CN116757600A - Warehouse abnormal part processing method, device, equipment and storage medium - Google Patents
Warehouse abnormal part processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116757600A CN116757600A CN202310662393.1A CN202310662393A CN116757600A CN 116757600 A CN116757600 A CN 116757600A CN 202310662393 A CN202310662393 A CN 202310662393A CN 116757600 A CN116757600 A CN 116757600A
- Authority
- CN
- China
- Prior art keywords
- warehouse
- video
- abnormal
- rechecking
- numbers
- 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.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 191
- 238000003672 processing method Methods 0.000 title description 3
- 238000001514 detection method Methods 0.000 claims abstract description 79
- 238000000034 method Methods 0.000 claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000012552 review Methods 0.000 claims description 56
- 230000006399 behavior Effects 0.000 claims description 35
- 238000012360 testing method Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 13
- 230000004044 response Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 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
- G06Q10/08—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a method for processing abnormal parts of a warehouse, which comprises the steps of obtaining all bill numbers in a warehouse database and cache videos of warehouse express corresponding to the bill numbers, and rechecking the cache videos by Ffmegs to generate a rechecked video group; training to obtain a target AI reasoning model, and simultaneously matching and binding the bill number and the rechecking video; when the problem of abnormal parts of the warehouse is fed back, matching and rechecking the video according to the number of the abnormal part freight list and marking the video as a detection video; and identifying and detecting an abnormal picture in the video, and acquiring behavior information of warehousing personnel according to the abnormal picture. The method comprises the steps of obtaining a bill number and rechecking video group of a warehouse express, training to obtain a target AI reasoning model, obtaining an abnormal picture when the abnormal part of the warehouse appears, analyzing behavior information of warehouse personnel, further tracking the abnormal part of the warehouse, effectively reducing the occurrence of the conditions of few lost goods, missed forwarding and damaged goods in the warehouse, and guaranteeing normal circulation of the goods in the warehouse by an efficient warehouse abnormal part processing mode.
Description
Technical Field
The invention relates to the technical field of logistics storage, in particular to a method, a device, equipment and a storage medium for processing abnormal parts of a warehouse.
Background
In modern society, along with the development of economy and technology, the express industry gradually becomes an indispensable important industry in people's daily life. Modern people, whether at home or at work, are increasingly dependent on the courier industry. In turn, the development of the express industry has also played a pushing role in economy and technology. From the economic aspect, the development of the express industry enables economic activities to be denser and the efficiency to be higher, and promotes the development of economy; from the technical point of view, the express industry has higher requirements on working efficiency, convenience and safety, has wide requirements on automation and intelligent application, and the application requirements in turn drive the invention and the production of new technologies, thereby promoting the progress of the technologies.
With the scale expansion, the problems of long-term existence in daily operation of warehouses are increasingly remarkable, for example, the warehouses of many e-commerce sellers frequently suffer from the situations of less goods, missed delivery, breakage and the like; the prior art lacks effective commodity tracking ways, so that commodities are difficult to position in time in the warehouse process, follow-up normal circulation is affected, and ageing of abnormal problems in warehouse operation cannot be guaranteed. It can be seen that there is a need for improvements and improvements in the art.
Disclosure of Invention
In view of the shortcomings of the prior art, the invention aims to provide a method, a device, equipment and a storage medium for processing abnormal parts of a warehouse, which are used for acquiring a bill number and a rechecking video group of the warehouse express, inputting the bill number and the rechecking video group into an initial model to train and obtain a target AI reasoning model, rapidly matching the rechecking video and marking a detection video based on the video when the abnormal parts of the warehouse appear, acquiring abnormal pictures from the detection video, analyzing behavior information of warehouse personnel, further tracking the abnormal parts of the warehouse, effectively reducing the occurrence of the conditions of few lost goods, missed delivery and damaged goods in the warehouse, and ensuring normal circulation of goods in the warehouse in an efficient abnormal part processing mode.
In order to achieve the above object, a first aspect of the present invention provides a method for processing abnormal parts in a warehouse, including the steps of: acquiring all the waybill numbers in a warehouse database, wherein the waybill numbers correspond to warehouse express items; obtaining a cache video of a warehouse express corresponding to the waybill number according to the waybill number, and rechecking the cache video by Ffmegs to generate a rechecked video group; inputting the rechecking video group into an inference model to be trained to obtain a target AI (advanced technology attachment) inference model, and deploying the target AI inference model into an AI inference platform; matching and binding a plurality of waybill numbers with a plurality of rechecking videos; when a problem of abnormal parts of the warehouse is fed back, acquiring information of the abnormal parts of the warehouse, wherein the information of the abnormal parts of the warehouse comprises abnormal part shipping list numbers, matching review videos according to the abnormal part shipping list numbers, and marking the matched review videos as detection videos; inputting the detection video into an AI reasoning platform to identify an abnormal picture in the detection video, and acquiring behavior information of warehousing personnel according to the abnormal picture.
Optionally, in a first implementation manner of the first aspect of the present invention, the acquiring all the waybill numbers in the warehouse database, where the waybill numbers correspond to warehouse express items includes: sending an acquisition instruction to a scanning equipment terminal to acquire image information of all warehouse express items; carrying out deformity correction on the image information to obtain a target image; and determining the bill numbers of all warehouse express items according to the target image.
Optionally, in a second implementation manner of the first aspect of the present invention, the obtaining, according to the waybill number, a buffered video of a warehouse express corresponding to the waybill number, and rechecking the buffered video with Ffmpeg to generate a rechecked video group includes: acquiring any waybill number, and judging whether the acquired waybill number accords with a preset waybill number format; if yes, obtaining a cache video of the warehouse express corresponding to the waybill number, and judging whether a time node of the cache video meets a preset time requirement or not; if yes, setting the video quality of the cached video by using Ffmegs algorithm according to the size of the storage available space so as to generate a rechecked video; and repeatedly acquiring the bill numbers until all the bill numbers generate corresponding rechecking videos, and summarizing all the rechecking videos to generate a rechecking video group.
