CN116882975B - Warehouse service method and system based on distributed computing - Google Patents
Warehouse service method and system based on distributed computing Download PDFInfo
- Publication number
- CN116882975B CN116882975B CN202310874689.XA CN202310874689A CN116882975B CN 116882975 B CN116882975 B CN 116882975B CN 202310874689 A CN202310874689 A CN 202310874689A CN 116882975 B CN116882975 B CN 116882975B
- Authority
- CN
- China
- Prior art keywords
- warehouse
- deformation
- goods shelf
- distributed computing
- chromatic aberration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000006378 damage Effects 0.000 claims abstract description 52
- 238000012423 maintenance Methods 0.000 claims abstract description 20
- 238000013145 classification model Methods 0.000 claims abstract description 18
- 230000004075 alteration Effects 0.000 claims description 29
- 238000000605 extraction Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims 2
- 238000004519 manufacturing process Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000009525 mild injury Effects 0.000 description 1
- 230000009526 moderate injury Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Abstract
The invention relates to a warehouse service method and system based on distributed computing, and relates to the technical field of warehouse service. The method comprises the following steps: acquiring parameters affecting the service life of a specified goods shelf from each of a plurality of target warehouses, identifying the color difference and deformation of the goods shelf and a new product based on the goods shelf image acquired by a camera in each target warehouse, and inputting input data into an attention model through each distributed computing node to obtain a first parameter characteristic; inputting the first parameter characteristic into a classification model to obtain damage degree; the method and the device accurately predict the damage degree of the goods shelf by combining the distributed calculation with the classification model and the attention model, and the final damage degree is obtained by fusing the damage degrees and is used for goods shelf maintenance, so that automatic goods shelf damage state identification is realized to a certain extent, and the goods shelf maintenance is convenient.
Description
Technical Field
The invention relates to the technical field of warehousing services, in particular to a warehousing service method and system based on distributed computing.
Background
And (3) warehousing: refers to the general term for the storage, preservation and warehouse-related storage activities of materials through a warehouse. It is generated along with the generation of material storage and also developed along with the development of productivity. Storage is one of important links of commodity circulation and is also an important prop for logistics activities.
The warehousing service can provide warehousing for clients, and an enterprise with certain warehousing capacity provides the content contained in the warehousing activity for the clients, and mainly comprises the following steps: warehouse entry, inventory, warehouse management, shipping and delivery of goods, and the like. At present, automatic warehousing services enter the field of view of the public, and automatic and intelligent warehousing services are realized through various sensors and robots.
In the warehouse service, the maintenance of the warehouse goods shelves is needed to be paid attention to, and damaged and rusted goods shelves are replaced in time so as to avoid damage to goods. At present, the goods shelf state identification aspect is manually overhauled, and an automatic scheme is not provided yet.
In view of this, the present invention has been proposed.
Disclosure of Invention
In order to solve the technical problems, the invention provides a storage service method and a storage service system based on distributed computation, which accurately predicts the damage degree of a goods shelf by combining a classification model and an attention model through the distributed computation, and the damage degrees are fused to obtain the final damage degree for the goods shelf maintenance, so that the automatic goods shelf damage state identification is realized to a certain extent, and the goods shelf maintenance is convenient.
The invention provides a warehouse service method based on distributed computation, which comprises the following steps:
s1, acquiring parameters affecting the service life of a specified goods shelf from each of a plurality of target warehouses, wherein the parameters at least comprise the temperature and the humidity of a warehouse environment, the load bearing of the goods shelf and the loading and unloading times;
s2, identifying color difference and deformation of a goods shelf and a new product based on goods shelf images acquired by cameras in each target warehouse;
s3, inputting the chromatic aberration and deformation from each target warehouse and the parameters into distributed computing nodes corresponding to the target warehouses, and inputting input data into an attention model through each distributed computing node to obtain first parameter characteristics focusing on the chromatic aberration and deformation;
s4, inputting the first parameter characteristics into a classification model through each distributed computing node to obtain damage degree;
s5, fusing all the damage degrees through the master node to obtain the final damage degree, wherein the final damage degree is used for carrying out shelf maintenance.
