WO2021077321A1

WO2021077321A1 - Electronic shelf label identification system and method, and server

Info

Publication number: WO2021077321A1
Application number: PCT/CN2019/112723
Authority: WO
Inventors: 侯世国; 梁敏; 金小平; 苏汛沅; 张彩蝶
Original assignee: 汉朔科技股份有限公司
Priority date: 2019-10-23
Filing date: 2019-10-23
Publication date: 2021-04-29

Abstract

An electronic shelf label identification system and method, and a server. Said system comprises: an electronic shelf label, configured to switch the current display page to a multi-character code page upon receipt of a multi-character code page switching instruction sent by a server, and to feed back a multi-character code page switching result to the server, the multi-character code page being used for displaying the identifier of the electronic shelf label; a camera, configured to take at least one picture of the electronic shelf label upon receipt of a photographing instruction, and to send the at least one picture to the server; and the server, configured to send the multi-character code page switching instruction to the electronic shelf label, send a photographing instruction to the camera when the received multi-character code page switching result is successful switching, receive at least one picture, and identify the identifier of the electronic shelf label according to the at least one picture. Said system can identify an electronic shelf label, and is efficient.

Description

Electronic price tag identification system, method and server

Technical field

The present invention relates to the Internet field, in particular to an electronic price tag identification system and method, and a server.

Background technique

In the prior art, the manual display method is mainly used to display the products in the supermarket. Generally, the computer typesetting of the product labels is completed and printed and then handed over to the manual display. The main disadvantage of the above manual display method is that it consumes a lot of manpower. The electronic price tag is a product in the new retail field, which can locate the product by identifying the electronic price tag, but there is currently a lack of effective methods for electronic price tag identification.

Summary of the invention

An embodiment of the present invention provides an electronic price tag identification system for identifying electronic price tags with high efficiency. The system includes:

The electronic price tag is used for: after receiving the multi-character code page switching instruction sent by the server, the current display page is switched to the multi-character code page, and the multi-character code page switching result is fed back to the server, and the multi-character code page is used for display The identification of the electronic price tag;

The camera is used to: after receiving the photographing instruction, take at least one picture of the electronic price tag, and send the at least one picture to the server;

The server is used to: send a multi-character code page switching instruction to the electronic price tag; after the received multi-character code page switching result is successful, send a photographing instruction to the camera; receive at least one picture; according to the at least one picture , The identification of the electronic price tag.

The embodiment of the present invention provides a server for identifying electronic price tags with high efficiency. The server includes:

The first instruction sending module is used to send a multi-word code page switching instruction to the electronic price tag;

The second instruction sending module is used to send a photographing instruction to the camera after the received multi-character code page switching result is that the switching is successful;

The receiving module is used for receiving the multi-character code page switching result of the electronic price tag according to the multi-character code page switching instruction, the multi-character code page is used to display the identification of the electronic price tag; receiving the electronic price tag photographed by the camera according to the photographing instruction At least one picture of

The identification module is used to identify the identification of the electronic price tag according to the at least one picture.

The embodiment of the present invention provides an electronic price tag identification method for identifying electronic price tags with high efficiency. The method includes:

Send a multi-character code page switching instruction to the electronic price tag;

Receiving the multi-character code page switching result fed back by the electronic price tag according to the multi-character code page switching instruction, where the multi-character code page is used to display the identification of the electronic price tag;

After the received multi-character code page switching result is that the switching is successful, send a photographing instruction to the camera;

Receive at least one picture of the electronic price tag taken by the camera according to the camera instruction;

According to the at least one picture, the identification of the electronic price tag is recognized.

The embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The processor implements the above electronic price tag identification method when the computer program is executed. .

The embodiment of the present invention also provides a computer-readable storage medium that stores a computer program for executing the above-mentioned electronic price tag identification method.

In the embodiment of the present invention, the electronic price tag is used to: after receiving the multi-character code page switching instruction sent by the server, switch the current display page to the multi-character code page, and feed back the multi-character code page switching result to the server. The multi-character code page is used to display the identification of the electronic price tag; the camera is used to: after receiving the photographing instruction, take at least one picture of the electronic price tag, and send the at least one picture to the server; the server is used to: The electronic price tag sends a multi-character code page switching instruction; after the received multi-character code page switching result is successful, send a photographing instruction to the camera; receive at least one picture; identify the electronic price tag according to the at least one picture Logo. In the above process, since the multi-character code page can directly display the identification of the electronic price tag, the server can quickly identify the electronic price tag based on the at least one picture by controlling the camera to take at least one picture of the multi-character code page Recognition, high efficiency.

