Article information identification method, equipment, medium and system

Abstract

The invention discloses an article information identification method, equipment, medium and system, electrical equipment comprises an article identification area, an image acquisition device and a bearing seat are arranged in the article identification area, and the method comprises the following steps: acquiring a first article image of a to-be-identified article borne on the bearing seat through the image acquisition device; obtaining target adjustment parameters according to the second article image, wherein the target adjustment parameters comprise a target adjustment parameter; controlling the bearing seat to rotate to a target state according to the target adjustment parameter; and under the condition that the to-be-identified article is rotated until the identification area of the to-be-identified article is opposite to the shooting angle of the image acquisition device, acquiring a second article image of the to-be-identified article through the image acquisition device, and acquiring article information of the to-be-identified article according to the second article image. According to the invention, the technical problem of low reliability of article information identification is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of electrical equipment, and in particular relates to an object information identification method, equipment, medium and system. Background Art

[0002] High-end wine lovers generally pursue quality and have high requirements for the wines stored in their wine cabinets. In addition to requiring a stable storage environment, they also want real-time access to the quantity of wines and information about each bottle, such as the date of storage, winery, and how it is used. However, users typically obtain this information through inconvenient searches. In related technologies, a camera installed on the top of the wine cabinet captures images of the entire interior to identify all the wines stored. However, due to differences in user placement of the wines, and variations in bottle shape, size, and label placement, it is impossible to identify specific information such as the specific type of wine and the winery. Similar issues also exist in other storage devices, resulting in insufficiently detailed and accurate information about stored items. Summary of the Invention

[0003] The present invention provides an item information recognition method, device, medium and system for solving the technical problem of being unable to recognize the item information of stored items.

[0004] In a first aspect of the present invention, a method for identifying item information is provided, which is applied to an electrical device including an item identification area, wherein an image acquisition device and a supporting seat are provided in the item identification area, the method comprising: obtaining a target adjustment parameter when an item to be identified is supported on the supporting seat; after controlling the supporting seat and / or the image acquisition device to move to a target state according to the target adjustment parameter, obtaining a first item image of the item to be identified through the image acquisition device, wherein the target state is that a marking area of ​​the item to be identified is opposite to a shooting angle of the image acquisition device; and obtaining item information of the item to be identified based on the first item image.

[0005] In combination with the first aspect, in some embodiments, acquiring the target adjustment parameter includes: acquiring a second object image of the object to be identified through the image acquisition device; and acquiring the target adjustment parameter based on the second object image.

[0006] In combination with the first aspect, in some embodiments, obtaining the target adjustment parameters based on the second object image includes: sending the second object image to a server so that the server performs image processing on the second object image to obtain the target adjustment parameters; and receiving the target adjustment parameters fed back by the server.

[0007] In combination with the first aspect, in some embodiments, a comparison model is deployed in the electrical device, and obtaining the target adjustment parameter based on the second object image includes: performing image classification on the second object image through the comparison model to obtain the target adjustment parameter, or performing information recognition on the second object image; if the object information of the object to be identified is not identified from the second object image, performing image classification on the second object image through the comparison model to obtain the target adjustment parameter.

[0008] In combination with the first aspect, in some embodiments, obtaining the item information of the item to be identified based on the first item image includes: sending the first item image to a server so that the server performs information recognition on the first item image to obtain the item information of the item to be identified; and receiving the item information of the item to be identified fed back by the server.

[0009] In combination with the first aspect, in some embodiments, after sending the first object image to the server, it also includes: if a first prompt message from the server is received, outputting the first prompt message, the first prompt message is sent when the server fails to recognize the object information of the object to be identified from the first object image, and the first prompt message is used to prompt the user to adjust the placement position and / or placement angle of the object to be identified on the supporting seat; after a preset delay in outputting the first prompt message, obtaining a third object image of the object to be identified carried on the supporting seat through the image acquisition device; and obtaining the object information of the object to be identified based on the third object image.

[0010] In combination with the first aspect, in some embodiments, the target adjustment parameter includes a first rotation parameter and a second rotation parameter; controlling the support base and / or the image acquisition device to move to the target state according to the target adjustment parameter includes: controlling the support base to rotate according to the first rotation parameter to adjust the orientation of the identification area of ​​the object to be identified; controlling the image acquisition device to rotate according to the second rotation parameter to adjust the shooting angle of the image acquisition device, and the axis of rotation of the image acquisition device is not parallel to the axis of rotation of the support base.

[0011] In combination with the first aspect, in some embodiments, the electrical device also includes a driving device for driving the supporting seat to rotate, and the power output shaft of the driving device is connected to the supporting seat; controlling the rotation of the supporting seat according to the first rotation parameter to adjust the orientation of the identification area of ​​the item to be identified includes: controlling the operation of the driving device according to the first rotation parameter, the operation of the driving device drives the supporting seat to rotate around an axis perpendicular to the supporting surface of the supporting seat, and the rotation of the supporting seat drives the item to be identified to rotate so that the identification area of ​​the item to be identified is opposite to the image acquisition device.

[0012] In a second aspect of the present invention, a method for identifying item information is provided, which is applied to a server, wherein the server establishes a communication connection with an electrical device, wherein the electrical device includes an item identification area, wherein an image acquisition device and a supporting seat are provided in the item identification area, and the method includes: generating a target adjustment parameter; sending the target adjustment parameter to the electrical device so that the electrical device controls the supporting seat and / or the image acquisition device to move to a target state according to the target adjustment parameter, and then obtaining a first item image of the item to be identified carried on the supporting seat through the image acquisition device, and obtaining item information of the item to be identified based on the first item image, wherein the target state is that the identification area of ​​the item to be identified is opposite to the shooting angle of the image acquisition device.

[0013] In combination with the second aspect, in some embodiments, generating target adjustment parameters includes: receiving a second object image from the electrical device, where the second object image is an image of the object to be identified located on the support seat obtained by the image acquisition device; performing image processing on the second object image to obtain the target adjustment parameters.

[0014] In combination with the second aspect, in some embodiments, a comparison model is deployed on the server, and the image processing of the second object image to obtain the target adjustment parameter includes: performing image classification on the second object image through the comparison model to obtain the target adjustment parameter; or performing information recognition on the second object image, and if the object information of the object to be identified is not identified from the second object image, performing image classification on the second object image through the comparison model to obtain the target adjustment parameter.

[0015] In combination with the second aspect, in some embodiments, the image classification of the second object image through the comparison model to obtain the target adjustment parameter includes: determining the size information of the object to be identified based on the second object image; inputting the second object image and the size information into the comparison model, and performing parameter matching through the comparison model to obtain the target adjustment parameter.

[0016] In conjunction with the second aspect, in some embodiments, the comparison model is a pre-established machine learning model or database, and the parameter matching through the comparison model to obtain the target adjustment parameter includes: predicting the adjustment parameter based on the second object image and the size information through the machine learning model to obtain the target adjustment parameter, the machine learning model is pre-trained using training samples, the training samples include training samples corresponding to multiple object sizes, and the training samples corresponding to each object size include object images of that size at different placement angles; or

[0017] The second object image is image-matched with object images in the database to match the target adjustment parameters, wherein the database includes a correspondence between object images and adjustment parameters for each object size at multiple shooting angles under multiple object sizes.

[0018] In a third aspect of the present invention, an electrical device is provided, comprising: a cabinet body, wherein an item identification area for accommodating items to be identified is provided in the cabinet body; an image acquisition device, arranged in the item identification area, and the shooting angle of the image acquisition device is toward a target position in the item identification area, and the target position is the position of the identification area of ​​the item to be identified; a supporting seat, arranged in the item identification area, and the supporting seat has a supporting surface for supporting the item to be identified; and a driving device, connected to the supporting seat to drive the supporting seat to rotate around an axis perpendicular to the supporting surface.

[0019] In combination with the third aspect, in some embodiments, it further includes: a positioning structure, which is arranged in the object identification area, and the positioning structure is used to limit the identification area of ​​the object to be identified to the target position.

[0020] In combination with the third aspect, in some embodiments, the electrical equipment is an item storage device, the cabinet body includes a cabinet shell and one or more shelves arranged in the cabinet shell, the cabinet shell and each of the shelves define the item identification area and multiple item storage areas; the positioning structure includes a positioning groove opened on one side of the shelf, and the groove direction of the positioning groove is opposite to the target position.

[0021] In combination with the third aspect, in some embodiments, the bearing seat is arranged at the bottom of the positioning groove; the driving device includes a driving motor, and the power output shaft of the driving motor is passed through the bottom of the positioning groove and fixedly connected to the bearing seat.

[0022] In combination with the third aspect, in some embodiments, the positioning structure further includes: a buffer member, which is arranged on the inner wall of the positioning groove.

[0023] In the fourth aspect of the present invention, an electronic device is also provided, comprising: a memory, a processor, and a computer program stored in the memory and runnable on the processor, characterized in that the processor is used to implement the object information identification method described in any embodiment of the first aspect or the object information identification method described in any embodiment of the second aspect when executing the computer program stored in the memory.

[0024] In the fifth aspect of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored, characterized in that when the program is executed by a processor, the method for identifying item information described in any embodiment of the first aspect or the method for identifying item information described in any embodiment of the second aspect is implemented.

[0025] In a sixth aspect of the present invention, there is provided an object information identification system, comprising an electrical device and a server, wherein the server establishes a communication connection with the electrical device, the electrical device comprises an object identification area, and an image acquisition device and a supporting seat are provided in the object identification area; the server is configured to generate target adjustment parameters and send the target adjustment parameters to the electrical device; the electrical device is configured to control the supporting seat and / or the image acquisition device to move to a target state according to the target adjustment parameters, obtain a first object image of the object to be identified carried on the supporting seat through the image acquisition device, and obtain object information of the object to be identified based on the first object image, wherein the target state is that the identification area of ​​the object to be identified is opposite to the shooting angle of the image acquisition device.

[0026] The one or more technical solutions provided by the embodiments of the present invention achieve at least the following technical effects or advantages:

[0027] Since the present invention utilizes the acquired target adjustment parameters to control the movement of the supporting seat and / or the image acquisition device, the identification area of ​​the object to be identified can be aligned with the shooting angle of the image acquisition device. After the identification area of ​​the object to be identified is aligned with the shooting angle of the image acquisition device, the first object image of the object to be identified is acquired by the image acquisition device, so that the acquired first object image can contain a clear and complete identification area of ​​the object to be identified, thereby improving the reliability of acquiring the object information of the object to be identified by capturing the object image, and eliminating the need for the user to manually adjust the position of the object to be identified on the supporting seat. Therefore, the technical effect of quickly and accurately identifying the object information of the object to be identified is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 A schematic diagram of the structure of electrical equipment provided by some embodiments of the present invention;

[0030] Figure 2 Schematic diagram of an object identification area in some embodiments of the present invention;

[0031] Figure 3 A schematic diagram of the position of an image acquisition device in some embodiments of the present invention;

[0032] Figure 4 Schematic diagrams of object identification areas in other embodiments of the present invention;

[0033] Figure 5 Schematic diagrams of object identification areas in some other embodiments of the present invention;

[0034] Figure 6 Schematic diagram of the structure of the supporting base and the driving device in some embodiments of the present invention;

[0035] Figure 7 for Figure 6 Cross-section of the middle bearing seat;

[0036] Figure 8 A flowchart of an item information identification method provided by some embodiments of the present invention;

[0037] Figure 9 Application scenarios of the object information identification method provided by some embodiments of the present invention;

[0038] Figure 10Flowcharts of object information identification methods provided in other embodiments of the present invention;

[0039] Figure 11 A schematic structural diagram of an electronic device provided in some embodiments of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0041] It should be noted that all directional indications in the embodiments of the present invention are only used to explain the relative position relationship and movement status of various components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0042] In the present invention, unless otherwise specified or limited, the terms "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can mean fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two elements or interaction between two elements, unless otherwise specified. Those skilled in the art will be able to understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0043] In addition, in the present invention, descriptions such as "first" and "second" are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0044] The embodiment of the present invention provides an electrical device 10, such as Figure 1 and Figure 2As shown, the electrical device 10 includes a cabinet 120, in which an item identification area 120a is provided. The item identification area 120a is a cavity for accommodating items to be identified. The item to be identified is an item with an identification area, such as alcoholic beverages, etc., wherein the identification area is an area that carries item information of the item to be identified. The identification area can be a label attached to the surface of the item or an image area printed on the surface of the item. The item to be identified can be alcoholic beverages (such as wine). An image acquisition device 121 and a support seat 122 for supporting the item to be identified are provided in the item identification area 120a. The support surface 122a of the support seat 122 is opposite to the target position in the item identification area 120a. The shooting angle of the image acquisition device 121 is opposite to the target position in the item identification area 120a. The target position is the position of the identification area of ​​the item to be identified when the item to be identified is supported on the support surface 122a of the support seat 122. The electrical device 10 also includes a driving device 123, which is connected to the supporting seat 122 to drive the supporting seat 122 to rotate around an axis perpendicular to the supporting surface 122a of the supporting seat 122. The rotation of the supporting seat 122 can drive the object to be identified placed on the supporting seat 122 to rotate, so as to change the orientation of the identification area of ​​the object to be identified relative to the image acquisition device 121.

[0045] In some embodiments, the electrical device 10 provided by the present invention further includes a positioning structure disposed in the item identification area 120a, the positioning structure being used to limit the position of the item to be identified in the item identification area 120a, so as to limit the identification area of ​​the item to be identified to the target position.

[0046] In some embodiments, the electrical device 10 provided by the present invention is an item storage device, which may be a household appliance for storing items, such as a refrigerator, a freezer, a vertical refrigerator, a wine cabinet, etc. Figure 1 As shown, in addition to the item identification area 120a, an item storage area 120b is also provided in the cabinet 120. The cabinet 120 includes a cabinet shell 125 and one or more shelves 126 disposed within the interior of the cabinet shell 125. The cabinet shell 125 and each shelf 126 define the item identification area 120a and the multiple item storage areas 120b.

[0047] It is understandable that the positioning structure may be disposed around the supporting seat 122 , so that when the object to be identified is supported on the supporting seat 122 , the horizontal position of the object to be identified is limited by the positioning structure.

[0048] In some embodiments, the positioning structure is integrally formed with the shelf 126 and is a part of the shelf 126, such as Figure 2As shown, the positioning structure includes a positioning groove 124a provided on the upper surface of the shelf 126 where the support seat 122 is located. The support seat 122 is embedded in the positioning groove 124a and is rotatable relative to the positioning groove 124a. In other words, the positioning groove 124a is provided on the upper surface of the shelf 126 for defining the object identification area 120a, and the notch direction of the positioning groove 124a is opposite to the target position. It can be understood that, as Figure 3 As shown, the positioning groove 124a can be a groove that adapts to the bottom shape of the object to be identified, and is used to place the object to be identified upright in the object identification area 120a. The bottom of the object to be identified falls into the positioning groove 124a and is supported on the support seat 122. It is understood that the projection of the positioning groove 124a along the groove direction can be circular, elliptical, or elongated to adapt to the bottom shape of the object to be identified.

[0049] In other embodiments, the positioning structure is independent of the shelf 126, such as Figures 4 and 5 As shown, the positioning structure is one or more positioning members 124b fixedly arranged on the upper surface of the shelf 126 where the support seat 122 is located. Figure 4 As shown, if the positioning structure is a single positioning member 124b fixedly arranged on the upper surface of the shelf 126 where the support seat 122 is located, the positioning member 124b can be a ring member to limit the position of the item to be identified on the support seat 122 in the horizontal direction. Figure 5 As shown, if the positioning structure is a plurality of positioning members 124b fixedly mounted on the upper surface of the shelf 126 on which the support seat 122 is located, the plurality of positioning members 124b surround and form an annular area. When an object to be identified is placed upright in the object identification area 120a, the bottom of the object to be identified is confined within the annular area enclosed by the positioning members 124b. The arc-shaped openings of the positioning members 124b are arranged relative to each other to form an annular area that horizontally confines the object to be identified.

[0050] like Figure 2 As shown, in some embodiments, the electrical device 10 may further include a buffer member 127 disposed inside the positioning structure. The buffer member 127 may be made of a lightweight, soft cushioning material, such as rubber, foam, etc. It is understood that if the positioning structure is the positioning groove 124a, the buffer member 127 is attached to the sidewall of the positioning groove 124a; if the positioning structure is the positioning member 124b, the buffer member 127 is attached to the annular inner wall of the positioning member 124b or the arc-shaped opening of each positioning member 124b.

[0051] like Figure 2As shown, in some embodiments, the positioning structure is a positioning groove 124a, and the bearing seat 122 is disposed at the bottom of the positioning groove 124a. The shape of the bearing seat 122 is adapted to the shape of the bottom of the positioning groove 124a so that the bearing seat 122 can be embedded in the bottom position of the positioning groove 124a. In other embodiments, the positioning structure is a positioning member 124b or multiple positioning members 124b fixed to the surface of the shelf 126. The bearing seat 122 is disposed on the surface of the shelf 126 or embedded in the interior of the shelf 126, and the bearing seat 122 is located below the annular area surrounded by the multiple positioning members 124b.

[0052] like Figure 6 As shown, in some embodiments, the driving device 123 includes a driving motor 123a, and the power output shaft of the driving motor 123a is fixedly connected to the supporting seat 122. Figure 2 As shown, for the positioning structure being a positioning groove 124a, the drive motor 123a can be buried in the cavity inside the shelf 126 or be arranged on the lower surface of the shelf 126, that is, another surface away from the surface where the positioning groove 124a is located, and the power output shaft of the drive motor 123a is passed through the bottom of the positioning groove 124a and is fixedly connected to the support seat 122 arranged in the positioning groove 124a.

[0053] In other embodiments, when the positioning structure is a positioning member 124b, a cavity for accommodating the drive motor 123a can be opened inside the shelf 126, and the drive motor 123a is buried in the cavity of the shelf 126. The drive motor 123a can also be fixedly set on the other surface of the shelf 126 away from the positioning member 124b. The power output shaft of the drive motor 123a passes through the shelf 126 and is fixedly connected to the support seat 122 located on the surface of the shelf 126.

[0054] In some embodiments, as Figure 6 and Figure 7 As shown, the driving device 123 also includes a rotating shaft 123b fixedly connected to the power output shaft of the driving motor 123a, and a clamping groove 122a is provided on the side of the supporting seat 122 away from the positioning groove 124a, and the rotating shaft 123b is clamped with the supporting seat 122 through the clamping groove 122a.

[0055] In other embodiments, the support base 122 is a circular support base with a gear on the edge, and the power output shaft sleeve of the drive motor 123a is provided with a drive wheel, and the drive motor 123a is gear-connected with the circular support base through the drive wheel (not shown).

[0056] Based on the same inventive concept, the present invention also provides an object information identification method, which is applied to an electrical device 10 including an object identification area 120a, such as Figures 1 to 7As shown, an image acquisition device 121 and a supporting seat 122 are provided in the object identification area 120a. The structure of the electrical device 10 can refer to one or more of the above embodiments, such as Figure 8 As shown, the object information identification method provided by the present invention includes the following steps S101 to S103.

[0057] S101 : When the object to be identified is placed on the supporting base 122 , a target adjustment parameter is obtained.

[0058] In some embodiments, step S101 includes: acquiring a second object image of the object to be identified by the image acquisition device 121 while the object to be identified is supported on the support base 122 ; and acquiring a target adjustment parameter according to the second object image.

[0059] In some embodiments, if it is detected that an object to be identified is placed in the object identification area 120a, the image acquisition device 121 is activated to capture the target position to obtain a second object image of the object to be identified.

[0060] In some embodiments, the electrical device further includes a cabinet door 110. Prior to step S101, the following may be performed: detecting whether the cabinet door 110 of the electrical device 10 is open. If the cabinet door 110 of the electrical device 10 is detected to be open, triggering the start of detecting whether an item to be identified is placed in the item identification area 120a. It is understood that the electrical device 10 is a wine cabinet, and the item to be identified is wine for which information is required to be identified. The wine information may include the specific type of wine, winery, vintage, etc.

[0061] A sensing device for sensing whether the cabinet door 110 is open or closed relative to the cabinet body 120 may be provided between the cabinet door 110 and the cabinet body 120. The sensing device generates a sensing signal indicating that the cabinet door 110 is opened when the cabinet door 110 is opened, and generates a sensing signal indicating that the cabinet door 110 is closed when the cabinet door 110 is closed, so that the electrical device 10 can detect whether the cabinet door 110 is opened and whether the cabinet door 110 is closed.

[0062] In some embodiments, a first presence sensing device is installed within the item identification area 120a for sensing whether an item to be identified has been placed within the item identification area 120a. The first presence sensing device may be a gravity sensor, an induction switch, or an infrared sensor, and may be disposed on the supporting surface 122a of the support base 122. When a user places an item to be identified within the item identification area 120a, the item to be identified is supported on the support base 122. The first presence sensing device generates a sensing signal indicating that an item has been placed within the item identification area 120a, enabling the electrical device 10 to detect that the item identification area 120a has changed from an empty state to a contained state, i.e., that an item to be identified has been placed within the item identification area 120a. If the change from an empty state to a contained state is detected, the image capture device 121 is activated to capture a target location within the item identification area 120a to obtain a second item image. The target location is the location of the identification area of ​​the item to be identified when the item to be identified is supported on the supporting surface of the support base 122.

[0063] In some embodiments, the second object image is a static picture of the object to be identified or a dynamic video at a certain angle obtained by the image acquisition device 121 shooting the target position.

[0064] like Figure 9 As shown, in an application scenario where the computing power of the electrical device 10 is relatively small, a communication connection is established between the electrical device 10 and the server 20. The electrical device 10 interacts with the server 20 to obtain target adjustment parameters based on the second object image. That is, in an application scenario where the computing power of the electrical device 10 is relatively small, obtaining target adjustment parameters based on the second object image includes: sending the second object image to the server 20, so that the server 20 performs image processing on the second object image after receiving the second object image to obtain the target adjustment parameters; and receiving the target adjustment parameters fed back by the server 20.

[0065] Next, after the server 20 receives the second object image, the process of performing image processing on the second object image to obtain the target adjustment parameter can be implemented in various ways, which are described below:

[0066] In some embodiments, after receiving the second object image, the server 20 performs information recognition on the second object image. Due to factors such as user operation differences, different types of objects, different brands of the same type of objects, different batches of the same type of objects, and different models, the identification area of ​​the object to be identified may deviate from the shooting angle of the image acquisition device 121. For example, the identification area of ​​the object to be identified may face away from the shooting angle of the image acquisition device 121, or part of the identification area may not be captured by the image acquisition device 121. These situations may result in the second object image lacking identifiable information or incomplete information, resulting in the inability to accurately identify the object information of the object to be identified when performing information recognition on the second object image. After the server 20 performs information recognition on the second object image, if the server 20 does not recognize the object information of the object to be identified from the second object image, the server 20 performs image classification on the second object image using a comparison model deployed on the server 20 to obtain target adjustment parameters. The server 20 then feeds the target adjustment parameters back to the electrical device 10. After the server 20 performs information recognition on the second object image, if the server 20 recognizes the object information of the object to be recognized from the second object image, the server 20 will feed back the object information recognized from the second object image to the electrical device 10. The electrical device 10 receives the object information of the object to be recognized fed back by the server 20, and the object information recognition process is completed.

[0067] In other embodiments, after receiving the second object image sent by the electrical device 10, the server 20 omits the process of identifying information on the second object image, and directly uses the comparison model deployed on the server 20 to compare the second object image to obtain the target adjustment parameter, and feeds back the object information identified from the second object image to the electrical device 10, wherein the parameter value of the target adjustment parameter is greater than or equal to 0.

[0068] It is understandable that the server 20 can be a cloud server or a local server.

[0069] In an application scenario where the computing power of the electrical device 10 is relatively high, the image of the second object can be processed locally on the electrical device 10 to obtain the target adjustment parameters. That is, the electrical device 10 does not need to interact with the server 20.

[0070] In some embodiments, locally performing image classification on the second object in the electrical device 10 to obtain the target adjustment parameter may include performing image classification on the second object in a comparison model deployed in the electrical device 10 to obtain the target adjustment parameter.

[0071] In other embodiments, the second object image is processed locally on the electrical device 10 to obtain target adjustment parameters, including: the electrical device 10 performs information recognition on the second object image; if the electrical device 10 does not recognize the object information of the object to be recognized from the second object image, the second object image is classified by a comparison model deployed on the electrical device 10 to obtain the target adjustment parameters; if the electrical device 10 recognizes the object information of the object to be recognized from the second object image, the target adjustment parameters are not required, and the information recognition process is completed.

[0072] In some embodiments, the electrical device 10 or the server 20 performs image classification on the second object image through a comparison model deployed on itself to obtain target adjustment parameters, which may include: determining size information of the object to be identified based on the second object image; inputting the second object image and size information into the comparison model, and performing parameter matching through the comparison model to obtain target adjustment parameters.

[0073] In some embodiments, whether the server 20 or the electrical device 10 performs image classification on the second object image using a comparison model deployed therein, the comparison model used can be a machine learning model. The machine learning model is pre-trained using training samples, wherein the training samples include training samples corresponding to multiple object sizes, and the training samples corresponding to each object size include images of objects of that size at different placement angles. The sample label of each training sample includes a rotation angle, or a rotation angle and rotation direction, or a rotation angle, rotation direction, and rotation speed. The trained machine learning model predicts adjustment parameters based on the second object image and size information to obtain target adjustment parameters.

[0074] In other embodiments, the comparison model used may be a database containing correspondences between object images of various sizes and at various shooting angles for each object size and adjustment parameters. Each object size corresponds to a value for the adjustment parameter at each placement angle, enabling the object to be identified to be rotated from its current placement angle to an angle corresponding to the shooting angle of the image acquisition device 121. The comparison model may use the second object image and size information as an index and compare it with object images of various sizes and at different placement angles stored in the database to retrieve the target adjustment parameters.

[0075] After obtaining the target adjustment parameters through any of the above-mentioned embodiments, step S102 is executed: after controlling the support base 122 and / or the image acquisition device 121 to move to a target state according to the target adjustment parameters, a first object image of the object to be identified is acquired through the image acquisition device 121, where the target state is that the identification area of ​​the object to be identified is aligned with the shooting angle of the image acquisition device 121.

[0076] In some embodiments, the target adjustment parameter may include a first rotation parameter for the support base 122 and / or a second rotation parameter for the image acquisition device 121. In some embodiments, the first rotation parameter includes a rotation angle; in other embodiments, the target adjustment parameter includes a rotation direction and a rotation angle; in yet other embodiments, the target adjustment parameter includes a rotation direction, a rotation angle, and a rotation angular velocity.

[0077] If the target adjustment parameters include a first rotation parameter and a second rotation parameter, the support base 122 is controlled to rotate according to the first rotation parameter to adjust the orientation of the identification area of ​​the object to be identified; and the image capture device 121 is controlled to rotate according to the second rotation parameter to adjust the shooting angle of the image capture device 121. The axis of rotation of the image capture device 121 is not parallel to the axis of rotation of the support base 122. For example, the axis of rotation of the image capture device 122 is perpendicular to the axis of rotation of the support base 122. That is, the support base 122 rotates about the vertical axis, while the image capture device 121 rotates about the horizontal axis. By controlling the joint rotation of the support base 122 and the image capture device 121, the image capture device 121 can more accurately capture the identification area of ​​the object to be identified.

[0078] In some embodiments, the electrical device 10 also includes a driving device 123 for driving the supporting seat 122 to rotate, and the power output shaft of the driving device 123 is connected to the supporting seat 122; the rotation of the supporting seat is controlled according to the first rotation parameter to adjust the orientation of the identification area of ​​the item to be identified, including: when the driving device 123 is operated according to the first rotation parameter, the direction and number of steps of the driving motor 123a are controlled, the operation of the driving device 123 drives the supporting seat 122 to rotate around an axis perpendicular to the supporting surface of the supporting seat 122 to a target state, and the rotation of the supporting seat 122 drives the item to be identified to rotate until the identification area of ​​the item to be identified is opposite to the image acquisition device 121.

[0079] In some embodiments, when the identification area of ​​the object to be identified is opposite to the shooting angle of the image acquisition device 121, the image acquisition device 121 is started to capture the target position in the object identification area 120a to obtain a first object image of the object to be identified.

[0080] It is understood that the image acquisition device 121 may include a single camera, and the first object image obtained during the current capture may be a static image of the object to be identified or a dynamic video of the object to be identified at a certain angle. To improve the reliability of obtaining object information of the object to be identified from the first object image, the image acquisition device 121 may include multiple cameras, and the first object image obtained during the current capture may include multiple images of the object to be identified at different angles or video clips of the object to be identified at multiple different angles.

[0081] S103: Acquire object information of the object to be identified based on the first object image.

[0082] In an application scenario where the computing power of the electrical device 10 is relatively large, obtaining the item information of the item to be identified based on the first item image may include: performing information recognition on the first item image locally on the electrical device 10 to obtain the item information of the item to be identified, without the need to interact with the server 20.

[0083] In an application scenario where the computing power of the electrical device 10 is relatively low, obtaining the item information of the item to be identified based on the first item image may include: sending the first item image to the server 20 so that the server 20 performs information recognition on the first item image to obtain the item information of the item to be identified; and receiving the item information of the item to be identified fed back by the server 20. It is understood that the server 20 may be a cloud server or a local server.

[0084] In some embodiments, when the electrical device 10 or the server 20 performs information recognition on the first object image, optical character recognition (OCR) technology may be used to extract a marking area from the first object image and perform text recognition on the marking area to identify the object information of the object to be recognized. Similarly, OCR technology may also be used when performing information recognition on the second object image.

[0085] In some embodiments, after sending the first object image to the server 20, it also includes: if a first prompt message is received from the server 20, the first prompt message is output, and the first prompt message is sent when the server 20 fails to recognize the object information of the object to be identified from the first object image. The first prompt message is used to prompt the user to adjust the placement position and / or placement angle of the object to be identified on the support base 122.

[0086] In some embodiments, after a preset time delay of outputting the first prompt information, a third object image of the object to be identified carried on the carrier 122 is acquired by the image acquisition device 121; and object information of the object to be identified is acquired based on the third object image.

[0087] In other embodiments, the position and / or angle of the object to be identified is detected to determine whether it has been adjusted within a preset time period after the first prompt message is output. If the position and / or angle of the object to be identified is detected to have been adjusted within the preset time period after the first prompt message is output, a third object image of the object to be identified supported on the support base 122 is captured by the image capture device 121. It is understood that the countdown to the preset time period is initiated simultaneously with or after the first prompt message is output.

[0088] In some embodiments, the specific implementation process of obtaining the item information of the item to be identified based on the third item image is similar to the specific implementation process of obtaining the item information of the item to be identified based on the first item image. The difference is that if the item information of the item to be identified is not identified from the third item image, a prompt message indicating that the item information of the item to be identified has failed to be identified is output.

[0089] In some embodiments, the first prompt information may be a graphic or text displayed on a display device of the electrical device 10 , or may be a prompt in the form of sound or light.

[0090] In some embodiments, the first prompt information may include reason information about the inability to identify the item information of the item to be identified from the first item image and / or graphic content and / or voice prompts guiding the user to correctly place the item to be identified in the item identification area 120a, etc.

[0091] Based on the same inventive concept, the present invention also provides an object information identification method, such as Figure 9 As shown, it is applied to the server 20, the server 20 establishes a communication connection with the electrical device 10, and the electrical device 10 includes an item identification area, such as Figure 1 As shown, an image acquisition device 121 and a supporting seat 122 are provided in the object identification area 120a. Figure 10 As shown, the object information identification method provided by the present invention and applied to the server 20 includes the following steps S201 to S202:

[0092] S201: Generate target adjustment parameters;

[0093] S202: Sending the target adjustment parameter to the electrical device 10 so that the electrical device 10 controls the support base 122 and / or the image acquisition device 121 to move to a target state according to the target adjustment parameter, and then acquiring a first object image of the object to be identified carried on the support base 122 through the image acquisition device 121, and acquiring object information of the object to be identified based on the first object image, wherein the target state is such that the identification area of ​​the object to be identified is aligned with the shooting angle of the image acquisition device 121.

[0094] In some embodiments, generating target adjustment parameters includes: receiving a second object image from the electrical device 10, where the second object image is an image of the object to be identified located on the support seat 122, obtained by the electrical device 10 through the image acquisition device 121; and performing image processing on the second object image to obtain the target adjustment parameters.

[0095] In some embodiments, performing image processing on the second object image to obtain the target adjustment parameter includes: performing image classification on the second object image through a comparison model to obtain the target adjustment parameter; in other embodiments, performing image processing on the second object image to obtain the target adjustment parameter includes: performing information recognition on the second object image, and if the object information of the object to be identified is not identified from the second object image, performing image classification on the second object image through a comparison model to obtain the target adjustment parameter.

[0096] In some embodiments, a comparison model is deployed on the server 20, and the second object image is classified by the comparison model to obtain target adjustment parameters, including: determining the size information of the object to be identified based on the second object image; inputting the second object image and the size information into the comparison model, and performing parameter matching by the comparison model to obtain the target adjustment parameters.

[0097] In some embodiments, the comparison model is a pre-established machine learning model, and performing parameter matching using the comparison model to obtain the target adjustment parameter includes: predicting the adjustment parameter based on the second object image and size information using the machine learning model to obtain the target adjustment parameter, wherein the machine learning model is pre-trained using training samples, the training samples including training samples corresponding to a plurality of object sizes, and the training samples corresponding to each object size including images of objects of that size at different placement angles;

[0098] In other embodiments, the comparison model is a pre-established database, and parameter matching is performed through the comparison model to obtain the target adjustment parameters, including: image matching the second object image with the object images in the database to match the target adjustment parameters, where the database includes a correspondence between object images and adjustment parameters of each object size at multiple shooting angles under multiple object sizes.

[0099] Since more implementation details of the item information identification method applied to the server 20 introduced in this embodiment can refer to the above-mentioned item information identification method applied to the electrical device 10, they are not repeated here for the sake of brevity.

[0100] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, such as Figure 11As shown, it includes a memory 1104, a processor 1102, and a computer program stored in the memory 1104 and executable on the processor 1102. When the electronic device is an electrical device 10, the processor 1102 executes the above-mentioned computer program to implement the above-mentioned method for identifying item information applied to the electrical device 10. When the electronic device is a server 20, the processor 1102 executes the above-mentioned computer program to implement the above-mentioned method for identifying item information applied to the server 20.

[0101] Among them, Figure 11 In the embodiment of the present invention, a bus architecture (represented by bus 1100) is shown. Bus 1100 may include any number of interconnected buses and bridges, and bus 1100 links various circuits including one or more processors represented by processor 1102 and memory represented by memory 1104. Bus 1100 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 1105 provides an interface between bus 1100 and receiver 1101 and transmitter 1103. Receiver 1101 and transmitter 1103 may be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 1102 is responsible for managing bus 1100 and general processing, while memory 1104 may be used to store data used by processor 1102 when performing operations.

[0102] Based on the same inventive concept, the present invention provides an item information identification system, such as Figure 9 As shown, the electrical device 10 includes an electrical device 10 and a server 20, and a communication connection is established between the server 20 and the electrical device 10. The electrical device 10 includes an object identification area 120a, and an image acquisition device 121 and a supporting seat 122 are provided in the object identification area 120a; the server 20 is used to: generate target adjustment parameters and send the target adjustment parameters to the electrical device 10; the electrical device 10 is used to: control the supporting seat 122 and / or the image acquisition device 121 to move to a target state according to the target adjustment parameters, and then obtain a first object image of the object to be identified carried on the supporting seat 122 through the image acquisition device 121, and obtain object information of the object to be identified based on the first object image. The target state is that the identification area of ​​the object to be identified is opposite to the shooting angle of the image acquisition device 121.

[0103] Since the item information identification system described in this embodiment is used to implement the item information identification method in the embodiments of the present invention, those skilled in the art will be able to understand the specific implementation and various variations of the item information identification system in this embodiment based on the item information identification method described in the embodiments of the present invention. Therefore, how the item information identification system implements the method in the embodiments of the present invention will not be described in detail here. As long as those skilled in the art can implement the item information identification system used in the item information identification method in the embodiments of the present invention, it falls within the scope of protection of the present invention.

[0104] Based on the same inventive concept, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the program implements an item information identification method to implement the above-mentioned item information identification method applied to the electrical device 10 or the above-mentioned item information identification method applied to the server 20.

[0105] In one or more embodiments of the present invention, the movement of the supporting seat and / or the image acquisition device is controlled by utilizing the acquired target adjustment parameters, so that the identification area of ​​the object to be identified is aligned with the shooting angle of the image acquisition device. After the identification area of ​​the object to be identified is aligned with the shooting angle of the image acquisition device, a first object image of the object to be identified is acquired by the image acquisition device, so that the acquired first object image can contain a clear and complete identification area of ​​the object to be identified, thereby improving the reliability of acquiring the object information of the object to be identified by capturing the object image, and eliminating the need for the user to manually adjust the position of the object to be identified on the supporting seat. Therefore, the technical effect of quickly and accurately identifying the object information of the object to be identified is achieved.

[0106] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0110] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0111] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for identifying item information, characterized in that: Applied to an electrical device including an object identification area, wherein an image acquisition device and a supporting seat are provided in the object identification area, the method comprises: When the object to be identified is carried on the carrying seat, obtaining target adjustment parameters; After controlling the support base and / or the image acquisition device to move to a target state according to the target adjustment parameter, a first object image of the object to be identified is acquired by the image acquisition device, wherein the target state is such that a marking area of ​​the object to be identified is aligned with a shooting angle of the image acquisition device; The object information of the object to be identified is acquired according to the first object image.

2. The method according to claim 1, wherein The obtaining of target adjustment parameters includes: acquiring a second image of the object to be identified by the image acquisition device; The target adjustment parameter is acquired according to the second object image.

3. The method according to claim 2, wherein The acquiring the target adjustment parameter according to the second object image includes: sending the second object image to a server, so that the server performs image processing on the second object image to obtain the target adjustment parameter; The target adjustment parameter fed back by the server is received.

4. The method according to claim 2, wherein A comparison model is deployed in the electrical device, and obtaining the target adjustment parameter according to the second object image includes: performing image classification on the second object image using the comparison model to obtain the target adjustment parameter, or Information recognition is performed on the second object image. If the object information of the object to be identified is not identified from the second object image, image classification is performed on the second object image using the comparison model to obtain the target adjustment parameter.

5. The method according to claim 2, wherein The acquiring the item information of the to-be-identified item according to the first item image includes: Sending the first object image to a server so that the server performs information recognition on the first object image to obtain object information of the object to be recognized; Receive the item information of the item to be identified fed back by the server.

6. The method according to claim 5, wherein After sending the first object image to the server, the method further includes: If a first prompt message is received from the server, the first prompt message is output. The first prompt message is sent when the server fails to recognize the item information of the item to be identified from the first item image. The first prompt message is used to prompt the user to adjust the placement position and / or placement angle of the item to be identified on the support base. After a preset time delay of outputting the first prompt information, acquiring, by the image acquisition device, a third object image of the object to be identified carried on the carrying seat; The object information of the object to be identified is acquired according to the third object image.

7. The method according to any one of claims 1 to 6, wherein The target adjustment parameters include a first rotation parameter and a second rotation parameter; The step of controlling the supporting base and / or the image acquisition device to move to a target state according to the target adjustment parameter includes: Controlling the rotation of the supporting base according to the first rotation parameter to adjust the orientation of the marking area of ​​the object to be identified; The image acquisition device is controlled to rotate according to the second rotation parameter to adjust the shooting angle of the image acquisition device, and the axis of rotation of the image acquisition device is not parallel to the axis of rotation of the supporting base.

8. The method according to claim 7, wherein The electrical device further comprises a driving device for driving the bearing seat to rotate, wherein a power output shaft of the driving device is connected to the bearing seat; The controlling the rotation of the supporting base according to the first rotation parameter to adjust the orientation of the marking area of ​​the object to be identified includes: The operation of the driving device is controlled according to the first rotation parameter. The operation of the driving device drives the supporting seat to rotate around an axis perpendicular to the supporting surface of the supporting seat. The rotation of the supporting seat drives the object to be identified to rotate so that the marking area of ​​the object to be identified is opposite to the image acquisition device.

9. A method for identifying item information, characterized in that: Applied to a server, the server establishes a communication connection with an electrical device, the electrical device includes an object identification area, an image acquisition device and a supporting seat are provided in the object identification area, and the method includes: generating target adjustment parameters; The target adjustment parameters are sent to the electrical device so that the electrical device controls the supporting seat and / or the image acquisition device to move to a target state according to the target adjustment parameters, and then a first object image of the object to be identified carried on the supporting seat is acquired by the image acquisition device, and object information of the object to be identified is acquired based on the first object image, wherein the target state is that the identification area of ​​the object to be identified is opposite to the shooting angle of the image acquisition device.

10. The method according to claim 9, wherein Generate target adjustment parameters, including: receiving a second object image from the electrical device, where the second object image is an image of the object to be identified located on the supporting seat, obtained by the image acquisition device; Perform image processing on the second object image to obtain the target adjustment parameter.

11. The method according to claim 10, wherein A comparison model is deployed on the server, and image processing is performed on the second object image to obtain the target adjustment parameter, including: performing image classification on the second object image using the comparison model to obtain the target adjustment parameter; or Information recognition is performed on the second object image. If the object information of the object to be identified is not identified from the second object image, image classification is performed on the second object image using the comparison model to obtain the target adjustment parameter.

12. The method according to claim 11, wherein The performing image classification on the second object image by using the comparison model to obtain the target adjustment parameter includes: determining size information of the object to be identified based on the second object image; The second object image and the size information are input into the comparison model, and parameter matching is performed through the comparison model to obtain the target adjustment parameters.

13. The method according to claim 12, wherein: The comparison model is a pre-established machine learning model or database, and the parameter matching is performed through the comparison model to obtain the target adjustment parameter, including: predicting an adjustment parameter based on the second object image and the size information using the machine learning model to obtain the target adjustment parameter, wherein the machine learning model is pre-trained using training samples, the training samples including training samples corresponding to a plurality of object sizes, and the training samples corresponding to each object size including images of objects of that size at different placement angles; or The second object image is image-matched with object images in the database to match the target adjustment parameters, wherein the database includes a correspondence between object images and adjustment parameters for each object size at multiple shooting angles under multiple object sizes.

14. An electrical device, characterized in that: include: A cabinet body, wherein an item identification area for accommodating items to be identified is provided in the cabinet body; An image acquisition device is disposed in the object identification area, and the shooting angle of the image acquisition device is directed toward a target position in the object identification area, where the target position is the location of the identification area of ​​the object to be identified; A supporting seat is provided in the item identification area, and the supporting seat has a supporting surface for supporting the item to be identified; A driving device is connected to the bearing seat to drive the bearing seat to rotate around an axis perpendicular to the bearing surface.

15. The electrical device according to claim 14, characterized in that: Also includes: A positioning structure is provided in the object identification area, and the positioning structure is used to limit the identification area of ​​the object to be identified to the target position.

16. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the item information identification method according to any one of claims 1 to 8 or the item information identification method according to any one of claims 9 to 13 when executing the computer program stored in the memory.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the item information identification method according to any one of claims 1 to 8 or the item information identification method according to any one of claims 9 to 13 is implemented.

18. An item information recognition system, characterized in that: The apparatus comprises an electrical device and a server, wherein the server establishes a communication connection with the electrical device, the electrical device comprises an object identification area, and an image acquisition device and a supporting seat are provided in the object identification area; The server is configured to generate target adjustment parameters and send the target adjustment parameters to the electrical device; The electrical device is used to control the support base and / or the image acquisition device to move to a target state according to the target adjustment parameter, obtain a first object image of the object to be identified carried on the support base through the image acquisition device, and obtain object information of the object to be identified based on the first object image, wherein the target state is that the identification area of ​​the object to be identified is opposite to the shooting angle of the image acquisition device.

Images