The invention provides a warehouse service system based on distributed computation, which comprises: the system comprises sensors deployed in a plurality of target warehouses, a warehouse-in module, a warehouse-out module, cameras, a distributed data processing module, distributed computing nodes and a master node;
the distributed data processing module is used for acquiring data from the sensor, the warehousing module and the ex-warehouse module to acquire parameters affecting the service life of the goods shelf from each target warehouse, wherein the parameters at least comprise the temperature and the humidity of the warehouse environment, the load bearing of the goods shelf and the loading and unloading times;
the distributed data processing module identifies the color difference and deformation of the goods shelf and the new product based on the goods shelf image acquired by the cameras in each target warehouse and inputs the color difference and deformation into the distributed computing nodes corresponding to the target warehouse;
the distributed computing nodes are stored with an attention model and a classification module, and are used for inputting input data into the attention model through each distributed computing node to obtain first parameter characteristics focusing on the chromatic aberration and the deformation, and inputting the first parameter characteristics into the classification model to obtain damage degree;
the master node is used for fusing the damage degrees to obtain the final damage degree, and the final damage degree is used for carrying out shelf maintenance.
The method provided by the invention has the following technical effects:
1) In theory, parameters affecting the service life of the shelf can directly lead to the damage degree of the shelf, the color difference and deformation of the shelf and the specific characterization of the damage of the shelf, the attention model is used for obtaining first parameter characteristics focusing on the color difference and the deformation, and the first parameter characteristics can actually lead to the damage degree of the shelf, so that the classification of the damage degree can be accurately obtained.
2) The distributed nodes corresponding to the target warehouse are adopted to respectively carry out attention and classification operation, so that the calculation efficiency is improved; the distributed nodes can be deployed in the target warehouse, so that the communication cost is saved.
3) And fusing the damage degrees through the master node, so that the damage degree of the same appointed goods shelf in different target warehouses is obtained by taking the difference of the target warehouses into consideration.
4) The final damage degree is used for shelf maintenance, and an automatic damage degree determination scheme is provided, so that manual participation is not needed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a warehousing service method based on distributed computing according to an embodiment of the present invention;
fig. 2 is a block diagram of a warehouse service system based on distributed computing according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
Fig. 1 is a flowchart of a warehousing service method based on distributed computing according to an embodiment of the present invention, including the following operations:
s1, acquiring parameters affecting the service life of a specified goods shelf from each of a plurality of target warehouses, wherein the parameters at least comprise the temperature and the humidity of a warehouse environment, the load bearing of the goods shelf and the loading and unloading times;
the target warehouse is a warehouse with specified shelves that are of a certain brand or manufacturer or price, ideally of consistent damage for the same time of use. Multiple target warehouses may be deployed in different cities or regions, but with the same shelves.
Temperature and humidity sensors deployed within a plurality of target warehouses are used to collect the temperature and humidity of the warehouse environment.
Specifically, S1 includes the following operations:
extracting warehouse entry goods information and warehouse exit goods information from each target warehouse; the warehouse-in goods information comprises warehouse-in goods related attributes, warehouse-in time, quantity, weight and the like, and the warehouse-in goods information comprises warehouse-out goods related attributes, warehouse-out time, quantity, weight and the like, and is specifically obtained from a warehouse-in module and a warehouse-out module.
Determining the loading and unloading times of all cargoes on the goods shelf according to the warehouse-in cargo information and the warehouse-out cargo information; certain impact can be generated on the goods shelf in the loading and unloading process, so that stress is generated on the goods shelf material, and the service life of the material can be influenced.
And determining the load bearing of the goods shelf according to the loading and unloading times and the weight of goods. The loading and unloading times and the goods shelf load bearing are counted in the time from the new goods (goods shelf) to the goods shelf in the current use.
S2, identifying color differences and deformation of the goods shelf and new goods based on goods shelf images acquired by cameras in each target warehouse.
The camera is just opposite to the whole goods shelf or the vulnerable part.
