CN110909698A

CN110909698A - Electronic scale recognition result output method, system, device and readable storage medium

Info

Publication number: CN110909698A
Application number: CN201911192440.0A
Authority: CN
Inventors: 陈建
Original assignee: Zhejiang Youyou Technology Co Ltd
Current assignee: Zhejiang Youyou Technology Co Ltd
Priority date: 2019-11-28
Filing date: 2019-11-28
Publication date: 2020-03-24

Abstract

The embodiment of the application discloses an electronic scale identification result output method. The method may include at least one of: the image to be identified of the current commodity acquired by the image acquisition device can be acquired. The image to be recognized can be recognized to obtain at least one recognition result. A candidate class for the current item may be determined from the at least one recognition result based on an output restriction condition. Commodity information of the candidate class may be acquired. The candidate categories of the current goods may be displayed based on the goods information. The electronic scale identification result output method disclosed by the embodiment of the application can effectively improve the output accuracy of the electronic scale identification result.

Description

Electronic scale recognition result output method, system, device and readable storage medium

Technical Field

The present disclosure relates to the field of electronic scales, and more particularly, to a method, a system, and an apparatus for outputting an identification result of an electronic scale, and a computer readable storage medium.

Background

At present, after a user purchases goods, some non-standard goods need a salesman to input a bar code, or the user needs to search a goods code by himself, and much time is needed for identifying the goods, so that the settlement efficiency of the goods is low. Therefore, the electronic scale identification result output method is provided so that commodities can be identified quickly and accurately.

Disclosure of Invention

One aspect of the embodiments of the present application provides an electronic scale recognition result output method. The electronic scale recognition result output method may include at least one of the following operations: the image to be identified of the current commodity acquired by the image acquisition device can be acquired. The image to be recognized can be recognized to obtain at least one recognition result. A candidate class for the current item may be determined from the at least one recognition result based on an output restriction condition. Commodity information of the candidate class may be acquired. The candidate categories of the current goods may be displayed based on the goods information.

Another aspect of the embodiments of the present application provides an electronic scale recognition result output method. The electronic scale recognition result output method may include at least one of the following operations: the image to be identified of the current commodity acquired by the image acquisition device can be acquired. Image features of the image to be recognized may be extracted. The image to be recognized may be recognized based on the recognition constraint and the image feature, resulting in at least one recognition result. A candidate class for the current item may be determined from the at least one recognition result. Commodity information of the candidate class may be acquired. The candidate categories may be displayed based on the merchandise information.

Another aspect of an embodiment of the present application provides an electronic scale recognition result output system, which includes a first obtaining module, a recognition module, a determination module, a second obtaining module, and a display module. The first obtaining module can be used for obtaining the image to be identified of the current commodity, which is collected by the image collecting device. The identification module may be configured to identify the image to be identified to obtain at least one identification result. The determining module may be configured to determine a candidate class for the current item from the at least one recognition result based on an output constraint. The second obtaining module may be configured to obtain commodity information of the candidate class. The display module may be configured to display the candidate class of the current item based on the item information.

Another aspect of the embodiments of the present application provides an electronic scale recognition result output system. The electronic scale identification result output system comprises a first acquisition module, an extraction module, an identification module, a determination module, a second acquisition module and a display module. The first obtaining module can be used for obtaining the image to be identified of the current commodity, which is collected by the image collecting device. The extraction module can be used for extracting the image characteristics of the image to be identified. The identification module may be configured to identify the image to be identified based on an identification limiting condition and the image feature to obtain at least one identification result. The determining module may be configured to determine a candidate class for the current item from the at least one recognition result. The second obtaining module may be configured to obtain commodity information of the candidate class. The display module may be configured to display the candidate categories based on the merchandise information.

Another aspect of the embodiments of the present application provides an electronic scale recognition result output apparatus including a processor for performing an electronic scale recognition result output method.

Another aspect of the embodiments of the present application provides a computer-readable storage medium storing computer instructions, and when the computer reads the computer instructions in the storage medium, the computer performs an electronic scale recognition result output method.

Drawings

The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a schematic diagram of an exemplary merchandise information acquisition system according to some embodiments of the present application;

fig. 2 is an exemplary flowchart of an electronic scale recognition result output method according to some embodiments of the present application;

FIG. 3 is an exemplary flow chart illustrating the determination of a candidate class for a current good according to some embodiments of the present application;

FIG. 4 is an exemplary flow chart illustrating another electronic scale identification result output method according to some embodiments of the present application;

FIG. 5 is a block diagram of an electronic scale recognition result output system according to some embodiments of the present application; and

fig. 6 is a block diagram of another electronic scale recognition result output system according to some embodiments of the present application.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

The electronic scale recognition result output method disclosed by the application can be applied to various scenes including but not limited to large-scale shopping malls, supermarkets, farmer markets and the like. At present, in the prior art, when bulk commodities are weighed and priced, the weights of the commodities can be weighed by an electronic scale so as to calculate the total price. And with the development of electronic commerce, electronic scales are used by more and more users. However, in the process of implementing the present invention, the inventor finds that the use of the current electronic scale has at least the following problems when in use: taking a supermarket as an example, when an electronic scale is used in the supermarket to weigh and price an article, the article to be weighed needs to be placed in a weighing area of the electronic scale, then a service worker confirms the type of the article, and the encoding or price of the article is assisted to be input for pricing. Therefore, the efficiency of identifying a product in settlement of the product is often influenced by experience of a service person, for example, the familiarity with the type of the product and the code of the product.

Therefore, in order to improve the settlement efficiency of a shopping mall for weighing and pricing commodities, the electronic scale recognition result output method is provided, so that the commodity recognition efficiency during commodity settlement is improved, and the commodity settlement efficiency is improved. The technical solutions disclosed in the present application are explained below by the description of the drawings.

