Commodity ex-warehouse rechecking method, device and equipment and storage medium

Abstract

The invention discloses a commodity ex-warehouse rechecking method and device, electronic equipment and a storage medium, and the system comprises the steps: obtaining a first rechecking image collected by an image collection device in response to a commodity ex-warehouse rechecking instruction, and carrying out the commodity recognition of the first rechecking image, and obtaining the first position information of a first commodity during ex-warehouse; receiving an input warehouse-out list bar code, and scanning the warehouse-out list bar code to obtain commodity information contained in the warehouse-out list bar code; processing according to the first re-checking image and the first warehousing image to obtain second position information when the first commodity is delivered out of the warehouse; and according to the first position information and the second position information, re-checking the first commodity, and when a first re-checking result of the first commodity is obtained, processing a second re-checking image acquired by the image acquisition device until an ex-warehouse re-checking result responding to the commodity ex-warehouse re-checking instruction is obtained. And the efficiency and accuracy of commodity ex-warehouse rechecking are improved.

Description

Technical Field

[0001] The present application relates to the field of logistics outbound technology, and in particular to a commodity outbound verification method, device, electronic equipment and storage medium. Background Art

[0002] The logistics industry is a complex industry that includes packaging, transportation, warehousing, freight forwarding and financial services, and has a fundamental and strategic position. At the same time, the rapid development of the logistics industry has become an indispensable link between producers and consumers.

[0003] At present, most logistics systems have a very complicated structure. The process of goods entering and leaving the warehouse is as follows: the goods enter the warehouse after passing the incoming inspection, and then the warehouse staff counts and calculates them, and then transports the goods to the corresponding storage space, and organizes and records the data list of the warehouse. Then, when leaving the warehouse, the warehouse staff takes out the goods according to the recorded information, and transports the goods to the corresponding storage place for sorting and recording after the review is completed. When reviewing the goods, it is usually checked and counted by manually scanning the barcode of the goods, which requires a lot of labor for scanning and counting, which is not conducive to the integrated control of the goods, and the efficiency of the outbound review is low. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, electronic device and storage medium for verifying the shipment of goods, so as to solve the technical problem of low efficiency of the shipment review of goods in the related art.

[0005] In a first aspect, an embodiment of the present application provides a method for reviewing a product shipment, comprising:

[0006] In response to a product outbound review instruction, a first review image acquired by an image acquisition device is acquired, and product recognition is performed on the first review image to obtain first position information of the first product when the product is outbound, wherein the first review image corresponds to the first product;

[0007] Receive an input outbound list barcode, and scan the outbound list barcode to obtain commodity information contained in the outbound list barcode, wherein the commodity information includes a first incoming image of each commodity and a total number of outbound commodities;

[0008] Processing the first review image and the first warehouse entry image to obtain second location information of the first commodity when it leaves the warehouse;

[0009] The first commodity is reviewed based on the first location information and the second location information, and when a first review result of the first commodity is obtained, the second review image captured by the image acquisition device is processed to obtain an outbound review result in response to the outbound review instruction of the commodity.

[0010] In a second aspect, the embodiment of the present application provides a method for reviewing the shipment of goods, including:

[0011] An image acquisition module is used to respond to a product delivery review instruction, obtain a first review image acquired by an image acquisition device, and perform product recognition on the first review image to obtain first position information of the first product when the product is delivered, wherein the first review image corresponds to the first product;

[0012] A code scanning and recognition module, used to receive an input outbound list barcode, and scan the outbound list barcode to obtain the commodity information contained in the outbound list barcode, wherein the commodity information includes a first incoming image of each commodity and the total number of outbound commodities;

[0013] a position determination module, configured to process the first review image and the first warehouse entry image to obtain second position information of the first commodity when it leaves the warehouse;

[0014] The review judgment module is used to review the first commodity according to the first location information and the second location information, and when obtaining the first review result of the first commodity, process the second review image collected by the image acquisition device to obtain an outbound review result in response to the outbound review instruction of the commodity.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned methods for reviewing the shipment of goods when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above-mentioned methods for reviewing the shipment of goods are implemented.

[0017] The embodiment of the present application provides a commodity outbound review system, method, electronic device and storage medium. When the outbound review of the commodity is required, the outbound review instruction is responded to to obtain the first review image collected by the image acquisition device, and the first review image is processed for commodity identification to obtain the first position information of the first commodity when it is outbound. At the same time, the incoming outbound list barcode is received, and the commodity information of all commodities that need to be outbound is obtained by scanning the outbound list barcode, including the first inbound image and the total number of outbound commodities. Then, the second position information of the first commodity when it is outbound is obtained according to the obtained first review image and the first inbound image. Then, the first commodity is reviewed according to the first position information and the second position information, and all commodities obtained in response to the outbound review instruction are reviewed in the way of reviewing the first commodity to obtain the corresponding review result. In the process of commodity outbound, the review of the commodity is completed through image analysis, processing and comparison, without manual intervention, shortening the time of the entire outbound process, saving costs and resources, and improving the efficiency and accuracy of commodity outbound review. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for checking the goods leaving the warehouse provided in an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of a first review image after grayscale processing provided in an embodiment of the present application;

[0020] Figure 3 is a flowchart of the steps of obtaining the second location information provided in an embodiment of the present application;

[0021] Figure 4 is another flowchart of the steps of obtaining the second location information provided in an embodiment of the present application;

[0022] Figure 5 It is a flowchart of the steps of obtaining a review result in response to a product delivery review instruction provided in an embodiment of the present application;

[0023] Figure 6 It is a structural schematic diagram of a control device for a sliding frame of a bridge-building machine provided in an embodiment of the present application;

[0024] Figure 7 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0025] Figure 8 This is another structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0028] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0029] In the related technology, the process of goods entering and leaving the warehouse in most logistics systems is as follows: the goods enter the warehouse after the incoming inspection is qualified, and then the warehouse staff counts and calculates them, and then transports the goods to the corresponding storage space, and organizes and records the data list of the warehouse. Then, when leaving the warehouse, the warehouse staff takes out the goods according to the recorded information, and transports the goods to the corresponding storage place for sorting and recording after the review is completed. When reviewing the goods, it is usually checked and counted by manually scanning the barcode of the goods, which requires a lot of labor for scanning and counting, which is not conducive to the integrated control of the goods, and the efficiency of the outbound review is low.

[0030] In order to solve the technical problems existing in the related art, the present application embodiment provides a method for checking the goods out of the warehouse, see Figure 1 , Figure 1 It is a flow chart of a method for checking the goods leaving the warehouse provided in an embodiment of the present application, and the method includes steps 101 to 104.

[0031] Step 101, responding to a product outbound review instruction, obtaining a first review image captured by an image acquisition device, and performing product recognition on the first review image to obtain first position information of the first product when it is outbound, wherein the first review image corresponds to the first product.

[0032] In one embodiment, when a product outbound review instruction is received, a first review image of the first product captured by a pre-set image capture device is obtained, and product identification is performed on the first review image to obtain the first position information of the first product when it is outbound, that is, the position of the first product in the first review image is obtained.

[0033] In actual applications, when goods are shipped out, the quantity of goods shipped out is large, and when conducting a review, the goods shipped out need to be consistent with the order information. When determining whether to conduct a review of the goods shipped out, it can be a soft trigger, such as a software signal or command, or a hard trigger, such as a physical button, etc., without specific restrictions.

[0034] Exemplarily, when responding to a product outbound review instruction, a corresponding image acquisition device, such as a camera, is pre-set in the product review area, and then when the sensor detects that a product has entered the product review area, the image acquisition device is controlled to shoot and acquire images to obtain corresponding product information. The first image information acquired by the image acquisition device is acquired based on the method, so that the product outbound review instruction can be triggered when the sensor detects that the product has entered the product review area, that is, when the product is detected by the set sensor, the product outbound review instruction is triggered, and then the product review instruction is responded to.

[0035] For image acquisition devices, such as cameras, relevant parameters can be pre-set, such as camera: 1 / 2.5" COMS color, 500W pixel drive industrial camera, effective pixel 2592*1944, C / CS interface, lens: 8mm, 2 / 3", 1:1.6, 5Mega Pixel, aperture F1..6-F16, C port, object distance: 500m, field of view: 400mm*350mm. Specific settings can be adjusted according to needs.

[0036] Furthermore, the first review image captured by the image acquisition device may include one commodity or multiple commodities, which is specifically determined based on the set image acquisition method. Then, when determining the first position information of the first commodity when it is shipped out in the first review image, the first commodity image is subjected to corresponding image processing, such as grayscale processing and feature extraction. Therefore, when obtaining the first position information, it includes: performing grayscale and Gaussian processing on the first review image to obtain the processed first review image; performing texture feature recognition on the processed first review image to obtain the contour features contained in the first review image, and obtaining the first position information of the first commodity when it is shipped out based on the contour features.

[0037] Specifically, when the first verification image is obtained to determine the first position information of the first commodity, a blurred grayscale image is obtained by performing grayscale and Gaussian processing on the first verification image. Since the texture features in the blurred grayscale image are highlighted, the texture features contained in the first verification image are obtained by extracting the texture features of the processed first verification image, and then the first commodity contained in the first verification image is obtained based on the texture features. In fact, when extracting the texture features, the contour information of the commodity can be extracted, and then the first commodity contained in the first verification image can be determined based on the contour information.

[0038] It should be noted that since the number of commodities included in the first review image may be multiple, when determining the location information of the commodities, the obtained location information may be one or multiple, depending on the number of commodities included in the first review image.

[0039] When determining the first product and the first location information, for the contour information obtained based on the texture feature, it can be set that only when the contour is complete, the product corresponding to the contour is marked as a normal product, otherwise it is marked as an abnormal product, that is, it is regarded as an invalid product. Figure 2 As shown, Figure 2 This is a schematic diagram of the first review image after grayscale processing provided by the embodiment of the present application. Taking the first review image containing two commodities as an example, after the blurred grayscale image is obtained by processing the first review image, it can be obtained through the determination of texture features that there are two commodities, but the outline of commodity 1 is a complete outline, while the outline of commodity 2 is an incomplete outline. At this time, when determining the commodities contained in the first review image, it is determined to be commodity 1, and commodity 2 is an invalid commodity. Then, when conducting commodity review, commodity 1 is reviewed, and commodity 2 is reviewed based on other commodity images.

[0040] Step 102, receiving an input outbound list barcode, and scanning the outbound list barcode to obtain commodity information contained in the outbound list barcode, wherein the commodity information includes a first incoming image of each commodity and the total number of outbound commodities.

[0041] In one embodiment, when the outbound review of goods is being processed, it is necessary to determine whether the outbound goods are consistent with the product information on the library list. Therefore, when responding to the outbound review instruction of goods, the input outbound list barcode is received, and then the outbound list barcode is scanned to obtain the product information contained in the outbound list barcode, and the product information contained in the outbound list barcode at least includes the first incoming image of each product and the total number of outbound products.

[0042] For example, when conducting the product outbound review process, first determine which products need to be outbound, and then determine whether the products that need to be outbound are completely outbound, and whether the products that do not need to be outbound are guaranteed not to be outbound. Therefore, before conducting the product outbound review process, the corresponding outbound list barcode can be obtained, wherein the outbound list barcode is generated based on the outbound product information, and then the products that need to be outbound are determined by scanning the barcode.

[0043] Furthermore, when obtaining the product information of the goods that need to be shipped out, it includes: identifying the barcode of the outbound list to obtain the product list corresponding to the barcode of the outbound list, and counting the product list to obtain the total number of outbound products in the product list; identifying the product identifier of each product included in the product list, and querying according to the product identifier to obtain the first incoming image corresponding to the product identifier.

[0044] Specifically, by scanning the barcode on the outbound list, a list of goods corresponding to the barcode on the outbound list is obtained, and then the list of goods is counted to obtain the total number of goods that need to be shipped out, that is, the total number of outbound goods. At the same time, image query and matching are performed based on the product identification of each product included in the product list to obtain the first incoming image corresponding to the product identification.

[0045] In actual applications, when goods are shipped out of the warehouse, it is necessary to ensure the accuracy and correctness of the shipped goods. At the same time, in order to facilitate the subsequent shipping review, when scanning and processing the barcode of the shipping list, it also includes: matching in the preset image library according to the product information, and determining whether the preset image library contains the image corresponding to the product information; if it is determined that the image corresponding to the product information is contained, executing the steps: processing according to the first review image and the first warehouse image to obtain the second position information of the first product when it is shipped out of the warehouse; if it is determined that the image corresponding to the product information is not contained, a prompt message is issued that the product information has not been entered.

[0046] For example, when processing, it is necessary to ensure that all commodities included in the barcode of the outbound list have been stored in advance, that is, they have been put into storage. Therefore, after obtaining the commodity information included in the barcode of the outbound list, it is determined whether the preset image library completely contains the commodity images of all commodities that need to be outbound. Only when it is completely included can accurate outbound review be performed. If it is not completely included, a prompt message that the commodity information has not been entered can be issued. By entering the commodity information in advance and judging the outbound review, the complete entry of the commodity information can be guaranteed, and the accuracy of the outbound commodity can be guaranteed.

[0047] Furthermore, before the goods are shipped out, the product information of all the goods entering the warehouse will be entered and stored. Specifically, when entering the product information, the image information of the goods entering the warehouse is collected and analyzed to obtain the product identification, product image, etc. of the goods.

[0048] Step 103: Process the first review image and the first warehouse-entering image to obtain second position information of the first commodity when it leaves the warehouse.

[0049] In one embodiment, after obtaining the product information of all products contained in the outbound list barcode by scanning the outbound list barcode, wherein the product information includes the first incoming image and the total number of outbound products, the second position information of the first product when outbound is obtained based on the collected first image information and the second image information, and then the first product is reviewed and judged based on the first position information and the second position information.

[0050] Exemplarily, when determining the second position information of the first commodity when leaving the warehouse based on the first review image and the first warehouse entry image, a Gaussian pyramid model corresponding to the first review image and the first warehouse entry image is constructed, and then the Gaussian image information at each level is processed to obtain the second position information. Figure 3 , Figure 3 It is a flowchart of the steps of obtaining the second location information provided in an embodiment of the present application, wherein the steps include steps 301 to 302.

[0051] Step 301, performing Gaussian downsampling processing on the first review image to obtain a first Gaussian image, and performing Gaussian downsampling processing on the first stored image to obtain a second Gaussian image;

[0052] Step 302: Perform matching calculation based on the first Gaussian image and the second Gaussian image to obtain second position information of the first commodity when it is shipped out of the warehouse.

[0053] Specifically, when processing according to the first review image and the first stored image, a multi-level Gaussian pyramid model corresponding to the first review image and the first stored image is constructed, and each level corresponds to a Gaussian image. When constructing the multi-level Gaussian pyramid model, the relationship between the Gaussian images at each level is an up and down sampling relationship. Specifically, each level of the image is obtained by downsampling the image of the previous level by 1 / 4. In practical applications, the number of levels of the Gaussian pyramid model is determined according to actual needs.

[0054] The first review image and the first warehouse-entry image are subjected to Gaussian downsampling processing respectively to obtain a first Gaussian image and a second Gaussian image, and then the first Gaussian image and the second Gaussian image are used to perform matching calculation to obtain second position information of the first commodity when it leaves the warehouse.

[0055] Further, when the second position information is obtained by matching the first Gaussian image and the second Gaussian image, it can be referred to Figure 4 , Figure 4 This is another flowchart diagram of the step of obtaining the second location information provided in an embodiment of the present application, wherein the step includes step 401 to step 404.

[0056] Step 401, obtaining an N-th level Gaussian image from the second Gaussian image, and performing rotation processing on the N-th level Gaussian image to obtain a processed N-th level Gaussian image, wherein the second Gaussian image contains the N-th level Gaussian image;

[0057] Step 402, processing and matching the processed Nth-level Gaussian image with the nth-level Gaussian image in the first Gaussian image to obtain the Nth-level position of the first product;

[0058] Step 403, determining a designated area in the N-1th level Gaussian image in the second Gaussian image according to the Nth level position, and performing matching calculation on the designated area and the second Gaussian image to obtain the N-1th level position of the second product, and performing matching calculation on the intermediate level Gaussian image in the second Gaussian image according to the N-1th level position to obtain the second level position of the first product, wherein the intermediate level Gaussian image is the second to N-1th level Gaussian images;

[0059] Step 404 , performing a matching calculation based on the first-level Gaussian image of the second-level position in the second Gaussian image to obtain second position information of the first product.

[0060] Exemplarily, when constructing a multi-level pyramid model of the first review image and the first warehousing image, the number of levels is set to N. Then, when obtaining a multi-level Gaussian image, it includes a 1st-level Gaussian image, a 2nd-level Gaussian image, ... an N-1th-level Gaussian image, and an Nth-level Gaussian image. When performing calculation and matching processing to obtain the second position information, processing is performed from high to bottom based on the levels, and after completing the processing of the 1st level, the second position information of the first product is obtained.

[0061] In actual processing, the number of levels of the multi-level Gaussian pyramid model corresponding to the first review image and the first storage image is the same, where N and n are only used to distinguish whether the Gaussian image belongs to the first review image or the first storage image. The Nth level Gaussian image is obtained in the second Gaussian image, and then the Nth level Gaussian image is rotated to obtain the processed Nth level Gaussian image, and then the processed Gaussian image is matched with the nth level Gaussian image in the first Gaussian image to obtain the Nth level position of the first commodity when leaving the warehouse, that is, the position of the first commodity in the N / nth level Gaussian image is obtained.

[0062] Due to the characteristics of Gaussian images, after obtaining the Nth level position, matching calculations are performed based on the Gaussian images of the next level based on the hierarchical relationship. Before performing the matching calculations, a specified area is first determined in the Gaussian image of the next level of the second Gaussian image (the N-1th level Gaussian image), that is, the area where the matching calculation is performed to determine the position, so as to perform matching calculation processing again to obtain the N-1th level position of the first product, and then process them in sequence to obtain the 1st level position of the first product, that is, the second position information of the first product when it is shipped out.

[0063] For example, when N is 3, when the second position information of the first commodity is obtained, wherein the position information includes the position and angle, the processing at this time includes: rotating the image information of the third-level Gaussian pyramid model of all commodities corresponding to the barcode of the outbound list by 15°, respectively, and performing matching calculations with the third-level Gaussian pyramid model of the first image information, and recording the position and angle of the first commodity in the third level; then, according to the matching result of the third level, performing matching calculations in the designated position ±25% area and angle ±10 degrees in the second-level Gaussian pyramid model corresponding to the second image information, and recording the approximate position and angle of the model of this level of the commodity in the outbound image information of the commodity; finally, according to the matching result of the second level, performing matching calculations in the designated position ±10% area and angle ±5 degrees in the first-level Gaussian pyramid model, and recording the position and angle of the model of this level of the commodity in the outbound image information of the commodity, that is, obtaining the second position information of the first commodity when it is outbound. Wherein, when rotating, the center point of the image is used as the rotation center, and the positive and negative angles represent clockwise rotation and counterclockwise rotation respectively.

[0064] Step 104, review the first commodity according to the first location information and the second location information, and when the first review result of the first commodity is obtained, process the second review image captured by the image acquisition device to obtain an outbound review result in response to the outbound review instruction of the commodity.

[0065] In one embodiment, after obtaining the second position information of the first product when it is shipped out through matching calculation, the first product will be reviewed based on the first position information and the second position information to obtain a review result of the first product, wherein the review result includes a successful review and a failed review. Then, the products in all the collected image information are reviewed in a loop until the review of the last reviewed image is completed, and then an outbound review result in response to the outbound review instruction of the product is obtained.

[0066] For example, when performing a review based on the first location information and the second location information, it is necessary to determine whether the first product exists and whether the two location information are accurate. When determining whether the location is accurate, the two locations are compared and calculated, such as by calculating the overlap rate of the first location information and the second location information. When executing a product outbound review instruction, in addition to locating and judging the location of the product, it is also necessary to count and record the number of products shipped out to determine whether the number of shipped products is correct. Therefore, when executing a product outbound review instruction and obtaining a review result, you can refer to Figure 5 , Figure 5 It is a flow chart of the steps of obtaining the review results in response to the commodity delivery review instruction provided in an embodiment of the present application, wherein the steps include steps 501 to 503.

[0067] Step 501, calculating the position overlap rate of the first position information and the second position information, and performing a review process on the first commodity according to the position overlap rate, until executing the commodity outbound review instruction, and obtaining a total review result of the commodities included in the outbound list barcode;

[0068] Step 502, counting the commodities whose position overlap rate is greater than a preset threshold, and obtaining the total number of commodities to be reviewed when executing the commodity delivery review instruction;

[0069] Step 503, obtaining a shipment review result in response to the shipment review instruction of the goods according to the total composite result, the total number of reviewed goods and the total number of shipped goods.

[0070] Specifically, when performing the review process, the position overlap rate of the first position information and the second position information is calculated, and the first product is reviewed according to the obtained position overlap rate until the product outbound review instruction is executed, and the total review result of the products included in the outbound list barcode is obtained. At the same time, when performing the review process, each product that is successfully reviewed will be counted once, that is, the products with a position overlap rate greater than a preset threshold will be counted to obtain the total number of reviewed products when the product outbound review instruction is executed. Finally, based on the obtained total review result, the total number of reviewed products and the total number of outbound products, the review result in response to the product outbound review instruction is obtained.

[0071] In practical applications, the preset threshold of the position overlap rate can be set to 90%, that is, when the obtained position overlap rate is greater than 90%, it is determined that the first position information and the second position information overlap, that is, it is determined that the first product exists, and counting is performed. For products with a position overlap rate of no more than 90%, since the product exists at this time, it is determined that an abnormal object exists at this time, and the product is not counted.

[0072] When the review result of the response product outbound review instruction is obtained, the review is determined to be passed only when the positions of all products are correct and the total number of reviewed products is consistent with the total number of outbound products. Otherwise, the review is determined to be unsuccessful and feedback is then processed. At the same time, for abnormal products, the location information of the abnormal products can be recorded and fed back to facilitate quick and accurate manual inspection of the abnormal products.

[0073] Furthermore, when the goods are reviewed based on the above-mentioned embodiments, the goods are photographed in advance to collect image information of the surface of the goods. Then, the collected image information of the goods is compared with the real-time image during the warehouse review, the position and quantity of the goods are located and found, and it is calculated whether the actual goods and the goods outbound list match to complete the review operation.

[0074] Before the product is reviewed for delivery, the product modeling can be processed when the product is received. The industrial camera is fixed vertically above the product modeling shooting area through a bracket, and the center of the camera lens is kept vertical to the center of the shooting area, and the camera field of view and the shooting area are kept overlapping. A single product is placed in the center of the shooting area, and the camera is soft-triggered to take a photo. After the camera takes the photo, it identifies the photo clarity (the clarity standard is 100 for clear photos taken at the same distance, and the subsequent photos are considered blurry if the value is less than 90), brightness (the brightness value is 100 for photos with uniform brightness taken at the same distance, and the subsequent photos are considered too dark if the value is less than 85), product placement (the straight-line distance between the center point of the product and the center point of the shooting area is less than 25mm), placement angle (horizontal or vertical placement, i.e. 0°, 90°, 180°, 270°, and ±5°), etc. to see if they meet the requirements. If any one does not meet the requirements, the user is prompted to make adjustments, and the photo is triggered again after the adjustment. If the requirements are met, the photo will be stored, and the product position identified from the photo will be cropped along the outline to be stored as a new image file. After the storage is completed, the user will be prompted to flip the product and collect images of other surfaces. After all surfaces are collected, the image is submitted to the server for storage.

[0075] Specifically, when processing the product model, the established product model will contain the basic information of the product and the surface image information of the product. Among them, the tool used to establish the product model is opencv, which is mainly used for image processing after taking photos, feature detection and matching of product photos, product image recognition and other links.

[0076] Exemplarily, when performing product modeling, at least one surface image information of the product is extracted. If multiple surface image information is included, the multiple image information will be analyzed to determine whether they are valid.

[0077] The following situations will be considered as invalid information:

[0078] 1. The image information of this face is exactly the same as that of other faces;

[0079] 2. The image area of ​​this surface is small and contains little effective image information;

[0080] 3. The surface image information has an inclusion relationship with other surface image information;

[0081] 4. The image information of this surface is extremely similar to that of other surfaces.

[0082] In addition, all product models will be extracted for analysis to ensure that the image information contained in different product models cannot be repeated or highly similar to avoid false detection. Specifically, all valid product models are extracted, and the image information contained in different product models is compared one by one. Any two image information cannot be repeated or highly similar. If there is duplication or high similarity, both image information will be set to a questionable state at the same time. The questionable state requires manual judgment to determine which image information is valid or both image information are set to invalid. If all the image information under the product model is in a questionable state, the model is invalid. The server-side modeling time and resource consumption are high, so a scheduled task is generally used during idle time.

[0083] In order to realize the automatic review process of goods outbound, the corresponding model can be pre-set and deployed to the client, and then the client can respond directly when outbound review process is required.

[0084] After completing the warehousing of goods and the deployment of the client, when conducting the outbound review of goods, first fix the industrial camera vertically above the outbound review area, and keep the camera field of view and the outbound review area overlapped. The outbound goods can be moved to the outbound review area in the set way. The position and angle of the goods can be arbitrary, but cannot exceed the scope of the review area, and the goods cannot cover each other (covered goods cannot be detected), and can be slightly staggered (the staggered area should be less than 10%, otherwise it cannot be successfully identified).

[0085] Then, after scanning the barcode of the product outbound list, the camera is triggered to take photos and identify, and the product outbound list is obtained according to the barcode and matched with the product model information in the model library. If the model library contains the model information of all products, the automatic identification process is carried out, otherwise it is prompted to be manually reviewed. The specific identification process includes: object contour recognition of the outbound review area photo, marking the object position according to the closed contour, and marking the existence of objects in the area; extracting the model information of the products contained in this list. The image information of each product is extracted and matched with the outbound review area photo, and the matching position and number are recorded; the above object position and product position are fitted. If there is an object in the area, but there is no matching corresponding product in the area, the area is marked as having unrecognized objects. Finally, when the result is output, the identified products are counted and the unrecognized objects are counted. If the number of products does not match or there are unrecognized objects, it is considered that the detection fails, otherwise it is considered that the detection passes and the detection result is output.

[0086] Specifically, when performing recognition processing, a three-level Gaussian pyramid model is constructed for the image information in each pre-stored inventory product model and the image information collected during the review, and the image information of the corresponding level is generated (each level of image is 1 / 4 of the image of the upper level).

[0087] Then, the approximate position and angle of the product in the outbound image information are calculated, and the calculation of the matching is carried out including: rotating the image information of the third-level Gaussian pyramid model in the image of each incoming product by 15° each time and performing matching calculations with the third-level Gaussian pyramid model of the collected image information, recording the approximate position and angle of the product model in the outbound image information of the product, and then performing matching calculations in the second-level Gaussian pyramid model in the image of the incoming product at a specified position ±25% area and an angle of ±10 degrees according to the third-level matching results, recording the approximate position and angle of the model at this level in the outbound image information of the product, and finally, performing matching calculations in the first-level Gaussian pyramid model in the image of the incoming product at a specified position ±10% area and an angle of ±5 degrees according to the second-level matching results, and recording the position and angle of the model at this level in the outbound image information of the product.

[0088] At the same time, the object contour is recognized on the captured commodity images to identify the object position, and the identified object position can be referenced Figure 2 , and the positions of the products obtained in the previous steps are compared one by one to calculate the coincidence rate between the object contour position and the position of the product in the outbound image.

[0089] Among them, before judging based on the position overlap rate, first determine whether the outline is complete. Only for products with complete outlines will they be reviewed, while for products with incomplete outlines, they will not be reviewed at present. Then, when reviewing based on the position overlap rate, if the position overlap rate is greater than 90%, it is considered to be position overlap, that is, the object is a known product; if the position overlap rate is not greater than 90%, it is considered to be position non-overlap, and the review is determined to have failed. Since the review process is streamlined, even if the product fails the review at present, it may succeed in the review in the subsequent process. Therefore, the product will not be directly judged as failed in the review at present, but will be judged later when the product outbound review instruction is executed, that is, the review results of all products will be obtained after the analysis and processing of the last image is completed.

[0090] However, when performing a review based on the captured images, if the current review fails, it is necessary to locate the product that failed the current review, that is, obtain the location information and record it. If the review is successful in the subsequent process, the recorded location information can be deleted.

[0091] In addition, during the review process, counting and statistical processing will be performed to count the goods that have passed the review during the entire review process to obtain the number of successful reviews. If the number of successful reviews is consistent with the goods outbound list and there are no unknown objects, it will be considered to have passed the review and the next step can be performed. Otherwise, it will be considered to have failed and manual intervention is required. At the same time, the cause of the abnormality is recorded, such as the specific location of the unknown object if there is an unknown object.

[0092] In summary, the present application discloses a method for checking the goods out of the warehouse. When the goods need to be checked out of the warehouse, the method responds to the goods out of the warehouse check instruction to obtain the first check image collected by the image acquisition device, and performs commodity recognition processing on the first check image to obtain the first position information of the first commodity when it is out of the warehouse. At the same time, the barcode of the incoming outbound list is received, and the commodity information of all commodities that need to be out of the warehouse, including the first inbound image and the total number of outbound commodities, is obtained by scanning and processing the barcode of the outbound list. Then, the obtained first check image and the first inbound image are processed to obtain the second position information of the first commodity when it is out of the warehouse. Then, the first commodity is checked according to the first position information and the second position information, and all commodities obtained in response to the goods outbound check instruction are checked in the way of checking the first commodity to obtain the corresponding check result. In the process of goods out of the warehouse, the goods are checked by analyzing, processing and comparing the images without manual intervention, which shortens the time of the entire outbound process, saves costs and resources, and improves the efficiency and accuracy of the goods outbound check.

[0093] According to the method described in the above embodiment, this embodiment will be further described from the perspective of the control device of the sliding frame of the bridge building machine. The control device of the sliding frame of the bridge building machine can be implemented as an independent entity, or it can be integrated in an electronic device, such as a terminal. The terminal may include a mobile phone, a tablet computer, etc.

[0094] See also Figure 6 , Figure 6 is a structural schematic diagram of a control device for a sliding frame of a bridge-building machine provided in an embodiment of the present application, such as Figure 6 As shown, the commodity delivery review device 600 provided in the embodiment of the present application includes:

[0095] The image acquisition module 601 is used to respond to the commodity outbound review instruction, obtain the first review image acquired by the image acquisition device, and perform commodity recognition on the first review image to obtain the first position information of the first commodity when it is outbound, wherein the first review image corresponds to the first commodity;

[0096] The barcode scanning and recognition module 602 is used to receive the input outbound list barcode and scan the outbound list barcode to obtain the commodity information contained in the outbound list barcode, wherein the commodity information includes the first inbound image of each commodity and the total number of outbound commodities;

[0097] The position determination module 603 is used to process the first review image and the first warehouse entry image to obtain the second position information of the first commodity when it leaves the warehouse;

[0098] The review judgment module 604 is used to review the first commodity according to the first position information and the second position information, and when the first review result of the first commodity is obtained, the second review image collected by the image acquisition device is processed to obtain the outbound review result in response to the outbound review instruction of the commodity.

[0099] In one embodiment, the code scanning and recognition module 602 is further used for:

[0100] Identify the barcode of the outbound list to obtain the product list corresponding to the barcode of the outbound list, and count the product list to obtain the total number of outbound products in the product list;

[0101] The commodity identification of each commodity included in the commodity list is identified, and a query is performed according to the commodity identification to obtain a first storage-entry image corresponding to the commodity identification.

[0102] In one embodiment, the location determination module 603 is further configured to:

[0103] Performing Gaussian downsampling processing on the first review image to obtain a first Gaussian image, and performing Gaussian downsampling processing on the first stored image to obtain a second Gaussian image;

[0104] A matching calculation is performed based on the first Gaussian image and the second Gaussian image to obtain second position information of the first commodity when it is shipped out of the warehouse.

[0105] In one embodiment, the location determination module 603 is further configured to:

[0106] Obtaining an N-th level Gaussian image from the second Gaussian image, and performing rotation processing on the N-th level Gaussian image to obtain a processed N-th level Gaussian image, wherein the second Gaussian image contains the N-th level Gaussian image;

[0107] The processed Nth-level Gaussian image is processed and matched with the nth-level Gaussian image in the first Gaussian image to obtain the Nth-level position of the first product;

[0108] Determine a designated area in the N-1th level Gaussian image in the second Gaussian image according to the Nth level position, and perform matching calculation on the designated area and the second Gaussian image to obtain the N-1th level position of the second product, and perform matching calculation based on the intermediate level Gaussian image in the second Gaussian image according to the N-1th level position to obtain the second level position of the first product, wherein the intermediate level Gaussian image is the second to N-1th level Gaussian images;

[0109] A matching calculation is performed based on the first-level Gaussian image of the second-level position in the second Gaussian image to obtain second position information of the first product.

[0110] In one embodiment, the review and determination module 604 is further configured to:

[0111] Calculate the position overlap rate of the first position information and the second position information, and perform a review process on the first commodity according to the position overlap rate, until the commodity compound instruction is executed to obtain a total review result of the commodities included in the barcode of the outbound list;

[0112] Count the commodities whose position overlap rate is greater than a preset threshold value, and obtain the total number of commodities to be reviewed when executing the commodity outbound review instruction;

[0113] According to the total compound result, the total number of reviewed goods and the total number of shipped goods, the shipping review result of the response goods compound instruction is obtained.

[0114] In one embodiment, the commodity delivery review device further includes a database judgment module for:

[0115] Matching the product information in a preset image library to determine whether the preset image library contains an image corresponding to the product information;

[0116] If it is determined that the image corresponding to the product information is included, the steps are executed: processing is performed according to the first review image and the first warehouse-entry image to obtain the second position information of the first product when it is shipped out of the warehouse;

[0117] If it is determined that the image corresponding to the product information is not included, a prompt message indicating that the product information has not been entered is issued.

[0118] In one embodiment, the image acquisition module 601 is further used for:

[0119] Performing grayscale and Gaussian processing on the first review image to obtain a processed first review image;

[0120] The texture features of the processed first verification image are recognized to obtain the contour features contained in the first verification image, and the first position information of the first commodity when it leaves the warehouse is obtained according to the contour features.

[0121] Also, see Figure 7 , Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, and the electronic device may be a mobile terminal such as a smart phone, a tablet computer, or the like. Figure 7 As shown, the electronic device 700 includes a processor 701 and a memory 702. The processor 701 is electrically connected to the memory 702.

[0122] The processor 701 is the control center of the electronic device 700. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device 700 and processes data by running or loading applications stored in the memory 702 and calling data stored in the memory 702, thereby monitoring the electronic device 700 as a whole.

[0123] In this embodiment, the processor 701 in the electronic device 700 will load the instructions corresponding to the processes of one or more applications into the memory 702 according to the following steps, and the processor 701 will run the application stored in the memory 702, thereby implementing any step in the commodity outbound review method provided in the above embodiment.

[0124] The electronic device 700 can implement the steps in any embodiment of the commodity shipment review method provided in the embodiments of the present application. Therefore, it can achieve the beneficial effects that can be achieved by any commodity shipment review method provided in the embodiments of the present application. Please refer to the previous embodiments for details and will not be repeated here.

[0125] See also Figure 8 , Figure 8 is another structural schematic diagram of an electronic device provided in an embodiment of the present application, such as Figure 8 As shown, Figure 8The specific structural block diagram of the electronic device provided in the embodiment of the present application is shown, and the electronic device can be used to implement the commodity delivery review method provided in the above embodiment. The electronic device 800 can be a mobile terminal such as a smart phone or a laptop computer.

[0126] The RF circuit 810 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, and thus communicate with a communication network or other devices. The RF circuit 810 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, user identity module (SIM) cards, memories, etc. The RF circuit 810 can communicate with various networks such as the Internet, corporate intranets, wireless networks, or communicate with other devices through wireless networks. The above-mentioned wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks. The above-mentioned wireless networks can use various communication standards, protocols and technologies, including but not limited to Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Wireless Fidelity (Wi-Fi) (such as Institute of Electrical and Electronics Engineers standards IEEE 802.11a, IEEE 802.11b, IEEE802.11g and / or IEEE802.11n), Voice over Internet Protocol (VoIP), Worldwide Interoperability for Microwave Access (Wi-Max), other protocols for email, instant messaging and short messages, and any other suitable communication protocols, even those that have not yet been developed.

[0127] The memory 820 can be used to store software programs and modules, such as the program instructions / modules corresponding to the commodity shipment review method in the above-mentioned embodiment. The processor 880 executes various functional applications and the commodity shipment review method by running the software programs and modules stored in the memory 820.

[0128] The memory 820 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 820 may further include a memory remotely arranged relative to the processor 880, and these remote memories may be connected to the electronic device 800 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0129] The input unit 830 can be used to receive uploaded digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Specifically, the input unit 830 may include a touch-sensitive surface 831 and other input devices 832. The touch-sensitive surface 831, also known as a touch display screen or touchpad, can collect user touch operations on or near it (such as operations performed by users using fingers, styluses, or any other suitable objects or accessories on or near the touch-sensitive surface 831), and drive corresponding connection devices according to a pre-set program. Optionally, the touch-sensitive surface 831 may include a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 880, and can receive and execute commands sent by the processor 880. In addition, the touch-sensitive surface 831 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 831, the input unit 830 may further include other input devices 832. Specifically, the other input devices 832 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0130] The display unit 840 can be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device 800, which can be composed of graphics, text, icons, videos and any combination thereof. The display unit 840 may include a display panel 841, and optionally, the display panel 841 may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, the touch-sensitive surface 831 may cover the display panel 841, and when the touch-sensitive surface 831 detects a touch operation on or near it, it is transmitted to the processor 880 to determine the type of the touch event, and then the processor 880 provides corresponding visual output on the display panel 841 according to the type of the touch event. Although in the figure, the touch-sensitive surface 831 and the display panel 841 are implemented as two independent components to implement input and output functions, in some embodiments, the touch-sensitive surface 831 can be integrated with the display panel 841 to implement input and output functions.

[0131] The electronic device 800 may also include at least one sensor 850, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 841 according to the brightness of the ambient light, and the proximity sensor may generate an interrupt when the flip cover is closed or closed. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that can also be configured in the electronic device 800, they will not be repeated here.

[0132] The audio circuit 860, the speaker 861, and the microphone 862 can provide an audio interface between the user and the electronic device 800. The audio circuit 860 can transmit the electrical signal converted from the received audio data to the speaker 861, which is converted into a sound signal for output; on the other hand, the microphone 862 converts the collected sound signal into an electrical signal, which is received by the audio circuit 860 and converted into audio data, and then the audio data is output to the processor 880 for processing, and then sent to another terminal through the RF circuit 810, or the audio data is output to the memory 820 for further processing. The audio circuit 860 may also include an earplug jack to provide communication between an external headset and the electronic device 800.

[0133] The electronic device 800 can help the user receive requests, send information, etc. through the transmission module 870 (such as a Wi-Fi module), which provides the user with wireless broadband Internet access. Although the transmission module 870 is shown in the figure, it is understandable that it is not a necessary component of the electronic device 800 and can be omitted as needed without changing the essence of the invention.

[0134] The processor 880 is the control center of the electronic device 800. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 820, and calling data stored in the memory 820, it executes various functions of the electronic device 800 and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 880 may include one or more processing cores; in some embodiments, the processor 880 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 880.

[0135] The electronic device 800 also includes a power supply 890 (such as a battery) for supplying power to various components. In some embodiments, the power supply can be logically connected to the processor 880 through a power management system, so that the power management system can manage charging, discharging, and power consumption management. The power supply 890 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0136] Although not shown, the electronic device 800 also includes a camera (such as a front camera, a rear camera), a Bluetooth module, etc., which will not be described in detail here. Specifically in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal also includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and are configured to be executed by one or more processors to implement any step in the commodity outbound review method provided in the above embodiment.

[0137] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation of the above modules can be found in the previous method embodiments, which will not be repeated here.

[0138] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions, and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present application provides a storage medium, which stores multiple instructions, and when the instructions are executed by the processor, any step in the commodity outbound review method provided in the above embodiments can be implemented.

[0139] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0140] Since the instructions stored in the storage medium can execute the steps in any embodiment of the commodity shipment review method provided in the embodiments of the present application, the beneficial effects that can be achieved by any commodity shipment review method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0141] The above is a detailed introduction to a method, device, electronic device and storage medium for checking the goods out of the warehouse provided by the embodiment of the present application. The principles and implementation methods of the present application are described in detail using specific examples herein. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application. Moreover, for those of ordinary skill in the art, without departing from the principles of the present application, several improvements and modifications can be made, and these improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A method for checking the goods leaving the warehouse, characterized in that: include: In response to a product outbound review instruction, a first review image acquired by an image acquisition device is acquired, and product recognition is performed on the first review image to obtain first position information of the first product when the product is outbound, wherein the first review image corresponds to the first product; Receive an input outbound list barcode, and scan the outbound list barcode to obtain commodity information contained in the outbound list barcode, wherein the commodity information includes a first incoming image of each commodity and a total number of outbound commodities; Processing the first review image and the first warehouse-entry image to obtain second location information of the first commodity when it leaves the warehouse; The first commodity is reviewed based on the first location information and the second location information, and when a first review result of the first commodity is obtained, the second review image captured by the image acquisition device is processed to obtain an outbound review result in response to the outbound review instruction of the commodity.

2. The method according to claim 1, characterized in that The scanning of the barcode of the outbound delivery list to obtain the commodity information contained in the barcode of the outbound delivery list includes: Identify the barcode of the outbound list to obtain a list of commodities corresponding to the barcode of the outbound list, and count the commodity list to obtain the total number of outbound commodities in the commodity list; The commodity identification of each commodity included in the commodity list is identified, and a query is performed according to the commodity identification to obtain a first storage image corresponding to the commodity identification.

3. The method according to claim 1, characterized in that The processing according to the first review image and the first warehouse entry image to obtain the second location information of the first commodity when it leaves the warehouse includes: Performing Gaussian downsampling processing on the first review image to obtain a first Gaussian image, and performing Gaussian downsampling processing on the first stored image to obtain a second Gaussian image; A matching calculation is performed based on the first Gaussian image and the second Gaussian image to obtain second position information of the first commodity when it is shipped out of the warehouse.

4. The method according to claim 3, characterized in that The performing matching calculation according to the first Gaussian image and the second Gaussian image to obtain the second location information of the first commodity when it is shipped out of the warehouse includes: Obtaining an N-th level Gaussian image from the second Gaussian image, and performing rotation processing on the N-th level Gaussian image to obtain a processed N-th level Gaussian image, wherein the second Gaussian image contains the N-th level Gaussian image; Processing and matching the processed Nth-level Gaussian image with the nth-level Gaussian image in the first Gaussian image to obtain the Nth-level position of the first product; Determine a designated area in the N-1th level Gaussian image in the second Gaussian image according to the Nth level position, and perform matching calculation on the designated area and the second Gaussian image to obtain the N-1th level position of the second product, and perform matching calculation based on the intermediate level Gaussian image in the second Gaussian image according to the N-1th level position to obtain the second level position of the first product, wherein the intermediate level Gaussian image is the second to N-1th level Gaussian images; A matching calculation is performed based on the first-level Gaussian image of the second-level position in the second Gaussian image to obtain the second position information of the first product.

5. The method according to claim 1, characterized in that The step of reviewing the first commodity according to the first location information and the second location information until the commodity delivery review instruction is executed and a review result is obtained includes: Calculate the position overlap rate of the first position information and the second position information, and perform a review process on the first commodity according to the position overlap rate, until the commodity outbound review instruction is executed to obtain a total review result of the commodities included in the outbound list barcode; Counting the commodities whose position overlap rate is greater than a preset threshold value, and obtaining the total number of commodities to be reviewed when executing the commodity delivery review instruction; According to the total composite result, the total number of reviewed commodities and the total number of shipped commodities, a shipment review result in response to the commodity shipment review instruction is obtained.

6. The method according to claim 1, characterized in that The method further comprises: Matching the product information in a preset image library to determine whether the preset image library contains an image corresponding to the product information; If it is determined that the image corresponding to the product information is included, the steps are executed: processing is performed according to the first review image and the first warehouse entry image to obtain the second position information of the first product when it is shipped out of the warehouse; If it is determined that the image corresponding to the product information is not included, a prompt message indicating that the product information has not been entered is issued.

7. The method according to claim 1, characterized in that The step of performing commodity identification on the first review image to obtain first location information of the first commodity when it is shipped out of the warehouse includes: Performing grayscale and Gaussian processing on the first review image to obtain a processed first review image; The texture features of the processed first review image are identified to obtain contour features contained in the first review image, and the first position information of the first commodity when it leaves the warehouse is obtained according to the contour features.

8. A commodity outbound review device, characterized in that: include: An image acquisition module is used to respond to a product delivery review instruction, obtain a first review image acquired by an image acquisition device, and perform product recognition on the first review image to obtain first position information of the first product when the product is delivered, wherein the first review image corresponds to the first product; A code scanning and recognition module, used to receive an input outbound list barcode, and scan the outbound list barcode to obtain the commodity information contained in the outbound list barcode, wherein the commodity information includes a first incoming image of each commodity and the total number of outbound commodities; a position determination module, configured to process the first review image and the first warehouse entry image to obtain second position information of the first commodity when it leaves the warehouse; The review judgment module is used to review the first commodity according to the first location information and the second location information, and when obtaining the first review result of the first commodity, process the second review image collected by the image acquisition device to obtain an outbound review result in response to the outbound review instruction of the commodity.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the steps in the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images