Specifically, S2 includes the following operations:
acquiring shelf images based on cameras in each target warehouse, and identifying the color and shape of a shelf from the shelf images; acquiring a new product image corresponding to the goods shelf, and identifying the color and the shape of the new product from the new product image; and comparing the color of the goods shelf with the color of the new product, and comparing the shape of the goods shelf with the shape of the new product to obtain chromatic aberration and deformation. The target recognition and detection technology, color comparison and shape comparison are all achieved by adopting a conventional image processing method, and the method is not limited by the patent.
In a specific scene, chromatic aberration occurs when the shelf is corroded, rusted or other substances affecting the service life are attached, and the consistency of light, shooting angle and shelf appearance is ensured during comparison. When the goods shelf is bent and broken, different shapes can be caused, and the shooting angle and the shooting height are ensured to be consistent during comparison.
The operations of S1 and S2 may be performed in particular by distributed data processing modules deployed at respective target warehouses.
S3, inputting the chromatic aberration and deformation from each target warehouse and the parameters into the distributed computing nodes corresponding to the target warehouses, and inputting input data into the attention model through each distributed computing node to obtain first parameter characteristics focusing on the chromatic aberration and deformation.
The distributed computing nodes can be deployed in the target warehouse, chromatic aberration and deformation from each target warehouse and the parameters are input into the distributed computing nodes corresponding to the target warehouse, input data are input into the Attention model Attention through each distributed computing node, the first parameter characteristics focusing on the chromatic aberration and the deformation are obtained, and communication cost is saved. The distributed computing node comprises a feature extraction model, an attribute model and a classification model.
The distributed data processing module is respectively connected with the distributed computing nodes and is used for inputting the chromatic aberration, the deformation and the parameters from each target warehouse into the distributed computing nodes corresponding to the target warehouses.
Since the color difference and the deformation are different types of data, the color difference and the deformation need to be normalized so as to be conveniently input into the Attention. The parameters in S1 are also of multiple types, and the parameters are input into a feature extraction model to obtain second parameter features when the types and the associated features among the types need to be extracted; the feature extraction model may be a neural network convolutional layer.
And each distributed node inputs the normalized chromatic aberration and deformation and the second parameter characteristic into the Attention to obtain a first parameter characteristic focusing on the chromatic aberration and deformation. The Attention model brings about from full focus to focus: the color difference and the deformation, that is, the first parameter characteristic is the main characteristic causing the color difference and the deformation, the redundant characteristic which does not cause the color difference and the deformation is filtered, and the damage degree can be accurately estimated. For example, some shelf materials are resistant to high temperatures, while higher temperature parameters are filtered out.
S4, inputting the first parameter characteristic into a classification model through each distributed computing node to obtain the damage degree.
The classification module may be a softmax model and the degree of damage may be manually divided, such as mild, moderate and severe, specifically outputting probabilities of respective degrees of damage.
S5, fusing all the damage degrees through the master node to obtain the final damage degree, wherein the final damage degree is used for carrying out shelf maintenance.
The main node is in communication connection with each distributed node, the probability of each damage degree is weighted and averaged, and the damage degree corresponding to the maximum probability value is taken as the final damage degree. The weight may be determined based on the number of shelves specified in each target warehouse.
Optionally, S6 further includes determining a maintenance priority of the shelf according to the final damage degree, and making a maintenance form according to the maintenance priority to provide to an overhaul department. Specifically, if severe damage is determined to be high priority, moderate damage is determined to be medium priority, and mild damage is determined to be low priority. And sorting the maintenance forms according to the priorities of various shelves, and providing the maintenance forms to an overhaul department.
In the above embodiment, the feature extraction model, the Attention model, and the classification model in the distributed computing node need to be trained in advance, and the three may be trained together.
Specifically, before S2, the method further includes: determining a plurality of sample warehouses that match different cargo related attributes; training the feature extraction model, the attention model, and the classification model based on the chromatic aberration, the deformation, and the second parameter features within the plurality of sample warehouses.