Optionally, in a third implementation manner of the first aspect of the present invention, inputting the review video set into an inference model to be trained to obtain a target AI inference model, and deploying the target AI inference model into an AI inference platform includes: determining the type of the target AI model, and acquiring data resources corresponding to the target AI model according to the type of the target AI model; establishing an initial AI reasoning model based on the data resource, uploading and caching the rechecked video into the initial AI reasoning model; after the initial AI reasoning model is subjected to the rechecking video training reconstruction, a pre-stored test video is obtained to test the initial AI reasoning model, and a target AI reasoning model is obtained; and deploying the target AI reasoning model into an AI reasoning platform.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the matching and binding the plurality of waybill numbers with the plurality of rechecking videos includes: determining the acquisition time of a plurality of waybill numbers and generating a plurality of waybill number scanning time points; extracting a plurality of starting time nodes of the rechecking videos to generate a plurality of starting time points of the rechecking videos; matching the plurality of waybill number scanning time points with the plurality of rechecking video starting time points, and binding the matched plurality of waybill numbers with the rechecking video.
Optionally, in a fifth implementation manner of the first aspect of the present invention, when the problem of the abnormal part of the warehouse is fed back, the abnormal part information of the warehouse is obtained, where the abnormal part information of the warehouse includes an abnormal part bill number, and the matched recheck video is marked as a detection video according to the abnormal part bill number, and includes: acquiring a preset binding rule; when a problem of abnormal parts of the warehouse is fed back, acquiring information of the abnormal parts of the warehouse, wherein the information of the abnormal parts of the warehouse comprises an abnormal part freight list number; quickly positioning the corresponding rechecking video according to the waybill number and the binding rule; marking the review video as a detection video and presenting the entire content of the detection video.
Optionally, in a sixth implementation manner of the first aspect of the present invention, inputting the detection video to the AI reasoning platform to identify an abnormal picture in the detection video, and acquiring behavior information of the warehousing personnel according to the abnormal picture includes: loading the detection video into the AI reasoning platform, determining a target person in the detection video, and predicting the motion trail of the target person; judging whether the actual track of the target person in the detection video is matched with the motion track; if not, intercepting the picture in the detection video and marking the picture as an abnormal picture; and analyzing the abnormal picture to acquire the behavior information of the warehouse personnel.
The second aspect of the present invention provides a warehouse abnormal part handling apparatus, comprising: the system comprises a bill number acquisition module, a bill number generation module and a bill number generation module, wherein the bill number acquisition module is used for acquiring all bill numbers in a warehouse database, and the bill numbers correspond to warehouse express items; the review video group module is used for acquiring review videos of warehouse express corresponding to the waybill number one by adopting an Ffmegs algorithm to generate a review video group; the reasoning model module is used for inputting the rechecking video group into a reasoning model to be trained to obtain a target AI reasoning model, and deploying the target AI reasoning model into an AI reasoning platform; the matching binding module is used for matching and binding the waybill numbers with the rechecking videos; the detection video module is used for acquiring the abnormal part information of the warehouse when the abnormal part problem of the warehouse is fed back, wherein the abnormal part information of the warehouse comprises abnormal part shipping list numbers, the matched rechecking videos are marked as detection videos according to the abnormal part shipping list numbers; and the behavior information module is used for inputting the detection video into the AI reasoning platform so as to identify an abnormal picture in the detection video and acquiring behavior information of warehousing personnel according to the abnormal picture.
Optionally, in a first implementation manner of the second aspect of the present invention, the waybill number obtaining module includes: an image information unit, a target image unit and a waybill number determining unit; the image information unit is used for sending an acquisition instruction to the scanning equipment terminal so as to acquire the image information of all warehouse express items; the target image unit is used for carrying out deformity correction on the image information to obtain a target image; and the waybill number determining unit is used for determining the waybill numbers of all warehouse express items according to the target image.
Optionally, in a second implementation manner of the second aspect of the present invention, the review video group module includes: the system comprises a waybill number format unit, a time requirement judging unit, a video quality setting unit and a rechecking video group unit; the waybill format unit is used for acquiring any waybill number and judging whether the acquired waybill number accords with a preset waybill number format or not; the time requirement judging unit is used for acquiring the cache video of the warehouse express corresponding to the freight list number and judging whether the time node of the cache video accords with the preset time requirement or not if the time node accords with the cache video; the video quality setting unit is used for setting the video quality of the cache video by using an Ffmegs algorithm according to the size of the storage available space if the video quality is in line with the storage available space so as to generate a rechecking video; the review video group unit is used for repeatedly acquiring the bill numbers until all the bill numbers generate corresponding review videos, and summarizing all the review videos to generate a review video group.
