary general hardware platform, and certainly can also be implemented by hardware.
  • the above-mentioned technical solutions can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic A disc, an optical disc, etc., includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the methods described in various embodiments or some parts of the embodiments.

Abstract

本申请提供一种物品查找方法、装置、空调设备和存储介质，其中方法包括：接收物品查找请求，确定所述物品查找请求中的物品描述信息；基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的；返回所述目标物品的位置信息，解决了查找物品受限于须知物品位置的问题，实现了对物品的快速、准确的查找，为用户查找物品节省了大量时间。

Description

物品查找方法、装置、空调设备和存储介质
相关申请的交叉引用
本申请要求于2021年04月25日提交的申请号为202110447054.2，名称为“物品查找方法、装置、空调设备和存储介质”的中国专利申请的优先权，其通过引用方式全部并入本文。
技术领域
本申请涉及家电技术领域，尤其涉及一种物品查找方法、装置、空调设备和存储介质。
背景技术
随着生活水平的提高，家中物品日益增多，物品的摆放较为混乱，导致许多物品在临时需要使用时难以被找到，人们需要从所有的物品中翻找出需要使用的物品，这不仅需要花费大量的时间，还会使得翻找后的场面混乱不堪。随着家中物品的增加，许多物品在日常生活中的使用频率并不高，但人们很少对这类物品进行统一的整理归纳，导致了人们日常生活的空间被各种使用率低下的物品占据，空间有效利用率较低，也浪费了物品的使用价值。
在日常生活中，多采用多功能储物柜存储物品，多功能储物柜采用分层式设计，将物品放置于其中时，可以对物品进行分类使物品摆放整齐，多功能储物柜设置有一个控制箱，控制箱与外界电源相连，控制箱连接执行机构，管理人员可根据需求在控制箱内输入所要取的物品的位置，控制箱发送控制指令至执行机构，执行机构在接收到控制指令后抓取所输位置的物品，节约翻找物品的时间。
但是，多功能储物柜的存储空间有限，且物品太多，人们通常很难记住物品所处的位置，所以多功能储物柜在存储物品，方便人们找寻物品方面仍然存在缺陷，因此，如何改善当前状况成为了亟待解决的问题。
发明内容
本申请提供一种物品查找方法、装置、空调设备和存储介质，用以解决现有技术中查找物品受限于须知物品位置的缺陷，实现了对物品的快速、准确的查找，为用户查找物品节省了大量时间。
本申请提供一种物品查找方法，包括：
接收物品查找请求，确定所述物品查找请求中的物品描述信息；
基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的；
返回所述目标物品的位置信息。
根据本申请提供一种的物品查找方法，还包括：
确定所述物品信息库中各候选物品的使用信息，所述使用信息是对所述图像中的物品与人员之间的关系进行检测得到的；
基于所述各候选物品的使用信息，生成断舍离物品清单并发送。
根据本申请提供一种的物品查找方法，所述确定所述物品信息库中各候选物品的使用信息，包括：
对所述图像进行人员检测；
若检测到所述图像中存在人员，则基于所述人员在图像中的位置信息，以及任一候选物品的位置信息，对所述人员和所述任一候选物品进行使用关系检测；
基于检测所得的使用关系结果，更新所述任一候选物品的使用信息。
根据本申请提供一种的物品查找方法，所述基于所述人员在图像中的位置信息，以及任一候选物品的位置信息，对所述人员和所述任一候选物品进行使用关系检测，包括：
将所述图像，以及所述人员在图像中的位置信息和任一候选物品的位置信息输入至关系检测模型中，得到所述关系检测模型输出的使用关系结果；
所述关系检测模型是基于样本图像以及其中的样本人员和样本物品的位置信息、使用关系标签训练得到的。
根据本申请提供一种的物品查找方法，所述物品信息库是基于如下步 骤确定的：
获取所述监控区域的图像；
将所述图像输入至目标检测模型，得到所述目标检测模型输出的各检测物品的属性信息和位置信息，所述目标检测模型是基于样本图像以及所述样本图像中各样本物品的属性信息和位置信息训练得到的；
基于各检测物品的属性信息和位置信息，更新所述物品信息库。
根据本申请提供一种的物品查找方法，所述基于各检测物品的属性信息和位置信息，更新所述物品信息库，包括：
若所述物品信息库中存在与任一检测物品的属性信息相匹配而位置信息不同的候选物品，则基于所述任一检测物品的位置信息，更新与所述任一检测物品的属性信息相匹配的候选物品的位置信息；
若所述物品信息库中不存在与任一检测物品的属性信息相匹配的候选物品，则将所述任一检测物品的属性信息和位置信息存入所述物品信息库。
根据本申请提供一种的物品查找方法，所述图像是基于空调设备内置的图像采集设备拍摄的。
本申请还提供的一种物品查找装置，包括：
接收单元，用于接收物品查找请求；