In practical applications, warehouses are limited by various factors such as temperature and humidity, and generally only limited types of goods are stored, so that the goods shelves are also limited in types. Based on this, the cargo-related attributes include at least the environmental requirements, volume, weight, and storage time of the cargo storage. For example, a sample warehouse matched with a low temperature and a sample warehouse matched with a cargo volume of more than 10 cubic meters are determined, so that the diversity of cargo related attributes is ensured, and the trained model is suitable for various cargos and various warehouses. Furthermore, from a plurality of sample warehouses matched with the relevant attributes of different cargoes, the temperature and humidity of different warehouse environments, the load bearing of a goods shelf and the loading and unloading times are easily obtained, so that the construction of qualified training samples is facilitated.
Optionally, since each sample warehouse is located in a different city/region, the data has a difference, and in order to solve the problem of information island and ensure data security, the feature extraction model, the attention model and the classification model are subjected to federal learning by a training center on the chromatic aberration, the deformation and the second parameter features derived from the plurality of sample warehouses. For a specific method of federal learning, see the prior art, for example, after each distributed computing node adopts local sample warehouse data for training, model parameters are transmitted to a training center; and the training center fuses the model parameters to obtain final model parameters.
The training center transmits the trained feature extraction model, the attribute model and the classification model to the distributed computing nodes for classifying the subsequent damage degree.
Referring to fig. 2, an embodiment of the present invention provides a warehouse service system based on distributed computing, including: the system comprises sensors deployed in a plurality of target warehouses, a warehouse-in module, a warehouse-out module, cameras, a distributed data processing module, distributed computing nodes and a master node.
The distributed data processing module is used for acquiring data from the sensor, the warehousing module and the ex-warehouse module to acquire parameters affecting the service life of the goods shelf from each target warehouse, wherein the parameters at least comprise the temperature and the humidity of the warehouse environment, the load bearing of the goods shelf and the loading and unloading times;
the distributed data processing module identifies the color difference and deformation of the goods shelf and the new product based on the goods shelf image acquired by the cameras in each target warehouse and inputs the color difference and deformation into the distributed computing nodes corresponding to the target warehouse;
the distributed computing nodes are stored with an attention model and a classification module, and are used for inputting input data into the attention model through each distributed computing node to obtain first parameter characteristics focusing on the chromatic aberration and the deformation, and inputting the first parameter characteristics into the classification model to obtain damage degree;
the master node is used for fusing the damage degrees to obtain the final damage degree, and the final damage degree is used for carrying out shelf maintenance.
Optionally, the system further comprises a training center for federally learning the feature extraction model, the attention model, and the classification model for the chromatic aberration, the deformation, and the second parameter feature from the plurality of sample warehouses; the plurality of sample warehouses are matched with different cargo related attributes; the feature extraction model is used for extracting features of the parameters.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in this specification, the terms "a," "an," "the," and/or "the" are not intended to be limiting, but rather are to be construed as covering the singular and the plural, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
It should also be noted that the positional or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (9)
1. A distributed computing-based warehousing service method, comprising:
s1, acquiring parameters affecting the service life of a specified goods shelf from each of a plurality of target warehouses, wherein the parameters at least comprise the temperature and the humidity of a warehouse environment, the load bearing of the goods shelf and the loading and unloading times;
s2, identifying color difference and deformation of the goods shelf and new products based on goods shelf images acquired by cameras in each target warehouse;
s3, inputting the chromatic aberration and the deformation from each target warehouse and the parameters into distributed computing nodes corresponding to the target warehouses, carrying out normalization processing on the chromatic aberration and the deformation through each distributed computing node, and inputting the parameters into a feature extraction model to obtain second parameter features; inputting the normalized chromatic aberration and deformation and the second parameter characteristics into an attention model to obtain first parameter characteristics focusing on the chromatic aberration and deformation; the first parameter features are main features causing chromatic aberration and deformation, and redundant features which cannot cause chromatic aberration and deformation are filtered;
s4, inputting the first parameter characteristics into a classification model through each distributed computing node to obtain damage degree;
s5, fusing all the damage degrees through the master node to obtain the final damage degree, wherein the final damage degree is used for carrying out shelf maintenance.