FIG. 1 is a schematic illustration of an exemplary merchandise information acquisition system according to some embodiments of the present application. As shown in fig. 1, the product information acquiring system 100 may be used for weighing and price settlement of products in a shopping mall or a supermarket. The merchandise information acquisition system 100 may include an information acquisition apparatus 110, a network 120, a terminal 130, a processing engine 140, and a storage device 150.

The information acquisition device 110 may include an acquisition device such as a camera and a sensor, and may also include data acquisition that supports related identification technologies such as Radio Frequency Identification (RFID) and product electronic tags (EPC). The camera means may comprise a video camera, video recorder, infrared camera or other device capable of acquiring image or video data. The sensor may include one or more of an infrared sensor, an ultrasonic sensor, a distance sensor, a light sensor, a gravity sensor, an acceleration sensor, a direction sensor, and the like, or any combination thereof.

The image information of the commodity acquired by the information acquisition device 110 and other related commodity information are transmitted to the terminal 130, and the terminal 130 can perform information identification on the commodity based on the related information. The terminal 130 may also be used to obtain manually entered information, display merchandise information, and otherwise process the merchandise information. In some embodiments, the information acquiring apparatus 110 may be integrated with the terminal 130, or may be separated from the terminal, and the present application is not limited thereto.

The terminal 130 may include a weighing apparatus 131 and a weighing aid 132, or any combination thereof. The terminal 130 may be a tool for weighing and settlement in a current market or supermarket, such as an electronic scale or an electromechanical combination scale. The weighing device 131 may comprise a scale pan, scale body or like weighing system. The weighing aid 132 may include force transfer systems (e.g., lever force transfer systems, sensors), indicating systems (e.g., dials, electronic displays), and buttons for entering merchandise information. In some embodiments, the terminal 130 may also include an RFID communication for contactless data exchange with a radio transceiver connected to the product.

In some embodiments, the weighing assisting device 132 may further include or be connected to a code printing device, and send the obtained weight of the commodity and the input commodity unit price information to the code printing device, and print an identifier such as a price label, a barcode, a two-dimensional code, or the like. In this specification, the terminal 130 may further include a function of directly performing settlement, and a salesperson may perform settlement for cash after weighing, or may perform weighing and settlement for payment by a customer.

Processing engine 140 may obtain user instructions from terminal 130 via network 120. Network 120 may be and/or include a public network (e.g., the internet), a private network (e.g., a Local Area Network (LAN), a Wide Area Network (WAN)), etc.), a wired network (e.g., an ethernet network), a wireless network (e.g., an 802.11 network, a Wi-Fi network, etc.), a cellular network (e.g., a Long Term Evolution (LTE) network), a frame relay network, a Virtual Private Network (VPN), a satellite network, a telephone network, a router, a hub, a switch, a server computer, and/or any combination thereof. Do only toBy way of example, network 120 may include a cable network, a wireline network, a fiber optic network, a telecommunications network, an intranet, a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), Bluetooth, or a network interface^TMNetwork purple bee^TMA network, a Near Field Communication (NFC) network, etc., or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired and/or wireless network access points, such as base stations and/or internet switching points, through which one or more components of system 100 may be connected to network 120 to exchange data and/or information. In some embodiments, the connection may be made using a cable, wireless network (bluetooth, WLAN, Wi-Fi, etc.), mobile network (3G, 4G, or 5G signals), or other connection means (VPN, shared network, NFC, etc.).

In some embodiments, processing engine 140 may execute or be used to perform the exemplary methods described herein, in accordance with data and/or instructions. For example, the processing engine 140 may acquire an image to be identified of the current article captured by the image capturing device. The image to be recognized can be recognized to obtain at least one recognition result. A candidate class for the current item may be determined from the at least one recognition result based on an output restriction condition. Commodity information of the candidate class may be acquired. The candidate categories of the current goods may be displayed based on the goods information.

In some embodiments, processing engine 140 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.

Storage device 150 may store data, instructions, and/or any other information. In some embodiments, storage device 150 may store data retrieved from terminal 130 and/or processing engine 140. In some embodiments, storage device 150 may store data and/or instructions that processing engine 140 may perform or be used to perform the exemplary methods described herein. In some embodiments, storage device 150 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state drives, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memory may include Random Access Memory (RAM). Exemplary RAM may include Dynamic RAM (DRAM), Double Data Rate Synchronous Dynamic RAM (DDRSDRAM), Static RAM (SRAM), thyristor RAM (T-RAM), and zero capacitance RAM (Z-RAM). Exemplary ROMs may include Mask ROM (MROM), Programmable ROM (PROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), compact disk ROM (CD-ROM), and digital versatile disk ROM, among others. In some embodiments, the storage device 150 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.

In some embodiments, storage device 150 may be connected to network 120 to communicate with one or more other components of system 100 (e.g., processing engine 140, terminal 130, etc.). One or more components of system 100 may access data or instructions stored in storage device 150 via network 120. In some embodiments, storage device 150 may be directly connected to or in communication with one or more other components of system 100 (e.g., processing engine 140, terminal 130, etc.). In some embodiments, storage device 150 may be part of processing engine 140.

Fig. 2 is an exemplary flowchart illustrating an electronic scale recognition result output method according to some embodiments of the present application. In some embodiments, one or more steps of method 200 may be implemented in system 100 shown in FIG. 1. For example, one or more steps of method 200 may be stored as instructions in storage device 150 and invoked and/or executed by processing engine 140.

And step 210, acquiring an image to be identified of the current commodity acquired by the image acquisition device. Step 210 may be performed by the first obtaining module 510.

In some embodiments, the image to be recognized may be image data captured by an image capture device, such as the image information acquisition device 110 shown in fig. 1. The image to be recognized can be used for recognizing the commodity class of the current commodity. The image acquisition device can be a camera, a video camera, a camera or a scanner. The current goods may be items placed in a certain area (e.g., an identification area of an electronic scale or within an image capturing range of an image capturing device). In some embodiments, the items may include merchandise that does not have an identification code, such as vegetables, fruits, eggs, or other non-standard merchandise. In some embodiments, the item may also include an item having an identification code, for example, a bulk item with an identification code package that the user needs to weigh for a fee after picking.

