Method and apparatus for determining properties of an article

Abstract

The application discloses a method and device for determining an attribute of an article, and relates to the technical field of computers. The method comprises the following steps: acquiring an article image of a preset article; identifying the article image by using a first image recognizer to obtain a first attribute value of the preset article and a score of the first attribute value; identifying the article image by using a second image recognizer to obtain a second attribute value of the preset article; determining the first attribute value as a target attribute value of the preset article in response to determining that the score of the first attribute value is greater than a preset threshold; and determining the second attribute value as the target attribute value of the preset article in response to determining that the score of the first attribute value is not greater than the preset threshold. The method can improve the accuracy of determining the attribute value of the article.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to a method and device for determining attributes of an item. BACKGROUND

[0002] A commodity can be described by using attribute information of the commodity, which can facilitate a user to search for a desired commodity and facilitate a push system to accurately push the commodity. An existing method for determining attribute information of a commodity usually includes: determining attribute information of a commodity by voting through multiple image recognition models, or determining attribute information of a commodity based on key information of the commodity.

[0003] However, the existing method for determining attribute information of a commodity has the problem of inaccuracy. SUMMARY

[0004] The present disclosure provides a method and device for determining attributes of an item, an electronic device, and a computer readable storage medium.

[0005] According to a first aspect of the present disclosure, a method for determining attributes of an item is provided, including: obtaining an item image of a preset item; identifying the item image by using a first image recognizer to obtain a first attribute value of the preset item and a score of the first attribute value; identifying the item image by using a second image recognizer to obtain a second attribute value of the preset item; in response to determining that the score of the first attribute value is greater than a preset threshold, determining the first attribute value as a target attribute value of the preset item; and in response to determining that the score of the first attribute value is not greater than the preset threshold, determining the second attribute value as the target attribute value of the preset item.

[0006] In some embodiments, identifying the item image by using the first image recognizer to obtain the first attribute value of the preset item and the score of the first attribute value includes: identifying the item image by using the first image recognizer to obtain multiple candidate attribute values under at least one candidate attribute of the preset item and a score of each of the multiple candidate attribute values; and for each of the at least one candidate attribute, determining a candidate attribute value with the highest score under the candidate attribute as the first attribute value under the candidate attribute.

[0007] In some embodiments, identifying the item image by using the second image recognizer to obtain the second attribute value of the preset item includes: identifying, by using the second image recognizer, a similarity between the item image and a candidate image in a database; obtaining multiple candidate images with a similarity to the item image satisfying an image similarity threshold; and determining the second attribute value according to attribute values corresponding to multiple candidate items to which the multiple candidate images belong.

[0008] In some embodiments, the method for determining the attribute of the item comprises: obtaining category information of a preset item; obtaining a first attribute value of the preset item and a score of the first attribute value, comprising: obtaining the first attribute value of the preset item under the category information and the score of the first attribute value; and obtaining a second attribute value of the preset item, comprising: obtaining the second attribute value of the preset item under the category information.

[0009] In some embodiments, the method for determining the attribute of the item further comprises: in response to determining that the similarity between the attribute value of the currently presented preset item and the target attribute value does not satisfy the similarity threshold, generating prompt information for indicating to modify the attribute value of the currently presented preset item.

[0010] According to a second aspect of the present disclosure, a device for determining the attribute of an item is provided, comprising: a first obtaining unit configured to obtain an item image of a preset item; a first obtaining unit configured to identify the item image using a first image recognizer, obtain a first attribute value of the preset item and a score of the first attribute value; a second obtaining unit configured to identify the item image using a second image recognizer, obtain a second attribute value of the preset item; a first determining unit configured to determine the first attribute value as a target attribute value of the preset item in response to determining that the score of the first attribute value is greater than a preset threshold; and a second determining unit configured to determine the second attribute value as the target attribute value of the preset item in response to determining that the score of the first attribute value is not greater than the preset threshold.

[0011] In some embodiments, the first obtaining unit comprises: a first obtaining module configured to identify the item image using the first image recognizer, obtain a plurality of candidate attribute values under at least one candidate attribute of the preset item and a score of each of the plurality of candidate attribute values; and a first determining module configured to determine, for each of the at least one candidate attribute, the candidate attribute value with the highest score under the candidate attribute as the first attribute value under the candidate attribute.

[0012] In some embodiments, the second obtaining unit comprises: a second obtaining module configured to identify the similarity between the item image and a candidate image in the database using the second image recognizer; a second determining module configured to obtain a plurality of candidate images with a similarity to the item image satisfying an image similarity threshold; and a third determining module configured to determine the second attribute value according to attribute values corresponding to a plurality of candidate items to which the plurality of candidate images belong.

[0013] In some embodiments, the apparatus comprises: a second acquisition unit configured to acquire category information of the preset item; a first obtaining unit comprising: a first obtaining submodule configured to obtain a first attribute value of the preset item under the category information and a score of the first attribute value; and a second obtaining unit comprising: a second obtaining submodule configured to obtain a second attribute value of the preset item under the category information.

[0014] In some embodiments, the apparatus further comprises: a prompting unit configured to, in response to determining that the similarity between the attribute value of the currently presented preset item and the target attribute value does not satisfy the similarity threshold, generate prompt information for indicating modification of the attribute value of the currently presented preset item.

[0015] According to a third aspect of the present disclosure, embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining an attribute of an item as provided in the first aspect.

[0016] According to a fourth aspect of the present disclosure, embodiments of the present disclosure provide a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method for determining an attribute of an item as provided in the first aspect.

[0017] The method and apparatus for determining an attribute of an item provided by the present disclosure comprise: acquiring an item image of a preset item; identifying the item image by using a first image recognizer to obtain a first attribute value of the preset item and a score of the first attribute value; identifying the item image by using a second image recognizer to obtain a second attribute value of the preset item; in response to determining that the score of the first attribute value is greater than a preset threshold, determining the first attribute value as a target attribute value of the preset item; and in response to determining that the score of the first attribute value is not greater than the preset threshold, determining the second attribute value as the target attribute value of the preset item, which can improve the accuracy of determining the attribute value of the item.

[0018] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings are used to better understand the present scheme, and do not limit the present application. Among them:

[0020] Figure 1 is an example system architecture diagram to which embodiments of the present application can be applied;

[0021] Figure 2is a flow chart of one embodiment of a method for determining an attribute of an item according to the present application;

[0022] Figure 3 is a flow chart of another embodiment of a method for determining an attribute of an item according to the present application;

[0023] Figure 4 is a flow chart of one application scenario of a method for determining an attribute of an item according to the present application;

[0024] Figure 5 is a flow chart of another application scenario of a method for determining an attribute of an item according to the present application;

[0025] Figure 6 is a structural schematic diagram of one embodiment of an apparatus for determining an attribute of an item according to the present application;

[0026] Figure 7 is a block diagram of an electronic device for implementing the method for determining an attribute of an item according to the embodiments of the present application. DETAILED DESCRIPTION

[0027] The exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to assist in understanding, and should be considered as merely exemplary. Thus, those of ordinary skill in the art will recognize various changes and modifications of the embodiments described herein, without departing from the scope and spirit of the present application. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0028] Figure 1 An exemplary system architecture 100 to which embodiments of the method for determining an attribute of an item or the apparatus for determining an attribute of an item of the present application can be applied is shown.

[0029] As shown in Figure 1 , the system architecture 100 can include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is a medium to provide a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0030] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 can be user terminal devices, on which various client applications can be installed, such as image type applications, video type applications, shopping type applications, chat type applications, search type applications, financial type applications, etc.

[0031] The terminal devices 101, 102, and 103 can be various electronic devices with a display screen and supporting receiving server messages, including but not limited to a smart phone, a tablet computer, an electronic book reader, an electronic player, a laptop computer, and a desktop computer, and the like.

[0032] The terminal devices 101, 102, and 103 can be hardware or software. When the terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, and when the terminal devices 101, 102, and 103 are software, they can be installed in the above-mentioned electronic devices. They can be implemented as multiple software or software modules (for example, multiple software modules for providing distributed services) or as a single software or software module. No specific limitation is made herein.

[0033] The server 105 can obtain an item image of a preset item through the terminal devices 101, 102, and 103, identify the item image by using a first image identifier, and obtain a first attribute value of the preset item and a score of the first attribute value, identify the item image by using a second image identifier, and obtain a second attribute value of the preset item, determine the first attribute value as a target attribute value of the preset item if it is determined that the score of the first attribute value is greater than a preset threshold, and determine the second attribute value as the target attribute value of the preset item if it is determined that the score of the first attribute value is not greater than the preset threshold.

[0034] It should be noted that the method for determining an item attribute provided by the embodiments of the present disclosure can be executed by the server 105, and accordingly, the apparatus for determining an item attribute can be arranged in the server 105.

[0035] It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely illustrative. Any number of terminal devices, networks, and servers can be provided according to implementation needs.

[0036] With reference to Figure 2 , a flow 200 of one embodiment of the method for determining an item attribute according to the present disclosure is shown, including the following steps:

[0037] Step 201: Obtain an item image of a preset item.

[0038] In the present embodiment, the execution subject of the method for determining an item attribute (for example, the server 105) obtains an item image of a preset item. Figure 1The server 105 shown can obtain the product image of the preset product through wired or wireless means. The preset product can be a product to be listed / published, or a product that has been listed. When the product is a product to be listed, the following steps can be used to obtain the attribute value of the product; when the product is a product that has been listed, the following steps can be used to verify whether the attribute value currently presented / displayed by the product is accurate. The attribute value refers to a specific parameter of the product / commodity under a certain attribute. For example, under the color attribute, the attribute value can be red, blue, etc.; under the mobile phone battery life attribute, the attribute value can be 10 hours, 20 hours, etc.; under the clothing size attribute, the attribute value can be small size, large size, etc.

[0039] In step 202, a first image recognizer is used to recognize the product image to obtain a first attribute value of the preset product and a score of the first attribute value.

[0040] In this embodiment, the first image recognizer can be used to recognize the product image of the preset product and obtain the first attribute value of the preset product and the score of the first attribute value. The first image recognizer can be a pre-trained image recognition model that can perform image recognition on an input image to determine the attribute value of the recognized image and the score (e.g., the accuracy probability) of the attribute value. The first image recognizer can be an image structure-based recognizer that is used to identify a specific attribute value of a product, and has the characteristics of high recognition accuracy but low recall rate.

[0041] In step 203, a second image recognizer is used to recognize the product image to obtain a second attribute value of the preset product.

[0042] In this embodiment, the second image recognizer can be used to recognize the product image of the preset product and obtain the second attribute value of the preset product. The second image recognizer can be a pre-trained image recognition model that can perform image recognition on an input image and determine multiple attribute values of the product contained in the image according to the recognition result. The second image recognizer can be a general attribute value recognizer that is used to identify multiple attribute values of a product, and has the characteristics of low recognition accuracy but high recall rate.

[0043] In step 204, in response to determining that the score of the first attribute value is greater than a preset threshold, the first attribute value is determined as the target attribute value of the preset product.

[0044] In this embodiment, if it is determined that the score of the first attribute value of the preset image obtained by the first image recognizer is greater than a preset threshold, the first attribute value can be determined as the target attribute value of the preset product.

[0045] In step 205, in response to determining that the score of the first attribute value is not greater than the preset threshold, the second attribute value is determined as the target attribute value of the preset object.

[0046] In this embodiment, if it is determined that the score of the first attribute value of the preset image obtained by the first image recognizer is not greater than the preset threshold, the second attribute value recognized by the second image recognizer can be determined as the target attribute value of the preset object.

[0047] The method for determining an attribute of an object provided in this embodiment comprises the following steps: obtaining an object image of a preset object; recognizing the object image by using a first image recognizer to obtain a first attribute value of the preset object and a score of the first attribute value; recognizing the object image by using a second image recognizer to obtain a second attribute value of the preset object; in response to determining that the score of the first attribute value is greater than a preset threshold, determining the first attribute value as a target attribute value of the preset object; and in response to determining that the score of the first attribute value is not greater than the preset threshold, determining the second attribute value as the target attribute value of the preset object. This can improve the accuracy of determining the attribute value of the object.

[0048] Optionally, the step of recognizing the object image by using the first image recognizer to obtain the first attribute value of the preset object and the score of the first attribute value comprises the following steps: recognizing the object image by using the first image recognizer to obtain multiple candidate attribute values under at least one candidate attribute of the preset object and a score of each candidate attribute value in the multiple candidate attribute values; and for each candidate attribute under the at least one candidate attribute, determining the candidate attribute value with the highest score under the candidate attribute as the first attribute value under the candidate attribute.

[0049] In this embodiment, the first image recognizer can be used to recognize the object image to obtain multiple candidate attribute values under at least one candidate attribute of the recognized object (for example, based on a picture containing clothes, multiple attributes such as length of clothes, length of sleeves and collar type can be output, and multiple candidate attribute values can be output under each attribute) and a score of each candidate attribute value recognized (the score is used to represent the accuracy of the first image recognizer in determining that the object has the candidate attribute value), and for each candidate attribute, the candidate attribute value with the highest score under the candidate attribute is determined as the first attribute value of the preset object under the candidate attribute output by the first image recognizer. In this way, the first image recognizer can determine multiple candidate attribute values based on multiple candidate attributes.

[0050] In this embodiment, the first image recognizer determines the first attribute value based on the score of the candidate attribute value, which can improve the accuracy and efficiency of determining the first attribute value.

[0051] Optionally, the second image recognizer is used to identify the item image to obtain the second attribute value of the preset item, including: using the second image recognizer to identify the similarity between the item image and the candidate image in the database; obtaining a plurality of candidate images with a similarity to the item image satisfying an image similarity threshold; and determining the second attribute value according to the attribute values corresponding to the plurality of candidate items to which the plurality of candidate images belong.

[0052] In the embodiment, the second image recognizer can be used to identify the similarity between the item image and the candidate image in the database, and obtain a plurality of candidate images with a similarity to the item image satisfying a pre-set image similarity threshold (which can be understood as a step of searching for an image from an image), determine a plurality of candidate items to which the plurality of candidate images belong respectively, and obtain at least one candidate attribute corresponding to the plurality of candidate items and a plurality of attribute values under each candidate attribute. When determining the second attribute value under each candidate attribute, for each candidate attribute, the attribute values of the plurality of candidate items under the candidate attribute and overlapping each other (or the highest number of overlapping) can be determined as the second attribute value of the preset item under the candidate attribute. Thus, the second image recognizer can determine a plurality of candidate attribute values based on a plurality of candidate attributes.

[0053] In the embodiment, the second image recognizer can search for candidate items with determined attribute values by using the image of the preset item, and determine the attribute value based on the attribute value of the candidate item as the second attribute value of the preset item, which can improve the recall rate of determining the second attribute value. Searching for items with attribute values in the database based on the image and using the attribute value of the item with the attribute value as the attribute value to be determined can reduce the time for generating the attribute value of the item and improve the efficiency of determining the second attribute value. In addition, since the attribute values stored in the database are usually verified during the use of the scene or verified by maintenance personnel, using the attribute values stored in the database as the attribute value to be determined can improve the accuracy of determining the second attribute value.

[0054] It should be noted that in step 202 or the optional implementation of step 202, a plurality of attributes of the item can be identified in parallel, that is, the identifiers respectively applied to different attributes of the item can identify different attributes of the item in parallel to identify the attribute value under each attribute and the score of the attribute value in parallel. In step 203 or the optional implementation of step 203, a plurality of attributes of the item can be identified in parallel to identify the attribute value under each attribute in parallel. It should be noted that step 202 and step 203 can be executed in parallel or sequentially. The optional implementation of step 202 and the optional implementation of step 203 can be executed in parallel or sequentially.

[0055] With reference to both Figure 3 , another embodiment of a method for determining an attribute of an item according to the present disclosure is shown as flow 300, comprising the following steps:

[0056] Step 301, obtaining an item image of a preset item and category information of the preset item.

[0057] In the present embodiment, the execution subject of the method for determining an attribute of an item (e.g. Figure 1 The server 105 shown) can obtain an item image of a preset item and category information of the preset item through wired or wireless means, wherein the category information of the preset item is used to represent the item category to which the preset item belongs.

[0058] Step 302, identifying the item image using a first image identifier to obtain a first attribute value of the preset item under the category information and a score of the first attribute value.

[0059] In the present embodiment, the first image identifier can be used to identify the item image of the preset item and obtain a first attribute value of the preset item under the category to which it belongs and a score of the first attribute value. It can be understood that the same item image can have different attribute values under different categories. For example, an image containing a cat has attribute values such as "Garfield, short hair cat" related to breed or "active" related to personality under the pet category, while an image containing a cat has attribute values such as "plastic material, metal material" related to material or "detachable" related to installation method under the handicraft category.

[0060] Step 303, identifying the item image using a second image identifier to obtain a second attribute value of the preset item under the category information.

[0061] In the present embodiment, the second image identifier can be used to identify the image of the preset item and obtain a second attribute value of the preset item under the category to which it belongs.

[0062] Step 304, in response to determining that the score of the first attribute value is greater than a preset threshold, determining the first attribute value as a target attribute value of the preset item.

[0063] Step 305, in response to determining that the score of the first attribute value is not greater than the preset threshold, determining the second attribute value as the target attribute value of the preset item.

[0064] The description of steps 304 and 305 in the present embodiment is consistent with the description of steps 204 and 205, which will not be repeated here.

[0065] The method for determining an attribute of an item provided in the present embodiment can be used to determine the attribute of the preset item in a more accurate and efficient manner compared to Figure 2The embodiments described add a step of obtaining the category information of the preset item, and the first attribute value and the second attribute value determined are both attribute values under the category information of the preset item, which can improve the accuracy of determining the first attribute value and the second attribute value, thereby improving the accuracy of determining the target attribute value of the preset item.

[0066] In the above combination Figure 2 and Figure 3 In some optional implementations of the embodiments described, the method for determining the attribute of the item further includes: in response to determining that the similarity between the attribute value of the preset item currently presented and the target attribute value does not satisfy the similarity threshold, generating prompt information for indicating modification of the attribute value of the preset item currently presented.

[0067] In the present embodiment, if it is determined that the similarity between the attribute value of the preset item currently presented and the target attribute value does not satisfy the similarity threshold, it indicates that the attribute value of the preset item currently presented is inaccurate, and the prompt information for indicating modification of the attribute value of the preset item currently presented is generated to prompt the user to update the attribute value of the preset item currently presented with the target attribute value.

[0068] In the present embodiment, the target attribute value determined based on the first image recognizer and the second image recognizer is used to detect whether the attribute value of the preset item currently presented is accurate, and prompt information is generated to prompt the user to update the attribute value of the preset item currently presented in the case where it is inaccurate, which can improve the efficiency of maintaining the item information and ensure the accuracy of the item information.

[0069] In some application scenarios, as Figure 4 shown, the method for determining the attribute of the item can be applied before a product is listed / published, including the following steps:

[0070] Step 401: Obtain the category to which the product belongs input by the user.

[0071] Step 402: Obtain the image of the product input by the user.

[0072] Step 403: Obtain the first recognition accuracy requirement (for example, 90%) input by the user, and obtain the attribute value of the product by using the method for determining the attribute of the item.

[0073] Specifically, the first image recognizer in the method for determining the attribute of the item determines that the accuracy of a certain attribute value is not less than 90%, and only then takes the attribute value as the first attribute value output by the first image recognizer, or the first image recognizer determines that the probability of the commodity having a certain attribute value is not less than 90%, and only then takes the attribute value as the first attribute value output by the first image recognizer; and the second image recognizer determines that the accuracy of a certain attribute value is not less than 90%, and only then takes the attribute value as the second attribute value output by the second image recognizer, or the second image recognizer determines that the probability of the commodity having a certain attribute value is not less than 90%, and only then takes the attribute value as the second attribute value output by the second image recognizer. Thus, it is ensured that the accuracy of the target attribute value determined by the method for determining the attribute of the item meets the recognition accuracy requirement input by the user.

[0074] In step 404, the attribute value of the commodity is calibrated based on the calibration information of the attribute value of the commodity input by the user.

[0075] In step 405, a second recognition accuracy requirement (for example, 98%) input by the user is obtained, and the attribute value of the commodity calibrated in step 404 is verified by the method for determining the attribute of the item.

[0076] Specifically, based on the second recognition accuracy requirement input by the user, the first image recognizer in the method for determining the attribute of the item determines that the accuracy of a certain attribute value is not less than 98%, and only then takes the attribute value as the first attribute value output by the first image recognizer, or the first image recognizer determines that the probability of the commodity having a certain attribute value is not less than 98%, and only then takes the attribute value as the first attribute value output by the first image recognizer; and the second image recognizer determines that the accuracy of a certain attribute value is not less than 98%, and only then takes the attribute value as the second attribute value output by the second image recognizer, or the second image recognizer determines that the probability of the commodity having a certain attribute value is not less than 98%, and only then takes the attribute value as the second attribute value output by the second image recognizer. Thus, it is ensured that the accuracy of the target attribute value determined by the method for determining the attribute of the item meets the recognition accuracy requirement input by the user. The target attribute value is compared with the attribute value calibrated in step 404 for similarity, and if the similarity does not meet a preset similarity threshold, a prompt information is sent to prompt the user to calibrate the attribute value again or to use the target attribute value.

[0077] In step 406, the commodity and the attribute value of the commodity are published.

[0078] It should be noted that in this application scenario, the commodity is usually a non-standard commodity, for example, clothes, shoes, handicrafts, etc. (The standard commodity corresponding to the non-standard commodity includes electronic products, electrical products, and other commodities with standard parameters or industry specifications.)

[0079] In some application scenarios, such as Figure 5 As shown in FIG. 6, the method for determining the attribute of an item can be applied after the goods are listed / published, for verifying whether the attribute value of the goods already published is accurate, including the following steps:

[0080] Step 501, the attribute value of the published goods is determined by the method for determining the attribute of an item, and the attribute value currently published / presented is compared with the determined attribute value for similarity to determine whether the attribute value currently presented is accurate.

[0081] Step 502, if the similarity between the attribute value currently presented and the determined attribute value does not satisfy the similarity threshold, for example, neither identical nor belonging to synonymous / similar language expressions, it is determined that the attribute value currently presented is inaccurate, the prompt information indicating to modify the attribute value currently presented is sent to the user, and the determined attribute value can be pushed to the user as the push information.

[0082] Step 503, the new attribute value of the goods is received by the user.

[0083] Step 504, after receiving the new attribute value of the goods input by the user, the method for determining the attribute of an item is used to determine again whether the new attribute value is accurate.

[0084] Step 505, the attribute value of the published goods is updated.

[0085] It should be noted that in this application scenario, the goods are usually non-standard goods.

[0086] Further referring to Figure 6 As an implementation of the method shown in the above figures, the present disclosure provides an embodiment of an apparatus for determining the attribute of an item, which corresponds to the method embodiment shown in Figure 2 and Figure 3 The apparatus can be specifically applied in various electronic devices.

[0087] As shown in FIG. 7, the apparatus for determining the attribute of an item includes a processor 701, a memory 702 and a communication interface 703. Figure 6As shown, the device for determining the attribute of the item in the embodiment comprises a first obtaining unit 601, a first obtaining unit 602, a second obtaining unit 603, a first determining unit 604, and a second determining unit 605. The first obtaining unit is configured to obtain an item image of a preset item. The first obtaining unit is configured to identify the item image by using a first image recognizer, and obtain a first attribute value of the preset item and a score of the first attribute value. The second obtaining unit is configured to identify the item image by using a second image recognizer, and obtain a second attribute value of the preset item. The first determining unit is configured to determine the first attribute value as a target attribute value of the preset item in response to determining that the score of the first attribute value is greater than a preset threshold. The second determining unit is configured to determine the second attribute value as the target attribute value of the preset item in response to determining that the score of the first attribute value is not greater than the preset threshold.

[0088] In some embodiments, the first obtaining unit comprises a first obtaining module configured to identify the item image by using the first image recognizer, and obtain a plurality of candidate attribute values under at least one candidate attribute of the preset item and a score of each of the plurality of candidate attribute values. The first determining module is configured to determine, for each of the at least one candidate attribute, a candidate attribute value with the highest score under the candidate attribute as the first attribute value under the candidate attribute.

[0089] In some embodiments, the second obtaining unit comprises a second obtaining module configured to identify, by using the second image recognizer, a similarity between the item image and a candidate image in the database. The second determining module is configured to obtain a plurality of candidate images with a similarity to the item image satisfying an image similarity threshold. The third determining module is configured to determine the second attribute value according to attribute values corresponding to a plurality of candidate items to which the plurality of candidate images belong.

[0090] In some embodiments, the device comprises a second obtaining unit configured to obtain category information of the preset item. The first obtaining unit comprises a first obtaining submodule configured to obtain a first attribute value of the preset item under the category information and a score of the first attribute value. The second obtaining unit comprises a second obtaining submodule configured to obtain a second attribute value of the preset item under the category information.

[0091] In some embodiments, the device further comprises a prompting unit configured to generate prompt information for indicating modification of the attribute value of the currently presented preset item in response to determining that a similarity between the attribute value of the currently presented preset item and the target attribute value does not satisfy a similarity threshold.

[0092] The units in the device 600 described above can refer to the units in the device 100 described with reference to FIG. 1. Figure 2 and Figure 3The steps in the described methods correspond. Thus the operations, features and technical effects described above for the method for determining an attribute of an item apply equally to the apparatus 600 and the units contained therein, which are not described again here.

[0093] According to embodiments of the present application, the present application also provides an electronic device and a readable storage medium.

[0094] As Figure 7 shown is a block diagram of an electronic device 700 for a method for determining an attribute of an item according to embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0095] As Figure 7 shown, the electronic device includes one or more processors 701, memory 702, and interfaces 703 for the various components. The various components communicate over one or more busses 704 that are associated with a bus interface 705. Memory 702 stores instructions and data used by the processor 701. The memory 702 can include non-removable memory and / or removable memory. The instructions and data include those specifically designed and constructed to carry out the functions described in the present application, and / or pre-existing components marginally coupled with the present application such as network interfaces and memory stored solely on a non-removable memory. Figure 7 The processor 701 is used to execute instructions for software running on the electronic device, including instructions for implementing functionality of the present application.

[0096] The memory 702 is a non-transitory computer-readable storage medium provided by the present application. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the method for determining an attribute of an item provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the method for determining an attribute of an item provided by the present application.

[0097] Memory 702, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for determining item attributes in the embodiments of this application (e.g., appendix). Figure 6 The first acquisition unit 601, the first acquisition unit 602, the second acquisition unit 603, the first determination unit 604, and the second determination unit 605 are shown. The processor 701 executes various functional applications and data processing of the server by running non-transient software programs, instructions, and modules stored in the memory 702, that is, it implements the method for determining item attributes in the above method embodiments.

[0098] Memory 702 may include a program storage area and a data storage area. The program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device for extracting video clips. Furthermore, memory 702 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 702 may optionally include memory remotely located relative to processor 701, and this remote memory may be connected to the electronic device for extracting video clips via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0099] The electronic device for determining the attributes of an item may further include: an input device 703, an output device 704, and a bus 705. The processor 701, memory 702, input device 703, and output device 704 may be connected via the bus 705 or other means. Figure 7 Taking the connection between China and Israel via bus 705 as an example.

[0100] Input device 703 can receive input digital or character information, and generate key signal inputs related to user settings and function control of the electronic device used to extract video clips, such as touch screens, keypads, mice, trackpads, touchpads, joysticks, one or more mouse buttons, trackballs, joysticks, etc. Output device 704 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The display device may include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device may be a touch screen.

[0101] Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0102] These computer programs (also known as programs, software, software applications or code) include machine instructions for the programmable processor, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0103] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0104] The systems and techniques described here can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0105] The computer system can include clients and servers. This relationship can be

[0106] It should be understood that the procedures shown above can be re-ordered, added to, or removed from, while still falling within the scope of the technology disclosed in this application. For example, the steps recited in this application can be performed in parallel, in series, or in a different order, without limitation, as long as the desired results of the technology disclosed in this application are achieved.

[0107] The specific embodiments have been shown and described for purposes of illustrating the applications disclosed herein, and not for purposes of limitation. It will be clear to those of ordinary skill in the art that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the applications. Any further modifications, changes, improvements, and the like that come within the spirit and scope of the applications should be considered as falling within the scope of the applications.

Claims

1. A method for determining item attributes, comprising: Get the image of the preset item; The first image recognizer is used to recognize the image of the item, and multiple candidate attribute values ​​under at least one candidate attribute of the preset item and the score of each candidate attribute value are obtained. The first attribute value of the at least one candidate attribute is determined based on the score of each candidate attribute value, and the score represents the accuracy probability of the candidate attribute value. A second image recognizer is used to identify the similarity between the item image and candidate images in the database, and to obtain multiple candidate images whose similarity with the item image meets the image similarity threshold. At least one candidate attribute corresponding to the multiple candidate items to which the multiple candidate images belong, and multiple attribute values ​​under each candidate attribute, are determined. The attribute value with the highest overlap among the multiple candidate items under each candidate attribute is determined as the second attribute value of the preset item under that candidate attribute. The second image recognizer is a general attribute value recognizer used to identify multiple attribute values ​​of the preset item. In response to determining that the score of the first attribute value is greater than a preset threshold, the first attribute value is determined as the target attribute value of the preset item; In response to determining that the score of the first attribute value is not greater than the preset threshold, the second attribute value is determined as the target attribute value of the preset item.

2. The method according to claim 1, wherein, The step of using a first image recognizer to recognize the image of the item and obtain a first attribute value of the preset item and a score for the first attribute value includes: The first image recognizer is used to recognize the image of the item, and multiple candidate attribute values ​​under at least one candidate attribute of the preset item are obtained, as well as the score of each candidate attribute value among the multiple candidate attribute values. For each candidate attribute under the at least one candidate attribute, the candidate attribute value with the highest score under that candidate attribute is determined as the first attribute value under that candidate attribute.

3. The method according to claim 1, wherein, The method includes: Obtain the category information of the preset items; The process of obtaining the first attribute value of the preset item and the score of the first attribute value includes: Obtain the first attribute value of the preset item under the category information, and the score of the first attribute value; Obtaining the second attribute value of the preset item includes: Obtain the second attribute value of the preset item under the category information.

4. The method according to claim 1, wherein, The method further includes: In response to determining that the similarity between the attribute value of the currently presented preset item and the target attribute value does not meet the similarity threshold, a prompt message is generated to instruct the modification of the attribute value of the currently presented preset item.

5. An apparatus for determining the properties of an article, comprising: The first acquisition unit is configured to acquire the image of a preset item; The first obtaining unit is configured to use a first image recognizer to recognize the image of the item, obtain multiple attribute values ​​under at least one candidate attribute of the preset item and a score for each candidate attribute value, and determine a first attribute value of the at least one candidate attribute based on the score of each candidate attribute value, wherein the score represents the accuracy probability of the candidate attribute value. The second obtaining unit is configured to use a second image recognizer to identify the similarity between the item image and candidate images in the database, obtain multiple candidate images whose similarity with the item image meets an image similarity threshold, determine at least one candidate attribute corresponding to the multiple candidate items to which the multiple candidate images belong, and multiple attribute values ​​under each candidate attribute, and determine the attribute value with the highest overlap among the multiple candidate items under each candidate attribute as the second attribute value of the preset item under that candidate attribute, wherein the second image recognizer is a general attribute value recognizer used to recognize multiple attribute values ​​of the preset item; The first determining unit is configured to determine the first attribute value as the target attribute value of the preset item in response to determining that the score of the first attribute value is greater than a preset threshold. The second determining unit is configured to determine the second attribute value as the target attribute value of the preset item in response to determining that the score of the first attribute value is not greater than the preset threshold.

6. The apparatus according to claim 5, wherein, The first obtaining unit includes: The first obtaining module is configured to use the first image recognizer to recognize the image of the item, and obtain multiple candidate attribute values ​​under at least one candidate attribute of the preset item, and a score for each of the multiple candidate attribute values; The first determining module is configured to, for each candidate attribute under the at least one candidate attribute, determine the candidate attribute value with the highest score under that candidate attribute as the first attribute value under that candidate attribute.

7. The apparatus according to claim 5, wherein, The device includes: The second acquisition unit is configured to acquire the category information of the preset item; The first obtaining unit includes: The first acquisition submodule is configured to acquire the first attribute value of the preset item under the category information, and the score of the first attribute value; The second obtaining unit includes: The second acquisition submodule is configured to acquire the second attribute value of the preset item under the category information.

8. The apparatus according to claim 5, wherein, The device further includes: The prompting unit is configured to generate a prompt message in response to determining that the similarity between the attribute value of the currently presented preset item and the target attribute value does not meet a similarity threshold, thereby instructing the modification of the attribute value of the currently presented preset item.

9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

Images