2. The method according to claim 1, wherein said S5 further comprises, thereafter:
and S6, determining the maintenance priority of the goods shelf according to the final damage degree, and manufacturing a maintenance form according to the maintenance priority to be provided for an overhaul department.
3. The method according to claim 1, further comprising, prior to said S2:
determining a plurality of sample warehouses that match different cargo related attributes;
training the feature extraction model, the attention model, and the classification model based on the chromatic aberration, the deformation, and the second parameter features within the plurality of sample warehouses.
4. A method according to claim 3, wherein the color differences, deformations and the second parameter features derived from the plurality of sample warehouses are federally learned by a training center for feature extraction models, attention models and classification models.
5. A method according to claim 3, wherein the cargo-related properties include at least environmental requirements, volume, weight and storage time of the cargo storage.
6. The method according to claim 1, wherein S2 comprises:
acquiring shelf images based on cameras in each target warehouse, and identifying the color and shape of a shelf from the shelf images;
acquiring a new product image corresponding to the goods shelf, and identifying the color and the shape of the new product from the new product image;
and comparing the color of the goods shelf with the color of the new product, and comparing the shape of the goods shelf with the shape of the new product to obtain chromatic aberration and deformation.
7. The method according to claim 1, wherein S1 comprises:
extracting warehouse entry goods information and warehouse exit goods information from each target warehouse;
determining the loading and unloading times of all cargoes on the goods shelf according to the warehouse-in cargo information and the warehouse-out cargo information;
and determining the load bearing of the goods shelf according to the loading and unloading times and the weight of goods.
8. A distributed computing-based warehousing service system, comprising: the system comprises sensors deployed in a plurality of target warehouses, a warehouse-in module, a warehouse-out module, cameras, a distributed data processing module, distributed computing nodes and a master node;
the distributed data processing module is used for acquiring data from the sensor, the warehousing module and the ex-warehouse module to acquire parameters affecting the service life of the goods shelf from each target warehouse, wherein the parameters at least comprise the temperature and the humidity of the warehouse environment, the load bearing of the goods shelf and the loading and unloading times;
the distributed data processing module identifies the color difference and deformation of the goods shelf and the new product based on the goods shelf image acquired by the cameras in each target warehouse and inputs the color difference and deformation into the distributed computing nodes corresponding to the target warehouse;
the distributed computing nodes are stored with an attention model and a classification module, and are used for carrying out normalization processing on chromatic aberration and deformation through each distributed computing node, and inputting the parameters into a feature extraction model to obtain second parameter features; inputting the normalized chromatic aberration and deformation and the second parameter characteristic into an attention model to obtain a first parameter characteristic focusing on the chromatic aberration and deformation, and inputting the first parameter characteristic into a classification model to obtain damage degree; the first parameter features are main features causing chromatic aberration and deformation, and redundant features which cannot cause chromatic aberration and deformation are filtered;
the master node is used for fusing the damage degrees to obtain the final damage degree, and the final damage degree is used for carrying out shelf maintenance.