Description of the drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the attached picture:

Figure 1 is a schematic diagram of an electronic price tag identification system in an embodiment of the present invention;

2 is a schematic diagram of a specific application of the electronic price tag identification system in an embodiment of the present invention;

Figure 3 is a schematic diagram of a server in an embodiment of the present invention;

Fig. 4 is a flowchart of an electronic price tag identification method in an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following describes the embodiments of the present invention in further detail with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and the description thereof are used to explain the present invention, but not as a limitation to the present invention.

In the description of this specification, the use of "including", "including", "having", "containing", etc., are all open terms, which means including but not limited to. Descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example," etc. mean that the specific feature, structure or feature described in conjunction with the embodiment or example is included in at least one of the present application In an embodiment or example. In this specification, the schematic representation of the above-mentioned terms does not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures or characteristics can be combined in any one or more embodiments or examples in a suitable manner. The order of the steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of the steps is not limited and can be appropriately adjusted as needed.

Fig. 1 is a schematic diagram of an electronic price tag identification system in an embodiment of the present invention. As shown in Fig. 1, the system includes:

The electronic price tag is used for: after receiving the multi-character code page switching instruction sent by the server, switch the current display page to the multi-character code page, and feed back the multi-character code page switching result to the server, and the multi-character code page is used for Display the identification of the electronic price tag;

The camera is configured to: after receiving the photographing instruction, take at least one picture of the electronic price tag, and send the at least one picture to the server;

The server is configured to: send a multi-character code page switching instruction to the electronic price tag; after the received multi-character code page switching result is successful, send a photographing instruction to the camera; receive at least one picture; according to the at least one Picture to identify the logo of the electronic price tag.

In the above embodiment, since the multi-character code page can directly display the identification of the electronic price tag, the server can quickly identify the electronic price tag based on the at least one picture by controlling the camera to take at least one picture of the multi-character code page. The identification of the signature is highly efficient.

In specific implementation, the multi-character code page is a pre-configured identification corresponding to the electronic price tag, and it can uniquely identify the electronic price tag. When displayed, it fills the electronic price tag screen, allowing the pictures taken from the camera to be quickly identified The identification of an electronic price tag generally does not have many characters in a multi-word code. For example, it can be composed of letters such as "ABED", coded according to the set rules, and can be stored in the server for easy reference. The camera takes at least one picture of the electronic price tag, and the multiple pictures taken are all multi-character code pages. The multiple shooting is to improve the accuracy of the identification of the electronic price tag.

Figure 2 is a schematic diagram of the specific application of the electronic price tag identification system in the embodiment of the present invention. Using supermarket commodity industry specifications, the products must be placed from the left to the left edge of the electronic price tag, and from the right to the left of the electronic price tag or on the shelf. Right edge. Camera 1 is installed on the opposite side of the shelf. For example, it can be a 2-megapixel POE camera. Both camera 1 and electronic price tag 2 communicate with the server. First, the server sends a multi-word code page switching instruction to the electronic price tag; After receiving the multi-character code page switching instruction sent by the server, the sign will switch the current display page to the multi-character code page, and feedback the multi-character code page switching result to the server. The server receives the multi-character code page switching result as successful Then, send a photo instruction to the camera, and after the received multi-character code page switch result is that the switch fails, continue to send the multi-character code page switch instruction to the electronic price tag, and the number of times the multi-character code page switch instruction is sent to the electronic price tag When the set number of times is reached, but the received multi-character code page switching results are all switching failures, an early warning message is generated to remind the electronic price tag management personnel of the communication between the electronic price tag server and the electronic price tag or that there is a problem with the electronic price tag itself. After receiving the photographing instruction, the camera takes at least one picture of the electronic price tag, and sends the at least one picture to the server, and the server recognizes the identifier of the electronic price tag according to the at least one picture. Since electronic price tag identification during normal working hours may affect the customer's shopping experience, multi-character code identification should be carried out during off-hours or before get off work as far as possible.

In an embodiment, the server is specifically used to:

The at least one picture is input into the deep learning model to identify the identification of the electronic price tag.

In one embodiment, the deep learning model is obtained by training using the following method:

Obtain historical pictures of the multi-character code page of the electronic price tag;

Extract feature vectors of historical pictures;

The deep learning model is trained using the feature vector.

In specific implementation, commonly used deep learning models include autoencoders, sparse encoders, convolutional neural networks, RNNs, and LSTMs. The training methods for deep learning models are roughly similar, namely the three steps in the above-mentioned embodiment. In addition, When using the feature vector to train the deep learning model, it specifically includes: adjusting the parameters of the deep learning model during the training process until the loss function of the deep learning model meets the preset convergence condition, and the trained deep learning model is obtained.

Dividing the historical pictures into training set data and test set data;

Extract the feature vector of the training set data;

Use the feature vector of the training set data to train the deep learning model,

Adjust the parameters of the deep learning model during the training process until the loss function of the deep learning model meets the preset convergence conditions to obtain the trained deep learning model;

Use the test set data to test the trained deep learning model;

When the accuracy of the trained deep learning model is less than the preset accuracy, increase the amount of training set data or adjust the ratio of training set data and test set data to retrain until the accuracy of the trained deep learning model is not less than the preset accuracy. Set the accuracy rate.

Using the deep learning module to identify the identification of the electronic price tag has high accuracy and high efficiency. Of course, it is understandable that there may be other ways of training the deep learning model, and relevant variations should fall within the protection scope of the present invention.

In one embodiment, the server is also used to:

Query the corresponding relationship between the identification on the electronic price tag and the items on the shelf, and determine the item corresponding to the electronic price tag.

In the above embodiment, the corresponding relationship between the identifier on the electronic price tag and the shelf item is stored in the server, and the item corresponding to the electronic price tag can be quickly determined through query.

In summary, in the electronic price tag identification system proposed in the embodiment of the present invention, the electronic price tag is used to switch the current display page to the multi-character code page after receiving the multi-character code page switching instruction sent by the server, The multi-character code page switching result is fed back to the server, the multi-character code page is used to display the identification of the electronic price tag; the camera is used to: after receiving the photographing instruction, take at least one picture of the electronic price tag, and the at least A picture is sent to the server; the server is used to: send a multi-character code page switching instruction to the electronic price tag; after the received multi-character code page switching result is successful, send a photographing instruction to the camera; receive at least one picture; According to the at least one picture, the identification of the electronic price tag is recognized. In the above process, since the multi-character code page can directly display the identification of the electronic price tag, the server can quickly identify the electronic price tag based on the at least one picture by controlling the camera to take at least one picture of the multi-character code page Recognition, high efficiency. In addition, the use of the deep learning module to identify the identification of the electronic price tag has high accuracy and high efficiency. When the camera used in this system performs multi-character price tag detection, it only needs to stay on the multi-character code page for a certain period of time for taking pictures. The power consumption is low, and the installation cost is extremely low. Only one camera is needed to display information. Real-time acquisition is strong.

The embodiment of the present invention also provides a server. FIG. 3 is a schematic diagram of the server in the embodiment of the present invention. As shown in FIG. 3, the server includes:

In an embodiment, the identification module is specifically used for:

Extract feature vectors of historical pictures;

The deep learning model is trained using the feature vector.

In an embodiment, the server further includes an item identification module for:

To sum up, in the server proposed by the embodiment of the present invention, the first instruction sending module is used to send a multi-character code page switching instruction to the electronic price tag; the second instruction sending module is used to send a multi-character code page switching instruction to the electronic price tag; The page switching result is that after the switching is successful, the camera sends a photographing instruction; the receiving module is used to receive the multi-character code page switching result fed back by the electronic price tag according to the multi-character code page switching instruction, and the multi-character code page is used to display the electronic price The identification of the electronic price tag; receiving at least one picture of the electronic price tag taken by the camera according to the photographing instruction; the identification module, which is used to identify the identification of the electronic price tag according to the at least one picture. In the above process, since the multi-character code page can directly display the identification of the electronic price tag, by controlling the camera to take at least one picture of the multi-character code page, the electronic price tag can be quickly identified based on the at least one picture. Recognition, high efficiency. Using the deep learning module to identify the identification of the electronic price tag has high accuracy and high efficiency. When the camera used in this system performs multi-character price tag detection, it only needs to stay on the multi-character code page for a certain period of time for taking pictures. The power consumption is low, and the installation cost is extremely low. Only one camera is needed to display information. Real-time acquisition is strong.

Based on the same inventive concept, embodiments of the present invention also provide an electronic price tag identification method, as described in the following embodiments. Since these problem-solving principles are similar to those of the server, the implementation of the electronic price tag identification method can refer to the implementation of the server, and the repetition will not be repeated.

Fig. 4 is a flowchart of an electronic price tag identification method in an embodiment of the present invention. As shown in Fig. 4, the method includes:

Step 401: Send a multi-character code page switching instruction to the electronic price tag;

Step 402: Receive the multi-character code page switching result fed back by the electronic price tag according to the multi-character code page switching instruction, where the multi-character code page is used to display the identification of the electronic price tag;

Step 403, after the received multi-character code page switching result is that the switching is successful, send a photographing instruction to the camera;

Step 404: Receive at least one picture of the electronic price tag taken by the camera according to the photographing instruction;

Step 405: Identify the identifier of the electronic price tag according to the at least one picture.

