Price tag content acquisition method and device, storage medium and computer device

Abstract

The application provides a price tag content acquisition method and device, a storage medium and a computer device. The method comprises the following steps: acquiring a price tag picture of a target price tag; detecting a name area and a product price of the price tag picture by using a target detection algorithm; performing content recognition on the name area by using an OCR algorithm to obtain a product name; matching the product name with a pre-constructed product information database to obtain a matching result; the matching result comprises a plurality of first candidate product data; matching price data of the plurality of first candidate product data in the matching result with the product price to obtain matching data; and determining target product data from the plurality of first candidate product data in the matching result according to the matching data, and determining the target product data as the price tag content of the target price tag. The application can accurately acquire the price tag content on the electronic price tag and the non-electronic price tag, and is beneficial to realizing real-time monitoring and management of the products on the shelves.

Description

Technical Field

[0001] This application relates to the field of price tag content detection and recognition technology, specifically to a method, apparatus, storage medium, and computer device for acquiring price tag content. Background Technology

[0002] Price tags are tools used to identify product information. With the advent of electronic price tags, merchants can display product information and large special characters on them, making it easier for shoppers to understand product names and prices. Merchants can also use algorithms to identify special characters and retrieve the product information they point to, thereby improving real-time monitoring and management of products on shelves and increasing the efficiency and accuracy of shelf management. However, traditional non-electronic price tags, due to size limitations, cannot simultaneously display product information and large special characters, nor can they rotate between these elements. Therefore, real-time monitoring and management of products on shelves with non-electronic price tags is difficult. Summary of the Invention

[0003] The purpose of this application is to overcome the shortcomings and deficiencies of the prior art and provide a method, device, storage medium and computer equipment for obtaining price tag content, which can accurately obtain the price tag content on electronic and non-electronic price tags, and facilitate the real-time monitoring and management of goods on shelves.

[0004] One embodiment of this application provides a method for obtaining price tag content, including:

[0005] Get the price tag image of the target price tag;

[0006] The name area and product price of the price tag image were detected using an object detection algorithm.

[0007] The product name is obtained by performing content recognition on the name area using an OCR algorithm;

[0008] The product names are matched with a pre-built product information database to obtain matching results; the matching results include several first candidate product data.

[0009] The price data of several first candidate product data in the matching results are matched with the product price to obtain matching data;

[0010] Based on the matching data, target product data is determined from a plurality of first candidate product data in the matching results, and the target product data is determined as the price tag content of the target price tag.

[0011] Furthermore, the step of detecting the name region and product price of the price tag image using an object detection algorithm includes:

[0012] The target detection algorithm is used to detect the name and price areas of the price tag image.

[0013] The target detection algorithm identifies the price numbers and price symbols in the price range to obtain the price of the commodity.

[0014] Further, the step of matching the product name with a pre-built product information database to obtain a matching result, wherein the matching result includes several first candidate product data, includes:

[0015] Obtain the similarity between the product name and the various product information data stored in the product information database;

[0016] The top few product information data with the highest similarity are determined as the first candidate product data.

[0017] Furthermore, the matching data includes the matching values ​​between each of the first candidate product data and the product price;

[0018] The step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0019] If all the matching values ​​of the matching data are less than the preset matching threshold, the first candidate product data with the highest similarity is determined as the target product data from the matching results.

[0020] Further, the step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0021] If there is a matching value in the matching data that is greater than or equal to a preset matching threshold, the corresponding first candidate product data is determined as the target product data.

[0022] Further, the step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0023] If at least two matching values ​​in the matching data are greater than or equal to a preset matching threshold, the corresponding first candidate product data is determined as the second candidate product data;

[0024] Based on the matching results, the similarity between each second candidate product data and the product information is obtained, and the second candidate product data with the highest similarity is determined as the target product data.

[0025] Further, the step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0026] If there are several second candidate product data with the highest similarity, randomly select one from the several second candidate product data with the highest similarity and determine it as the target product data.

[0027] One embodiment of this application also provides a price tag content acquisition device, including:

[0028] The image acquisition module is used to acquire images of the target price tag.

[0029] The detection module is used to detect the name area and product price of the price tag image using a target detection algorithm;

[0030] The recognition module is used to perform content recognition on the name area using an OCR algorithm to obtain the product name;

[0031] The first matching module is used to match the product name with a pre-built product information database to obtain a matching result; the matching result includes several first candidate product data.

[0032] The second matching module is used to match the price data of several first candidate product data in the matching result with the product price to obtain matching data;

[0033] The price tag content acquisition module is used to determine target product data from a plurality of first candidate product data in the matching results based on the matching data, and to determine the target product data as the price tag content of the target price tag.

[0034] An embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the price tag content acquisition method described above.

[0035] One embodiment of this application also provides a computer device, including a storage device, a processor, and a computer program stored in the storage device and executable by the processor, wherein the processor executes the computer program to implement the steps of the price tag content acquisition method as described above.

[0036] Compared to related technologies, this application uses an object detection algorithm to detect the name region and product price of a price tag image. Then, it matches the product name identified from the name region using an OCR algorithm with a pre-built product information database. Next, it obtains the price data of several first candidate product data from the matching results and the matching data of the product price. Based on the matching data, it determines the target product data from the several first candidate product data from the matching results, thereby obtaining the price tag content of the target price tag. Regardless of whether the price tag image corresponds to an electronic price tag or a traditional non-electronic price tag, this application can accurately obtain the price tag content on the price tag, which is beneficial for real-time monitoring and management of products on the shelf.

[0037] To provide a clearer understanding of this application, the specific embodiments of this application will be described below in conjunction with the accompanying drawings. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating a method for obtaining price tag content according to an embodiment of this application.

[0039] Figure 2 This is a flowchart illustrating a method for obtaining price tag content according to an embodiment of this application.

[0040] Figure 3 This is a schematic diagram of a price tag image for a method of obtaining price tag content according to an embodiment of this application.

[0041] Figure 4 This is a schematic diagram of the module connections of a price tag content acquisition device according to an embodiment of this application.

[0042] 1. Image acquisition module; 2. Detection module; 3. Recognition module; 4. First matching module; 5. Second matching module; 6. Price tag content acquisition module. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0044] It should be understood that the described embodiments are merely some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of the embodiments of this application.

[0045] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. The singular forms "a," "the," and "the" used in this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. The word "if" as used herein can be interpreted as "when," "when," or "in response to determination."

[0046] Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0047] Please see Figure 1-2 The method for obtaining price tag content in the first embodiment of this application includes:

[0048] S1: Get the price tag image of the target price tag.

[0049] The price tag images can be obtained using a camera, for example, by taking pictures of the price tags of various products on the shelf using a camera corresponding to the shelf. Optionally, the camera can also be an AI camera or an AI robot.

[0050] S2: The name area and product price of the price tag image are detected using an object detection algorithm.

[0051] Among them, the object detection algorithm is a deep learning-based object detection algorithm. The object detection algorithm is trained by training samples of price tag images labeled with name region, price region and product price on the price region, so that the object detection algorithm can be used to detect the name region and product price of price tag images.

[0052] S3: The product name is obtained by performing content recognition on the name area using an OCR algorithm.

[0053] OCR, or Character Recognition, is an effective image processing algorithm specifically designed for character recognition and detection. It boasts advantages such as high accuracy and strong stability, and can recognize dozens of languages ​​including Chinese, English, Japanese, Korean, Arabic, and Italian.

[0054] S4: Match the product name with the pre-built product information database to obtain a matching result; the matching result includes several first candidate product data.

[0055] Matching product names with a pre-built product information database is implemented using Transformer's database text matching algorithm, which greatly reduces the number of first-candidate product data.

[0056] S5: Match the price data of several first candidate product data in the matching result with the product price to obtain matching data.

[0057] The matching data includes the price data of several first candidate products in the matching results and the matching situation of the product price. It can be used to indicate the first candidate product that best matches the price tag image.

[0058] S6: Based on the matching data, determine the target product data from a plurality of first candidate product data in the matching results, and determine the target product data as the price tag content of the target price tag.

[0059] Compared to related technologies, this application uses an object detection algorithm to detect the name region and product price of a price tag image. Then, it matches the product name identified from the name region using an OCR algorithm with a pre-built product information database. Next, it obtains the price data of several first-candidate product data from the matching results and compares it with the product price. Based on the matching data, it determines the target product data from these first-candidate product data, thus obtaining the price tag content of the target price tag. Regardless of whether the price tag image corresponds to an electronic or traditional non-electronic price tag, this application can accurately obtain the price tag content, which is beneficial for real-time monitoring and management of products on shelves. Furthermore, this application further improves the accuracy of the obtained price tag content through a two-step data matching process.

[0060] In a feasible embodiment, step S2: detecting the name region and product price of the price tag image using an object detection algorithm, includes:

[0061] S21: The name area and price area of ​​the price tag image are detected by the target detection algorithm.

[0062] S22: The price numbers and price symbols of the price range are identified by the target detection algorithm to obtain the price of the commodity.

[0063] In this embodiment, since the price of a commodity is composed of simple numbers and numerical symbols, the object detection algorithm based on deep learning can also detect and classify the numbers and numerical symbols, thereby obtaining the commodity price based on the classification results output by the algorithm.

[0064] For example, price tag images such as Figure 3 As shown, the object detection algorithm can detect the area corresponding to the product name "X Soft Long-Lasting Anti-Dandruff Shampoo X500ml" and the areas corresponding to the product price such as "9", ".", "9", and "9", where "X" represents illegible Chinese characters. The deep learning-based object detection algorithm can not only provide the specific location coordinates of the target area but also classify the target area.

[0065] In a feasible embodiment, step S4: matching the product name with a pre-built product information database to obtain a matching result; the matching result includes a number of first candidate product data steps, including:

[0066] S41: Obtain the similarity between the product name and the various product information data stored in the product information database.

[0067] S42: The top few product information data with the highest similarity are determined as the first candidate product data.

[0068] In this embodiment, considering whether the content of the target price tag is blurry or whether the price tag image is obscured, the top few product information data with the highest similarity are determined as the first candidate product data. For example, the top three product information data with the highest similarity are determined as the first candidate product data, and then the first candidate product data is used for secondary matching, which can further improve the accuracy of obtaining the price tag content.

[0069] In one feasible embodiment, the matching data includes matching values ​​between each of the first candidate product data and the product price;

[0070] Step S6: The step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0071] S61: If the matching values ​​of the matching data are all less than the preset matching threshold, the first candidate product data with the highest similarity is determined as the target product data from the matching results.

[0072] The matching threshold is a user-preset percentage value. It serves as a parameter to determine whether the matched data meets the user's requirements. For example, the matching threshold can be set to 100%, 98%, 90%, etc.

[0073] In a feasible embodiment, step S6: determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0074] S62: If there is a matching value in the matching data that is greater than or equal to a preset matching threshold, the corresponding first candidate product data is determined as the target product data.

[0075] When the matching value is greater than or equal to the preset matching threshold, it means that the price data of the corresponding first candidate product data matches the product price.

[0076] In a feasible embodiment, step S6: determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0077] S631: If there are at least two matching values ​​in the matching data that are greater than or equal to a preset matching threshold, the corresponding first candidate product data is determined as the second candidate product data;

[0078] S632: Based on the matching results, obtain the similarity between each of the second candidate product data and the product information, and determine the second candidate product data with the highest similarity as the target product data.

[0079] In a feasible embodiment, step S6: determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes:

[0080] S633: If there are several second candidate product data with the highest similarity, randomly select one from the several second candidate product data with the highest similarity and determine it as the target product data.

[0081] In this embodiment, by matching data twice, the target product data that best matches the price tag image can be used as the price tag content.

[0082] For example, price tag images such as Figure 3As shown in the figure, since the content in the product name area is of text type, the target detection algorithm cannot classify and identify its content. Therefore, only the specific position coordinates output by the algorithm are used. The product price is a combination of simple numbers and symbols (e.g., "."), and each number and symbol can be easily detected and classified by the target detection algorithm. Therefore, the classification result output by the algorithm can be directly used as the product price information. For the product name area, the OCR algorithm is used to identify its content, and the preliminary product name can be obtained. Due to the small size of the price tag, the font size of the product information displayed on the price tag is smaller, and limited by the imaging quality of the camera, sometimes the product information displayed on the price tag cannot be clearly shown, such as Figure 3 The Chinese characters before the character "柔" and after the character "发" shown in the figure may not be clearly shown because the Chinese characters themselves are very complex or the camera takes pictures unclearly. In this case, the single OCR algorithm cannot identify the Chinese characters before the character "柔" and after the character "发", that is, the product name information cannot be accurately identified. At this time, when the product name is matched with the pre-constructed product information database, three first candidate product data such as "飘柔长效去屑洗发水500ml", "轻柔长效去屑洗发水500ml", "哲柔长效去屑洗发液500ml" may be obtained. At this time, through steps S5 - S6 and S61 - S633, the closest one can be selected from the three first candidate product data to determine the price tag content of the target price tag, which greatly improves the accuracy of recognition.

[0083] Please refer to Figure 4 , the second embodiment of the present application provides a price tag content acquisition device, including:

[0084] A picture acquisition module 1 for acquiring a price tag picture of a target price tag;

[0085] A detection module 2 for detecting the name area and product price of the price tag picture through a target detection algorithm;

[0086] An identification module 3 for identifying the content of the name area through the OCR algorithm to obtain a product name;

[0087] A first matching module 4 for matching the product name with a pre-constructed product information database to obtain a matching result; the matching result includes several first candidate product data;

[0088] A second matching module 5 for matching the price data of several first candidate product data in the matching result with the product price to obtain matching data;

[0089] The price tag content acquisition module 6 is used to determine target product data from a plurality of first candidate product data in the matching results based on the matching data, and to determine the target product data as the price tag content of the target price tag.

[0090] It should be noted that the price tag content acquisition device provided in the second embodiment of this application is only illustrated by the above-described division of functional modules when executing the price tag content acquisition method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the price tag content acquisition device provided in the second embodiment of this application and the price tag content acquisition method in the first embodiment of this application belong to the same concept. The implementation process is detailed in the method embodiment, and will not be repeated here. The device embodiment described above is merely illustrative. The components described as separate parts may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the solution of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0091] An embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the price tag content acquisition method described above.

[0092] One embodiment of this application also provides a computer device, including a storage device, a processor, and a computer program stored in the storage device and executable by the processor, wherein the processor executes the computer program to implement the steps of the price tag content acquisition method as described above.

[0093] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function selected in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function selected in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0098] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0100] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for obtaining price tag content, characterized in that, include: Get the price tag image of the target price tag; The name area and product price of the price tag image were detected using an object detection algorithm. The product name is obtained by performing content recognition on the name area using an OCR algorithm; The product names are matched with a pre-built product information database to obtain matching results; the matching results include several first candidate product data. The price data of several first candidate product data in the matching results are matched with the product price to obtain matching data; Based on the matching data, target product data is determined from a plurality of first candidate product data in the matching results, and the target product data is determined as the price tag content of the target price tag; The step of matching the product name with a pre-built product information database to obtain a matching result, wherein the matching result includes several first candidate product data, includes: Obtain the similarity between the product name and the various product information data stored in the product information database; The top few product information data with the highest similarity are determined as the first candidate product data.

2. The method for obtaining price tag content according to claim 1, characterized in that, The step of detecting the name region and product price of the price tag image using an object detection algorithm includes: The target detection algorithm is used to detect the name and price areas of the price tag image. The target detection algorithm identifies the price numbers and price symbols in the price range to obtain the price of the commodity.

3. The method for obtaining price tag content according to claim 1, characterized in that, The matching data includes the matching values ​​between each of the first candidate product data and the product price; The step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes: If all the matching values ​​of the matching data are less than the preset matching threshold, the first candidate product data with the highest similarity is determined as the target product data from the matching results.

4. The method for obtaining price tag content according to claim 1, characterized in that, The step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes: If there is a matching value in the matching data that is greater than or equal to a preset matching threshold, the corresponding first candidate product data is determined as the target product data.

5. The method for obtaining price tag content according to claim 1, characterized in that, The step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes: If at least two matching values ​​in the matching data are greater than or equal to a preset matching threshold, the corresponding first candidate product data is determined as the second candidate product data; Based on the matching results, the similarity between each second candidate product data and the product information is obtained, and the second candidate product data with the highest similarity is determined as the target product data.

6. The method for obtaining price tag content according to claim 5, characterized in that, The step of determining target product data from a plurality of first candidate product data in the matching results based on the matching data, and determining the target product data as the price tag content of the target price tag, includes: If there are several second candidate product data with the highest similarity, randomly select one from the several second candidate product data with the highest similarity and determine it as the target product data.

7. A device for acquiring price tag content, characterized in that, include: The image acquisition module is used to acquire images of the target price tag. The detection module is used to detect the name area and product price of the price tag image using a target detection algorithm; The recognition module is used to perform content recognition on the name area using an OCR algorithm to obtain the product name; The first matching module is used to match the product name with a pre-built product information database to obtain a matching result; the matching result includes several first candidate product data. The second matching module is used to match the price data of several first candidate product data in the matching result with the product price to obtain matching data; The price tag content acquisition module is used to determine target product data from a plurality of first candidate product data in the matching results based on the matching data, and to determine the target product data as the price tag content of the target price tag. The method involves matching the product name with a pre-built product information database to obtain a matching result; the matching result includes several first candidate product data, including: Obtain the similarity between the product name and the various product information data stored in the product information database; The top few product information data with the highest similarity are determined as the first candidate product data.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the steps of the method for obtaining price tag content as described in any one of claims 1 to 6.

9. A computer device, characterized in that: It includes a storage device, a processor, and a computer program stored in the storage device and executable by the processor, wherein the processor executes the computer program to implement the steps of the price tag content acquisition method as described in any one of claims 1 to 6.

Images