WO2021057879A1

WO2021057879A1 - Data processing system and method, electronic device, and computer readable storage medium

Info

Publication number: WO2021057879A1
Application number: PCT/CN2020/117621
Authority: WO
Inventors: 应高选; 张宇翔; 蒋佳忆
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2019-09-29
Filing date: 2020-09-25
Publication date: 2021-04-01
Also published as: CN112580379B; CN112580379A

Abstract

Embodiments of the present invention provide a data processing system and method, an electronic device, and a computer readable storage medium. The system comprises: an image acquisition module, used for photographing according to at least one photographing route set for a goods shelf, and acquiring an image comprising an information identification code of an object placed on the goods shelf, wherein the photographing route is composed of multiple photographing points; an image processing module, used for processing the image acquired by the image acquisition module to obtain the information identification code; and an analysis module, used for analyzing object information of the object according to the information identification code obtained by the image processing module. According to the embodiments of the present invention, the goods shelf is photographed, and the information identification code of the object placed on the goods shelf is obtained, so as to quickly and accurately analyze the object information, thereby improving the speed and accuracy of shelf digitization.

Description

Data processing system and method, electronic equipment, and computer readable storage medium

This application claims the priority of a Chinese patent application filed on September 29, 2019 with the application number 201910936976.2 and the title of the invention "data processing system and method, electronic equipment, and computer-readable storage medium", the entire content of which is incorporated by reference In this application.

Technical field

The present invention relates to the field of electronic technology, and in particular to a data processing system and method, electronic equipment, and computer-readable storage media.

Background technique

In offline stores, various products are displayed on the shelves. If you implement digital operations on the shelves, that is, structured storage of the information on the shelves and the products displayed on the shelves, you will be able to promptly remind the clerk to replenish the goods, or notify the clerk of the incorrect information on the display of the product to correct it in time, so as to realize the change. Operate and manage stores well.

In the prior art, generally, the commodity information of the commodity is obtained by taking a picture of the commodity displayed on the shelf and adopting the method of image feature recognition.

However, on the one hand, because the sample training speed of the feature recognition algorithm model is much lower than the speed of new products, the efficiency of shelf digitization is very low; on the other hand, due to the variety of product categories and complex scenarios in the store, the shelf is digitized. The accuracy rate is low.

Summary of the invention

The embodiments of the present invention provide a data processing system and method, an electronic device, and a computer-readable storage medium to solve the defects of low data processing efficiency and low accuracy in the prior art.

To achieve the foregoing objective, an embodiment of the present invention provides a data processing system, including:

The image acquisition module is configured to shoot according to at least one shooting route set for the shelf, and collect an image containing the information identification code of the object placed on the shelf, wherein the shooting route is composed of a plurality of shooting points;

An image processing module, configured to process the image collected by the image collection module to obtain the information identification code;

The analysis module is configured to analyze the object information of the object according to the information identification code obtained by the image processing module.

The embodiment of the present invention also provides a data processing method, including:

Shooting according to at least one shooting route set for the shelf, and collecting an image containing the information identification code of the object placed on the shelf, wherein the shooting route is composed of a plurality of shooting points;

Performing an image processing operation on the image to obtain the information identification code;

Perform a parsing operation on the information identification code to obtain the object information of the object.

The embodiment of the present invention also provides an electronic device, including:

Memory, used to store programs;

The processor is configured to run the program stored in the memory for:

The embodiment of the present invention also provides a computer-readable storage medium on which instructions are stored, and the instructions include:

The data processing system and method, electronic equipment, and computer-readable storage medium provided by the embodiments of the present invention can quickly and accurately analyze the object information by photographing the shelf and obtaining the information identification code of the object placed on the shelf. The speed and accuracy of shelf digitization.

The above description is only an overview of the technical solution of the present invention. In order to understand the technical means of the present invention more clearly, it can be implemented in accordance with the content of the specification, and in order to make the above and other objectives, features and advantages of the present invention more obvious and understandable. In the following, specific embodiments of the present invention will be cited.

Description of the drawings

By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only used for the purpose of illustrating the preferred embodiments, and are not considered as a limitation to the application. Also, throughout the drawings, the same reference symbols are used to denote the same components. In the attached picture:

FIG. 1 is a schematic diagram of an application scenario of an embodiment of a data processing system provided by the present invention;

2 is a system block diagram of another embodiment of the data processing system provided by the present invention;

Figure 3 is a flowchart of an embodiment of a data processing method provided by the present invention;

4 is a flowchart of another embodiment of the data processing method provided by the present invention;

FIG. 5 is a schematic structural diagram of an embodiment of an electronic device provided by the present invention.

detailed description

Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the drawings show exemplary embodiments of the present disclosure, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

In the prior art, generally, the commodity information of the commodities displayed on the shelf is obtained by taking pictures of the commodities displayed on the shelves, and using the method of image feature recognition to identify the photographed commodity pictures. However, on the one hand, because the sample training speed of the feature recognition algorithm model is much lower than the speed of new products, the data processing efficiency is very low; on the other hand, due to the variety of product categories and complex scenes in the store, data processing is The accuracy rate is low.

Therefore, in view of the shortcomings of the prior art, this application proposes a data processing system for the digital scene of shelves. The main principle is: for the shelves arranged in the store, a fixed shooting route is set in advance, and the image acquisition module (for example, , Lidar-based navigation and positioning shop patrol robot) according to the shooting point in the shooting route to take fixed-point shooting to collect the image containing the information identification code of the object, and process the image through the image processing module to obtain the information identification code of the object, And analyze the object information identified by the information identification code through the analysis module. The object information of the objects (commodities) placed on the shelves can be quickly and accurately obtained, so as to improve the speed and accuracy of the shelf digitization. In addition, the image acquisition module can collect multiple frames of images for the same information identification code, for example, to form video data, and the image processing module can process the video data, and the obtained object identification code has higher accuracy.

The above-mentioned embodiments are descriptions of the technical principles of the embodiments of the present invention, and the specific technical solutions of the embodiments of the present invention will be further described in detail below through a plurality of embodiments.

Example one

FIG. 1 is a schematic diagram of an application scenario of an embodiment of a data processing system provided by the present invention. The structure shown in FIG. 1 is only one example of a data processing system to which the technical solution of the present invention can be applied. As shown in Figure 1, in the digitalized scenario of a shelf, a shooting route composed of multiple shooting points is set for the shelf. The shooting route can be one or more. When there are multiple shooting routes, the shooting route can be selected for shooting according to the user's input, or the best shooting route can be calculated adaptively. The data processing system is equipped with an image acquisition module, such as a shop-patrolling robot, to perform fixed-point shooting according to each shooting point in the shooting route to collect images. The image contains the information identification code of the object placed on the shelf, such as the product identification code . Specifically, the information identification code can uniquely identify the object information of the object, for example, it may be a barcode, a two-dimensional code, or the like. After the patrol robot collects the image, it sends the image to the image processing module for processing to obtain the identification code of each information in the image. Then, the image processing module sends the obtained information identification codes to the analysis module to analyze the object information of the corresponding objects according to the information identification codes, and then send the object information to the database for storage to realize shelf digitization.

The data processing system provided by the embodiment of the present invention quickly and accurately analyzes the object information by taking pictures of the shelves and obtaining the information identification codes of the objects placed on the shelves, thereby improving the speed and accuracy of the shelf digitization.

Example two

Fig. 2 is a system block diagram of another embodiment of the data processing system provided by the present invention. As shown in FIG. 2, on the basis of the embodiment shown in FIG. 1, the data processing system provided in the embodiment of the present invention processes the two-dimensional code that uniquely identifies the object information. Specifically, the data processing system provided by the embodiment of the present invention includes: an image acquisition module 21, an image processing module 22, and an analysis module 23. The image processing module 22 may include: a region cropping unit 221, a calculation unit 222, an image restoration unit 223, and a two-dimensional code correction unit 224.

Among them, the area cropping unit 221 can be used to detect the quadrilateral graphics in the image collected by the image collection module 21, and use each quadrilateral graphics as the upper left corner, the lower left corner, and the upper right corner in the image according to a preset length. The corners and the lower right corner are expanded to form a target area for the quadrilateral figure; the calculation unit 222 is used to calculate the number of similar quadrilaterals in each target area, where the similar quadrilaterals are those whose area difference is less than the first preset threshold. Quadrilateral graphics; the image restoration unit 223 is used to perform image restoration processing for a target area where the number of similar quadrilaterals is less than three, so that the number of similar quadrilaterals in the target area is three; the two-dimensional code correction unit 224 is used for A target area with three similar quadrilaterals is detected, the vertices of the QR code are detected, and the target area is restored to a square area through an affine transformation operation, and a rotation operation is performed on the square area so that the three similar quadrilaterals are in the square respectively. The upper left, lower left, and upper right corners of the area.

In the embodiment of the present invention, the image acquisition module 21 can photograph shelves and objects on the shelves according to a fixed step along the shooting route, and send the image containing the two-dimensional code of the object to the image processing module 22 for image processing operations. To get the QR code in the image. After the region cropping unit 221 in the image processing module 22 receives the image collected by the image acquisition module 21, it first detects the quadrilateral graphics in the image, and expands each quadrilateral graphics as the target area in the image according to a preset length, namely , The region of interest of the two-dimensional code (two-dimensional code ROI). Specifically, a quadrilateral graphic can be extended as the upper left corner to obtain a target area. Therefore, by taking a quadrilateral graph as the upper left corner, the lower left corner, the upper right corner and the lower right corner respectively, four target areas for the quadrilateral graph can be obtained.

Then, the calculation unit 222 calculates the number of similar quadrilaterals in each target area. When there are three similar quadrilaterals in a target area, it can be basically determined that the graphic in the target area is a two-dimensional code. Therefore, the two-dimensional code correction unit 224 can correct the target area. Specifically, the two-dimensional code fixed-point detection operation can be performed in the target area, and the target area can be restored to a square through affine transformation, and the square can be rotated, so that three similar quadrilaterals are respectively in the upper left corner and the lower left corner of the square area. And the upper right corner. Thus, the two-dimensional code is obtained.

When the calculation unit 222 calculates that there are less than three similar quadrilaterals in a target area, the image restoration unit 223 may perform image restoration processing on the target area. If the restored target area contains three similar quadrilaterals, the two-dimensional code correction unit 224 performs correction processing to obtain a two-dimensional code; if there are still less than three similar quadrilaterals after the restoration processing, it means that the target area cannot be restored. Discard the target area directly.

If the number of similar quadrilaterals in the target area calculated by the calculation unit 222 is more than three, or the number of similar quadrilaterals in the target area restored by the image restoration unit 223 is more than three, it means that the target area graphic is not Two-dimensional code, also discard the target area.

In addition, when setting the shooting point, the image acquisition module 21 can include overlapping areas in the two adjacent left and right images collected by the adjacent shooting points, so as to compensate for the missed detection of the QR code and increase the upturn rate of the shelf. That is, the ratio of the number of different two-dimensional codes identified by the detection to the total number of two-dimensional codes on the shelf.

Further, at least two upper and lower acquisition sub-modules may be arranged in the image acquisition module 21, for example, two cameras are arranged vertically, so that two adjacent upper and lower images collected at the same shooting point include overlapping areas. In this way, it can also make up for the missed inspection of the two-dimensional code and increase the turnover rate of shelves.

In addition, in the embodiment of the present invention, a mixed processing mode can be set, that is, the image acquisition module 21 and the image processing module 22 can be used to obtain the information identification code for the scene of irregular shelves; for regular shelves (for example, smart shelves or In the scenario of a shelf with an electronic price tag, etc., a receiving module 24 can be set in the data processing system, and the receiving module 24 can be used to receive the object information of the object automatically sent by the shelf. Regular shelves can report object information by themselves, thereby improving data processing efficiency.

On this basis, the data processing system provided by the embodiment of the present invention may further include a verification module 25. The verification module 25 may be used to verify the object information parsed by the parsing module 23 according to the object information received by the receiving module 24.

In the embodiment of the present invention, when the goods are misplaced, the verification failure information can be fed back to the user. Therefore, the data processing system may further include: a feedback module 26, which can be used to verify the object information in the verification module 25 When the verification fails, the verification failure feedback message is sent.

Furthermore, in the embodiment of the present invention, a "dual engine" mode can be set, that is, when the two-dimensional code cannot be identified, the collection of a product image is triggered to directly identify the product. Therefore, the data processing system may further include: an object information obtaining module 27, which may be used to obtain an image of the object when the analysis module 23 fails to obtain the object information of the object, and recognize the image to obtain Object information of the object.

Still further, in the embodiment of the present invention, the data processing system may further include: a route adjustment module 28, which may be configured to generate a new shooting route according to the result obtained by the image processing module 22 with respect to the information identification code. Adjust the shooting route.

In addition, in the embodiment of the present invention, the image acquisition module 21 may be an automatic moving image acquisition device (for example, a robot with an image acquisition function), a handheld image acquisition device (the image acquisition device is held by the user), or a surveillance camera device (not During the peak shopping period, the cameras used to monitor the flow of people are reused) and so on.

In the data processing system provided by the embodiment of the present invention, the shelves are photographed in the store according to the preset shooting route through the image acquisition module, the images of all shelves are collected in batches, and the two-dimensional codes in the images are automatically obtained, which can quickly and accurately analyze Output the object information, increase the turnover rate of the shelf, and store the complete shelf information in a structured manner, thereby improving the speed and accuracy of the shelf digitization.

Example three

Fig. 3 is a flowchart of an embodiment of a data processing method provided by the present invention. The execution subject of this method may be the above-mentioned data processing system, various terminal devices with functions such as image acquisition, image processing, and data processing, or may be devices or chips integrated on these devices. As shown in Figure 3, the data processing method includes the following steps:

301. Shoot according to at least one shooting route set for the shelf, and collect an image containing the information identification code of the object placed on the shelf.

In the embodiment of the present invention, the shooting route is composed of a plurality of shooting points. After setting up a shooting route composed of multiple shooting points for the shelf, during the shelf digitization process, firstly, the shooting is carried out according to the preset shooting route to obtain the image containing the information identification code. Specifically, the information identification code can uniquely identify the object information of the object set on the shelf, for example, it may be a barcode, a two-dimensional code, or the like.

302. Perform image processing operations on the foregoing image to obtain an information identification code.

In the embodiment of the present invention, after the image is collected, image processing is performed on it to obtain each information identification code in the image.

303. Perform a parsing operation on the above-mentioned information identification code to obtain object information of the object.

Then, the object information of the corresponding object is parsed according to the information identification code, and the object information is sent to the database for storage, so as to realize the digitalization of the shelf.

The data processing method provided by the embodiment of the present invention quickly and accurately analyzes the object information by photographing the shelf and obtaining the information identification code of the object placed on the shelf, thereby improving the speed and accuracy of shelf digitization.

Example four

Fig. 4 is a flowchart of another embodiment of a data processing method provided by the present invention. As shown in FIG. 4, based on the embodiment shown in FIG. 3, the data processing method provided in this embodiment may further include the following steps:

401. Shoot according to a shooting route set for a shelf, and collect an image containing an information identification code of an object placed on the shelf.

In the embodiment of the present invention, when setting the shooting point, the image acquisition module can make the two adjacent left and right images collected by the adjacent shooting point include overlapping areas, so as to compensate for the missed detection of the two-dimensional code and improve the shelf life. Turn-up rate, that is, the ratio of the number of different two-dimensional codes detected and identified to the total number of two-dimensional codes on the shelf.

Further, it is also possible to collect at least two images that are adjacent to each other up and down at the same shooting point in the shooting route, so that the two images contain overlapping areas. In this way, it can also make up for the missed inspection of the two-dimensional code and increase the turnover rate of the shelf.

402. Detect quadrilateral figures in the image, and expand each quadrilateral figure as an upper left corner, a lower left corner, an upper right corner, and a lower right corner according to a preset length in the image to form a target area for the quadrilateral figure.

In the embodiment of the present invention, after the image is collected, the quadrilateral graphics in the image are first detected, and each quadrilateral graphics is expanded into the target area according to the preset length in the image, that is, the region of interest of the two-dimensional code (two-dimensional code). Code ROI). Specifically, a quadrilateral graphic can be extended as the upper left corner to obtain a target area. Therefore, by using a quadrilateral graphic as the upper left corner, the lower left corner, the upper right corner, and the lower right corner, respectively, four target areas for the quadrilateral graphic can be obtained.

403. Count the number of similar quadrilaterals in each target area.

In the embodiment of the present invention, similar quadrilaterals are a plurality of quadrilateral graphs whose area difference is smaller than the first preset threshold.

404. Determine whether the two-dimensional code in the target area is complete according to the number of similar quadrilaterals. If the number of similar quadrilaterals is three, it means that the two-dimensional code in the target area is complete, and step 406 is executed for the target area. If the number of similar quadrilaterals is less than three, it means that the two-dimensional code in the target area is incomplete. Then, step 405 is executed for the target area.

405. Perform image restoration processing for a target area where the number of similar quadrilaterals is less than three, so that the number of similar quadrilaterals in the target area is three.

If the restored target area contains three similar quadrilaterals, perform the following step 406 to obtain the QR code; if there are still less than three similar quadrilaterals after the restoration process, it means that the target area is unrecoverable, and the target area is discarded directly .

406. Perform a correction operation on the target area.

In the embodiment of the present invention, when there are three similar quadrilaterals in a target area, it can be basically determined that the graphic in the target area is a two-dimensional code. Therefore, a correction operation can be performed on the target area. Specifically, the two-dimensional code fixed-point detection operation can be performed in the target area, and the target area can be restored to a square area through affine transformation, and the square area can be rotated so that three similar quadrilaterals are respectively in the upper left corner of the square area, The lower left corner and the upper right corner. Thus, the two-dimensional code is obtained.

If the number of similar quadrilaterals in the target area is more than three, it means that the target area graphic is not a two-dimensional code, and the target area is also discarded.

407. Perform an analysis operation on the foregoing two-dimensional code to obtain object information of the object.

In the embodiment of the present invention, if the analysis of the two-dimensional code fails, the target area is discarded.

408. Determine whether the parsed object information is duplicated with the parsed object information, and if it is duplicated, discard the duplicate object information, and retain the parsed object information first.

In addition, in the embodiment of the present invention, a mixed processing mode can be set, that is, the information identification code can be obtained by adopting the above steps for the scene of irregular shelves; for regular shelves (for example, smart shelves or shelves with electronic price tags, etc.) In the scene, you can receive the object information of the object automatically sent by the shelf. Regular shelves can report object information by themselves, thereby improving data processing efficiency.

On this basis, in the embodiment of the present invention, the object information obtained by analyzing the information identification code can also be verified according to the object information automatically sent by the shelf. When the goods are misplaced and the verification of the object information fails, it can also provide feedback to the user, that is, send verification failure feedback information.

Furthermore, in the embodiment of the present invention, a "dual engine" mode can be set, that is, when the two-dimensional code cannot be identified, the collection of a product image is triggered to directly identify the product. That is, when the analysis of the information identification code fails, the image of the object is obtained, and the image is recognized to obtain the object information of the object.

Furthermore, in the embodiment of the present invention, a new shooting route may be generated according to the result of obtaining the information identification code, so as to adjust the shooting route.

The data processing method provided by the embodiment of the present invention can quickly and accurately analyze the object information by photographing shelves in a store according to a preset shooting route, collecting images of all shelves in batches, and automatically acquiring the two-dimensional codes in the images. , Improve the shelf turnover rate and store the complete shelf information in a structured manner, thereby improving the speed and accuracy of shelf digitization.

Example five

The internal functions and structure of the data processing system are described above, and the system can be implemented as an electronic device. FIG. 5 is a schematic structural diagram of an embodiment of an electronic device provided by the present invention. As shown in FIG. 5, the electronic device includes a memory 51 and a processor 52.

The memory 51 is used to store programs. In addition to the aforementioned programs, the memory 51 can also be configured to store other various data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phone book data, messages, pictures, videos, etc.

The memory 51 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

The processor 52 is not only limited to the central processing unit (CPU), but may also be a graphics processing unit (GPU), field programmable gate array (FPGA), embedded neural network processor (NPU) or artificial intelligence (AI) chip Wait for the processing chip. The processor 52 is coupled with the memory 51, and executes the program stored in the memory 51 for:

Shoot according to at least one shooting route set for the shelf, and collect an image containing the information identification code of the object placed on the shelf, where the shooting route is composed of multiple shooting points;

Perform image processing operations on the above-mentioned image to obtain the information identification code;

The information identification code is analyzed to obtain the object information of the above object.

Further, as shown in FIG. 5, the electronic device may further include: a communication component 53, a power supply component 54, an audio component 55, a display 56 and other components. Only some components are schematically shown in FIG. 5, which does not mean that the electronic device only includes the components shown in FIG. 5.

The communication component 53 is configured to facilitate wired or wireless communication between the electronic device and other devices. Electronic devices can access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination of them. In an exemplary embodiment, the communication component 53 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 53 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

The power supply component 54 provides power for various components of the electronic device. The power supply component 54 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic devices.

The audio component 55 is configured to output and/or input audio signals. For example, the audio component 55 includes a microphone (MIC), and the microphone is configured to receive external audio signals when the electronic device is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may be further stored in the memory 51 or transmitted via the communication component 53. In some embodiments, the audio component 55 further includes a speaker for outputting audio signals.

The display 56 includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.

A person of ordinary skill in the art can understand that all or part of the steps in the foregoing method embodiments can be implemented by a program instructing relevant hardware. The aforementioned program can be stored in a computer readable storage medium. When the program is executed, it executes the steps including the foregoing method embodiments; and the foregoing storage medium includes: ROM, RAM, magnetic disk, or optical disk and other media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be equivalently replaced; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention. range.

Claims

A data processing system, characterized in that it comprises:

The image acquisition module is configured to shoot according to at least one shooting route set for the shelf, and collect an image containing the information identification code of the object placed on the shelf, wherein the shooting route is composed of a plurality of shooting points;

An image processing module, configured to process the image collected by the image collection module to obtain the information identification code;

The analysis module is configured to analyze the object information of the object according to the information identification code obtained by the image processing module.
The data processing system according to claim 1, further comprising:

The receiving module is configured to receive the object information of the object automatically sent by the shelf.
The data processing system according to claim 2, further comprising:

The verification module is configured to verify the object information parsed by the parsing module according to the object information received by the receiving module.
The data processing system according to claim 3, further comprising:

The feedback module is configured to send verification failure feedback information when the verification module fails to verify the object information.
The data processing system according to claim 1, wherein the image acquisition module is an automatic moving image acquisition device, a handheld image acquisition device, or a surveillance camera device.
The data processing system according to claim 1, further comprising:

The object information obtaining module is configured to obtain an image of the object when the analysis module fails to obtain the object information of the object, and recognize the image to obtain the object information of the object.
The data processing system according to claim 1, further comprising:

The route adjustment module is configured to generate a new shooting route according to the result of obtaining the information identification code by the image processing module.
The data processing system according to any one of claims 1 to 7, wherein the information identification code is a barcode or a two-dimensional code that uniquely identifies the object information of the object.
The data processing system according to any one of claims 1 to 7, wherein the information identification code is a two-dimensional code that uniquely identifies the object information of the object, and the image processing module includes:

The area cropping unit is configured to detect the quadrilateral figures in the image for the image collected by the image collection module, and use each quadrilateral figure as the upper left corner and the upper left corner of the image according to a preset length. Expand the lower left corner, upper right corner, and lower right corner to form a target area for the quadrilateral figure;

A calculating unit, configured to calculate the number of similar quadrilaterals in each of the target regions, wherein the similar quadrilaterals are multiple quadrilateral graphics with an area difference less than a first preset threshold;

An image restoration unit, configured to perform image restoration processing on the target area where the number of similar quadrilaterals is less than three, so that the number of similar quadrilaterals in the target area is three;