In some embodiments, the image acquisition device may obtain the image to be identified of the current commodity by taking a picture, scanning, or shooting a video. For example, the image acquisition device may directly photograph in a photographing manner to obtain an image to be recognized, or scan the current commodity in a scanning manner, convert an optical signal irradiated on the current commodity into a corresponding electrical signal, and convert the corresponding electrical signal into image data to obtain the image to be recognized; or shooting a short video for the current commodity through the camera, and capturing an image of a video frame from the short video as an image to be identified. In some embodiments, the image to be identified may be obtained directly from the acquisition device that acquires the current product, such as the information acquisition device 110, or may be obtained from a storage device (e.g., the storage device 150) or a product database via a network (e.g., the network 120), or may be obtained via an interface or other means.

And step 220, identifying the image to be identified to obtain at least one identification result. Step 220 may be performed by the identification module 520.

In some embodiments, the identification result may be a classification result about the current item, which is obtained from image information of the image to be identified after the image to be identified is processed by an image identification technology. In some embodiments, the number of recognition results obtained by recognizing the image to be recognized may be one. In some embodiments, the number of recognition results obtained by recognizing the image to be recognized may be multiple. For example only, taking the current commodity as a potato in vegetables, after the current commodity is identified by the image identification technology, the obtained identification result may be a plurality of identification results with similar shapes such as potatoes, lotus roots, kiwifruits or ginseng fruits.

In some embodiments, the image to be recognized may be recognized using image recognition techniques. Specifically, the image to be recognized may be recognized based on a machine learning model. In some embodiments, features may be extracted from the image, and then the features may be input into the machine learning model through recognition by the machine learning model facing the classification, so as to obtain a classification result. The classification result may be one or more classification values corresponding to the category of the commodity. It may also be an evaluation value belonging to a certain category for the image to be recognized. For example, an image has an evaluation value of 0.92 for a potato and an evaluation value of 0.89 for a kiwi. The classification model used may include KNN, SVM or BP neural networks, among others. Preferably, in some embodiments, the image may be directly input to a Convolutional Neural Network (CNN) based machine learning model, resulting in a classification result. Alternatively, the image to be recognized may be preprocessed before recognition, for example, to adjust the brightness, remove noise, and the like. The machine learning models can be obtained through training. The features can be extracted based on the sample pictures by taking the actual commodity types of the sample pictures as the identifiers or corresponding training can be directly carried out on the machine learning model based on the pictures.

In some embodiments, image recognition may be based on other common image recognition algorithms. The image recognition algorithm may include: scale Invariant Feature Transform (SIFT) algorithm, Speeded Up Robust Features (SURF) algorithm, corner detection (Harris) algorithm, feature point detection (FAST) algorithm, etc.

Step 230, determining a candidate class of the current product from the at least one recognition result based on the output limiting condition. Step 230 may be performed by determination module 530.

In some embodiments, the output limiting condition may be a filtering condition that filters some of the at least one recognition result. In some embodiments, it may be that the image recognition algorithm determines the candidate class for the current item based on an output constraint. In some embodiments, it may be that the user determines the candidate class for the current item according to an output restriction. Further description of the output limiting conditions can be found elsewhere in the present application, for example, in the description of fig. 3, which is not repeated here.

In some embodiments, the candidate category of the current item may be a certain category determined from the at least one recognition result. For example, taking the current commodity as a potato as an example, after the image to be recognized is recognized, the obtained recognition result may include a potato, a lotus root, a kiwi fruit and a ginseng fruit, and finally, the type of the potato which may be a candidate of the current commodity is determined from the recognition result according to the output limitation condition. In some embodiments, the candidate categories of the current item may be a plurality of categories determined a plurality of times from the at least one recognition result. For example, also taking the current commodity as a potato as an example, the recognition result may include a potato, a lotus root, a kiwi fruit, and a ginseng fruit, and the potato and the ginseng fruit may be the candidate class of the current commodity, which is finally determined from the recognition result based on the output limit. Reference may be made to other parts of the description, for example, fig. 3, regarding how to determine a candidate class from the recognition result based on the output restriction condition.

And step 240, acquiring commodity information of the candidate class. Step 240 may be performed by the second obtaining module 540.

In some embodiments, the commodity information may be integrated information including a name, unit price, place of manufacture, manufacturer, date of manufacture, commodity number, and the like of the candidate class. For example, in the case where the candidate is a potato, the product information may be potato/potato, renminbi 2.00 yuan/kg, Sichuan of origin, XX agricultural company of manufacturer, 1 month and 1 day of 2019, product number 123456, and the like. In some embodiments, the merchandise information may be obtained directly from the electronic scale, may be obtained from a storage device (e.g., storage device 150) or a merchandise database via a network (e.g., network 120), or may be obtained via an interface or other means.

And 250, displaying the candidate categories based on the commodity information. Step 250 may be performed by display module 550.

In some embodiments, the displaying may be displaying the commodity information of the candidate category through the display module 550, and the displaying may be used for verification and confirmation by the user. The display content may be the commodity information of the candidate class, and the display mode may be characters, pictures, texts, images, videos, and the like, which is not limited in this specification. Further explanation of the manner of display may be found elsewhere in this specification, for example, in fig. 3.

It should be noted that the above description related to the flow 200 is only for illustration and explanation, and does not limit the applicable scope of the present application. Various modifications and changes to flow 200 will be apparent to those skilled in the art in light of this disclosure. However, such modifications and variations are intended to be within the scope of the present application.

FIG. 3 is an exemplary flow chart illustrating the determination of a candidate class for a current good according to some embodiments of the present application. In some embodiments, one or more steps of method 300 may be implemented in system 100 shown in FIG. 1. For example, one or more steps of method 300 may be stored as instructions in storage device 150 and invoked and/or executed by processing engine 140. In some embodiments, the method 300 may be performed by the determination module 530.

And 310, determining effective recognition results in the recognition results based on the output limiting conditions.

In some embodiments, the output constraints may include context information, inventory information, historical sales data, and the like. In some embodiments, the valid recognition result may be a recognition result of a candidate class corresponding to the valid recognition result, which is likely to be the genuine class of the current commodity. It is also understood that the recognition result remaining after the possibly incorrect recognition result is removed from the recognition results. Specifically, the output restriction condition may be matched with the recognition result to obtain a valid recognition result. In some embodiments, the valid recognition result may be determined based on an output constraint using an image recognition algorithm. In some embodiments, it may be that the user determines the valid recognition result from the recognition results according to an output restriction condition. The output limitation condition may be obtained directly from the image capturing apparatus (e.g., the information obtaining apparatus 110 in fig. 1), or may be obtained from a storage device (e.g., the storage device 150), a product database via a network (e.g., the network 120), or may be obtained via an interface or other means.

How to determine the valid recognition result in the recognition results can be performed by using various methods, which are only examples, and the methods in the following embodiments may be used, and other methods may also be used, and the present invention is not limited.

In some embodiments, a valid result of the recognition results may be determined based on context information. The scene information may be store area information of a position where the electronic scale is located, for example, the scene information may be a fruit store area, a vegetable store area, a meat store area, a seafood store area, or the like. In some embodiments, the recognition result may be matched with the context information to determine that the recognition result is a valid recognition result if the recognition result matches with the context information. For example, the scene information is a vegetable store area, and the recognition result includes potatoes, kiwi fruits, lotus roots and ginseng fruits. Matching the recognition result with a vegetable store area, wherein the kiwi fruits and the ginseng fruits belong to fruits and are not matched with the vegetable store area; the potatoes and the lotus roots belong to the matching of the vegetable and vegetable store areas, and therefore the identification results of the corresponding potatoes and the corresponding lotus roots can be used as effective identification results. In some embodiments, the scene information may be obtained directly by the image capture device (e.g., the information obtaining device 110), may be obtained from a storage device (e.g., the storage device 150) or a scene database via a network (e.g., the network 120), or may be obtained via an interface or other means.

In some embodiments, a valid identification result of the valid identification results may be determined based on inventory information. The inventory information may include warehousing information, inventory remaining information, and ex-warehouse information. In some embodiments, after acquiring inventory information corresponding to the identification result, it may be determined whether the product corresponding to the identification result has inventory according to the inventory information, and in a case where the product corresponding to the identification result has inventory, the identification result may be determined to be the valid identification result. For example, after the inventory information corresponding to the identification result is obtained, if the product corresponding to the identification result does not have inventory according to the warehousing information, the inventory remaining information and the ex-warehouse information of the inventory information, the current product may not be the candidate class corresponding to the identification result; on the contrary, if the product has the stock, the current product may be the candidate class corresponding to the recognition result, and the recognition result may be regarded as a valid recognition result. In some embodiments, inventory information may be obtained directly from the electronic scale, may be obtained from a storage device (e.g., storage device 150) or a database of merchandise via a network (e.g., network 120), or may be obtained via an interface or otherwise.

In some embodiments, it may be determined whether the identification result is the valid identification result based on the historical sales data and the inventory information. The historical sales data may reflect sales of the goods over a certain period of time, and the probability of the user selecting the goods may be derived based on the sales. Similarly, the inventory information may reflect the commodity selection probability of the user to a certain extent, and the sales condition of the commodity may be obtained according to the inventory information and the inventory remaining information, or the inventory information and the inventory leaving information, so that the commodity sales are more, the user selection probability is higher, the probability that the user selects the commodity is higher, the probability that the candidate type corresponding to the identification result is the current commodity is higher, and the corresponding identification result may be an effective identification result. In some embodiments, historical sales data may be obtained directly from the electronic scale, may be obtained from a storage device (e.g., storage device 150) or a database of goods via a network (e.g., network 120), or may be obtained via an interface or otherwise.

In step 320, the identification evaluation value of the effective identification result is obtained.

In some embodiments, the identification evaluation value may be an evaluation value of the probability that the effective identification result is the correct item class of the current commodity by the identification module 520. In some embodiments, the identification evaluation value may be derived from an evaluation value of a kind of an image to be identified, which is obtained by identifying an image according to a machine learning model. For example, in the classification result obtained by identifying the image by using the machine learning model, through statistics, the average of the evaluation values of the images to be identified in the similar classification result, which belong to potatoes, is 0.92, and the average of the evaluation values of the images which belong to kiwifruits is 0.89, so that the identification evaluation value can be the average evaluation value of the classification result. In some embodiments, the identification evaluation value may be obtained directly from the electronic scale, may be obtained from a storage device (e.g., the storage device 150) or a product database via a network (e.g., the network 120), or may be obtained via an interface or other means.

Step 330, based on the identification evaluation value, determining the candidate class of the current commodity from the effective identification result.

In some embodiments, the candidate categories of the current item may be one or more categories determined from the at least one recognition result. In some embodiments, the identification evaluation value may be an average evaluation value of images to be identified belonging to a certain category. The evaluation value can extract features from the image, and then the features are recognized by a machine learning model facing the classification and input into the machine learning model. In some embodiments, the valid recognition result whose recognition evaluation value is the largest may be determined as the candidate class of the current article. In some embodiments, the identification evaluation values may be sorted from large to small, and the valid identification results ranked N-th before the evaluation value are the candidate class of the current product, where N is an integer greater than or equal to 2, such as 2, 3, 5, 7, 9, 10, and so on. In some embodiments, a corresponding recognition probability may be obtained according to the maximum result of the recognition evaluation value, and then it is determined whether the recognition probability is greater than a preset confidence threshold, and if the recognition probability is greater than the confidence threshold, it may be determined that the effective recognition result with the maximum recognition evaluation value is the candidate class of the current commodity. The confidence threshold may be set according to the confidence that the valid recognition result corresponding to the maximum recognition evaluation value of each candidate item is the correct value of the current item.

After determining the candidate category of the current commodity, the corresponding commodity information may be displayed, and various methods may be adopted during the display, which is only an example, and the method in the following embodiment may be adopted, or other methods may also be adopted, and the present invention is not limited.

In some embodiments, the candidate class whose identification evaluation value satisfies the preset condition may be highlighted based on the identification evaluation value. For example, taking the current commodity as a potato, the identification results include a potato, a lotus root, a kiwi fruit, and a ginseng fruit, and the corresponding identification evaluation values may be 0.95, 0.70, 0.80, and 0.90, respectively. In some embodiments, the preset condition may be a condition set for whether or not to display the candidate class, and may include that the identification evaluation value is greater than a preset threshold and/or that the identification evaluation value is located N bits before the evaluation value ranking, where N is an integer greater than or equal to 2. In some embodiments, the highlighting may distinguish the corresponding display result from other display results, which may be more likely to be the focus of attention of the user, facilitating the user's selection.

In some embodiments, the preset condition may be that the recognition evaluation value is greater than a preset threshold value. In some embodiments, the preset condition may be to identify that the evaluation value is located N bits before the evaluation value ranking, where N is an integer equal to or greater than 2. For example, the recognition evaluation values are sorted from large to small, and the candidate class corresponding to the recognition evaluation value ranked three top is highlighted. In some embodiments, the preset condition may be that the identification evaluation value is greater than a preset threshold value and the rank name is N bits before the evaluation value ranking, where N is an integer greater than or equal to 2. For example, taking the current commodity as a potato, the recognition result includes a potato, a lotus root, a kiwi fruit, and a ginseng fruit, the corresponding recognition evaluation values thereof may be 0.95, 0.93, 0.92, and 0.90, respectively, the preset threshold value is 0.90, and when N is 2, the candidate categories corresponding to the recognition evaluation values of 0.95 and 0.93 are highlighted so as to be distinguished from the candidate categories corresponding to the recognition evaluation values of 0.92 and 0.90.

In some embodiments, the highlighting may include one or a combination of highlighting, marking, feature graphics, or magnifying. The highlight display may be display in bright eye color such as yellow or red; the mark display may be a display in which a mark (e.g., a text mark, a graphic mark) is added to the candidate class, for example, the recognition evaluation value of the candidate class corresponding to the display is marked with the recognition evaluation value of 0.95; the feature graph display may be to display the candidate class in a certain graph (e.g., a quadrangle, a diamond, or a triangle), for example, the candidate class may be displayed inside a five-pointed star graph; the enlarged display may show that the proportion area of the corresponding candidate class is larger than that of other candidate classes.

It should be noted that the above description related to the flow 300 is only for illustration and explanation, and does not limit the applicable scope of the present application. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of this disclosure. However, such modifications and variations are intended to be within the scope of the present application.

Fig. 4 is an exemplary flowchart illustrating another electronic scale recognition result output method according to some embodiments of the present application. In some embodiments, one or more steps of method 400 may be implemented in system 100 shown in FIG. 1. For example, one or more steps of method 400 may be stored as instructions in storage device 150 and invoked and/or executed by processing engine 140.

And step 410, acquiring an image to be identified of the current commodity acquired by the image acquisition device. Step 410 may be performed by a first obtaining module 610.

In some embodiments, the image to be identified may be image data acquired by an image acquisition device, such as the information acquisition device 110 shown in fig. 1. The image to be recognized can be used for recognizing the commodity class of the current commodity. The current item may be an item placed in a particular area. Further description may be found elsewhere in this specification, for example, in fig. 2.

Step 420, extracting image features of the image to be recognized. Step 420 may be performed by feature extraction module 620.

In some embodiments, the image features may be color features, texture features, shape features, spatial relationship features, and the like. Image features may be extracted from the image to be identified by the extraction module 620. In particular, feature extraction may be performed by a machine learning model. The machine learning model may be a class-oriented machine learning model, such as a CNN model, a KNN model, an SVM model, or a BP neural network model.

And 430, identifying the image to be identified based on the identification limiting conditions and the image characteristics to obtain at least one identification result. Step 430 may be performed by identification module 630.

In some embodiments, the identification restriction may include scenario information, inventory information, historical sales data, and the like. In some embodiments, the recognition constraint may be partially the same as the output constraint in this specification. The same is that the content included in the recognition constraint may be the same as the content included in the output constraint; the difference is that the recognition limiting condition is used for recognizing the image to be recognized to obtain a recognition result, and the output limiting condition is used for screening the recognition result obtained by recognizing the image to be recognized. It is understood that the two methods for outputting the recognition result of the electronic scale disclosed by the present invention may differ only in the step positions in the process.

In some embodiments, the identification result may be a classification result about the current item obtained from image information of the image to be identified, after the image to be identified is processed by an image identification technology, in combination with an identification limitation condition and an image feature.

How to perform recognition according to the recognition restriction conditions and the image features to obtain the recognition result can be performed in various ways, and the method in the following embodiment may be used, or other methods may be used, which is not limited in the present invention.

In some embodiments, the scene information of the scene where the electronic scale is located may be directly obtained by the acquisition device, such as the information acquisition device 110, or may be obtained from a storage device (e.g., the storage device 150) or a commodity database via a network (e.g., the network 120), or may be obtained via an interface or other means. Then, based on the scene information, the commodity type corresponding to the scene where the electronic scale is located can be determined. And identifying the image to be identified based on the commodity type and the image characteristics. In some embodiments, the type of the commodity may be a type of a commodity corresponding to a scene, for example, vegetables, fruits, books, furniture, and the like. The commodity types of the determined types are compared with the image characteristics, so that the number of the compared commodities can be effectively reduced, the complexity of identification and calculation is reduced, and the image identification efficiency is improved. More description of the scene information can be found in other parts of the invention, for example, fig. 3.