Optionally, in a third implementation manner of the second aspect of the present invention, the inference model module includes: the system comprises a data resource acquisition unit, an initial AI reasoning model unit, a target AI reasoning model unit and a model deployment unit; the data resource acquisition unit is used for determining the type of the target AI model and acquiring data resources corresponding to the target AI model according to the type of the target AI model; the initial AI reasoning model unit is used for establishing an initial AI reasoning model based on the data resource, uploading the rechecked video and caching the rechecked video into the initial AI reasoning model; the target AI reasoning model unit is used for acquiring a pre-stored test video to test the initial AI reasoning model after the initial AI reasoning model is subjected to the rechecking video training reconstruction to obtain a target AI reasoning model; the model deployment unit is used for deploying the target AI reasoning model into an AI reasoning platform.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the matching binding module includes: a scanning time point unit, a starting time point unit, and a matching binding unit; the scanning time point unit is used for determining the acquisition time of a plurality of waybill numbers and generating a plurality of waybill number scanning time points; the starting time point unit is used for extracting a plurality of starting time nodes of the rechecking videos and generating a plurality of rechecking video starting time points; the matching binding unit is used for matching the plurality of waybill number scanning time points with the plurality of rechecking video starting time points and binding the plurality of waybill numbers which are matched with the rechecking video.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the detecting video module includes: binding a rule unit, a warehouse abnormal part information unit, a rechecking video positioning unit and a detection video unit; the binding rule unit is used for acquiring a preset binding rule; the abnormal warehouse part information unit is used for acquiring abnormal warehouse part information when the abnormal warehouse part problem is fed back, wherein the abnormal warehouse part information comprises abnormal part freight list numbers; the rechecking video positioning is used for rapidly positioning the corresponding rechecking video according to the waybill number and the binding rule; the detection video unit is used for marking the rechecking video as the detection video and presenting the whole content of the detection video.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the behavior information module includes: the system comprises a motion trail prediction unit, a motion trail matching unit, an abnormal picture unit and a behavior information unit; the motion trail prediction unit is used for loading the detection video into the AI reasoning platform, determining a target person in the detection video and predicting the motion trail of the target person; the motion trail matching unit is used for judging whether the actual trail of the target person in the detection video is matched with the motion trail; the abnormal picture unit is used for intercepting pictures in the detection video and marking the pictures as abnormal pictures if not; the behavior information unit is used for analyzing the abnormal picture to acquire behavior information of warehouse personnel.
A third aspect of the present invention provides a warehouse anomaly handling device comprising a memory and at least one processor, the memory having computer readable instructions stored therein; the at least one processor invokes the computer readable instructions in the memory to perform the steps of the warehouse anomaly handling method as described above.
A fourth aspect of the present invention provides a computer readable storage medium having stored thereon computer readable instructions which when executed by a processor perform the steps of a warehouse anomaly handling method as described above.
As described above, the warehouse abnormal part processing method has the following beneficial effects: the method comprises the steps of obtaining a bill number and a rechecking video group of a warehouse express, inputting the bill number and the rechecking video group into an initial model to train to obtain a target AI reasoning model, rapidly matching the rechecking video and marking a detection video based on the rapid matching rechecking video when the abnormal warehouse express appears, obtaining abnormal pictures from the detection video, analyzing behavior information of warehouse personnel, further tracking the abnormal warehouse express, effectively reducing the occurrence of the conditions of few lost goods, missed delivery and damaged goods in the warehouse, and guaranteeing normal circulation of goods in the warehouse in an efficient abnormal warehouse express processing mode.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for processing abnormal parts in a warehouse;
FIG. 2 is a flowchart of another method of the warehouse exception handling method provided by the present invention;
FIG. 3 is a flowchart of another method of the warehouse exception handling method provided by the present invention;
FIG. 4 is a flowchart of another method of the warehouse exception handling method provided by the present invention;
FIG. 5 is a flowchart of another method of the method for processing abnormal parts in a warehouse provided by the invention;
FIG. 6 is a flowchart of another method of the warehouse exception handling method provided by the present invention;
FIG. 7 is a flowchart of another method of the method for processing abnormal parts in a warehouse according to the present invention;
FIG. 8 is a block diagram of a warehouse exception handling device according to the present invention;
FIG. 9 is another architecture diagram of a warehouse anomaly handling device provided by the present invention;
fig. 10 is a schematic diagram of a warehouse abnormal part processing device provided by the invention.
Detailed Description
The invention provides a method, a device, equipment and a storage medium for processing abnormal parts of a warehouse, which are used for acquiring a bill number and a rechecking video group of the warehouse express, inputting the bill number and the rechecking video group into an initial model to train and obtain a target AI reasoning model, rapidly matching the rechecking video and marking a detection video based on the rechecking video when the abnormal parts of the warehouse appear, acquiring an abnormal picture from the detection video, analyzing behavior information of warehousing personnel, further tracking the abnormal parts of the warehouse, effectively reducing the occurrence of the conditions of few lost goods, missed delivery and damaged goods of the warehouse, and ensuring the normal circulation of the goods in the warehouse in an efficient abnormal part processing mode. In order to make the objects, technical solutions and effects of the present invention clearer and more specific, the present invention will be described in further detail below with reference to the accompanying drawings and examples.
In the description of the present invention, it should be understood that the azimuth or positional relationship indicated by the terms "up, down, left, right", etc. are based on the azimuth or positional relationship shown in the drawings, and are merely for convenience in describing the present invention and for simplifying the description, and are not to be construed as limiting the present invention; furthermore, the terms "mounted," "connected," and the like, are to be construed broadly and, as appropriate, the specific meaning of the terms in the present invention will be understood by those of ordinary skill in the art.
Referring to fig. 1, the invention provides a method for processing abnormal parts in a warehouse, comprising the following steps:
101. acquiring all the waybill numbers in a warehouse database, wherein the waybill numbers correspond to warehouse express items;
in the embodiment, all the bill numbers are acquired through the warehouse database, so that all the bill numbers can be stably and completely acquired, the integrity of the bill numbers is ensured, each bill number is matched and corresponds to a warehouse express, the first warehouse express inventory is completed, and the warehouse state of the warehouse express inventory is timely updated.
102. Obtaining a cache video of a warehouse express corresponding to the waybill number according to the waybill number, and rechecking the cache video by Ffmegs to generate a rechecked video group;
In the embodiment, a ffmpeg technology is adopted, a list number and a corresponding cache video are bound, a file index path is generated, and the list number and the cache video are stored in a database according to the file index path; preferably, all the cached videos are reviewed and the review video group is generated.
103. Inputting the rechecking video group into an inference model to be trained to obtain a target AI (advanced technology attachment) inference model, and deploying the target AI inference model into an AI inference platform;
the method comprises the steps that an inference model to be trained is generated by data resources of a warehouse to obtain a target AI inference model based on warehouse requirements, and in the actual use process, the target AI inference model can rapidly check a rechecking video group, and specific images and pictures are obtained from the rechecking video group.
104. Matching and binding a plurality of waybill numbers with a plurality of rechecking videos;
the plurality of bill numbers and the plurality of review videos are matched and bound, and warehouse express items can be further checked in the matching process; after the matching binding is completed, the composite video or the bill number corresponding to the warehouse express can be quickly searched by reading the bill number or the rechecking video of the warehouse express.
105. When a problem of abnormal parts of the warehouse is fed back, acquiring information of the abnormal parts of the warehouse, wherein the information of the abnormal parts of the warehouse comprises abnormal part shipping list numbers, matching review videos according to the abnormal part shipping list numbers, and marking the matched review videos as detection videos;
when a warehouse abnormal part appears, the corresponding rechecking video can be quickly obtained by the bill number of the warehouse abnormal part, and the method has the advantage of short response time; in this embodiment, the review video is marked as a detection video, so that the detection video and the review video form a distinct distinction, and extraction of the detection video and the review video is facilitated.
106. Inputting the detection video into an AI reasoning platform to identify an abnormal picture in the detection video, and acquiring behavior information of warehousing personnel according to the abnormal picture.
The abnormal picture of the detection video is intercepted in the AI reasoning platform, the behavior information of the warehouse personnel can be obtained through analysis of the abnormal picture, the abnormal part of the warehouse can be conveniently inferred and tracked, and the accurately intercepted abnormal picture on the AI reasoning platform is beneficial to accurately analyzing the behavior information of the warehouse personnel.
Referring to fig. 2, in a first implementation manner of a method for processing abnormal parts in a warehouse according to an embodiment of the present invention, the method for obtaining all the waybill numbers in a warehouse database, where the waybill numbers correspond to warehouse express parts includes:
201. Sending an acquisition instruction to a scanning equipment terminal to acquire image information of all warehouse express items;
optionally, an acquisition instruction is sent to the code scanning gun or other code scanning equipment, the bar code or the two-dimensional code on each cargo is scanned through the code scanning gun or other code scanning equipment, the bar code or the two-dimensional code is compared with information on a warehouse outlet bill, the number and the state of the cargo are automatically identified and recorded, and meanwhile data interaction is carried out with a warehouse management system.
202. Carrying out deformity correction on the image information to obtain a target image;
optionally, the selected camera is installed above the workbench, a proper camera angle is selected according to the field of view range and illumination condition of the monitoring target, configuration and strategy of the camera are optimized, parameters such as working mode, triggering condition, storage mode and analysis method of the camera are set according to requirements and functions of the WMS system, and data interaction and instruction issuing are carried out with the WMS system.
203. And determining the bill numbers of all warehouse express items according to the target image.
And positioning a bar code, a two-dimensional code or a waybill number area on each target image, focusing the area to acquire the waybill number, and improving the acquisition speed of the waybill number.
Referring to fig. 3, in a second implementation manner of a method for processing abnormal parts in a warehouse according to an embodiment of the present invention, the method for obtaining a buffered video of a warehouse express corresponding to a waybill number according to the waybill number, and rechecking the buffered video by using Ffmpeg to generate a rechecked video group includes:
301. acquiring any waybill number, and judging whether the acquired waybill number accords with a preset waybill number format;
in this embodiment, the waybill format is preset and stored in the server, and preferably, the acquired waybill number is compared with the preset waybill format, and when the acquired waybill number accords with the preset waybill format, the acquired waybill number is judged to be correct.
302. If yes, obtaining a cache video of the warehouse express corresponding to the waybill number, and judging whether a time node of the cache video meets a preset time requirement or not; 303. if yes, setting the video quality of the cached video by using Ffmegs algorithm according to the size of the storage available space so as to generate a rechecked video;
the determined waybill number is used for quickly judging and generating a corresponding rechecking video, and in the embodiment, the Ffmteg algorithm can modify the format, the picture and the video frame of the rechecking video.
304. And repeatedly acquiring the bill numbers until all the bill numbers generate corresponding rechecking videos, and summarizing all the rechecking videos to generate a rechecking video group.
Summarizing the recheck videos corresponding to all the waybill numbers to obtain a recheck video group, so that data arrangement and collection of all warehouse express items in the warehouse are facilitated, and omission of the waybill numbers or the cache videos is avoided through standard data sampling.
Referring to fig. 4, in a third implementation manner of a method for processing abnormal parts in a warehouse in an embodiment of the present invention, inputting the review video set into an inference model to be trained to obtain a target AI inference model, and deploying the target AI inference model into an AI inference platform, where the method includes:
401. determining the type of the target AI model, and acquiring data resources corresponding to the target AI model according to the type of the target AI model; 402. establishing an initial AI reasoning model based on the data resource, uploading and caching the rechecked video into the initial AI reasoning model; 403. after the initial AI reasoning model is subjected to the rechecking video training reconstruction, a pre-stored test video is obtained to test the initial AI reasoning model, and a target AI reasoning model is obtained; 404. and deploying the target AI reasoning model into an AI reasoning platform.
The target AI model through rechecking video training and testing video testing has higher reasoning precision and response speed, can be compatible with various storage models in the storage process, and meets the use requirements of various storage types.
Referring to fig. 5, in a fourth implementation manner of a method for processing abnormal parts in a warehouse according to an embodiment of the present invention, the matching and binding a plurality of waybill numbers with a plurality of rechecking videos includes:
501. determining the acquisition time of a plurality of waybill numbers and generating a plurality of waybill number scanning time points; 502. extracting a plurality of starting time nodes of the rechecking videos to generate a plurality of starting time points of the rechecking videos;
the method has the advantages that the scanning time of the bill number and the rechecking video starting time node are respectively used as the reference, the information of each warehouse express is corresponding, the operation is simple and convenient, the operation errors can be reduced in the actual operation process, and the operation accuracy is improved.
503. Matching the plurality of waybill number scanning time points with the plurality of rechecking video starting time points, and binding the matched plurality of waybill numbers with the rechecking video.
By using the scanning time of the bill number and the rechecking video start time node as the reference, the unique identification is matched for each warehouse express item in the time dimension, the marking operation is simplified, and the operation on each warehouse express item can be reduced.
Referring to fig. 6, in a fifth implementation manner of a method for processing abnormal parts in a warehouse according to an embodiment of the present invention, when a problem of abnormal parts in the warehouse is fed back, abnormal part information of the warehouse is obtained, the abnormal part information includes abnormal part shipping numbers, and matching review videos according to the abnormal part shipping numbers, and marking the matched review videos as detection videos includes:
601. acquiring a preset binding rule; 602. when a problem of abnormal parts of the warehouse is fed back, acquiring information of the abnormal parts of the warehouse, wherein the information of the abnormal parts of the warehouse comprises an abnormal part freight list number; 603. quickly positioning the corresponding rechecking video according to the waybill number and the binding rule; 604. marking the review video as a detection video and presenting the entire content of the detection video.
The abnormal parts of the warehouse are reversely tracked according to preset binding rules, and when the bill numbers of the abnormal parts of the warehouse are acquired, the corresponding rechecking videos are immediately positioned, so that the response waiting time is shortened, and the running efficiency is ensured.
Referring to fig. 7, in a sixth implementation manner of a method for processing abnormal parts in a warehouse according to an embodiment of the present invention, the inputting a detection video into an AI reasoning platform to identify an abnormal picture in the detection video, and obtaining behavior information of a warehouse personnel according to the abnormal picture includes:
701. Loading the detection video into the AI reasoning platform, determining a target person in the detection video, and predicting the motion trail of the target person; 702. judging whether the actual track of the target person in the detection video is matched with the motion track;
in this embodiment, each operation of the stocker is performed according to an operation specification, so each process can form a corresponding motion track, and whether the current frame is an abnormal frame can be determined by determining whether the actual track of the stocker matches with the motion track.
703. If not, intercepting the picture in the detection video and marking the picture as an abnormal picture; 704. and analyzing the abnormal picture to acquire the behavior information of the warehouse personnel.
And intercepting a specific abnormal picture from the cached video with the specified duration, and analyzing the behavior information of the warehousing personnel by the determined abnormal picture, namely accurately judging the behavior of the warehousing personnel only through the abnormal picture with less information quantity, thereby greatly reducing the operation quantity.
The method for processing the abnormal parts in the warehouse in the embodiment of the present invention is described above, and the device for processing the abnormal parts in the warehouse in the embodiment of the present invention is described below, referring to fig. 8 and fig. 9, where an implementation manner of the device for processing the abnormal parts in the embodiment of the present invention includes: the freight list number acquisition module 801 is configured to acquire all freight list numbers in a warehouse database, where the freight list numbers correspond to warehouse express items; in the embodiment, all the bill numbers are acquired through the warehouse database, so that all the bill numbers can be stably and completely acquired, the integrity of the bill numbers is ensured, each bill number is matched and corresponds to a warehouse express, the first warehouse express inventory is completed, and the warehouse state of the warehouse express inventory is timely updated.
The review video group module 802 is configured to acquire review videos of warehouse express corresponding to the waybill number one by adopting an Ffmpeg algorithm, and generate a review video group; in the embodiment, a ffmpeg technology is adopted, a list number and a corresponding cache video are bound, a file index path is generated, and the list number and the cache video are stored in a database according to the file index path; preferably, all the cached videos are reviewed and the review video group is generated.
The reasoning model module 803 is configured to input the review video set into a reasoning model to be trained, obtain a target AI reasoning model, and deploy the target AI reasoning model into an AI reasoning platform; the method comprises the steps that an inference model to be trained is generated by data resources of a warehouse to obtain a target AI inference model based on warehouse requirements, and in the actual use process, the target AI inference model can rapidly check a rechecking video group, and specific images and pictures are obtained from the rechecking video group.
A matching binding module 804, configured to match and bind the plurality of waybill numbers with the plurality of review videos; the plurality of bill numbers and the plurality of review videos are matched and bound, and warehouse express items can be further checked in the matching process; after the matching binding is completed, the composite video or the bill number corresponding to the warehouse express can be quickly searched by reading the bill number or the rechecking video of the warehouse express.
The detection video module 805 is configured to obtain, when a problem of a warehouse abnormal part is fed back, information of the warehouse abnormal part, where the information of the warehouse abnormal part includes an abnormal part shipping list number, match a review video according to the abnormal part shipping list number, and mark the matched review video as a detection video; when a warehouse abnormal part appears, the corresponding rechecking video can be quickly obtained by the bill number of the warehouse abnormal part, and the method has the advantage of short response time; in this embodiment, the review video is marked as a detection video, so that the detection video and the review video form a distinct distinction, and extraction of the detection video and the review video is facilitated.
The behavior information module 806 is configured to input the detection video to the AI reasoning platform, so as to identify an abnormal picture in the detection video, and obtain behavior information of the warehousing personnel according to the abnormal picture. The abnormal picture of the detection video is intercepted in the AI reasoning platform, the behavior information of the warehouse personnel can be obtained through analysis of the abnormal picture, the abnormal part of the warehouse can be conveniently inferred and tracked, and the accurately intercepted abnormal picture on the AI reasoning platform is beneficial to accurately analyzing the behavior information of the warehouse personnel.
Optionally, in a first implementation manner of the device for processing abnormal parts in a warehouse in this embodiment of the present invention, the waybill number obtaining module 801 includes: an image information unit 8011, a target image unit 8012, and a waybill number determination unit 8013; the image information unit 8011 is configured to send an acquisition instruction to a scanning device terminal, so as to acquire image information of all warehouse express items; optionally, an acquisition instruction is sent to the code scanning gun or other code scanning equipment, the bar code or the two-dimensional code on each cargo is scanned through the code scanning gun or other code scanning equipment, the bar code or the two-dimensional code is compared with information on a warehouse outlet bill, the number and the state of the cargo are automatically identified and recorded, and meanwhile data interaction is carried out with a warehouse management system. The target image unit 8012 is configured to perform deformity correction on the image information, and obtain a target image; optionally, the selected camera is installed above the workbench, a proper camera angle is selected according to the field of view range and illumination condition of the monitoring target, configuration and strategy of the camera are optimized, parameters such as working mode, triggering condition, storage mode and analysis method of the camera are set according to requirements and functions of the WMS system, and data interaction and instruction issuing are carried out with the WMS system. The waybill number determining unit 8013 is configured to determine the waybill numbers of all warehouse express items according to the target image. And positioning a bar code, a two-dimensional code or a waybill number area on each target image, focusing the area to acquire the waybill number, and improving the acquisition speed of the waybill number.
Optionally, in a second implementation manner of the device for processing abnormal parts in a warehouse in this embodiment of the present invention, the review video group module 802 includes: a waybill number format unit 8021, a time requirement judging unit 8022, a video quality setting unit 8023 and a review video group unit 8024; the waybill format unit 8021 is configured to obtain any waybill number, and determine whether the obtained waybill number accords with a preset waybill number format; in this embodiment, the waybill format is preset and stored in the server, and preferably, the acquired waybill number is compared with the preset waybill format, and when the acquired waybill number accords with the preset waybill format, the acquired waybill number is judged to be correct. The time requirement judging unit 8022 is configured to obtain a buffered video of a warehouse express corresponding to a waybill number if the time requirement is met, and judge whether a time node of the buffered video meets a preset time requirement; the video quality setting unit 8023 is configured to set, if the video quality is met, the video quality of the buffered video by using an Ffmpeg algorithm according to the size of the storage available space, so as to generate a review video; the determined waybill number is used for quickly judging and generating a corresponding rechecking video, and in the embodiment, the Ffmteg algorithm can modify the format, the picture and the video frame of the rechecking video. The review video group unit 8024 is configured to repeatedly obtain the order numbers until all the order numbers generate corresponding review videos, and aggregate all the review videos to generate a review video group. Summarizing the recheck videos corresponding to all the waybill numbers to obtain a recheck video group, so that data arrangement and collection of all warehouse express items in the warehouse are facilitated, and omission of the waybill numbers or the cache videos is avoided through standard data sampling.
Optionally, in a third implementation manner of the device for processing abnormal parts in a warehouse in an embodiment of the present invention, the inference model module 803 includes: a data resource acquisition unit 8031, an initial AI reasoning model unit 8032, a target AI reasoning model unit 8033, and a model deployment unit 8034; the data resource obtaining unit 8031 is configured to determine a type of the target AI model, and obtain a data resource corresponding to the target AI model according to the type of the target AI model; the initial AI reasoning model unit 8032 is configured to establish an initial AI reasoning model based on the data resource, upload the review video, and cache the review video into the initial AI reasoning model; the target AI reasoning model unit 8033 is configured to obtain a pre-stored test video to test the initial AI reasoning model after the initial AI reasoning model is subjected to the rechecking video training reconstruction, so as to obtain a target AI reasoning model; the model deployment unit 8034 is configured to deploy the target AI reasoning model into an AI reasoning platform. The target AI model through rechecking video training and testing video testing has higher reasoning precision and response speed, can be compatible with various storage models in the storage process, and meets the use requirements of various storage types.
Optionally, in a fourth implementation manner of the device for processing abnormal parts in a warehouse in this embodiment of the present invention, the matching binding module 804 includes: a scanning time point unit 8041, a start time point unit 8042, and a matching binding unit 8043; the scanning time point unit 8041 is configured to determine acquisition times of a plurality of waybill numbers, and generate a plurality of waybill number scanning time points; the starting time point unit 8042 is configured to extract a plurality of starting time nodes of the review video, and generate a plurality of review video starting time points; the method has the advantages that the scanning time of the bill number and the rechecking video starting time node are respectively used as the reference, the information of each warehouse express is corresponding, the operation is simple and convenient, the operation errors can be reduced in the actual operation process, and the operation accuracy is improved. The matching binding unit 8043 is configured to match a plurality of waybill number scanning time points with a plurality of rechecking video start time points, and bind a plurality of waybill numbers that are matched with the rechecking video. By using the scanning time of the bill number and the rechecking video start time node as the reference, the unique identification is matched for each warehouse express item in the time dimension, the marking operation is simplified, and the operation on each warehouse express item can be reduced.
Optionally, in a fifth implementation manner of the warehouse abnormal part processing device in the embodiment of the present invention, the detecting video module 805 includes: a binding rule unit 8051, a warehouse abnormal piece information unit 8052, a review video positioning unit 8053 and a detection video unit 8054; the binding rule unit 8051 is configured to obtain a preset binding rule;
the abnormal warehouse part information unit 8052 is configured to obtain abnormal warehouse part information when a problem of abnormal warehouse parts is fed back, where the abnormal warehouse part information includes an abnormal part freight list number; the rechecking video positioning 8053 is used for rapidly positioning the corresponding rechecking video according to the waybill number and the binding rule; the detection video unit 8054 is configured to mark the review video as a detection video, and present the entire content of the detection video. The abnormal parts of the warehouse are reversely tracked according to preset binding rules, and when the bill numbers of the abnormal parts of the warehouse are acquired, the corresponding rechecking videos are immediately positioned, so that the response waiting time is shortened, and the running efficiency is ensured.
Optionally, in a sixth implementation manner of the device for processing abnormal parts in a warehouse in this embodiment of the present invention, the behavior information module 806 includes: a motion trajectory prediction unit 8061, a motion trajectory matching unit 8062, an abnormal picture unit 8063, and a behavior information unit 8064; the motion trail prediction unit 8061 is configured to load the detection video into the AI inference platform, determine a target person in the detection video, and predict a motion trail of the target person; in this embodiment, each operation of the stocker is performed according to an operation specification, so each process can form a corresponding motion track, and whether the current frame is an abnormal frame can be determined by determining whether the actual track of the stocker matches with the motion track. The motion trail matching unit 8062 is configured to determine whether an actual trail of the target person in the detected video is matched with the motion trail; the abnormal picture unit 8063 is configured to intercept a picture in the detected video and mark the picture as an abnormal picture if not; the behavior information unit 8064 is configured to analyze the abnormal image, so as to obtain behavior information of the warehousing personnel. And intercepting a specific abnormal picture from the cached video with the specified duration, and analyzing the behavior information of the warehousing personnel by the determined abnormal picture, namely accurately judging the behavior of the warehousing personnel only through the abnormal picture with less information quantity, thereby greatly reducing the operation quantity.
Fig. 8 and fig. 9 are a detailed description of the device for processing a warehouse abnormal part in the embodiment of the present invention from the point of view of modularized functional entities, and a detailed description of the device for processing a warehouse abnormal part in the embodiment of the present invention from the point of view of hardware processing.
Fig. 10 is a schematic structural diagram of a warehouse anomaly handling device according to an embodiment of the present invention, where the device 900 may vary considerably in configuration or performance, and may include one or more processors (centra lprocess ing un its, CPU) 910 (e.g., one or more processors) and memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) storing applications 933 or data 932. Wherein the memory 920 and storage medium 930 may be transitory or persistent storage. The program stored on the storage medium 930 may include one or more modules (not shown), each of which may include a series of instruction operations in the device 900. Still further, the processor 910 may be configured to communicate with a storage medium 930 to execute a series of instruction operations in the storage medium on the device 900.
The device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input/output interfaces 960, and/or one or more operating systems 931, such as Windows Serve, mac OS X, un ix, linux, freeBSD, and the like.
The embodiment of the invention also provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium, and can also be a volatile computer readable storage medium, wherein instructions are stored in the computer readable storage medium, and when the instructions run on a computer, the instructions cause the computer to execute the steps of the method for processing abnormal parts in a warehouse.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system or apparatus and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
If implemented as a software functional unit and sold or used as a stand-alone product, or that contributes to the prior art, or that all or part of the technical solution may be embodied in the form of a software product stored in a storage medium comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In summary, the method, the device, the equipment and the storage medium for processing the abnormal parts of the warehouse acquire the order numbers and the rechecking video groups of the warehouse express, input the order numbers and the rechecking video groups into the initial model to train and obtain the target AI reasoning model, rapidly match the rechecking video and mark the detection video based on the rechecking video when the abnormal parts of the warehouse appear, acquire abnormal pictures from the detection video, analyze behavior information of warehouse personnel, track the abnormal parts of the warehouse, effectively reduce the occurrence of the conditions of few lost goods, missed delivery and damaged goods of the warehouse, and ensure the normal circulation of the goods in the warehouse in an efficient abnormal part processing mode. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
It will be understood that equivalents and modifications will occur to those skilled in the art based on the present invention and its spirit, and all such modifications and substitutions are intended to be included within the scope of the present invention.
Claims (10)
1. The method for processing the abnormal parts of the warehouse is characterized by comprising the following steps of:
acquiring all the waybill numbers in a warehouse database, wherein the waybill numbers correspond to warehouse express items;
Obtaining a cache video of a warehouse express corresponding to the waybill number according to the waybill number, and rechecking the cache video by Ffmegs to generate a rechecked video group;
inputting the rechecking video group into an inference model to be trained to obtain a target AI (advanced technology attachment) inference model, and deploying the target AI inference model into an AI inference platform;
matching and binding a plurality of waybill numbers with a plurality of rechecking videos;
when a problem of abnormal parts of the warehouse is fed back, acquiring information of the abnormal parts of the warehouse, wherein the information of the abnormal parts of the warehouse comprises abnormal part shipping list numbers, matching review videos according to the abnormal part shipping list numbers, and marking the matched review videos as detection videos;
inputting the detection video into an AI reasoning platform to identify an abnormal picture in the detection video, and acquiring behavior information of warehousing personnel according to the abnormal picture.
2. The method for processing abnormal parts of warehouse according to claim 1, wherein the step of obtaining all the waybill numbers in the warehouse database, the waybill numbers corresponding to the warehouse express parts, comprises:
sending an acquisition instruction to a scanning equipment terminal to acquire image information of all warehouse express items;
carrying out deformity correction on the image information to obtain a target image;
And determining the bill numbers of all warehouse express items according to the target image.
3. The method for processing abnormal parts of warehouse of claim 1, wherein the obtaining the buffered video of the warehouse express corresponding to the waybill number according to the waybill number and rechecking the buffered video by using Ffmpeg to generate a rechecked video group comprises:
acquiring any waybill number, and judging whether the acquired waybill number accords with a preset waybill number format;
if yes, obtaining a cache video of the warehouse express corresponding to the waybill number, and judging whether a time node of the cache video meets a preset time requirement or not;
if yes, setting the video quality of the cached video by using Ffmegs algorithm according to the size of the storage available space so as to generate a rechecked video;
and repeatedly acquiring the bill numbers until all the bill numbers generate corresponding rechecking videos, and summarizing all the rechecking videos to generate a rechecking video group.
4. The method for processing abnormal parts in warehouse of claim 1, wherein the inputting the rechecking video group into the inference model to be trained to obtain the target AI inference model, and deploying the target AI inference model into the AI inference platform, comprises:
Determining the type of the target AI model, and acquiring data resources corresponding to the target AI model according to the type of the target AI model;
establishing an initial AI reasoning model based on the data resource, uploading and caching the rechecked video into the initial AI reasoning model;
after the initial AI reasoning model is subjected to the rechecking video training reconstruction, a pre-stored test video is obtained to test the initial AI reasoning model, and a target AI reasoning model is obtained;
and deploying the target AI reasoning model into an AI reasoning platform.
5. The method for processing abnormal parts in warehouse of claim 1, wherein the matching and binding the plurality of waybill numbers and the plurality of rechecking videos comprises:
determining the acquisition time of a plurality of waybill numbers and generating a plurality of waybill number scanning time points;
extracting a plurality of starting time nodes of the rechecking videos to generate a plurality of starting time points of the rechecking videos;
matching the plurality of waybill number scanning time points with the plurality of rechecking video starting time points, and binding the matched plurality of waybill numbers with the rechecking video.
6. The method for processing abnormal parts of a warehouse according to claim 1, wherein when a problem of abnormal parts of the warehouse is fed back, information of abnormal parts of the warehouse is obtained, the information of abnormal parts of the warehouse includes abnormal part bill numbers, the review videos are matched according to the abnormal part bill numbers, and the matched review videos are marked as detection videos, and the method comprises the steps of:
Acquiring a preset binding rule;
when a problem of abnormal parts of the warehouse is fed back, acquiring information of the abnormal parts of the warehouse, wherein the information of the abnormal parts of the warehouse comprises an abnormal part freight list number;
quickly positioning the corresponding rechecking video according to the waybill number and the binding rule;
marking the review video as a detection video and presenting the entire content of the detection video.
7. The method for processing abnormal parts in warehouse according to claim 1, wherein the inputting the detection video into the AI inference platform to identify an abnormal picture in the detection video, and acquiring the behavior information of the warehouse personnel according to the abnormal picture comprises:
loading the detection video into the AI reasoning platform, determining a target person in the detection video, and predicting the motion trail of the target person;
judging whether the actual track of the target person in the detection video is matched with the motion track;
if not, intercepting the picture in the detection video and marking the picture as an abnormal picture;
and analyzing the abnormal picture to acquire the behavior information of the warehouse personnel.
8. A warehouse abnormal part handling device, comprising:
the system comprises a bill number acquisition module, a bill number generation module and a bill number generation module, wherein the bill number acquisition module is used for acquiring all bill numbers in a warehouse database, and the bill numbers correspond to warehouse express items;
The review video group module is used for acquiring review videos of warehouse express corresponding to the waybill number one by adopting an Ffmegs algorithm to generate a review video group;
the reasoning model module is used for inputting the rechecking video group into a reasoning model to be trained to obtain a target AI reasoning model, and deploying the target AI reasoning model into an AI reasoning platform;
the matching binding module is used for matching and binding the waybill numbers with the rechecking videos;
the detection video module is used for acquiring the abnormal part information of the warehouse when the abnormal part problem of the warehouse is fed back, wherein the abnormal part information of the warehouse comprises abnormal part shipping list numbers, the matched rechecking videos are marked as detection videos according to the abnormal part shipping list numbers;
and the behavior information module is used for inputting the detection video into the AI reasoning platform so as to identify an abnormal picture in the detection video and acquiring behavior information of warehousing personnel according to the abnormal picture.
9. A warehouse anomaly handling device comprising a memory and at least one processor, the memory having computer readable instructions stored therein;
the at least one processor invoking the computer readable instructions in the memory to perform the steps of the warehouse anomaly handling method of any one of claims 1-7.
10. A computer readable storage medium having computer readable instructions stored thereon, which when executed by a processor, perform the steps of the warehouse anomaly handling method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310662393.1A CN116757600A (en) | 2023-06-05 | 2023-06-05 | Warehouse abnormal part processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310662393.1A CN116757600A (en) | 2023-06-05 | 2023-06-05 | Warehouse abnormal part processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116757600A true CN116757600A (en) | 2023-09-15 |
Family
ID=87952541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310662393.1A Pending CN116757600A (en) | 2023-06-05 | 2023-06-05 | Warehouse abnormal part processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116757600A (en) |
-
2023
- 2023-06-05 CN CN202310662393.1A patent/CN116757600A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20090164305A1 (en) | System and method for managing product quality | |
| CN110705666A (en) | Artificial intelligence cloud computing display rack goods and label monitoring and goods storage method | |
| CN111507147A (en) | Intelligent inspection method and device, computer equipment and storage medium | |
| CN111967322B (en) | Data processing method, device, electronic equipment and storage medium | |
| US11409888B2 (en) | Security information processing device, information processing method, and recording medium | |
| CN108830833B (en) | Online evaluation method of workpiece identification project, server and terminal | |
| CN115632966A (en) | Automatic operation and maintenance method of Internet of things equipment based on cloud computing | |
| CN114444997A (en) | Intelligent warehousing system based on supply chain management | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| Trajkova et al. | Active learning for automated visual inspection of manufactured products | |
| CN112965852A (en) | Error positioning method and device based on log analysis | |
| CN115660610B (en) | Decentralized cooperative office system and method | |
| CN116757600A (en) | Warehouse abnormal part processing method, device, equipment and storage medium | |
| CN112347131A (en) | Urban rail project demand identification and coverage method and device | |
| CN110223015B (en) | Logistics process link processing method, management system, device and storage equipment | |
| CN115168509A (en) | Processing method and device of wind control data, storage medium and computer equipment | |
| CN109919543A (en) | A kind of method and apparatus of monitoring waste processing | |
| CN115660540A (en) | Cargo tracking method, cargo tracking device, computer equipment and storage medium | |
| CN110968779A (en) | Processing method and device for crawling webpage information | |
| CN114139853A (en) | Steel structure product list processing method and device based on big data | |
| CN110717131B (en) | Page revising monitoring method and related system | |
| CN109857818B (en) | Method and device for determining production relation, storage medium and electronic equipment | |
| CN108197882B (en) | Warehouse management system | |
| CN112184108A (en) | Tool management method and system | |
| CN112612882B (en) | Review report generation method, device, equipment and storage medium |
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 |