The two-dimensional code correction unit is used to detect the vertices of the two-dimensional code for the target area with three similar quadrilaterals, and restore the target area to a square area through an affine transformation operation, and target the square area Perform a rotation operation so that the three similar quadrilaterals are respectively at the upper left corner, the lower left corner and the upper right corner of the square area.
The data processing system according to claim 1, wherein the shooting point is set such that the two adjacent left and right images collected by the adjacent shooting point include an overlapping area.
The data processing system according to claim 1, wherein the image acquisition module includes at least two acquisition sub-modules arranged up and down, so that the two adjacent upper and lower images collected at the same shooting point contain Overlapping area.
A data processing method, characterized in that it comprises:

Shooting according to at least one shooting route set for the shelf, and collecting an image containing the information identification code of the object placed on the shelf, wherein the shooting route is composed of a plurality of shooting points;

Performing an image processing operation on the image to obtain the information identification code;

Perform a parsing operation on the information identification code to obtain the object information of the object.
The data processing method according to claim 12, further comprising:

Receiving the object information of the object automatically sent by the shelf.
The data processing method according to claim 13, further comprising:

The object information obtained by parsing the information identification code is verified according to the object information automatically sent by the shelf.
The data processing method according to claim 14, further comprising:

When the verification of the object information fails, the verification failure feedback information is sent.
The data processing method according to claim 12, further comprising:

When the object information of the object fails to be obtained, an image of the object is obtained, the image is recognized, and the object information of the object is obtained.
The data processing method according to claim 12, further comprising:

According to the acquisition result of the information identification code, a new shooting route is generated.
The data processing method according to any one of claims 12 to 17, wherein the information identification code is a barcode or a two-dimensional code that uniquely identifies the object information of the object.
The data processing method according to any one of claims 12 to 17, wherein the information identification code is a two-dimensional code that uniquely identifies the object information of the object, and the image processing is performed on the image The operation to obtain the information identification code includes:

Detect quadrilateral figures in the image, and expand each quadrilateral figure as the upper left corner, the lower left corner, the upper right corner and the lower right corner according to a preset length in the image to form a target for the quadrilateral figure area;

Calculating the number of similar quadrilaterals in each target area, where the similar quadrilaterals are a plurality of quadrilateral graphics whose area difference is less than a first preset threshold;

For the target area where the number of similar quadrilaterals is three, the vertices of the two-dimensional code are detected, and the target area is restored to a square area through an affine transformation operation, and a rotation operation is performed on the square area to make three The similar quadrilaterals are respectively at the upper left corner, the lower left corner and the upper right corner of the square area.
20. The data processing method according to claim 19, characterized in that, before detecting the vertices of the two-dimensional code for the two-dimensional code area with three similar quadrilaterals, the method further comprises:

For the target area where the number of similar quadrilaterals is less than three, image restoration processing is performed, so that the number of similar quadrilaterals in the target area is three.
The data processing method according to claim 12, wherein the shooting point is set such that the two adjacent left and right images collected by the adjacent shooting point include overlapping areas.
The data processing method according to claim 12, wherein the shooting according to at least one shooting route set for the shelf, and collecting an image containing the information identification code of the object placed on the shelf, comprises:

At the same shooting point in the shooting route, at least two images that are adjacent to each other up and down are collected, so that the two images include overlapping areas.
An electronic device, characterized in that it comprises:

Memory, used to store programs;

The processor is configured to run the program stored in the memory for:

Shooting according to at least one shooting route set for the shelf, and collecting an image containing the information identification code of the object placed on the shelf, wherein the shooting route is composed of a plurality of shooting points;

Performing an image processing operation on the image to obtain the information identification code;

Perform a parsing operation on the information identification code to obtain the object information of the object.
A computer-readable storage medium having instructions stored on the computer-readable storage medium, the instructions including:

Shooting according to at least one shooting route set for the shelf, and collecting an image containing the information identification code of the object placed on the shelf, wherein the shooting route is composed of a plurality of shooting points;

Performing an image processing operation on the image to obtain the information identification code;

Perform a parsing operation on the information identification code to obtain the object information of the object.