In some embodiments, the inventory information corresponding to the electronic scales may be obtained directly from the electronic scales, or may be obtained from a storage device (e.g., storage device 150) or a goods database via a network (e.g., network 120), or may be obtained via an interface or in another manner, and then the valid class currently having inventory in the inventory may be determined based on the inventory information; and finally, identifying the image to be identified based on the effective category and the image characteristics. By acquiring the inventory information, the current commodities which are still sold can be known, so that when the image characteristics are compared, the comparison of the image characteristics and invalid categories can be omitted, the quantity of the commodities which need to be compared can be effectively reduced, the complexity of identification and calculation is reduced, and the image identification efficiency is improved. More description of the inventory information may be found in other parts of the invention, such as in FIG. 3.

In some embodiments, the electronic scale may be obtained directly from the electronic scale, or may be obtained from a storage device (e.g., the storage device 150) or a product database via a network (e.g., the network 120), or historical sales data corresponding to the electronic scale may be obtained via an interface or in another manner, then a characteristic product type with a higher probability of being selected by a user may be determined based on the historical sales data, and finally the image to be recognized may be recognized based on the characteristic product type and the image feature. In some embodiments, the characteristic merchandise types may include hot merchandise, necessities of life, and the like. The characteristic commodity type is obtained by analyzing historical sales data, for example, in a certain time period, the quantity of certain commodity sales data is large, and then the corresponding commodity can be regarded as the characteristic commodity type. When image recognition is carried out, the image characteristics can be preferentially compared with the commodities corresponding to the characteristic commodity types, the probability of obtaining recognition results through image comparison is increased, further, the calculation complexity can be effectively reduced, and the image recognition efficiency is improved. More description of the historical sales data can be found in other parts of the invention, such as in FIG. 3.

Step 440, determining a candidate class of the current item from the at least one recognition result. Step 440 may be performed by determination module 640.

In some embodiments, the candidate category of the current item may be a certain category determined from the at least one recognition result. In some embodiments, the candidate category for the current item may be more than one category determined multiple times from the at least one recognition result. In some embodiments, the candidate class of the current article may be determined from the recognition result by an image recognition algorithm, and may also be determined from the recognition result by a user.

In some embodiments, the candidate class of the current article may be determined by acquiring a recognition evaluation value of the recognition result and then determining the candidate class based on the recognition evaluation value.

In some embodiments, the identification evaluation value may be an evaluation value of a probability that the identification result is a correct item class of the current article. In some embodiments, the recognition result of which the recognition evaluation value is the largest may be determined as the candidate class of the current article. In some embodiments, the identification evaluation values may be sorted from large to small, and the top N-ranked identification results are the candidate classes of the current product, where N is an integer greater than or equal to 2.

In some embodiments, the identification evaluation value may be obtained from a history of image identification performed by the electronic scale,

the identification evaluation value of the identification result may be obtained directly from the electronic scale, may be obtained from a storage device (e.g., the storage device 150) or a commodity database via a network (e.g., the network 120), or may be obtained via an interface or other means.

And step 450, acquiring commodity information of the candidate class. Step 450 may be performed by the second obtaining module 650.

In some embodiments, the commodity information may be integrated information including a name of the candidate class, unit price, manufacturer, date of manufacture, major component, commodity number, and the like. Detailed descriptions may be found elsewhere in this specification, for example, in fig. 2. In some embodiments, the merchandise information may be obtained directly from the electronic scale, may be obtained from a storage device (e.g., storage device 150) or a merchandise database via a network (e.g., network 120), or may be obtained via an interface or other means.

Step 460, displaying the candidate class of the current commodity based on the commodity information. Step 460 may be performed by display module 660.

In some embodiments, the displaying may be displaying the commodity information of the candidate class through the display module 660. In some embodiments, the merchandise information may be displayed in various ways, for example, an identification picture for clear identification may be displayed, and information such as the name and unit price of the candidate merchandise may be included in the identification picture (e.g., an advertisement picture); video display can also be adopted, the video display can comprise the names and unit prices of the candidate commodities, and voice broadcasting can be carried out according to the video picture.

In some embodiments, the candidate class whose identification evaluation value satisfies the preset condition may be highlighted based on the identification evaluation value. The highlighting may include one or a combination of highlighting, marking, feature graphical display, magnifying, flashing. For example, the highlight may be a color with high visibility such as red or yellow, taking the highlight as an example. The candidate categories that satisfy the preset condition may also be highlighted in a highlighted and enlarged manner at the same time.

In some embodiments, the predetermined condition may be that the evaluation value of the identification product is greater than a predetermined threshold value and/or that the evaluation value of the identification product is N bits before the evaluation value ranking, where N is an integer greater than or equal to 2. In some embodiments, the predetermined condition may be that the identification evaluation value is greater than a threshold value, which may be highlighted whenever the threshold value is reached or exceeded. For example, in some embodiments, the identification results may be potatoes, lotus roots, kiwifruits and ginseng fruits, the identification evaluation values of which are 0.95, 0.88, 0.83 and 0.90, respectively, and the threshold is set to 0.90, then the potatoes and ginseng fruits satisfying the threshold may be highlighted. In some embodiments, the threshold may be set by computational analysis of historical image recognition data of the electronic scale. In some embodiments, the preset condition may be to identify that the evaluation value is located N bits before the evaluation value ranking, where N is an integer equal to or greater than 2. For example, when N is 3, the evaluation values of 0.95, 0.88, 0.83, and 0.90 are respectively assumed as candidates obtained by the primary image recognition, such as potato, lotus root, kiwi, and ginseng fruit. After ranking the three types of Chinese gooseberries, the first three types of Chinese gooseberries are respectively potato with an evaluation value of 0.95, ginseng fruit with an evaluation value of 0.90 and Chinese gooseberry with an evaluation value of 0.88, so that the display module 660 can highlight the three types of Chinese gooseberries and normally display the Chinese gooseberries. In some embodiments, the predetermined condition may be that the estimated value of the identification is greater than a predetermined threshold value and the identified estimated value is N bits before the ranking of the estimated values. More description about the preset condition and the evaluation value can be found elsewhere in this specification, for example, fig. 3.

It should be noted that the above description related to the flow 500 is only for illustration and explanation, and does not limit the applicable scope of the present application. Various modifications and changes to flow 500 may occur to those skilled in the art upon review of the present application. However, such modifications and variations are intended to be within the scope of the present application. For example, the commodity information of the candidate category is displayed in a characteristic pattern and highlighted manner.

Fig. 5 is a block diagram of an electronic scale recognition result output system according to some embodiments of the present application.

As shown in fig. 5, the electronic scale recognition result output system may include a first obtaining module 510, a recognition module 520, a determination module 530, a second obtaining module 540, and a display module 550.

The first acquisition module 510 may be used for acquisition of an image to be identified.

In some embodiments, the image to be identified may be used to identify the item class of the current item. The acquisition mode can be photographing, GIF recording, short video recording and the like. For example, a short video may be taken of the current commodity, and an image of one video frame may be cut from the short video as the image to be recognized.

The recognition module 520 may be used to recognize the acquired image to be recognized.

In some embodiments, the recognition module 520 may perform image feature extraction on the image to be recognized, and then perform image recognition based on the extracted image features. In some embodiments, the image may also be pre-processed prior to recognition, e.g., to adjust the darkness, to denoise, etc. And then identifying the image to be identified. In some embodiments, the recognition module 520 may also directly recognize the image to be recognized. After the image to be recognized is recognized, at least one recognition result corresponding to the image to be recognized can be obtained.

The determination module 530 may be used to determine a candidate class for the current item.

In some embodiments, the determining module 530 may determine the candidate class of the current item from at least one recognition result based on an output limitation. The output restriction condition may be scene information, inventory information, historical sales data information, and the like. In some embodiments, the determining module 530 may filter the at least one recognition result according to an output constraint to determine the candidate class. In some embodiments, the determination module 530 may also determine the candidate class in response to an instruction of a user.

The second obtaining module 540 may be configured to obtain commodity information of the candidate class.

In some embodiments, the commodity information of the candidate class may include integrated information of commodity name, unit price, place of manufacture, manufacturer, date of manufacture, commodity number, and the like. The second obtaining module 540 may obtain the commodity information directly from the electronic scale, or may obtain the commodity information from a storage device (e.g., the storage device 150) or a commodity database via a network (e.g., the network 120), or via an interface or other means.

The display module 550 may be used to display commodity information of the candidate class.

In some embodiments, the display module 550 may display the commodity information of the candidate class in one or more manners, which may include text display, image display, video display, and the like. In some embodiments, the display module 550 may highlight the merchandise information, and the highlighting may include one or more of highlighting, marking, displaying a characteristic graphic, and magnifying.

For more description of the block portions of this specification reference may be made to the flow chart portion.

As shown in fig. 6, the electronic scale recognition result output system may include a first obtaining module 610, an extracting module 620, a recognizing module 630, a determining module 640, a second obtaining module 650, and a displaying module 660.

The first acquisition module 610 may be used for acquisition of an image to be identified.

In some embodiments, the image to be identified may be used to identify the item class of the current item. The acquisition mode can be photographing, GIF recording, short video recording and the like. For example, after the GIF image is acquired, one frame of image is extracted from the GIF image as the image to be recognized.

The extraction module 620 may be used to extract image features of the image to be recognized.

In some embodiments, the extraction module 620 may extract the image features from the image to be recognized based on a machine learning model. In some embodiments, the extraction module 620 may also pre-process the image to be recognized before extracting the image features. The image features may be color features, texture features, shape features, spatial relationship features, and the like.

The recognition module 630 may be used to recognize the image to be recognized.

In some embodiments, the recognition module 630 may recognize the image to be recognized based on the recognition constraint and the image feature, resulting in at least one recognition result. The recognition module 630 may match recognition constraints with image features to recognize the image to be recognized. In some embodiments, the identification restriction condition may include scenario information, inventory information, historical sales data information, and the like.

The determination module 640 may be used to determine a candidate class for the current item.

In some embodiments, the determining module 640 may determine the candidate class for the current item from one or more recognition results. In some embodiments, the determining module 640 may obtain the identification evaluation value of the identification result, and may determine the candidate class of the current article based on the identification evaluation value.

The second obtaining module 650 may be configured to obtain the commodity information of the candidate commodity.

In some embodiments, the commodity information of the candidate class may include integrated information of commodity name, unit price, place of manufacture, manufacturer, date of manufacture, commodity number, and the like. The second obtaining module 650 may obtain the commodity information directly from the electronic scale, or may obtain the commodity information from a storage device (e.g., the storage device 150) or a commodity database via a network (e.g., the network 120), or via an interface or other means.

The display module 660 may be configured to display the commodity information of the candidate class.

In some embodiments, the display module 660 may display the commodity information of the candidate class in one or more manners, which may include text display, image display, video display, and the like. In some embodiments, the display module 660 may highlight the merchandise information, and the highlighting may include one or more of highlighting, marking, displaying a characteristic graphic, and magnifying.

It should be appreciated that the systems and modules thereof shown in fig. 5 and/or 6 may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above descriptions of the candidate item display and determination system and the modules thereof are only for convenience of description, and are not intended to limit the present application within the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. For example, in some embodiments, for example, the first acquiring module 510, the identifying module 520, the determining module 530, the second acquiring module 540 and the displaying module 550 disclosed in fig. 5 may be different modules in one system, or may be a module that implements the functions of two or more of the above modules. For example, the second acquiring module 540 and the displaying module 550 may be two modules, or one module may have both acquiring and displaying functions. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present application.