In one embodiment, identifying the identifier of the electronic price tag according to the at least one picture includes:

Extract feature vectors of historical pictures;

The deep learning model is trained using the feature vector.

In an embodiment, the method further includes:

To sum up, in the method proposed in the embodiment of the present invention, the multi-character code page switching instruction is sent to the electronic price tag; the multi-character code page switching result fed back by the electronic price tag according to the multi-character code page switching instruction is received. The code page is used to display the identification of the electronic price tag; after the received multi-character code page switching result is successful, send a photo instruction to the camera; receive at least one picture of the electronic price tag taken by the camera according to the photo instruction; The at least one picture identifies the identification of the electronic price tag. In the above process, since the multi-character code page can directly display the identification of the electronic price tag, by controlling the camera to take at least one picture of the multi-character code page, the electronic price tag can be quickly identified based on the at least one picture. Recognition, high efficiency. Using the deep learning module to identify the identification of the electronic price tag has high accuracy and high efficiency. When the camera used in this system performs multi-character price tag detection, it only needs to stay on the multi-character code page for a certain period of time for taking pictures. The power consumption is low, and the installation cost is extremely low. Only one camera is needed to display information. Real-time acquisition is strong.

Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

The present invention is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment can be used to generate It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in further detail. It should be understood that the above descriptions are only specific embodiments of the present invention and are not intended to limit the scope of the present invention. The scope of protection, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of protection of the present invention.

Claims

An electronic price tag identification system, which is characterized in that it comprises:

The electronic price tag is used for: after receiving the multi-character code page switching instruction sent by the server, switch the current display page to the multi-character code page, and feed back the multi-character code page switching result to the server, and the multi-character code page is used for Display the identification of the electronic price tag;

The camera is configured to: after receiving the photographing instruction, take at least one picture of the electronic price tag, and send the at least one picture to the server;

The server is configured to: send a multi-character code page switching instruction to the electronic price tag; after the received multi-character code page switching result is successful, send a photographing instruction to the camera; receive at least one picture; according to the at least one Picture to identify the logo of the electronic price tag.
The electronic price tag identification system according to claim 1, wherein the server is specifically configured to:

The at least one picture is input into the deep learning model to identify the identification of the electronic price tag.
The electronic price tag recognition system according to claim 2, wherein the deep learning model is obtained by training using the following method:

Obtain historical pictures of the multi-character code page of the electronic price tag;

Extract feature vectors of historical pictures;

The deep learning model is trained using the feature vector.
The electronic price tag identification system according to claim 1, wherein the server is further used for:

Query the corresponding relationship between the identification on the electronic price tag and the items on the shelf, and determine the item corresponding to the electronic price tag.
A server, characterized in that it comprises:

The first instruction sending module is used to send a multi-word code page switching instruction to the electronic price tag;

The second instruction sending module is used to send a photographing instruction to the camera after the received multi-character code page switching result is that the switching is successful;

The receiving module is used for receiving the multi-character code page switching result of the electronic price tag according to the multi-character code page switching instruction, the multi-character code page is used to display the identification of the electronic price tag; receiving the electronic price tag photographed by the camera according to the photographing instruction At least one picture of

The identification module is used to identify the identification of the electronic price tag according to the at least one picture.
The server according to claim 5, wherein the identification module is specifically used for:

The at least one picture is input into the deep learning model to identify the identification of the electronic price tag.
The server according to claim 6, wherein the deep learning model is obtained by training using the following method:

Obtain historical pictures of the multi-character code page of the electronic price tag;

Extract feature vectors of historical pictures;

The deep learning model is trained using the feature vector.
8. The server of claim 6, further comprising an item identification module, configured to:

Query the corresponding relationship between the identification on the electronic price tag and the items on the shelf, and determine the item corresponding to the electronic price tag.
An electronic price tag identification method, which is characterized in that it comprises:

Send a multi-character code page switching instruction to the electronic price tag;

Receiving the multi-character code page switching result fed back by the electronic price tag according to the multi-character code page switching instruction, where the multi-character code page is used to display the identification of the electronic price tag;

After the received multi-character code page switching result is that the switching is successful, send a photographing instruction to the camera;

Receive at least one picture of the electronic price tag taken by the camera according to the camera instruction;

According to the at least one picture, the identification of the electronic price tag is recognized.
A computer device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein the processor implements the method of claim 9 when the computer program is executed.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the method of claim 9.