9. The system of claim 8, further comprising a training center for federally learning the color differences, deformations, and the second parametric feature pair feature extraction model, attention model, and classification model from a plurality of sample warehouses;
the plurality of sample warehouses are matched with different cargo related attributes;
the feature extraction model is used for extracting features of the parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310874689.XA CN116882975B (en) | 2023-07-17 | 2023-07-17 | Warehouse service method and system based on distributed computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310874689.XA CN116882975B (en) | 2023-07-17 | 2023-07-17 | Warehouse service method and system based on distributed computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116882975A CN116882975A (en) | 2023-10-13 |
| CN116882975B true CN116882975B (en) | 2024-01-30 |
Family
ID=88261742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310874689.XA Active CN116882975B (en) | 2023-07-17 | 2023-07-17 | Warehouse service method and system based on distributed computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882975B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107504999A (en) * | 2017-08-08 | 2017-12-22 | 北京物资学院 | A kind of storage rack safe early warning and health evaluating method and device |
| CN108291880A (en) * | 2015-03-13 | 2018-07-17 | 科内克斯伯德有限公司 | Arrangement, method, apparatus and software for checking counter |
| CN112950549A (en) * | 2021-02-04 | 2021-06-11 | 科大智能物联技术有限公司 | Goods shelf deformation detection system and detection method based on machine vision |
| CN113283848A (en) * | 2021-07-21 | 2021-08-20 | 湖北浩蓝智造科技有限公司 | Goods warehousing detection method, warehousing system and storage medium |
| CN114898191A (en) * | 2022-04-25 | 2022-08-12 | 池明旻 | Hand-held fabric fiber component nondestructive cleaning analyzer and method |
| CN115039045A (en) * | 2019-11-25 | 2022-09-09 | 强力物联网投资组合2016有限公司 | Intelligent vibration digital twinning system and method for industrial environments |
-
2023
- 2023-07-17 CN CN202310874689.XA patent/CN116882975B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108291880A (en) * | 2015-03-13 | 2018-07-17 | 科内克斯伯德有限公司 | Arrangement, method, apparatus and software for checking counter |
| CN107504999A (en) * | 2017-08-08 | 2017-12-22 | 北京物资学院 | A kind of storage rack safe early warning and health evaluating method and device |
| CN115039045A (en) * | 2019-11-25 | 2022-09-09 | 强力物联网投资组合2016有限公司 | Intelligent vibration digital twinning system and method for industrial environments |
| CN112950549A (en) * | 2021-02-04 | 2021-06-11 | 科大智能物联技术有限公司 | Goods shelf deformation detection system and detection method based on machine vision |
| CN113283848A (en) * | 2021-07-21 | 2021-08-20 | 湖北浩蓝智造科技有限公司 | Goods warehousing detection method, warehousing system and storage medium |
| CN114898191A (en) * | 2022-04-25 | 2022-08-12 | 池明旻 | Hand-held fabric fiber component nondestructive cleaning analyzer and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116882975A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220084186A1 (en) | Automated inspection system and associated method for assessing the condition of shipping containers | |
| US20190220692A1 (en) | Method and apparatus for checkout based on image identification technique of convolutional neural network | |
| US20170091706A1 (en) | System for monitoring the condition of packages throughout transit | |
| US10810543B2 (en) | Populating catalog data with item properties based on segmentation and classification models | |
| CN112861631B (en) | Wagon balance human body intrusion detection method based on Mask Rcnn and SSD | |
| US11288539B1 (en) | Tiered processing for item identification | |
| US10769399B2 (en) | Method for improper product barcode detection | |
| US20170004384A1 (en) | Image based baggage tracking system | |
| CN111222389B (en) | Analysis method and system for commodity on super commodity shelf | |
| US11157978B2 (en) | Systems and methods for managing data related to vehicle(s) | |
| US20200193281A1 (en) | Method for automating supervisory signal during training of a neural network using barcode scan | |
| US11257032B2 (en) | Smart audit or intervention in an order fulfillment process | |
| US10713614B1 (en) | Weight and vision based item tracking | |
| CN112561543A (en) | E-commerce platform false transaction order monitoring method and system based on full-period logistics data analysis and cloud server | |
| US11748787B2 (en) | Analysis method and system for the item on the supermarket shelf | |
| Higa et al. | Robust estimation of product amount on store shelves from a surveillance camera for improving on-shelf availability | |
| EP3113091A1 (en) | Image based baggage tracking system | |
| CN116882975B (en) | Warehouse service method and system based on distributed computing | |
| Balaska et al. | Smart counting of unboxed stocks in the Warehouse 4.0 ecosystem | |
| Dong | Design and development of Intelligent Logistics Tracking System based on computer algorithm | |
| US20210366048A1 (en) | Methods and systems for reacting to loss reporting data | |
| CN115518893A (en) | Intelligent logistics cargo sorting system based on data analysis | |
| CN114255377A (en) | Differential commodity detection and classification method for intelligent container | |
| US20240062157A1 (en) | Logistics management system | |
| US20230062764A1 (en) | Method, system and computer program products for management of supply chains and/or inventory for perishable goods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |