A method and system for automatically generating storage address for stacker based on artificial intelligence

Through the automatic generation method and system of stacker storage registration registration based on artificial intelligence, the storage registration information of goods is dynamically checked and verified, which solves the problem of high storage registration error rate in the existing technology and improves the storage registration Accuracy and quality of the address.

CN118458207BActive Publication Date: 2024-11-29AEROSPACE JICHUANG IOT RES INST (NANJING) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410928903.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-11
Publication Date
2024-11-29
Estimated Expiration
2044-07-11

AI Technical Summary

Technical Problem

In the prior art, the error rate of goods entering the warehouse is high, and it is impossible to find errors in the warehouse in time, resulting in poor registration of goods entering the warehouse.

Method used

Using the automatic generation method and system of stacker entry and registration address based on artificial intelligence, it is detected by obtaining the storage entry form, matching the storage registration data, analyzing the images collected by the image acquisition equipment, retrieving the stacker path and patrol robots. warehousing information, dynamically check and verify, and correct the warehouse registration information.

Benefits of technology

Effectively reduce the error rate of goods entering and registering, improve the timeliness and accuracy of goods entering and registering errors, and improve the quality of goods entering and registering.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118458207B_ABST
    Figure CN118458207B_ABST
Patent Text Reader

Abstract

The present invention discloses an automatic generation method and system for stacker entry addressing based on artificial intelligence, which relates to the field of image processing, wherein the method comprises: matching the first entry registration data group of the first category of goods in M ​​categories of goods; analyzing the first entry image collected by the image acquisition device at the first entry time to obtain the first entry identification information; retrieving the first entry path of the stacker at the first entry time; obtaining the first storage information detected by the inspection robot at the first destination position; proofreading and analyzing the first entry registration data group, the first entry identification information and the first storage information to obtain the first proofreading result; correcting the first entry addressing information according to the first proofreading result to obtain the first entry addressing correction result. The method solves the technical problems in the prior art that the error rate of goods entry addressing is high, the goods entry addressing errors cannot be discovered in time, and the goods entry addressing effect is poor.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an artificial intelligence-based automatic generation method and system for stacker entry addressing. Background Art

[0002] The addressing of goods entering the warehouse is of great significance to warehouse management. Through reliable addressing of goods entering the warehouse, real-time tracking of goods can be achieved, ensuring the accurate location and quantity of goods in the warehouse, which helps to optimize inventory layout and improve inventory accuracy. In addition, through addressing of goods entering the warehouse, the specified number of goods can be quickly located and taken out, ensuring the accuracy and efficiency of outbound operations, which helps to improve the operational efficiency and quality of warehouses and reduce the waste of manpower and material resources.

[0003] In the prior art, there is a technical problem that the error rate of goods entry addressing is high and the errors of goods entry addressing cannot be discovered in time, resulting in poor goods entry addressing effect. Summary of the invention

[0004] The present application provides a method and system for automatically generating warehouse addressing for stackers based on artificial intelligence. The method solves the technical problems in the prior art that the error rate of warehouse addressing for goods is high, errors in warehouse addressing for goods cannot be discovered in time, and the effect of warehouse addressing for goods is poor. By dynamically checking and verifying the warehouse addressing for goods, the error rate of warehouse addressing for goods is effectively reduced, the timeliness and accuracy of detecting errors in warehouse addressing for goods are improved, and the quality of warehouse addressing for goods is improved.

[0005] In view of the above problems, the present application provides a method and system for automatically generating stacker entry address based on artificial intelligence.

[0006] In a first aspect, the present application provides an artificial intelligence-based automatic generation method for stacker crane entry addressing, wherein the method is applied to an artificial intelligence-based automatic generation system for stacker crane entry addressing, the system is communicatively connected to an image acquisition device, a stacker crane and an inspection robot, the method comprising: obtaining an entry form, the entry form is received from a client of a target warehouse, the entry form comprises M groups of entry registration data for M categories of goods, M being an integer greater than or equal to 1; matching a first entry registration data group of a first category of goods in the M categories of goods in the M groups of entry registration data, the first entry registration data group comprising a first entry time, a first pre-entry number and a first entry quantity of the first category of goods; analyzing the first entry image captured by the image acquisition device at the first entry time to obtain The first warehousing identification information includes the first warehousing identification product, the first warehousing identification quantity and the first warehousing identification number; the first warehousing path of the stacker at the first warehousing time is retrieved, and the first warehousing path includes the first destination location; the first storage information detected by the inspection robot at the first destination location is obtained, and the first storage information includes the first storage product type, the first storage product quantity and the first storage product number; the first warehousing registration data group, the first warehousing identification information and the first warehousing information are proofread and analyzed to obtain a first proofreading result; the first warehousing addressing information is corrected according to the first proofreading result to obtain a first warehousing addressing correction result, and the first warehousing addressing information refers to the warehousing addressing information of the first category of products.

[0007] In a second aspect, the present application further provides an automatic generation system for stacker entry addressing based on artificial intelligence, wherein the system is communicatively connected with an image acquisition device, a stacker and an inspection robot, and the system comprises: an entry order acquisition module, the entry order acquisition module is used to acquire an entry order, the entry order is received from a client of a target warehouse, the entry order comprises M groups of entry registration data of M categories of goods, M is an integer greater than or equal to 1; a data matching module, the data matching module is used to match a first entry registration data group of a first category of goods in the M categories of goods in the M groups of entry registration data, the first entry registration data group comprises a first entry time, a first pre-entry number and a first entry quantity of the first category of goods; an image analysis module, the image analysis module is used to analyze the first entry image acquired by the image acquisition device at the first entry time to obtain first entry identification information, the first entry identification information comprises a first entry identification goods a storage path retrieval module, the storage path retrieval module is used to retrieve the first storage path of the stacker at the first storage time, the first storage path includes a first destination location; a storage information acquisition module, the storage information acquisition module is used to acquire the first storage information detected by the inspection robot at the first destination location, the first storage information includes the first storage product type, the first storage product quantity and the first storage product number; a proofreading and analysis module, the proofreading and analysis module is used to proofread and analyze the first storage registration data group, the first storage identification information and the first storage information to obtain a first proofreading result; an storage address correction module, the storage address correction module is used to correct the first storage address information according to the first proofreading result to obtain a first storage address correction result, the first storage address information refers to the storage address information of the first category of goods.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The first entry time, the first pre-entry number and the first entry quantity of the first category of goods in the M categories of goods are matched through the M groups of entry registration data in the entry order; the first entry image acquired by the image acquisition device at the first entry time is analyzed to obtain the first entry identification goods, the first entry identification quantity and the first entry identification number; the first destination position of the stacker at the first entry time is retrieved; the first storage goods type, the first storage goods quantity and the first storage goods number detected by the inspection robot at the first destination position are obtained; the first proofreading result is obtained by proofreading and analyzing the first entry registration data group (the first entry time, the first pre-entry number and the first entry quantity), the first entry identification information (the first entry identification goods, the first entry identification quantity and the first entry identification number) and the first storage information (the first storage goods type, the first storage goods quantity and the first storage goods number); the first entry addressing information is corrected according to the first proofreading result to obtain the first entry addressing correction result. By dynamically checking and verifying the goods' entry addressing, the error rate of goods' entry addressing can be effectively reduced, the timeliness and accuracy of detecting errors in goods' entry addressing can be improved, and the quality of goods' entry addressing can be improved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings of the embodiments of the present invention. Obviously, the drawings in the following description only relate to some embodiments of the present invention, but are not intended to limit the present invention.

[0012] Figure 1 A schematic diagram of a process for automatically generating a stacker entry address based on artificial intelligence for this application;

[0013] Figure 2 A schematic diagram of a process for obtaining a first proofreading result in an automatic generation method for stacker entry addressing based on artificial intelligence in the present application;

[0014] Figure 3 This application discloses a structural schematic diagram of an automatic generation system for stacker entry addressing based on artificial intelligence. DETAILED DESCRIPTION

[0015] The present application provides an artificial intelligence-based automatic generation method and system for stacker warehouse addressing. It solves the technical problems in the prior art that the error rate of goods warehouse addressing is high, the goods warehouse addressing errors cannot be discovered in time, and the goods warehouse addressing effect is poor. By dynamically checking and verifying the goods warehouse addressing, the error rate of goods warehouse addressing is effectively reduced, the timeliness and accuracy of detecting goods warehouse addressing errors are improved, and the quality of goods warehouse addressing is improved.

[0016] Embodiment 1

[0017] Please see attached Figure 1 The present application provides an artificial intelligence-based stacker entry address automatic generation method, wherein the method is applied to an artificial intelligence-based stacker entry address automatic generation system, the system is connected to an image acquisition device, a stacker and an inspection robot, and the method specifically comprises the following steps:

[0018] Obtaining a warehouse entry form, the warehouse entry form being received from a client of a target warehouse, the warehouse entry form including M groups of warehouse entry registration data of M categories of goods, where M is an integer greater than or equal to 1;

[0019] Matching a first warehouse registration data group of a first category of goods in the M categories of goods in the M groups of warehouse registration data, wherein the first warehouse registration data group includes a first warehouse entry time, a first pre-warehousing number, and a first warehouse entry quantity of the first category of goods;

[0020] Connect to the client of the target warehouse and retrieve the warehouse entry form. The target warehouse is any warehouse that uses the aforementioned artificial intelligence-based stacker warehouse entry address automatic generation system for intelligent goods warehouse entry addressing. The client of the target warehouse is a warehouse management terminal that performs warehouse scheduling such as warehouse entry management, outbound management, inventory management, and order processing on the target warehouse. The warehouse entry form includes M groups of warehouse entry registration data for M categories of goods, and M is an integer greater than or equal to 1. Among the M categories of goods, each category of goods includes multiple goods belonging to the same type of goods. Each group of warehouse entry registration data includes the warehouse entry time corresponding to each category of goods in the M categories of goods (the warehouse entry time parameter corresponding to each product in this category of goods), the pre-warehouse number (the pre-warehouse number parameter corresponding to each product in this category of goods) and the warehouse entry quantity (the total quantity of goods in this category of goods).

[0021] Further, each category of goods in the M categories of goods is set as the first category of goods in turn, and a group of warehouse registration data corresponding to the first category of goods in the M groups of warehouse registration data is set as the first warehouse registration data group. The first category of goods is each category of goods in the M categories of goods in turn. The first warehouse registration data group includes the first warehouse entry time, the first pre-warehousing number and the first warehouse entry quantity of the first category of goods. The first warehouse entry time includes multiple warehouse entry time parameters corresponding to multiple goods in the first category of goods. The first pre-warehousing number includes multiple pre-warehousing number parameters corresponding to multiple goods in the first category of goods. The first warehouse entry quantity includes the total quantity corresponding to multiple goods in the first category of goods.

[0022] Analyze the first warehouse entry image captured by the image acquisition device at the first warehouse entry time to obtain first warehouse entry identification information, where the first warehouse entry identification information includes a first warehouse entry identification product, a first warehouse entry identification quantity, and a first warehouse entry identification number;

[0023] The first storage-in identification information is obtained by analyzing the first storage-in image collected by the image collection device at the first storage-in time, including:

[0024] Segmenting the first stored image to obtain a first image block set, where the first image block set includes N image blocks, where N is an integer greater than 1;

[0025] Preprocessing a first image block among the N randomly extracted image blocks to obtain a first image preprocessing coefficient;

[0026] Retrieving a predetermined characteristic function to perform weighted calculation on the first image AC coefficient in the first image preprocessing coefficient to obtain a first image texture feature;

[0027] Wherein, the expression of the predetermined characteristic function is as follows:

[0028] ;

[0029] in, Characterizing the first image texture feature, Characterizing the first image AC coefficient, The first image block set representing the first stored image Image blocks, Characterizes the influence factor of the first image AC coefficient on the texture feature of the first image.

[0030] Comparing the first image texture feature with a first predetermined texture feature of the first category of goods to obtain a first comparison deviation;

[0031] The first incoming identification product is determined according to the first comparison deviation.

[0032] The image data of the image acquisition device is retrieved according to the first warehousing time to obtain the first warehousing image. The image acquisition device is a device in the prior art that can acquire warehousing images of the target warehouse (such as a CCD sensor, etc.). The first warehousing image includes warehousing image data corresponding to each warehousing time parameter within the first warehousing time. Then, each warehousing image data in the first warehousing image is respectively identified as goods, that is, a random warehousing image data in the first warehousing image is segmented according to a preset image block size pre-set and determined by the said artificial intelligence-based stacker warehousing address automatic generation system, to obtain the first image block set corresponding to the warehousing image data. The first image block set includes N image blocks, where N is an integer greater than 1. Moreover, each image block satisfies the preset image block size.

[0033] Further, N image blocks are randomly extracted to obtain a first image block, and the first image block is preprocessed to obtain a first image preprocessing coefficient. The first image preprocessing coefficient includes a first image AC coefficient. The image AC coefficient is calculated by comparing the difference between the original image and the transmitted image. The image AC coefficient takes into account factors such as image brightness, contrast, and color balance to quantify the quality of image transmission. The image AC coefficient ranges from 0 to 1, where 1 represents a completely undistorted image and 0 represents a completely distorted image. Then, the first image AC coefficient in the first image preprocessing coefficient is weightedly calculated according to a predetermined feature function to obtain a first image texture feature. The first image texture feature includes texture features such as the size and shape of the product packaging box. The expression of the predetermined feature function is as follows:

[0034] ;

[0035] in, Characterize the first image texture feature, Characterize the first image AC coefficient, The first image block set representing the first stored image Image blocks, Characterizes the influence factor of the first image AC coefficient on the texture feature of the first image.

[0036] Connect the stacker entry address automatic generation system based on artificial intelligence, retrieve the first predetermined texture feature of the first category of goods, and compare the first image texture feature with the first predetermined texture feature to obtain a first comparison deviation. The first predetermined texture feature includes the predetermined texture feature of the goods corresponding to each of the goods in the first category of goods (texture feature information such as the size and shape of the goods packaging box corresponding to each of the goods). The first comparison deviation includes multiple image texture deviations. The image texture deviation is data information used to characterize the difference between the first image texture feature and the predetermined texture feature of the goods. The greater the difference between the first image texture feature and the predetermined texture feature of the goods, the greater the corresponding image texture deviation. Then, the goods corresponding to the smallest image texture deviation in the first comparison deviation are recorded as the first identified goods, and the first identified goods are added to the first entry identification goods. The first entry identification goods include the identification goods corresponding to each entry image data in the first entry image.

[0037] The step of analyzing the first storage-in image acquired by the image acquisition device at the first storage-in time to obtain the first storage-in identification information further includes:

[0038] Analyze and obtain the number of first stored images in the first stored images;

[0039] Recording the result obtained by adding the first number of stored images as the first number of stored recognition images;

[0040] Recognize the text in the first storage image to obtain the first storage identification number;

[0041] The first warehousing identification product, the first warehousing identification quantity and the first warehousing identification number constitute the first warehousing identification information.

[0042] The total number of the storage image data in the first storage image is set as the first storage image number, and the first storage image number is output as the first storage identification number. Then, the text in the first storage image is recognized to obtain the first storage identification number, and the first storage identification product, the first storage identification number and the first storage identification number are output as the first storage identification information. The first storage identification number includes the text information in the first storage image.

[0043] Retrieving a first storage path of the stacker at the first storage time, wherein the first storage path includes a first destination location;

[0044] Acquire first storage information detected by the inspection robot at the first destination location, where the first storage information includes a first storage commodity type, a first storage commodity quantity, and a first storage commodity number;

[0045] According to the first warehousing time, data of the stacker is retrieved to obtain the first warehousing path. The stacker is a warehousing equipment used to stack and pick up and place goods in the target warehouse. The first warehousing path includes a first destination position. The first destination position includes the goods transportation terminal position corresponding to the stacker at the first warehousing time. Then, the inspection robot reads the storage information according to the first destination position to obtain the first storage information. The inspection robot is a storage inspection robot of the target warehouse. The first storage information includes the first storage goods category, the first storage goods quantity and the first storage goods number. The first storage goods category includes the goods category information detected by the inspection robot at the first destination position. The first storage goods quantity includes the goods quantity parameters detected by the inspection robot at the first destination position. The first storage goods number includes the storage goods number information detected by the inspection robot at the first destination position.

[0046] Proofreading and analyzing the first warehouse entry registration data group, the first warehouse entry identification information, and the first warehousing information to obtain a first proofreading result;

[0047] As attached Figure 2 As shown, the first warehouse entry registration data group, the first warehouse entry identification information and the first warehousing information are proofread and analyzed to obtain a first proofreading result, including:

[0048] When the first warehouse entry identification product is the first category of products, a first collation relationship is formed based on the first warehouse entry quantity, the first warehouse entry identification quantity and the first warehouse storage product quantity, and a second collation relationship is formed based on the first pre-warehouse entry number, the first warehouse entry identification number and the first warehouse storage product number;

[0049] Proofreading and analyzing the first proofreading relationship and the second proofreading relationship respectively to obtain the first proofreading result.

[0050] When the first entry identification product is a first category product, the first entry quantity, the first entry identification quantity and the first storage product quantity are set as the first proofreading relationship, and the first pre-entry number, the first entry identification number and the first storage product number are set as the second proofreading relationship. Then, the first proofreading relationship and the second proofreading relationship are proofread and analyzed to obtain the first proofreading result. The first proofreading result includes the proofreading degree of the entry quantity-identification quantity, the proofreading degree of the entry quantity-storage product quantity, and the proofreading degree of the identification quantity-storage product quantity corresponding to the first proofreading relationship, and the proofreading degree of the pre-entry number-identification number, the proofreading degree of the pre-entry number-storage product number, and the proofreading degree of the identification number-storage product number corresponding to the second proofreading relationship.

[0051] Exemplarily, when obtaining the first proofreading result, any two parameters in the first proofreading relationship are compared to obtain the proofreading degree of the incoming quantity-identification quantity, the proofreading degree of the incoming quantity-warehouse goods quantity, and the proofreading degree of the identification quantity-warehouse goods quantity corresponding to the first proofreading relationship. Then, any two parameters in the second proofreading relationship are compared respectively to obtain the proofreading degree of the pre-incoming number-identification number, the proofreading degree of the pre-incoming number-warehouse goods number, and the proofreading degree of the identification number-warehouse goods number corresponding to the second proofreading relationship. For example, when obtaining the proofreading degree of the incoming quantity-identification quantity, the first incoming quantity and the first incoming identification quantity in the first proofreading relationship are compared to obtain the proofreading degree of the incoming quantity-identification quantity. The proofreading degree of the incoming quantity-identification quantity is data information used to characterize the consistency between the first incoming quantity and the first incoming identification quantity. The higher the consistency between the first incoming quantity and the first incoming identification quantity, the greater the corresponding proofreading degree of the incoming quantity-identification quantity. The calibration degree of incoming quantity - storage goods quantity, calibration degree of identification quantity - storage goods quantity, calibration degree of number before incoming quantity - identification number, calibration degree of number before incoming quantity - storage goods number, calibration degree of identification number - storage goods number are obtained in the same way and have similar meanings as the calibration degree of incoming quantity - identification quantity, and will not be repeated here.

[0052] By performing proofreading analysis on the first proofreading relationship and the second proofreading relationship respectively, the accuracy of goods entry addressing is improved.

[0053] Obtaining a first storage product prediction number according to the first warehousing time, the first destination location, and the first pre-warehousing number;

[0054] The first warehouse product forecast number and the first warehouse product number form a third proofreading relationship;

[0055] The result obtained by proofreading and analyzing the third proofreading relationship is added to the first proofreading result.

[0056] The first entry time, the first destination location and the first pre-entry number are input into the storage number prediction library to obtain the first storage product prediction number. The storage number prediction library includes multiple storage number records. Each storage number record includes the historical entry time, the historical destination location, the historical pre-entry number and the historical storage product number. Then, the first storage product prediction number and the first storage product number are set as the third proofreading relationship, and the third proofreading relationship is proofread and analyzed to obtain the product prediction number-storage product number proofreading degree, and the product prediction number-storage product number proofreading degree is added to the first proofreading result to improve the comprehensiveness and accuracy of the product entry address proofreading. The product prediction number-storage product number proofreading degree is data information used to characterize the consistency between the first storage product prediction number and the first storage product number. The stronger the consistency between the first storage product prediction number and the first storage product number, the higher the corresponding product prediction number-storage product number proofreading degree.

[0057] The first warehousing addressing information is corrected according to the first proofreading result to obtain a first warehousing addressing correction result, wherein the first warehousing addressing information refers to the warehousing addressing information of the first category of goods.

[0058] The first warehouse entry addressing information is corrected according to the first proofreading result to obtain the first warehouse entry addressing correction result, including:

[0059] Extracting a first proofreading anomaly from the first proofreading result;

[0060] Performing a traceback process on the first proofreading exception to obtain a first exception traceback process result;

[0061] The first warehousing addressing information is corrected based on the first abnormal tracing processing result.

[0062] The stacker crane entry address automatic generation system based on artificial intelligence is connected to retrieve the first entry address information. The first entry address information refers to the entry address information of the first category of goods. The first entry address information includes the entry time, entry quantity, entry location (storage location number, row number, layer number, etc.), entry number, etc. corresponding to the first category of goods.

[0063] Further, it is judged whether each proofreading degree in the first proofreading result meets the preset proofreading degree. The preset proofreading degree includes the proofreading degree range preset and determined by the said artificial intelligence-based stacker storage address automatic generation system. If a proofreading degree in the first proofreading result does not meet the preset proofreading degree, then the parameter corresponding to the proofreading degree is set as the first proofreading exception. Then, the first proofreading exception is traced, that is, the first proofreading exception is corrected to obtain the first abnormal traceability processing result, and the first storage addressing information is corrected according to the first abnormal traceability processing result to obtain the first storage addressing correction result, thereby improving the accuracy of the storage addressing of the goods. Among them, the first proofreading exception is the parameter corresponding to the proofreading degree that does not meet the preset proofreading degree in the first proofreading result. The first abnormal traceability processing result includes the corrected first proofreading exception. The first storage addressing correction result is the updated first storage addressing information obtained by updating the data of the first storage addressing information according to the first abnormal traceability processing result. Exemplarily, if the proofreading degree of the incoming quantity-identified quantity in the first proofreading result does not meet the preset proofreading degree, the first incoming quantity and the first incoming identification quantity corresponding to the proofreading degree of the incoming quantity-identified quantity are set as the first proofreading exception. Then, the first incoming quantity and the first incoming identification quantity are corrected to obtain the corrected first incoming quantity and the corrected first incoming identification quantity, and the corrected first incoming quantity and the corrected first incoming identification quantity are set as the first abnormality tracing processing result, and the first incoming addressing information is updated according to the first abnormality tracing processing result, thereby correcting the first incoming addressing information.

[0064] In summary, the method for automatically generating stacker entry address based on artificial intelligence provided by the present application has the following technical effects:

[0065] The first entry time, the first pre-entry number and the first entry quantity of the first category of goods in the M categories of goods are matched through the M groups of entry registration data in the entry order; the first entry image acquired by the image acquisition device at the first entry time is analyzed to obtain the first entry identification goods, the first entry identification quantity and the first entry identification number; the first destination position of the stacker at the first entry time is retrieved; the first storage goods type, the first storage goods quantity and the first storage goods number detected by the inspection robot at the first destination position are obtained; the first proofreading result is obtained by proofreading and analyzing the first entry registration data group (the first entry time, the first pre-entry number and the first entry quantity), the first entry identification information (the first entry identification goods, the first entry identification quantity and the first entry identification number) and the first storage information (the first storage goods type, the first storage goods quantity and the first storage goods number); the first entry addressing information is corrected according to the first proofreading result to obtain the first entry addressing correction result. By dynamically checking and verifying the goods' entry addressing, the error rate of goods' entry addressing can be effectively reduced, the timeliness and accuracy of detecting errors in goods' entry addressing can be improved, and the quality of goods' entry addressing can be improved.

[0066] Embodiment 2

[0067] Based on the same inventive concept as the method for automatically generating the address of a stacker entering the warehouse based on artificial intelligence in the aforementioned embodiment, the present invention also provides an automatic generation system for automatically generating the address of a stacker entering the warehouse based on artificial intelligence, and the system is connected to the image acquisition device, the stacker and the inspection robot for communication, see the attached Figure 3 , the system comprising:

[0068] An entry order acquisition module, the entry order acquisition module is used to acquire an entry order, the entry order is received from a client of a target warehouse, the entry order includes M groups of entry registration data of M categories of goods, M is an integer greater than or equal to 1;

[0069] a data matching module, the data matching module being used to match a first warehouse registration data group of a first category of goods in the M categories of goods in the M groups of warehouse registration data, the first warehouse registration data group including a first warehouse entry time, a first pre-warehousing number and a first warehouse entry quantity of the first category of goods;

[0070] An image analysis module, the image analysis module is used to analyze the first warehouse entry image collected by the image acquisition device at the first warehouse entry time to obtain first warehouse entry identification information, wherein the first warehouse entry identification information includes a first warehouse entry identification commodity, a first warehouse entry identification quantity and a first warehouse entry identification number;

[0071] A storage path retrieval module, the storage path retrieval module is used to retrieve a first storage path of the stacker at the first storage time, the first storage path including a first destination position;

[0072] A storage information acquisition module, the storage information acquisition module is used to acquire first storage information detected by the inspection robot at the first destination location, the first storage information including a first storage commodity type, a first storage commodity quantity and a first storage commodity number;

[0073] A proofreading and analysis module, the proofreading and analysis module is used to proofread and analyze the first warehouse entry registration data group, the first warehouse entry identification information and the first warehousing information to obtain a first proofreading result;

[0074] The warehouse entry address correction module is used to correct the first warehouse entry address information according to the first proofreading result to obtain the first warehouse entry address correction result. The first warehouse entry address information refers to the warehouse entry address information of the first category of goods.

[0075] Furthermore, the image analysis module is also used for:

[0076] Segmenting the first stored image to obtain a first image block set, where the first image block set includes N image blocks, where N is an integer greater than 1;

[0077] Preprocessing a first image block among the N randomly extracted image blocks to obtain a first image preprocessing coefficient;

[0078] Retrieving a predetermined characteristic function to perform weighted calculation on the first image AC coefficient in the first image preprocessing coefficient to obtain a first image texture feature;

[0079] Comparing the first image texture feature with a first predetermined texture feature of the first category of goods to obtain a first comparison deviation;

[0080] The first incoming identification product is determined according to the first comparison deviation.

[0081] Wherein, the expression of the predetermined characteristic function is as follows:

[0082] ;

[0083] in, characterizing the first image texture feature, Characterizing the first image AC coefficient, The first image block set representing the first stored image Image blocks, Characterizes the influence factor of the first image AC coefficient on the texture feature of the first image.

[0084] Furthermore, the image analysis module is also used for:

[0085] Analyze and obtain the number of first stored images in the first stored images;

[0086] Recording the result obtained by adding the first number of stored images as the first number of stored recognition images;

[0087] Recognize the text in the first storage image to obtain the first storage identification number;

[0088] The first warehousing identification product, the first warehousing identification quantity and the first warehousing identification number constitute the first warehousing identification information.

[0089] Furthermore, the proofreading and analysis module is also used for:

[0090] When the first warehouse entry identification product is the first category of products, a first collation relationship is formed based on the first warehouse entry quantity, the first warehouse entry identification quantity and the first warehouse storage product quantity, and a second collation relationship is formed based on the first pre-warehouse entry number, the first warehouse entry identification number and the first warehouse storage product number;

[0091] Proofreading and analyzing the first proofreading relationship and the second proofreading relationship respectively to obtain the first proofreading result.

[0092] Furthermore, the proofreading and analysis module is also used for:

[0093] Obtaining a first storage product prediction number according to the first warehousing time, the first destination location, and the first pre-warehousing number;

[0094] The first warehouse product forecast number and the first warehouse product number form a third proofreading relationship;

[0095] The result obtained by proofreading and analyzing the third proofreading relationship is added to the first proofreading result.

[0096] Furthermore, the entry address correction module is also used for:

[0097] Extracting a first proofreading anomaly from the first proofreading result;

[0098] Performing a traceback process on the first proofreading exception to obtain a first exception traceback process result;

[0099] The first warehousing addressing information is corrected based on the first abnormal tracing processing result.

[0100] An artificial intelligence-based automatic generation system for stacker entry addressing provided in an embodiment of the present invention can execute an artificial intelligence-based automatic generation method for stacker entry addressing provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0101] The modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0102] The present application provides an artificial intelligence-based automatic generation method for stacker entry addressing, wherein the method is applied to an artificial intelligence-based automatic generation system for stacker entry addressing, and the method comprises: matching the first entry time, the first pre-entry number and the first entry quantity of the first category of goods in the M categories of goods through M groups of entry registration data in the entry order; analyzing the first entry image captured by the image acquisition device at the first entry time to obtain the first entry identification goods, the first entry identification quantity and the first entry identification number; retrieving the first destination position of the stacker at the first entry time; obtaining The inspection robot detects the first storage goods type, the first storage goods quantity and the first storage goods number at the first destination; by proofreading and analyzing the first warehouse registration data group (first warehouse time, first warehouse pre-number and first warehouse quantity), the first warehouse identification information (first warehouse identification goods, first warehouse identification quantity and first warehouse identification number) and the first warehouse information (first warehouse goods type, first warehouse quantity and first warehouse number), the first proofreading result is obtained; according to the first proofreading result, the first warehouse addressing information is corrected to obtain the first warehouse addressing correction result. The technical problem that the error rate of warehouse addressing of goods in the prior art is high, the warehouse addressing errors of goods cannot be discovered in time, and the warehouse addressing effect of goods is poor is solved. By dynamically checking and verifying the warehouse addressing of goods, the error rate of warehouse addressing of goods is effectively reduced, the timeliness and accuracy of detecting warehouse addressing errors of goods are improved, and the quality of warehouse addressing of goods is improved.

[0103] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. An artificial intelligence-based automatic generation method for stacker entry address recognition, characterized in that: The method is applied to an artificial intelligence-based automatic generation system for stacker warehouse addressing, the system is communicatively connected with an image acquisition device, a stacker and an inspection robot, and the method comprises: Obtaining a warehouse entry form, the warehouse entry form being received from a client of a target warehouse, the warehouse entry form including M groups of warehouse entry registration data of M categories of goods, where M is an integer greater than or equal to 1; Matching a first warehouse registration data group of a first category of goods in the M categories of goods in the M groups of warehouse registration data, wherein the first warehouse registration data group includes a first warehouse entry time, a first pre-warehousing number, and a first warehouse entry quantity of the first category of goods; Analyze the first warehouse entry image captured by the image acquisition device at the first warehouse entry time to obtain first warehouse entry identification information, where the first warehouse entry identification information includes a first warehouse entry identification product, a first warehouse entry identification quantity, and a first warehouse entry identification number; Retrieving a first storage path of the stacker at the first storage time, wherein the first storage path includes a first destination location; Acquire first storage information detected by the inspection robot at the first destination location, where the first storage information includes a first storage commodity type, a first storage commodity quantity, and a first storage commodity number; Proofreading and analyzing the first warehouse entry registration data group, the first warehouse entry identification information, and the first warehousing information to obtain a first proofreading result; Correcting the first warehouse entry addressing information according to the first proofreading result to obtain a first warehouse entry addressing correction result, wherein the first warehouse entry addressing information refers to the warehouse entry addressing information of the first category of goods; The first storage-in identification information is obtained by analyzing the first storage-in image collected by the image collection device at the first storage-in time, including: Segmenting the first stored image to obtain a first image block set, where the first image block set includes N image blocks, where N is an integer greater than 1; Preprocessing a first image block among the N randomly extracted image blocks to obtain a first image preprocessing coefficient; Retrieving a predetermined characteristic function to perform weighted calculation on the first image AC coefficient in the first image preprocessing coefficient to obtain a first image texture feature; Comparing the first image texture feature with a first predetermined texture feature of the first category of goods to obtain a first comparison deviation; Determining the first incoming identification product according to the first comparison deviation; The first warehouse entry registration data group, the first warehouse entry identification information and the first warehousing information are proofread and analyzed to obtain a first proofreading result, including: When the first warehouse entry identification product is the first category of products, a first collation relationship is formed based on the first warehouse entry quantity, the first warehouse entry identification quantity and the first warehouse storage product quantity, and a second collation relationship is formed based on the first pre-warehouse entry number, the first warehouse entry identification number and the first warehouse storage product number; Proofreading and analyzing the first proofreading relationship and the second proofreading relationship respectively to obtain the first proofreading result.

2. The method according to claim 1, characterized in that: The expression of the predetermined characteristic function is as follows: ; in, Characterizing the first image texture feature, Characterizing the first image AC coefficient, The first image block set representing the first stored image Image blocks, Characterizes the influence factor of the first image AC coefficient on the texture feature of the first image.

3. The method according to claim 2, characterized in that: Analyzing the first storage-in image captured by the image capture device at the first storage-in time to obtain first storage-in identification information includes: Analyze and obtain the number of first stored images in the first stored images; Recording the result obtained by adding the first number of stored images as the first number of stored recognition images; Recognize the text in the first storage image to obtain the first storage identification number; The first warehousing identification product, the first warehousing identification quantity and the first warehousing identification number constitute the first warehousing identification information.

4. The method according to claim 1, characterized in that: The method also includes: Obtaining a first storage product prediction number according to the first warehousing time, the first destination location, and the first pre-warehousing number; The first warehouse product forecast number and the first warehouse product number form a third proofreading relationship; The result obtained by proofreading and analyzing the third proofreading relationship is added to the first proofreading result.

5. The method according to claim 4, characterized in that: Correcting the first warehouse entry addressing information according to the first proofreading result to obtain a first warehouse entry addressing correction result includes: Extracting a first proofreading anomaly from the first proofreading result; Performing a traceback process on the first proofreading exception to obtain a first exception traceback process result; The first warehousing addressing information is corrected based on the first abnormal tracing processing result.

6. An artificial intelligence-based automatic generation system for stacker entry address recognition, characterized in that: The system is used to execute the method according to any one of claims 1 to 5, the system is communicatively connected with an image acquisition device, a stacker and an inspection robot, and the system comprises: An entry order acquisition module, the entry order acquisition module is used to acquire an entry order, the entry order is received from a client of a target warehouse, the entry order includes M groups of entry registration data of M categories of goods, M is an integer greater than or equal to 1; a data matching module, the data matching module being used to match a first warehouse registration data group of a first category of goods in the M categories of goods in the M groups of warehouse registration data, the first warehouse registration data group including a first warehouse entry time, a first pre-warehousing number and a first warehouse entry quantity of the first category of goods; An image analysis module, the image analysis module is used to analyze the first warehouse entry image collected by the image acquisition device at the first warehouse entry time to obtain first warehouse entry identification information, wherein the first warehouse entry identification information includes a first warehouse entry identification commodity, a first warehouse entry identification quantity and a first warehouse entry identification number; A storage path retrieval module, the storage path retrieval module is used to retrieve a first storage path of the stacker at the first storage time, the first storage path including a first destination position; A storage information acquisition module, the storage information acquisition module is used to acquire first storage information detected by the inspection robot at the first destination location, the first storage information including a first storage commodity type, a first storage commodity quantity and a first storage commodity number; A proofreading and analysis module, the proofreading and analysis module is used to proofread and analyze the first warehouse entry registration data group, the first warehouse entry identification information and the first warehousing information to obtain a first proofreading result; The warehouse entry address correction module is used to correct the first warehouse entry address information according to the first proofreading result to obtain the first warehouse entry address correction result. The first warehouse entry address information refers to the warehouse entry address information of the first category of goods.

Citation Information

Patent Citations

  • Vehicle accessory storage method and mechanism and computer readable storage medium

    CN115303700A

  • Automatic addressing method for logistics robot

    CN117022959A