确定单元，用于确定所述物品查找请求中的物品描述信息；还用于基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，
检测单元，用于对监控区域的图像进行目标检测，确定所述物品信息库；
返回单元，用于返回所述目标物品的位置信息。
本申请还提供一种空调设备，包括图像采集设备，所述图像采集设备用于采集监控区域的图像，并传输至物品查找装置。
本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如上述任一种所述物品查找方法的步骤。
本申请提供的物品查找方法、装置、空调设备和存储介质，通过对监控区域的图像进行目标检测，构建物品信息库；将物品描述信息与物品信息库的进行匹配，根据匹配结果确定物品的位置信息，解决了查找物品受限于须知物品位置的问题，实现了对物品的快速、准确的查找，为用户查找物品节省了大量时间。
附图说明
为了更清楚地说明本申请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一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，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他的附图。
图1是本申请提供的物品查找方法的流程示意图；
图2是本申请提供的物品查找装置的结构示意图；
图3是本申请提供的空调设备的结构示意图；
图4是本申请提供的电子设备的结构示意图。。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请中的附图，对本申请中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，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，都属于本申请保护的范围。
图1是本申请提供的物品查找方法的流程示意图，如图1所示，该方法的执行主体可以是室内智能联网下的空调设备内置的处理器，也可以是直接控制各个智能设备的服务端。此处的空调设备可以是挂壁式空调、立柜式空调、窗式空调、吊顶式空调等，以下以处理器为例进行说明，该方法包括：
步骤110，接收物品查找请求，确定所述物品查找请求中的物品描述信息。
此处，物品查找请求是用户通过用户端设备发出的查找某一物品的请求，此处用户端设备可以是智能手机、平板电脑，还可以是其他智能数码 产品，本申请实施例对此不作具体限定。物品描述信息为用户对需查找物品的描述。
具体地，当用户需寻找某一物品却难以找到时，可通过用户端设备登录设备上的软件，在软件上发送物品查找请求，物品查找请求中包括需查找物品的相关信息，即物品描述信息。物品描述信息即物品的属性信息，物品的属性信息可以是物品的名称、类别，也可以是物品的尺寸、形状，还可以是物品的颜色、用途，本申请实施例对此不做具体限定。
当接收到用户端设备发出的物品查找请求后，处理器从物品查找请求中确定需查找物品的物品描述信息。确定物品查找请求中携带的物品描述信息后，执行步骤120。
步骤120，基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的。
此处的监控区域即需进行图像采集的区域，具体可以是客厅、厨房，也可以是卧室、储物间，本申请实施例对此不作具体限定。图像采集设备的安装位置可以是监控区域的墙壁上，也可以是监控区域的天花板上，本申请实施例对此不作具体限定。监控区域可以是一个也可以是多个，在控制区域为多个的情况下，需要对各个监控区域进行图像采集。
具体地，用户可通过用户端设备登录软件，在软件上开启防遗忘功能，防遗忘功能开启后，可对通过图像采集设备针对监控区域进行图像采集。在此基础上，处理器对采集的图像进行目标检测，获取检测结果。即对图像中各物品进行检测，获取图像中各物品的属性信息和位置信息，根据各物品的属性信息和位置信息构建物品信息库。物品信息库包括多个候选物品的属性信息和位置信息，多个候选物品即图像中的各物品。
需要说明的是，当有重要物品需要特殊记忆时，用户还可通过用户端设备登录软件开启特殊记忆功能，特殊记忆功能开启后可对监控区域内该重要物品进行特殊图像采集。
确定物品描述信息后，处理器根据物品描述信息和物品信息库，判断物品信息库中是否存在与物品查找请求中物品描述信息相匹配的属性信 息。
若存在与物品描述信息相匹配的属性信息，则将该属性信息对应的候选物品作为目标物品，即目标物品的属性信息与物品查找请求中携带的物品描述信息相匹配。然后从物品信息库中确定该候选物品的位置信息，即目标物品的位置信息。确定目标物品的位置信息后，执行步骤130。
例如，用户需查找一个保温杯，用户发送的物品查找请求中携带的物品描述信息可以是需查找物品的名称为保温杯，需查找物品的颜色为蓝色，需查找物品的形状为圆柱形，需查找物品的分类为生活用品。物品信息库中各候选物品可以包括书本、钢笔、纸巾、箱子、衣服、保温杯等。其中，书本的属性信息可以是名称为高等数学，颜色为红白相间，形状为长方体，分类为书籍；纸巾的属性信息可以是名称为手帕纸，颜色为蓝色，形状为长方体，分类为生活用品；保温杯的名称为保温杯，颜色为蓝色，形状为圆柱形，分类为生活用品。处理器接收到带有物品描述信息的物品查找请求后，将物品信息库中各候选物品的属性信息与物品描述信息进行匹配，确定物品信息库中保温杯的属性信息与物品描述信息相匹配，即确定物品信息库中的保温杯为需查找物品，然后从物品信息库中确定保温杯的位置信息。