The beneficial effects that may be brought by the embodiments of the present application include, but are not limited to: (1) after the image to be recognized is recognized to obtain the recognition result, the recognition result is preliminarily screened according to the output limiting condition to obtain an effective recognition result, and then the candidate class of the current commodity is determined from the effective recognition result according to the recognition evaluation value, so that the recognition accuracy of the current commodity is effectively improved. (2) The candidate class of at least one current commodity can be determined from the effective recognition result, so that after the determined candidate class is displayed to a user, the user can freely select, and the recognition accuracy of the commodity class and the use experience of the user are further improved. (3) The identification limiting conditions are added into the identification process of the image to be identified, the commodity types used for identification comparison are determined through the identification limiting conditions, and the quantity of commodities needing comparison can be reduced, so that the calculation complexity of the image identification process is reduced, and the image identification efficiency is improved. It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. An electronic scale recognition result output method is characterized by comprising the following steps:

acquiring an image to be identified of a current commodity acquired by an image acquisition device;

identifying the image to be identified to obtain at least one identification result;

determining a candidate class of the current commodity from the at least one recognition result based on an output limitation condition;

acquiring commodity information of the candidate class;

and displaying the candidate class of the current commodity based on the commodity information.

2. The method of claim 1, wherein determining the candidate class for the current item from the at least one recognition result based on the output constraint comprises:

determining a valid recognition result among the recognition results based on the output restriction condition;

acquiring the identification evaluation value of the effective identification result;

determining a candidate class of the current article from the valid recognition result based on the recognition evaluation value.

3. The method of claim 2, wherein determining valid ones of the recognition results based on the output constraints comprises:

acquiring scene information of a scene where the electronic scale is located;

matching the recognition result with the scene information;

and under the condition that the identification result is matched with the scene information, determining the identification result as the effective identification result.

4. The method of claim 2, wherein determining valid ones of the recognition results based on the output constraints comprises

Acquiring inventory information corresponding to the identification result;

judging whether the corresponding goods of the identification result have stock according to the stock information;

and under the condition that the corresponding goods of the identification result have stock, determining the identification result as the effective identification result.

5. The method of claim 4, further comprising:

acquiring historical sales data corresponding to the identification result;

determining whether the identification result is the valid identification result based on the historical sales data and the inventory information.

6. The method of claim 2, wherein said displaying the candidate class for the current item based on the item information comprises:

and highlighting the candidate class of which the identification evaluation value meets the preset condition based on the identification evaluation value.

7. The method of claim 6, wherein the highlighting comprises at least one of:

highlighting, marking, feature graphic display, or magnifying display.

8. The method according to claim 6, wherein the preset conditions include:

the identification evaluation value is larger than a preset threshold value and/or the identification evaluation value is located at N bits before evaluation value sorting, wherein N is an integer larger than or equal to 2.

9. A method for weighing by an electronic scale is characterized by comprising the following steps:

extracting image features of the image to be recognized;

identifying the image to be identified based on identification limiting conditions and the image characteristics to obtain at least one identification result;

determining a candidate class of the current item from the at least one recognition result;

acquiring commodity information of the candidate class;

and displaying the candidate class based on the commodity information.

10. The method according to claim 9, wherein the identifying the image to be identified based on the identification limiting condition and the image feature comprises:

acquiring scene information of a scene where the electronic scale is located;

determining the commodity type corresponding to the scene where the electronic scale is located based on the scene information;

and identifying the image to be identified based on the commodity type and the image characteristics.

11. The method according to claim 9, wherein the identifying the image to be identified based on the identification limiting condition and the image feature comprises:

acquiring inventory information corresponding to the electronic scale;

determining a valid class currently in stock based on the inventory information;

and identifying the image to be identified based on the effective product class and the image characteristics.

12. The method according to claim 9, wherein the identifying the image to be identified based on the identification limiting condition and the image feature comprises:

acquiring historical sales data corresponding to the electronic scale;

determining the characteristic commodity type with higher user selection probability based on the historical sales data;

and identifying the image to be identified based on the characteristic commodity type and the image characteristics.

13. The method of claim 9, wherein said determining a candidate class for said current item from said at least one recognition result comprises:

acquiring a recognition evaluation value of the recognition result;

determining a candidate class of the current article based on the recognition evaluation value.

14. The method of claim 13, wherein said displaying the candidate categories based on the merchandise information comprises:

15. The method of claim 14, wherein the highlighting includes at least one of:

highlighting, marking, feature graphic display, or magnifying display.

16. The method according to claim 15, wherein the preset condition comprises:

17. An electronic scale recognition result output system, characterized in that the system comprises:

the first acquisition module is used for acquiring the image to be identified of the current commodity acquired by the image acquisition device;

the identification module is used for identifying the image to be identified to obtain at least one identification result;

a determining module, configured to determine a candidate class of the current product from the at least one recognition result based on an output limiting condition;

the second acquisition module is used for acquiring the commodity information of the candidate class;

and the display module is used for displaying the candidate class of the current commodity based on the commodity information.

18. An electronic scale recognition result output system, characterized in that the system comprises:

the extraction module is used for extracting the image characteristics of the image to be identified;

the identification module is used for identifying the image to be identified based on identification limiting conditions and the image characteristics to obtain at least one identification result;

a determining module, configured to determine a candidate class of the current product from the at least one recognition result;

and the display module is used for displaying the candidate categories based on the commodity information.

19. An electronic scale weighing apparatus, the apparatus comprising a processor and a memory; the memory is configured to store instructions, and the instructions, when executed by the processor, cause the apparatus to perform operations corresponding to the electronic scale recognition result output method according to any one of claims 1 to 8 or 9 to 16.

20. A computer-readable storage medium, wherein the storage medium stores computer instructions, and when the computer instructions in the storage medium are read by a computer, the computer executes the electronic scale recognition result output method according to any one of claims 1 to 7 or 9 to 16.