相应地，若物品信息库中不存在与物品描述信息相匹配的属性信息，则确定物品描述信息对应的需查找物品为新增物品，并将物品描述信息存入物品信息库，以便后续对监控区域的图像进行目标检测，检测到图像中存在与物品描述信息相匹配的属性信息时，将属性信息对应的物品确定为需查找物品。从图像中获取需查找物品的位置信息，并将位置信息存入物品信息库，与物品描述信息共同构成需查找物品的完整信息。
步骤130，返回所述目标物品的位置信息。
具体地，处理器确定目标物品的位置信息后，将目标物品的位置信息返回至发出物品查找请求的用户端设备，以供用户通过用户端设备获知需查找物品的位置信息。用户获知需查找物品的位置信息后，可直接从位置信息描述的位置处，找到需查找物品。
本申请提供的物品查找方法，通过对监控区域的图像进行目标检测，构建物品信息库；将物品描述信息与物品信息库的进行匹配，根据匹配结 果确定物品的位置信息，解决了查找物品受限于须知物品位置的问题，实现了对物品的快速、准确的查找，为用户查找物品节省了大量时间。
基于上述实施例，该方法还包括：确定所述物品信息库中各候选物品的使用信息，所述使用信息是对所述图像中的物品与人员之间的关系进行检测得到的；
基于所述各候选物品的使用信息，生成断舍离物品清单并发送。
此处的物品的使用信息为确定物品被使用时处理器记录的信息。物品的使用信息可以是物品的历次使用时间，也可以是物品的是使用频率，本申请实施例对此不作具体限定。
具体地，构建完成物品信息库后，还需对物品信息库中各候选物品的使用信息进行记录。记录各候选物品的使用信息的过程包括对监控区域的图像中任一物品与人员之间的关系进行检测，根据检测结果判断该物品是否被使用；若判定该物品被使用，则更新该物品的使用信息。
相应地，若根据检测结果判断该物品未被使用，则不对该物品的使用信息进行更新，或者在距离上次使用该物品预设时长之后，可以清空该物品的使用信息。
进一步地，物品信息库中各候选物品的使用信息记录完成后，根据各候选物品的使用信息，生成断舍离物品清单，并将生成的断舍离清单发送至用户端设备，以供用户通过用户端设备确认是否舍弃断舍离清单内的各物品。此处的断舍离清单是处理器根据物品信息库中各候选物品的使用信息确定的可以舍弃的候选物品的清单。根据各候选物品的使用信息，生成断舍离物品清单的方式有多种。
例如，根据物品信息库中各候选物品的使用信息，确定各候选物品在预设时间内是否被使用，若任一物品在预设时间内未被使用，则表明用户已经一段时间未使用该物品，可将该物品列入断舍离清单，并将断舍离清单发送至用户端设备，以供用户通过用户端设备确认是否舍弃断舍离清单内的各物品。
若确定任一候选物品在预设时间内被使用，则表明用户在一段时间内使用过该物品，不用将该物品列入断舍离清单。
需要说明的是，预设时间是用户根据自身情况通过用户端设备预先设 定的时间，或是处理器在被制造时，默认的时间。预设时间可以是三个月、四个月，也可以是半年、一年，本申请实施例对此不作具体限定。
又例如，根据物品信息库中各候选物品的使用信息，确定各候选物品在预设时间内的使用次数，若任一物品在预设时间内的使用次数小于预设次数，则表明用户未经常使用该物品，该物品被使用的频率较低，可将该物品列入断舍离清单，并将断舍离清单发送至用户端设备，以供用户通过用户端设备确认是否舍弃断舍离清单内的各物品。
若任一物品在预设时间内的使用次数大于等于预设次数，则表明用户经常使用该物品，该物品被使用的频率较高，无需将该物品列入断舍离清单。
需要说明的是，预设次数是用户根据自身情况通过用户端设备和预设时间预先设定的次数，或是处理器在被制造时，默认的与预设时间匹配的次数。预设次数可以是两次、三次，也可以是五次、十次，本申请实施例对此不作具体限定。
基于上述实施例，生成断舍离物品清单并发送，之后还包括：
用户接收到处理器发送的断舍离清单，根据自身需求、物品价值和占用空间，对断舍离清单内各物品进行确认，确认是否舍弃断舍离清单内的各物品。若用户确认舍弃断舍离清单内任一物品，则可通过用户端设备返回断舍离清单内确认进行断舍离的物品。
若用户确认无需舍弃断舍离清单内各物品，则可通过用户端设备返回无需舍弃断舍离清单内各物品的指示，或通过用户端设备将断舍离清单内各物品移出断舍离清单。
进一步地，处理器接收到用户基于断舍离清单返回的确认进行断舍离的物品后，根据确认进行断舍离的物品的价值、占用空间等信息，生成断舍离方案，并将生成的断舍离方案发送至用户端设备，以供用户通过用户端设备选择确认进行断舍离的断舍离方案。
基于上述实施例，所述确定所述物品信息库中各候选物品的使用信息，包括：
对所述图像进行人员检测；
若检测到所述图像中存在人员，则基于所述人员在图像中的位置信息， 以及任一候选物品的位置信息，对所述人员和该候选物品进行使用关系检测；
基于检测所得的使用关系结果，更新该候选物品的使用信息。
具体地，对监控区域的图像进行人员检测，检测监控区域的图像中是否存在人员。若检测到监控区域的图像中存在人员，则从图像中获取人员的位置信息。根据人员在图像中的位置信息以及物品信息库中任一候选物品的位置信息，对人员和该候选物品进行使用关系检测，获取使用关系结果。此处的使用关系检测为检测人员是否使用该候选物品，若确认使用该候选物品，则记录该候选物品的使用信息。
进一步地，根据检测获取的使用关系结果，即记录的该候选物品的使用信息，判断物品信息库中该候选物品的使用信息中是否存在记录的使用信息，若不存在，则对物品信息库中该候选物品的使用信息进行更新，即将记录的该候选物品的使用信息添加至物品信息库中该候选物品的使用信息中。
若物品信息库中该候选物品的使用信息中存在记录的使用信息，则无需对物品信息库中该候选物品的使用信息进行更新。
基于上述实施例，所述基于所述人员在图像中的位置信息，以及任一候选物品的位置信息，对所述人员和该候选物品进行使用关系检测，包括：
将所述图像，以及所述人员在图像中的位置信息和任一候选物品的位置信息输入至关系检测模型中，得到所述关系检测模型输出的使用关系结果；
所述关系检测模型是基于样本图像以及其中的样本人员和样本物品的位置信息、使用关系标签训练得到的。
具体地，对监控区域进行样本图像采集，对样本图像进行目标检测和人员检测，获取样本图像中的样本人员的位置信息和样本物品的位置信息。此处的使用关系标签为已知的图像中人员与候选物品的使用关系。
关系检测模型进行训练的过程如下：将样本图像、样本图像中的样本人员的位置信息和样本图像中的样本物品的位置信息输入至关系检测模型，获取关系检测模型输出的使用关系结果，将输出的使用关系结果与使用关系标签进行对比，根据对比结果第一次调整关系检测模型的参数；再 将样本图像、样本图像中的样本人员的位置信息和样本图像中的样本物品的位置信息输入至第一次调整参数后的关系检测模型，获取第一次调整参数后的关系检测模型输出的使用关系结果，并将输出的使用关系结果与使用关系标签进行对比，根据对比结果第二次调整关系检测模型的参数；重复上述过程，直至关系检测模型输出的使用关系结果与使用关系标签一致，结束训练，获得训练好的关系检测模型。
将监控区域的图像，以及人员在图像中的位置信息和物品信息库中任一候选物品的位置信息输入至训练好的关系检测模型中，获取关系检测模型输出的使用关系结果。根据关系检测模型输出的使用关系结果，对物品信息库中该候选物品的使用信息进行更新。
基于上述实施例，所述物品信息库是基于如下步骤确定的：
获取所述监控区域的图像；
将所述图像输入至目标检测模型，得到所述目标检测模型输出的各检测物品的属性信息和位置信息，所述目标检测模型是基于样本图像以及所述样本图像中各样本物品的属性信息和位置信息训练得到的；
基于各检测物品的属性信息和位置信息，更新所述物品信息库。
具体地，目标检测模型进行训练的过程如下：将样本图像输入至目标检测模型，获取目标检测模型输出的各检测物品的属性信息和位置信息，将输出的各检测物品的属性信息和位置信息与样本图像中各样本物品的属性信息和位置信息进行对比，根据对比结果第一次调整目标检测模型的参数；再将样本图像输入至第一次调整参数后的目标检测模型，获取第一次调整参数后的目标检测模型输出的各检测物品的属性信息和位置信息，并将输出的各检测物品的属性信息和位置信息与样本图像中各样本物品的属性信息和位置信息进行对比，根据对比结果第二次调整目标检测模型的参数；重复上述过程，直至目标检测模型输出的各检测物品的属性信息和位置信息与样本图像中各样本物品的属性信息和位置信息一致，结束训练，获得训练好的目标检测模型。
将获取的监控区域的图像输入至训练好的目标检测模型中，获取目标检测模型输出的各检测物品的属性信息和位置信息。根据关系检测模型输出的各检测物品的属性信息和位置信息，对物品信息库进行更新。
基于上述实施例，所述基于各检测物品的属性信息和位置信息，更新所述物品信息库，包括：
若所述物品信息库中存在与任一检测物品的属性信息相匹配而位置信息不同的候选物品，则基于该检测物品的位置信息，更新与该检测物品的属性信息相匹配的候选物品的位置信息；
若所述物品信息库中不存在与任一检测物品的属性信息相匹配的候选物品，则将该检测物品的属性信息和位置信息存入所述物品信息库。
具体地，根据关系检测模型输出的各检测物品的属性信息和位置信息，判断物品信息库中是否存在与任一检测物品的属性信息相匹配的候选物品。若存在与该检测物品的属性信息相匹配的候选物品，即该候选物品与该检测物品为同一物品，则判断该候选物品的位置信息与该检测物品的位置信息是否相同，即判断物品信息库中该候选物品的位置是否发生了变化；若该候选物品的位置信息与该检测物品的位置信息不同，即确定该候选物品的位置发生了变化，则根据该检测物品的位置信息，对物品信息库中与该候选物品的位置信息进行更新，则将物品信息库中该候选物品的位置信息更新为该检测物品的位置信息。
若物品信息库中存在与任一检测物品的属性信息相匹配的候选物品，且该候选物品的位置信息与该检测物品的位置信息相同，即该检测物品的属性信息和位置信息分别与物品信息库中该候选物品的属性信息和位置信息相同，则无需对物品信息库中该候选物品的位置信息进行更新。
相应地，若物品信息库中不存在与该检测物品的属性信息相匹配的候选物品，则表明该检测物品为控制区域内新增的物品，可将该检测物品的属性信息和位置信息存入物品信息库。
基于上述实施例，所述图像是基于空调设备内置的图像采集设备拍摄的。
具体地，图像采集设备设置于空调设备的内部，图像采集设备对监控区域进行图像采集。需要说明的是，图像采集设备对监控区域进行图像采集的周期可以是固定的，可以是变化的。用户可以根据自身需求通过用户端设备对图像采集设备拍摄图像的周期进行设定。此处的图像采集设备可以是摄像头，也可以是扫描仪，本申请实施例对此不作具体限定。
下面对本申请提供的物品查找装置进行描述，下文描述的物品查找装置与上文描述的物品查找方法可相互对应参照。
图2是本申请提供的空气调节控制装置的结构示意图。如图2所示，该装置包括：
接收单元210，用于接收物品查找请求；
确定单元220，用于确定所述物品查找请求中的物品描述信息；还用于基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，
检测单元230，用于对监控区域的图像进行目标检测，确定所述物品信息库；
返回单元240，用于返回所述目标物品的位置信息。
本申请提供的物品查找装置，通过对监控区域的图像进行目标检测，构建物品信息库；将物品描述信息与物品信息库的进行匹配，根据匹配结果确定物品的位置信息，解决了查找物品受限于须知物品位置的问题，实现了对物品的快速、准确的查找，为用户查找物品节省了大量时间。
基于上述实施例，确定单元220用于：
确定所述物品信息库中各候选物品的使用信息，所述使用信息是对所述图像中的物品与人员之间的关系进行检测得到的；
基于所述各候选物品的使用信息，生成断舍离物品清单并发送。
基于上述实施例，检测单元230用于：
对所述图像进行人员检测；
若检测到所述图像中存在人员，则基于所述人员在图像中的位置信息，以及任一候选物品的位置信息，对所述人员和该候选物品进行使用关系检测；
基于检测所得的使用关系结果，更新该候选物品的使用信息。
基于上述实施例，检测单元230用于：
将所述图像，以及所述人员在图像中的位置信息和任一候选物品的位置信息输入至关系检测模型中，得到所述关系检测模型输出的使用关系结果；
所述关系检测模型是基于样本图像以及其中的样本人员和样本物品的位置信息、使用关系标签训练得到的。
基于上述实施例，检测单元230用于：
获取所述监控区域的图像；
将所述图像输入至目标检测模型，得到所述目标检测模型输出的各检测物品的属性信息和位置信息，所述目标检测模型是基于样本图像以及所述样本图像中各样本物品的属性信息和位置信息训练得到的；
基于各检测物品的属性信息和位置信息，更新所述物品信息库。
基于上述实施例，所述装置还包括更新单元，用于：
若所述物品信息库中存在与任一检测物品的属性信息相匹配而位置信息不同的候选物品，则基于该检测物品的位置信息，更新与该检测物品的属性信息相匹配的候选物品的位置信息；
若所述物品信息库中不存在与任一检测物品的属性信息相匹配的候选物品，则将该检测物品的属性信息和位置信息存入所述物品信息库。
基于上述实施例，所述图像是基于空调设备内置的图像采集设备拍摄的。
图3是本申请提供的空调设备的结构示意图，如图3所示，该设备包括图像采集设备310，所述图像采集设备310用于采集监控区域的图像，并传输至物品查找装置。
图4示例了一种电子设备的实体结构示意图，如图4所示，该电子设备可以包括：处理器(processor)410、通信接口(Communications Interface)420、存储器(memory)430和通信总线440，其中，处理器410，通信接口420，存储器430通过通信总线440完成相互间的通信。处理器410可以调用存储器430中的逻辑指令，以执行物品查找方法，该方法包括：接收物品查找请求，确定所述物品查找请求中的物品描述信息；基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的；返回所述目标物品的位置信息。
此外，上述的存储器430中的逻辑指令可以通过软件功能单元的形式 实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案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中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
另一方面，本申请还提供一种计算机程序产品，所述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机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，计算机能够执行上述各方法所提供的物品查找方法，该方法包括：接收物品查找请求，确定所述物品查找请求中的物品描述信息；基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的；返回所述目标物品的位置信息。
又一方面，本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现以执行上述各提供的物品查找方法，该方法包括：接收物品查找请求，确定所述物品查找请求中的物品描述信息；基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的；返回所述目标物品的位置信息。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
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各实施方式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。基于这样的理解，上述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，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (10)

  1. 一种物品查找方法，其特征在于，包括：
    接收物品查找请求，确定所述物品查找请求中的物品描述信息；
    基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，所述物品信息库是对监控区域的图像进行目标检测确定的；
    返回所述目标物品的位置信息。
  2. 根据权利要求1所述的物品查找方法，其特征在于，还包括：
    确定所述物品信息库中各候选物品的使用信息，所述使用信息是对所述图像中的物品与人员之间的关系进行检测得到的；
    基于所述各候选物品的使用信息，生成断舍离物品清单并发送。
  3. 根据权利要求2所述的物品查找方法，其特征在于，所述确定所述物品信息库中各候选物品的使用信息，包括：
    对所述图像进行人员检测；
    若检测到所述图像中存在人员，则基于所述人员在图像中的位置信息，以及任一候选物品的位置信息，对所述人员和所述任一候选物品进行使用关系检测；
    基于检测所得的使用关系结果，更新所述任一候选物品的使用信息。
  4. 根据权利要求3所述的物品查找方法，其特征在于，所述基于所述人员在图像中的位置信息，以及任一候选物品的位置信息，对所述人员和所述任一候选物品进行使用关系检测，包括：
    将所述图像，以及所述人员在图像中的位置信息和任一候选物品的位置信息输入至关系检测模型中，得到所述关系检测模型输出的使用关系结果；
    所述关系检测模型是基于样本图像以及其中的样本人员和样本物品的位置信息、使用关系标签训练得到的。
  5. 根据权利要求1至4中任一项所述的物品查找方法，其特征在于，所述物品信息库是基于如下步骤确定的：
    获取所述监控区域的图像；
    将所述图像输入至目标检测模型，得到所述目标检测模型输出的各检测物品的属性信息和位置信息，所述目标检测模型是基于样本图像以及所述样本图像中各样本物品的属性信息和位置信息训练得到的；
    基于各检测物品的属性信息和位置信息，更新所述物品信息库。
  6. 根据权利要求5所述的物品查找方法，其特征在于，所述基于各检测物品的属性信息和位置信息，更新所述物品信息库，包括：
    若所述物品信息库中存在与任一检测物品的属性信息相匹配而位置信息不同的候选物品，则基于所述任一检测物品的位置信息，更新与所述任一检测物品的属性信息相匹配的候选物品的位置信息；
    若所述物品信息库中不存在与任一检测物品的属性信息相匹配的候选物品，则将所述任一检测物品的属性信息和位置信息存入所述物品信息库。
  7. 根据权利要求1至4中任一项所述的物品查找方法，其特征在于，所述图像是基于空调设备内置的图像采集设备拍摄的。
  8. 一种物品查找装置，其特征在于，包括：
    接收单元，用于接收物品查找请求；
    确定单元，用于确定所述物品查找请求中的物品描述信息；还用于基于所述物品描述信息和物品信息库，确定目标物品的位置信息，所述物品信息库包括多个候选物品的属性信息和位置信息，所述目标物品的属性信息与所述物品描述信息相匹配，
    检测单元，用于对监控区域的图像进行目标检测，确定所述物品信息库；
    返回单元，用于返回所述目标物品的位置信息。
  9. 一种空调设备，包括图像采集设备，所述图像采集设备用于采集监控区域的图像，并传输至物品查找装置。
  10. 一种非暂态计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述物品查找方法的步骤。
PCT/CN2021/132758 2021-04-25 2021-11-24 物品查找方法、装置、空调设备和存储介质 WO2022227526A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110447054.2 2021-04-25
CN202110447054.2A CN113269828B (zh) 2021-04-25 2021-04-25 物品查找方法、装置、空调设备和存储介质

Publications (1)

Publication Number Publication Date
WO2022227526A1 true WO2022227526A1 (zh) 2022-11-03

Family

ID=77229290

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132758 WO2022227526A1 (zh) 2021-04-25 2021-11-24 物品查找方法、装置、空调设备和存储介质

Country Status (2)

Country Link
CN (1) CN113269828B (zh)
WO (1) WO2022227526A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113269828B (zh) * 2021-04-25 2023-07-18 青岛海尔空调器有限总公司 物品查找方法、装置、空调设备和存储介质
CN114003034A (zh) * 2021-10-26 2022-02-01 山东新一代信息产业技术研究院有限公司 一种巡检机器人巡检规划的制定方法、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462530A (zh) * 2014-12-23 2015-03-25 小米科技有限责任公司 用户喜好的分析方法及装置、电子设备
CN109614897A (zh) * 2018-11-29 2019-04-12 平安科技（深圳）有限公司 一种室内查找物品的方法及终端
CN109961074A (zh) * 2017-12-22 2019-07-02 深圳市优必选科技有限公司 一种查找物品的方法、机器人及计算机可读存储介质
CN109993045A (zh) * 2017-12-29 2019-07-09 杭州海康威视系统技术有限公司 物品查找方法及查找装置、查找系统和机器可读存储介质
CN111582038A (zh) * 2020-04-10 2020-08-25 上海明略人工智能(集团)有限公司 查找物品方法、装置、存储介质及移动机器人
CN113269828A (zh) * 2021-04-25 2021-08-17 青岛海尔空调器有限总公司 物品查找方法、装置、空调设备和存储介质

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
HK1216218A2 (zh) * 2015-08-26 2016-10-21 Oscl Pacific Ltd 用於物品查找及定位的系統及方法
CN107507058A (zh) * 2017-08-13 2017-12-22 广东聚联电子商务股份有限公司 一种闲置物品共享方法
CN108052860A (zh) * 2017-11-06 2018-05-18 珠海格力电器股份有限公司 物品检索方法及装置
CN108536573B (zh) * 2018-04-17 2021-03-26 中山市华南理工大学现代产业技术研究院 一种vr应用性能及用户行为监控的方法
CN109145901B (zh) * 2018-08-14 2023-04-21 腾讯科技（深圳）有限公司 物品识别方法、装置、计算机可读存储介质和计算机设备
CN109451240B (zh) * 2018-12-04 2021-01-26 百度在线网络技术（北京）有限公司 对焦方法、装置、计算机设备和可读存储介质
CN109816947A (zh) * 2019-02-28 2019-05-28 广州骅视电子技术有限公司 一种多功能智能分析物品丢失报警监控系统
CN111046211A (zh) * 2019-12-25 2020-04-21 维沃移动通信有限公司 物品查找方法及电子设备
CN111507207A (zh) * 2020-03-30 2020-08-07 宇龙计算机通信科技(深圳)有限公司 物品收纳方法、装置、存储介质及终端
CN111538861B (zh) * 2020-04-22 2023-08-15 浙江大华技术股份有限公司 基于监控视频进行图像检索的方法、装置、设备及介质
CN112017319B (zh) * 2020-08-21 2022-03-25 中建二局第一建筑工程有限公司 一种智能巡更安防方法、装置、系统及存储介质
CN112198810B (zh) * 2020-11-06 2023-05-16 青岛海尔空调器有限总公司 用于智能家居设备导航控制的方法、装置及智能家居设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462530A (zh) * 2014-12-23 2015-03-25 小米科技有限责任公司 用户喜好的分析方法及装置、电子设备
CN109961074A (zh) * 2017-12-22 2019-07-02 深圳市优必选科技有限公司 一种查找物品的方法、机器人及计算机可读存储介质
CN109993045A (zh) * 2017-12-29 2019-07-09 杭州海康威视系统技术有限公司 物品查找方法及查找装置、查找系统和机器可读存储介质
CN109614897A (zh) * 2018-11-29 2019-04-12 平安科技（深圳）有限公司 一种室内查找物品的方法及终端
CN111582038A (zh) * 2020-04-10 2020-08-25 上海明略人工智能(集团)有限公司 查找物品方法、装置、存储介质及移动机器人
CN113269828A (zh) * 2021-04-25 2021-08-17 青岛海尔空调器有限总公司 物品查找方法、装置、空调设备和存储介质

Also Published As

Publication number Publication date
CN113269828A (zh) 2021-08-17
CN113269828B (zh) 2023-07-18

Similar Documents

Publication Publication Date Title
WO2022227526A1 (zh) 物品查找方法、装置、空调设备和存储介质
CN104394045B (zh) 针对智能设备的场景模式推荐方法和装置
CN104460328B (zh) 基于设定场景模式的智能设备控制方法和装置
US20200175850A1 (en) System and method for providing customized connected device functionality and for operating a connected device via an alternate object
CN110308660B (zh) 智能设备控制方法及装置
JP6905087B2 (ja) 物品探索方法、装置及びロボット
WO2021098536A1 (zh) 基于场景识别的清扫方法、系统、扫地设备及存储介质
CN104899403B (zh) 一种从cad设计图纸自动生成装修预算报价的方法和系统
CN104903876B (zh) 电气设备管理装置、电气设备管理方法以及电气设备管理系统
CN106452987B (zh) 一种语音控制方法及装置、设备
CN110726231B (zh) 空调的控制方法和装置
TWI653595B (zh) 儲藏物的位置追蹤方法
CN106647311A (zh) 智能中控系统、设备、服务器及智能设备控制方法
CN105550228A (zh) 智能储物装置及基于智能储物装置的存取识别方法、系统
CN104009898A (zh) 家用电器及其控制方法和装置
CN109856980B (zh) 智能家居设备推荐方法、装置、物联网系统以及云服务器
CN110889573A (zh) 一种设备选型方法及其装置
CN108920123A (zh) 信息的显示方法、装置、存储介质和处理器
JP2020087224A (ja) 情報処理装置、及び情報処理プログラム
CN104102328B (zh) 信息处理方法和信息处理设备
CN108475044A (zh) 信息处理装置、电子设备、方法及程序
CN106997506A (zh) 用于跨设备营销的同一空间设备的分组方法及其系统
CN114120996A (zh) 语音交互方法及装置
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
CN109873994A (zh) 一种智能设备及其信息处理方法、计算机存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21938985

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE