CN117635004A - Logistics problem piece processing method, device, equipment and storage medium - Google Patents
Logistics problem piece processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117635004A CN117635004A CN202311696689.1A CN202311696689A CN117635004A CN 117635004 A CN117635004 A CN 117635004A CN 202311696689 A CN202311696689 A CN 202311696689A CN 117635004 A CN117635004 A CN 117635004A
- Authority
- CN
- China
- Prior art keywords
- logistics
- model
- current
- express
- task
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000012384 transportation and delivery Methods 0.000 claims abstract description 31
- 230000002776 aggregation Effects 0.000 claims description 19
- 238000004220 aggregation Methods 0.000 claims description 19
- 238000007689 inspection Methods 0.000 claims description 18
- 238000012795 verification Methods 0.000 claims description 10
- 230000004931 aggregating effect Effects 0.000 claims description 7
- 230000000379 polymerizing effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 22
- 238000007726 management method Methods 0.000 abstract description 10
- 238000012360 testing method Methods 0.000 description 16
- 238000012216 screening Methods 0.000 description 14
- 238000009826 distribution Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 239000011265 semifinished product Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent 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
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of logistics management and discloses a method, a device, equipment and a storage medium for processing logistics problem pieces. The method comprises the following steps: acquiring current logistics data of a current express, judging whether the current express is a problem piece to be signed, and if so, generating a checking and accepting task; acquiring a historical logistics data set of a local express item according to a checking and accepting task, and training a global model to obtain a logistics track prediction model; inputting current logistics data into a logistics track prediction model to obtain a logistics track prediction result; judging whether the current express arrives at the terminal dispatch network point, if so, informing the terminal dispatch network point to carry out the acceptance checking treatment on the current express according to the acceptance checking task. According to the logistics problem piece processing method, when the express delivery is judged to be the problem piece for signing in, the express delivery position is determined through the logistics track prediction model and is issued in time, and the website is prompted to process the problem piece, so that the logistics problem piece solving efficiency is effectively improved.
Description
Technical Field
The present invention relates to the field of logistics management technologies, and in particular, to a method, an apparatus, a device, and a storage medium for processing a logistics problem piece.
Background
In the intelligent logistics technical process based on the Internet of things, the intelligent terminal acquires various attribute information of the commodity by using sensing technologies such as Radio Frequency Identification (RFID) technology, X-ray induction, laser scanning and the like, and transmits the information to the intelligent data center through communication means to carry out centralized statistics, analysis, management, sharing and utilization on the data, so that decision support is provided for logistics management and even whole business management, and the logistics is used for meeting the demands of customers, and the whole process of planning, implementation and management from the production place of the commodity to the consumption place of the commodity is realized by the raw materials, semi-finished products, finished products or related information in a mode of transportation, storage, distribution and the like at the lowest cost.
In the prior art, the situation that the customer receives the express, but does not sign for confirmation often occurs, and when the time limit of a certain sign is exceeded, the express which is not signed for becomes a problem piece. But the website responsible for confirming whether the express is signed or not in the prior art can not timely acquire the generation of the problem piece, so that the unmarked fast-forwarding can not be issued and timely processed, and the processing efficiency of the logistic problem piece is affected.
Accordingly, the prior art is still in need of improvement and development.
Disclosure of Invention
The invention mainly aims to solve the problems that in the prior art, a website responsible for confirming whether express is signed or not cannot acquire the generation of a problem piece in time, so that the unmarked quick progression cannot be issued and processed in time, and the processing efficiency of the logistic problem piece is affected.
The first aspect of the invention provides a method for processing logistic problem pieces, which comprises the following steps: acquiring current logistics data of a current express, judging whether the current express is a problem piece to be signed or not according to the current logistics data, and if so, generating a checking and accepting task; acquiring a historical logistics data set of a local express item according to the acceptance task, and training a global model according to the historical logistics data set to obtain a logistics track prediction model; inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express; judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, informing the terminal dispatch website to carry out acceptance prompting processing on the current express according to the acceptance prompting task.
Optionally, in a first implementation manner of the first aspect of the present invention, the step of obtaining current logistics data of a current express, judging whether the current express is a to-be-signed problem piece according to the current logistics data, if so, generating a checking and accepting task includes: acquiring signing data in the current logistics data of the current express, judging whether the signing data is in a preset signing time range, and if not, judging that the current express is the to-be-signed problem piece; generating a signing text according to the to-be-signed question piece, and generating the signing task according to the signing text.
Optionally, in a second implementation manner of the first aspect of the present invention, the step of obtaining a historical logistics data set of the local express according to the acceptance task, and training a global model according to the historical logistics data set, and obtaining a logistics track prediction model includes: when the acceptance task is received, acquiring the historical logistics data set of the local express according to the acceptance task, and determining the global model corresponding to the task node on the verification node blockchain according to the acceptance task; and carrying out iterative training on the global model according to the historical logistics data set until the global model meets a preset requirement or the iterative training frequency reaches a preset iterative frequency, and obtaining the logistics track prediction model.
Optionally, in a third implementation manner of the first aspect of the present invention, the step of performing iterative training on the global model according to the historical logistics data set until the global model meets a preset requirement or the iterative training number reaches a preset iteration number, and obtaining the logistics track prediction model includes: acquiring a historical logistics data set of the local express, and performing iterative training on the global model of the task node according to the historical logistics data set until the global model meets a preset requirement or the iterative training times reach preset iterative times; and acquiring a plurality of local models in iterative training, polymerizing the plurality of local models into an integral model and a check model, and obtaining the logistics track prediction model according to the integral model and the check model.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the step of obtaining a plurality of local models in iterative training, aggregating the plurality of local models into an overall model and a test model, and obtaining the logistic track prediction model according to the overall model and the test model includes: acquiring a plurality of local models in iterative training, performing aggregation according to the local models to obtain an overall model, removing any one of the local models, and performing aggregation on the rest of the local models to obtain a plurality of inspection models; calculating model precision of the integral model and the plurality of inspection models, and extracting the inspection model with highest precision from the plurality of inspection models according to the model precision of the integral model to obtain the logistics track prediction model.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the step of inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express includes: acquiring the waybill information of the current express in the current logistics data, and inputting the waybill information into the logistics track prediction model; and predicting the logistics track of the current express according to the waybill information based on the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the step of determining, according to the result of predicting the physical distribution track, whether the current express delivery has reached a terminal dispatch node, if yes, notifying the terminal dispatch node to perform a prompt acceptance process on the current express delivery according to the prompt acceptance task includes: judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, sending the acceptance task to the terminal dispatch website; and controlling the terminal dispatch website to carry out the acceptance checking treatment on the current rapid progress according to the acceptance checking task, and importing the current logistics data into an acceptance checking statistical table.
A second aspect of the present invention provides a logistic problem piece processing apparatus, comprising: the problem piece judging module is used for acquiring current logistics data of the current express, judging whether the current express is a problem piece to be signed or not according to the current logistics data, and if so, generating a prompt acceptance task; the prediction model generation module is used for acquiring a historical logistics data set of the local express according to the acceptance task, and training a global model according to the historical logistics data set to obtain a logistics track prediction model; the prediction result input module is used for inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express; and the problem piece processing module is used for judging whether the current express arrives at the terminal dispatch website according to the logistics track prediction result, if so, notifying the terminal dispatch website to carry out the acceptance prompting processing on the current express according to the acceptance prompting task.
Optionally, in a first implementation manner of the second aspect of the present invention, the problem piece judging module includes: the problem piece judging unit is used for acquiring signing data in the current logistics data of the current express, judging whether the signing data are in a preset signing time range, and if not, judging that the current express is the problem piece to be signed; and the signing-in task generating unit is used for generating signing-in texts according to the to-be-signed-in problem pieces and generating the signing-in tasks according to the signing-in texts.
Optionally, in a second implementation manner of the second aspect of the present invention, the prediction model generating module includes: the global model determining submodule is used for acquiring the historical logistics data set of the local express item according to the acceptance task when the acceptance task is received, and determining the global model corresponding to the task node on the verification node block chain according to the acceptance task; and the prediction model generation sub-module is used for carrying out iterative training on the global model according to the historical logistics data set until the global model meets a preset requirement or the iterative training times reach the preset iteration times, so as to obtain the logistics track prediction model.
Optionally, in a third implementation manner of the second aspect of the present invention, the prediction model generating submodule includes: the iteration training unit is used for acquiring a historical logistics data set of the local express, carrying out iteration training on the global model of the task node according to the historical logistics data set, and stopping until the global model meets a preset requirement or the iteration training frequency reaches a preset iteration frequency; the model aggregation unit is used for acquiring a plurality of local models in iterative training, aggregating the plurality of local models into an integral model and a check model, and obtaining the logistics track prediction model according to the integral model and the check model.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the model aggregation unit includes: the model aggregation subunit is used for acquiring a plurality of local models in iterative training, aggregating according to the local models to obtain the integral model, removing any one local model in the local models, and aggregating the rest local models to obtain a plurality of inspection models; and the model precision detection subunit is used for calculating the model precision of the integral model and the plurality of inspection models, and extracting the inspection model with the highest precision from the plurality of inspection models according to the model precision of the integral model to obtain the logistics track prediction model.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the prediction result input module includes: the waybill information input unit is used for acquiring the waybill information of the current express in the current logistics data and inputting the waybill information into the logistics track prediction model; and the logistics track prediction unit is used for predicting the logistics track of the current express according to the waybill information based on the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the problem piece processing module includes: the task sending unit is used for judging whether the current express arrives at the terminal dispatch website according to the logistics track prediction result, and if yes, sending the acceptance task to the terminal dispatch website; and the acceptance checking processing unit is used for controlling the terminal dispatch network point to carry out acceptance checking processing on the current rapid progression according to the acceptance checking task and importing the current logistics data into an acceptance checking statistical table.
A third aspect of the present invention provides a logistic problem piece processing apparatus, comprising: a memory and at least one processor, the memory having computer readable instructions stored therein, the memory and the at least one processor being interconnected by a line; the at least one processor invokes the computer readable instructions in the memory to cause the logistic problem piece processing device to perform the steps of the logistic problem piece processing method as described above.
A fourth aspect of the present invention provides a computer readable storage medium having stored therein computer readable instructions which when run on a computer cause the computer to perform the steps of the logistical problem piece processing method as described above.
The beneficial effects are that: according to the technical scheme, whether the express delivery is a signing-in problem piece is judged through signing-in time limit of the logistics express delivery, and when the fact that the logistics express delivery signing-in problem piece is judged, a signing-in task is correspondingly generated; meanwhile, the position of the website reached by the logistics express delivery is obtained through the logistics track prediction model obtained through the training of the historical logistics data set, so that the attendance task can be issued to the corresponding website in time, verification processing is carried out on the attendance of the current logistics express delivery through the corresponding website, and the issuing and processing efficiency of the logistics express delivery problem piece is effectively improved.
Drawings
FIG. 1 is a first flowchart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 2 is an overall flow chart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 3 is a second flowchart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 4 is a third flow chart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 5 is a fourth flowchart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 6 is a fifth flowchart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 7 is a sixth flowchart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 8 is a seventh flowchart of a method for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 9 is a schematic structural view of a device for handling logistic problem pieces according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of another embodiment of a device for handling logistic problem pieces according to the present invention;
fig. 11 is a schematic structural diagram of a logistic problem piece processing device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for processing a logistic problem piece, which are used for acquiring current logistic data of a current express, judging whether the current express is a problem piece to be signed or not according to the current logistic data, and if so, generating a checking and accepting task; acquiring a historical logistics data set of a local express item according to the acceptance task, and training a global model according to the historical logistics data set to obtain a logistics track prediction model; inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express; judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, informing the terminal dispatch website to carry out acceptance prompting processing on the current express according to the acceptance prompting task. According to the method for processing the logistic problem pieces, when the express delivery is judged to be the problem pieces to be signed, the position of the express delivery is determined through the logistic track prediction model and is issued in time, and the net points are prompted to process the problem pieces, so that the solution efficiency of the logistic problem pieces is effectively improved.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
In the intelligent logistics technical process based on the Internet of things, the intelligent terminal acquires various attribute information of the commodity by using sensing technologies such as Radio Frequency Identification (RFID) technology, X-ray induction, laser scanning and the like, and transmits the information to the intelligent data center through communication means to carry out centralized statistics, analysis, management, sharing and utilization on the data, so that decision support is provided for logistics management and even whole business management, and the logistics is used for meeting the demands of customers, and the whole process of planning, implementation and management from the production place of the commodity to the consumption place of the commodity is realized by the raw materials, semi-finished products, finished products or related information in a mode of transportation, storage, distribution and the like at the lowest cost.
In the prior art, the situation that the customer receives the express, but does not sign for confirmation often occurs, and when the time limit of a certain sign is exceeded, the express which is not signed for becomes a problem piece. But the website responsible for confirming whether the express is signed or not in the prior art can not timely acquire the generation of the problem piece, so that the unmarked fast-forwarding can not be issued and timely processed, and the processing efficiency of the logistic problem piece is affected.
In order to solve the problems, the invention provides a logistic problem piece processing method which comprises the following steps: when the express package is determined to be a problem piece (the express package exceeding the signing time limit range), the type of the signing is set, and the description content of the problem piece is automatically brought out (used for prompting or reminding a website to confirm the signing). And meanwhile, checking the logistics track through the waybill number information, issuing the task, determining whether the task is issued successfully (judging whether the express delivery reaches the terminal assignment website), if so, prompting the website to sign and confirm the problem piece, and inputting the problem piece information into a statistics list for registration.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1 and fig. 2, and a first embodiment of a method for handling logistic problem pieces in the embodiment of the present invention includes:
S101, acquiring current logistics data of a current express, judging whether the current express is a to-be-signed problem piece according to the current logistics data, and if so, generating a checking and accepting task;
the method comprises the steps of judging whether the current express is a signing problem piece or not by acquiring a signing time limit range corresponding to the current express, automatically prompting if the current express exceeds the signing time limit range, displaying information of the problem piece, and generating a corresponding signing task according to the display information of the problem piece, wherein the signing task aims at determining terminal network points, and sending display information of the attached problem piece to the corresponding terminal network points.
S102, acquiring a historical logistics data set of a local express item according to the acceptance task, and training a global model according to the historical logistics data set to obtain a logistics track prediction model;
according to the method, a historical logistics data set recorded in a local database is collected, a global model is determined by combining a federal learning mode, and the global model is trained through the historical logistics data set, so that a logistics track prediction model is obtained; the logistics track of the current express delivery can be checked through the logistics track prediction model, so that whether the express delivery reaches the terminal assignment center is judged.
Federal machine learning (Federated machine learning), also known as federal learning, joint learning, or federal learning. Federal learning defines a machine learning framework under which the problem of disparate data owners collaborating without exchanging data is solved by designing a virtual model. The virtual model is the optimal model for each party to aggregate data together, and each region serves a local target according to the model. Federal learning requires that this modeling result should be infinitely close to the traditional model, i.e., the result of modeling by aggregating data from multiple data owners together. Under federal mechanisms, the identities and roles of the participants are the same, and a shared data policy can be established. Since the data is not transferred, user privacy is not revealed or data specifications are not affected.
Federal learning has three major components: data sources, federal learning systems, and users. Under the federal learning system, each data source side performs data preprocessing, establishes a learning model thereof together, and feeds back an output result to a user.
Federal learning is used as an emerging machine learning framework, and can help each platform to achieve the purpose of co-modeling only by sharing model weights on the premise of not affecting data privacy safety. Meanwhile, the block chain is introduced to replace a central aggregation server of federation learning, so that the decentralization and the transparency of disclosure of the whole federation learning process are realized.
S103, inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express;
according to the invention, the current data is input into the logistics track prediction model, the logistics track of the current express corresponding to the current data can be checked through the learning ability of the logistics track prediction model after the history logistics data set training, and the logistics position of the current express is input.
The historical logistics data set comprises freight bill data and logistics data, wherein the freight bill data comprises freight bill numbers, express license plate numbers, sender information, receiver information, order generation time, transportation start time, vehicle types, goods types, longitude and latitude of pick-up places, longitude and latitude of discharge places, whole-course transportation distance and predicted delivery time; the logistics data comprise the current location and the location time of the express delivery vehicle.
And S104, judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, informing the terminal dispatch website to carry out acceptance prompting processing on the current express according to the acceptance prompting task.
When the current express delivery reaches the terminal dispatch website according to the logistics track prediction result, the sign-in task can be sent to the terminal dispatch website; when the terminal dispatch network point receives the signing-in task, the signing-in task can be analyzed, so that the current express corresponding to the problem piece can be determined, the terminal dispatch network point can determine the problem piece information in time, and verification and signing-in confirmation reminding can be performed in time.
Referring to fig. 3, a second embodiment of a method for handling logistic problem pieces according to an embodiment of the present invention includes:
s201, acquiring signing data in the current logistics data of the current express, judging whether the signing data is in a preset signing time range, and if not, judging that the current express is the to-be-signed problem piece;
s202, generating a signing text according to the to-be-signed question piece, and generating the signing task according to the signing text.
Setting signing aging range: if it belongs to the entry to the current day 23 before the current day 17: 59, if the sign-in is not signed in before, pushing the sign-in scanning to a large front position for inputting the sign-in the next morning; if the next day 23 after the 17 th day: 59, if the sign-in is not signed in before, the sign-in data is pushed in the early morning to enter the sign-in.
When the express sign-in exceeds the sign-in time limit, the express is judged to be a problem piece, the type of the problem piece is set to be a sign-in type, and meanwhile, prompt information is popped up, and the pop-up window can be closed only by clicking the confirmation.
The setting prompt information is as follows: the problem part type is a special type of 'signing in', the noble driver is requested to confirm the submission, and all complaints and arbitrated complaints generated after submitting the type of express part signing in are born by the issuing company. ".
The problem piece description content is set to be a fixed text of automatic filling, automatic filling (back-end return) is carried out after the type of the catalyst is selected, and modification is not supported. The text content is set as follows: "how good the noble driver is, how good the member I can verify that the member receiving client has received, how fast the noble driver has not uploaded the signoff, please verify as soon as possible, enter the signoff, and thank you.
Referring to fig. 4, a third embodiment of a method for handling logistic problem pieces according to an embodiment of the present invention includes:
s301, when the acceptance task is received, acquiring the historical logistics data set of the local express item according to the acceptance task, and determining the global model corresponding to the task node on the verification node block chain according to the acceptance task;
s302, carrying out iterative training on the global model according to the historical logistics data set until the global model meets a preset requirement or the iterative training frequency reaches a preset iterative frequency, and obtaining the logistics track prediction model.
The invention constructs a logistics track prediction model in a federal learning mode, and the basic construction process of the logistics track prediction model comprises the following steps: screening nodes-federal learning initialization-federal learning iterative training-generating and storing allocation results.
Specifically, 1, screening node: the task issuing node issues tasks, verifies task nodes of query nodes on a task issuing chain of the problem piece on the node block chain, and screens the task issuing nodes and task executing nodes.
2. Federal learning initialization: after the federal learning determines the task execution node, a digital certificate is firstly allocated to the node participating in training and the authority is set. Participants with digital certificates can communicate through channels, multitasking parallel training is achieved, permission is set, so that a local model which is uploaded by other nodes cannot be stolen due to the fact that communication among task execution nodes is not available, and data privacy safety is guaranteed.
3. Federal learning iterative training: the task issuing node sends an initial global model, and the task executing node receives the global model, trains the global model on a local data set to obtain a local model and uploads the local model to the task issuing node; and then the task release node screens the local model, and the data set meeting the requirements is aggregated into a total office model by using a federal average algorithm. And then the model is sent to a task execution node, the next round of iterative training is carried out until the final model meets the requirement of a task release node, or the iteration number reaches the upper limit, and the training is finished, so that the logistics track prediction model is obtained.
4. Generating and storing an allocation result: and the verification node respectively generates distribution results according to the behavior of the node in the training process, the task release node and the task execution node.
Referring to fig. 5, a fourth embodiment of a method for handling logistic problem pieces according to an embodiment of the present invention includes:
s3021, acquiring a historical logistics data set of the local express, and performing iterative training on the global model of the task node according to the historical logistics data set until the global model meets a preset requirement or the iterative training frequency reaches a preset iterative frequency;
s3022, acquiring a plurality of local models in iterative training, polymerizing the plurality of local models into an integral model and a check model, and obtaining the logistics track prediction model according to the integral model and the check model.
The allocation result for generating the task release node comprises the following steps: after the task issuing node screens the task executing node, consensus is achieved on the screening result of the task executing result, and the distribution result is recorded; after the task release node finishes screening the local model, the verification node agrees with the screening result and the aggregation result, and the distribution result is recorded.
The allocation result for generating the task release execution node comprises: according to the screening result of the task release nodes, the local model of the task execution nodes participating in aggregation generates a numerical value according to the precision by utilizing softmax and records the numerical value in the distribution result, and the task execution nodes not participating in aggregation record as 0.
Meanwhile, the historical logistics data set is used when the logistics track prediction model is trained, the safety of user data is ensured, the model training process is more open and safe due to the fact that local model weights of each round of federal learning are uplink, model weight data of the whole process are highly transparent, all nodes can be checked, and the data cannot be tampered after being uplink.
When the historical logistics data set is acquired, the method further comprises a preprocessing and feature screening process for the local original data set. When the historical logistics data set is preprocessed, numerical processing is carried out on the attribute of the sign of the historical logistics data set, and then normalization is carried out on all data to obtain a standardized historical logistics data set.
Referring to fig. 6, a fifth embodiment of a method for handling logistic problem pieces according to an embodiment of the present invention includes:
s30221, acquiring a plurality of local models in iterative training, performing aggregation according to the local models to obtain an overall model, removing any one of the local models, and performing aggregation on the rest of the local models to obtain a plurality of inspection models;
S30222, calculating model precision of the integral model and the plurality of inspection models, and extracting an inspection model with highest precision from the plurality of inspection models according to the model precision of the integral model to obtain the logistics track prediction model.
Specifically, the determining process for the logistics track prediction model comprises the following steps: after the iterative training is completed, all received local models are aggregated, the local models are screened, the local models which finally participate in the aggregation are determined, and the logistics track prediction model is obtained.
After the iterative training is completed, the process of aggregating all received local models is as follows: after receiving the local models, the task release node aggregates all the local models into an integral model M; screening a local model: deleting the first local model to aggregate into a test model ml, testing the test model ml and the whole model M on a test set, and eliminating the local model if the accuracy of the test model ml is greater than that of the whole model M. Traversing all the local models in the mode to finish the preliminary screening of all the local models; determining a local model that ultimately participates in the aggregation: the local models which are reserved through the previous screening are aggregated to obtain a test model mk, the test model mk and a test set are tested, the precision of all the test model sets and the precision of the whole model M are compared, the model with the highest precision is selected as the final global model of the previous screening, and the corresponding local model is used as the local model which finally participates in aggregation (namely, the logistics track prediction model in the invention).
Referring to fig. 7, a sixth embodiment of a method for handling logistic problem pieces according to an embodiment of the present invention includes:
s401, acquiring the waybill information of the current express in the current logistics data, and inputting the waybill information into the logistics track prediction model;
s402, predicting the logistics track of the current express according to the waybill number information based on the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express.
According to the method, the logistics track inspection of the current express is completed by acquiring the waybill number information in the logistics data of the current express. Through with the waybill information input to commodity circulation orbit prediction model, and commodity circulation orbit prediction model is under carrying out local historical dataset and federal study's combined action, can carry out accurate check-up to the commodity circulation orbit of current express delivery according to the waybill information, simultaneously, can export commodity circulation orbit result.
Referring to fig. 8, a seventh embodiment of a method for handling logistic problem pieces according to an embodiment of the present invention includes:
s501, judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, sending the acceptance task to the terminal dispatch website;
S502, controlling the terminal dispatch website to carry out the acceptance check processing on the current rapid progress according to the acceptance check task, and importing the current logistics data into an acceptance check statistical table.
When the logistics track prediction result is received, the logistics track prediction result is compared with the logistics data of the current express, so that whether the distance between the logistics track prediction result and a preset point in the logistics data is smaller than or equal to a preset error distance is judged, and the accuracy of the logistics track prediction result is proved only when the distance between the logistics track prediction result and the preset point in the logistics data is smaller than or equal to the preset error distance.
Because even if the result of the logistics track prediction of the current express is obtained, it does not necessarily represent that the current express actually occurs, for example, the freight driver may perform the check-in operation at a certain place, but the freight driver does not actually transport the freight of the current express to the destination. In order to prevent the occurrence of the situation, the invention further searches the real logistics track data of the current express after receiving and acquiring the logistics track prediction result of the current express.
When the terminal dispatch website receives the checking and accepting task and confirms the information of the problem pieces, the terminal dispatch website can issue the problem pieces of the checking and accepting type, the issued problem pieces are uniformly entered into a checking and accepting statistics list, the information is pushed to a large front (a storage warehouse close to a consumer) by a collaboration system for the past-time non-signed freight list to be forced to be signed and accepted, and meanwhile, the terminal dispatch website is charged for 10 yuan/ticket at the whole, so special prompt is needed during issuing.
Specifically, the method can be specifically operated in a system display interface as follows: 1. clicking a problem piece, displaying a page to be replied, sliding and displaying other tabs, switching other tabs after selecting, and viewing all lists and the network points; 2. selecting a notification class, and switching to view a notification class problem piece list; 3. the left side below shows the number of all problem pieces under the current screening condition; 4. the screening icon is displayed on the right side of the lower part, and the screening spring frame is popped up by clicking the lower part
Meanwhile, the user can click a preset card area to enter a question piece detail page, wherein the detail page comprises a bill number, a question piece description, content details, pay registration, reply records, logistics tracks, bar code distribution, record list information, question replies (content+accessory), and operation buttons: reply, forward, and case.
The bill number is used for displaying the bill number digits, clicking and copying, copying the bill number and prompting 'copy success'. Meanwhile, the information can be copied by one key, and the click prompt is "copy successful" (the website usually follows the problem of the client channel through the bill number on the WeChat), so that the website can copy the problem directly and paste the information to the WeChat chat frame, or make other spare use.
The copied contents are as follows: "order number + issue time + issue piece type + issue piece description".
The field display content includes: 1. problem piece type: displaying the type of the problem piece of the current bill number; 2. the issuing site: dot name + dot code; 3. the receiving station: dot name + dot code, source of problem piece: displaying the source of the problem piece, and describing the problem piece: problem piece content, release time: problem piece release time, accessory: clicking the picture thumbnail, previewing the large picture, and sliding and switching left and right. The attachment information is not a fixed presentation field, and the presentation is only needed when the attachment is in the problem piece.
In summary, the invention can issue the problem pieces in time, thereby not only improving the processing efficiency of the logistic problem pieces, but also automatically distributing the express pieces, saving the workload and avoiding the data confusion.
The method for processing the logistic problem piece in the embodiment of the present invention is described above, and the device for processing the logistic problem piece in the embodiment of the present invention is described below, referring to fig. 9, where one embodiment of the device for processing the logistic problem piece in the embodiment of the present invention includes:
the problem piece judging module 50 is configured to obtain current logistics data of a current express, judge whether the current express is a problem piece to be signed according to the current logistics data, and if so, generate a acceptance task;
The prediction model generating module 60 is configured to obtain a historical logistics data set of the local express item according to the acceptance task, and train the global model according to the historical logistics data set to obtain a logistics track prediction model;
the predicted result input module 70 is configured to input the current logistics data into the logistics track prediction model, so as to obtain a logistics track predicted result corresponding to the current express;
and the problem piece processing module 80 is configured to determine whether the current express delivery has reached a terminal dispatch website according to the result of the logistics track prediction, if yes, notify the terminal dispatch website to perform a prompt acceptance process on the current express delivery according to the prompt acceptance task.
Referring to fig. 10, another embodiment of a logistic problem piece processing device according to an embodiment of the present invention includes:
the problem piece judging module 50 is configured to obtain current logistics data of a current express, judge whether the current express is a problem piece to be signed according to the current logistics data, and if so, generate a acceptance task;
the prediction model generating module 60 is configured to obtain a historical logistics data set of the local express item according to the acceptance task, and train the global model according to the historical logistics data set to obtain a logistics track prediction model;
The predicted result input module 70 is configured to input the current logistics data into the logistics track prediction model, so as to obtain a logistics track predicted result corresponding to the current express;
and the problem piece processing module 80 is configured to determine whether the current express delivery has reached a terminal dispatch website according to the result of the logistics track prediction, if yes, notify the terminal dispatch website to perform a prompt acceptance process on the current express delivery according to the prompt acceptance task.
In this embodiment, the problem piece determination module 50 includes:
a problem piece determining unit 501, configured to obtain sign-in data in the current logistics data of the current express, determine whether the sign-in data is within a preset sign-in time range, and if not, determine that the current express is the problem piece to be signed;
and the sign-in task generating unit 502 is configured to generate a sign-in text according to the to-be-signed-in question piece, and generate the sign-in task according to the sign-in text.
In this embodiment, the prediction model generating module 60 includes:
the global model determining submodule 601 is configured to obtain the historical logistics data set of the local express item according to the acceptance task when the acceptance task is received, and determine the global model corresponding to the task node on the verification node block chain according to the acceptance task;
And the prediction model generation sub-module 602 is configured to perform iterative training on the global model according to the historical logistics data set, and stop until the global model meets a preset requirement or the iterative training frequency reaches a preset iteration frequency, so as to obtain the logistics track prediction model.
In this embodiment, the prediction model generation sub-module 602 includes:
the iteration training unit 6021 is configured to obtain a historical logistics data set of the local express, perform iteration training on the global model of the task node according to the historical logistics data set, and stop the process until the global model meets a preset requirement or the iteration training frequency reaches a preset iteration frequency;
the model aggregation unit 6022 is configured to obtain a plurality of local models in iterative training, aggregate the plurality of local models into an overall model and a test model, and obtain the logistics track prediction model according to the overall model and the test model.
In the present embodiment, the model aggregation unit 6022 includes:
a model aggregation subunit 60221, configured to obtain a plurality of local models in iterative training, aggregate according to a plurality of local models to obtain an overall model, remove any one of the local models, and aggregate the remaining local models to obtain a plurality of inspection models;
And the model precision detection subunit 60222 is configured to calculate model precision of the whole model and the plurality of test models, and extract a test model with highest precision from the plurality of test models according to the model precision of the whole model, so as to obtain the logistics track prediction model.
In this embodiment, the prediction result input module 70 includes:
a waybill information input unit 701, configured to obtain waybill information of the current express in the current logistics data, and input the waybill information into the logistics track prediction model;
and the logistics track prediction unit 702 is configured to predict the logistics track of the current express according to the waybill number information based on the logistics track prediction model, so as to obtain a logistics track prediction result corresponding to the current express.
In this embodiment, the problem-piece processing module 80 includes:
a task sending unit 801, configured to determine, according to the result of the physical distribution track prediction, whether the current express arrives at a terminal dispatch website, and if yes, send the acceptance task to the terminal dispatch website;
and the acceptance checking unit 802 is configured to control the terminal dispatch website to perform acceptance checking processing on the current fast-forwarding according to the acceptance checking task, and import the current logistics data into an acceptance checking statistical table.
The invention provides a logistic problem piece processing method, which judges whether an express delivery is a logistic problem piece or not through the signing time limit of the logistic express delivery, and correspondingly generates a logistic signing task when judging that the logistic express delivery is a logistic problem piece; meanwhile, the position of the website reached by the logistics express delivery is obtained through the logistics track prediction model obtained through the training of the historical logistics data set, so that the attendance task can be issued to the corresponding website in time, verification processing is carried out on the attendance of the current logistics express delivery through the corresponding website, and the issuing and processing efficiency of the logistics express delivery problem piece is effectively improved.
The above fig. 9 and fig. 10 describe the logistic problem piece processing device in the embodiment of the present invention in detail from the point of view of modularized functional entities, and the logistic problem piece processing device in the embodiment of the present invention is described in detail from the point of view of hardware processing.
Fig. 11 is a schematic structural diagram of a logistical problem piece processing device according to an embodiment of the present invention, where the logistical problem piece processing device 10 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 11 (e.g., one or more processors) and a memory 12, and one or more storage media 13 (e.g., one or more mass storage devices) storing application programs 133 or data 132. Wherein the memory 12 and the storage medium 13 may be transitory or persistent storage. The program stored in the storage medium 13 may include one or more modules (not shown), each of which may include a series of instruction operations for the logistical problem piece processing device 10. Still further, the processor 11 may be configured to communicate with the storage medium 13 and execute a series of instruction operations in the storage medium 13 on the logistical problem piece processing device 10.
The logistical problem piece processing apparatus 10 may also include one or more power supplies 14, one or more wired or wireless network interfaces 15, one or more input/output interfaces 16, and/or one or more operating systems 131, such as Windows service, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the apparatus configuration shown in fig. 11 is not limiting of the logistical problem piece processing apparatus 10 and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored that, when executed on a computer, cause the computer to perform the steps of a method for handling logistical problem pieces.
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.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or 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.
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 technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The logistic problem piece processing method is characterized by comprising the following steps of:
acquiring current logistics data of a current express, judging whether the current express is a problem piece to be signed or not according to the current logistics data, and if so, generating a checking and accepting task;
acquiring a historical logistics data set of a local express item according to the acceptance task, and training a global model according to the historical logistics data set to obtain a logistics track prediction model;
inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express;
judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, informing the terminal dispatch website to carry out acceptance prompting processing on the current express according to the acceptance prompting task.
2. The method for processing a logistic problem piece according to claim 1, wherein the step of obtaining current logistic data of a current express, judging whether the current express is a problem piece to be signed according to the current logistic data, and if yes, generating a checking and accepting task comprises:
Acquiring signing data in the current logistics data of the current express, judging whether the signing data is in a preset signing time range, and if not, judging that the current express is the to-be-signed problem piece;
generating a signing text according to the to-be-signed question piece, and generating the signing task according to the signing text.
3. The method for processing a logistic problem piece according to claim 1, wherein the step of obtaining a historical logistic data set of a local express piece according to the acceptance task, and training a global model according to the historical logistic data set, and obtaining a logistic track prediction model comprises the steps of:
when the acceptance task is received, acquiring the historical logistics data set of the local express according to the acceptance task, and determining the global model corresponding to the task node on the verification node blockchain according to the acceptance task;
and carrying out iterative training on the global model according to the historical logistics data set until the global model meets a preset requirement or the iterative training frequency reaches a preset iterative frequency, and obtaining the logistics track prediction model.
4. The logistic problem piece processing method according to claim 3, wherein the step of performing iterative training on the global model according to the historical logistic data set until the global model meets a preset requirement or the iterative training number reaches a preset iteration number, and obtaining the logistic track prediction model includes:
acquiring a historical logistics data set of the local express, and performing iterative training on the global model of the task node according to the historical logistics data set until the global model meets a preset requirement or the iterative training times reach preset iterative times;
and acquiring a plurality of local models in iterative training, polymerizing the plurality of local models into an integral model and a check model, and obtaining the logistics track prediction model according to the integral model and the check model.
5. The logistic problem piece processing method according to claim 4, wherein the step of acquiring a plurality of local models in iterative training, aggregating a plurality of local models into an overall model and a check model, and obtaining the logistic trajectory prediction model from the overall model and the check model comprises:
Acquiring a plurality of local models in iterative training, performing aggregation according to the local models to obtain an overall model, removing any one of the local models, and performing aggregation on the rest of the local models to obtain a plurality of inspection models;
calculating model precision of the integral model and the plurality of inspection models, and extracting the inspection model with highest precision from the plurality of inspection models according to the model precision of the integral model to obtain the logistics track prediction model.
6. The method for processing a logistic problem piece according to claim 1, wherein the step of inputting the current logistic data into the logistic track prediction model to obtain a logistic track prediction result corresponding to the current express comprises the steps of:
acquiring the waybill information of the current express in the current logistics data, and inputting the waybill information into the logistics track prediction model;
and predicting the logistics track of the current express according to the waybill information based on the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express.
7. The method for processing a logistic problem piece according to claim 1, wherein the step of judging whether the current express delivery has reached a terminal dispatch site according to the logistic track prediction result, if yes, notifying the terminal dispatch site to perform the acceptance check processing on the current express delivery according to the acceptance check task comprises:
Judging whether the current express arrives at a terminal dispatch website according to the logistics track prediction result, if so, sending the acceptance task to the terminal dispatch website;
and controlling the terminal dispatch website to carry out the acceptance checking treatment on the current rapid progress according to the acceptance checking task, and importing the current logistics data into an acceptance checking statistical table.
8. A logistic problem piece processing device, characterized by comprising:
the problem piece judging module is used for acquiring current logistics data of the current express, judging whether the current express is a problem piece to be signed or not according to the current logistics data, and if so, generating a prompt acceptance task;
the prediction model generation module is used for acquiring a historical logistics data set of the local express according to the acceptance task, and training a global model according to the historical logistics data set to obtain a logistics track prediction model;
the prediction result input module is used for inputting the current logistics data into the logistics track prediction model to obtain a logistics track prediction result corresponding to the current express;
and the problem piece processing module is used for judging whether the current express arrives at the terminal dispatch website according to the logistics track prediction result, if so, notifying the terminal dispatch website to carry out the acceptance prompting processing on the current express according to the acceptance prompting task.
9. A logistical problem piece processing device, comprising a memory and at least one processor, wherein the memory stores computer readable instructions;
the at least one processor invoking the computer readable instructions in the memory to perform the steps of the logistic problem piece processing method of any one of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon, which when executed by a processor, perform the steps of the logistic problem piece processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311696689.1A CN117635004A (en) | 2023-12-11 | 2023-12-11 | Logistics problem piece processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311696689.1A CN117635004A (en) | 2023-12-11 | 2023-12-11 | Logistics problem piece processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117635004A true CN117635004A (en) | 2024-03-01 |
Family
ID=90026655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311696689.1A Pending CN117635004A (en) | 2023-12-11 | 2023-12-11 | Logistics problem piece processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117635004A (en) |
-
2023
- 2023-12-11 CN CN202311696689.1A patent/CN117635004A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10628805B2 (en) | Calculating and reducing carbon footprint in a waste management plan | |
| US20120047080A1 (en) | Waste Management and Recycling Tracking System | |
| US20120330707A1 (en) | Web-based communication platform | |
| CN103493076B (en) | For the method and system for the improvement reservation system for optimizing the searching request repeated | |
| US11620590B1 (en) | Network value of a flight leg booking | |
| WO2018006716A1 (en) | Order information processing method, apparatus and system | |
| WO2013040025A2 (en) | Methods and apparatus to monitor products in stores | |
| CN102870110B (en) | Document registration system | |
| KR101919865B1 (en) | Apparatus and method for managing electronic receipt | |
| Saeed Osman | Modeling and simulation for inventory management of repairable items in maintenance systems | |
| JP7553941B2 (en) | Expense inspection device, expense inspection method, and program | |
| CN117235040A (en) | Big data center frame system based on data management | |
| US20230214731A1 (en) | Denied Boarding Impacts | |
| CN117635004A (en) | Logistics problem piece processing method, device, equipment and storage medium | |
| JP6038478B2 (en) | Sales support system and server | |
| JP6534141B2 (en) | Budget control system, budget control method and budget control program | |
| CN105934767A (en) | Job site material tracking and discrepancy reconciliation | |
| CN114819820A (en) | Intelligent supply chain management method, device, system and medium based on artificial intelligence | |
| CN113763053A (en) | Block chain-based method for evaluating user activity level of big data e-commerce platform | |
| CN111612349A (en) | Detection center service management method, device and system | |
| CN113779241A (en) | Information acquisition method and device, computer readable storage medium and electronic equipment | |
| US20140278739A1 (en) | Methods and apparatus to monitor products in stores | |
| CN110838003A (en) | Management system, method, device and readable medium for shared office | |
| US20140067698A1 (en) | Delivery service carbon calculator | |
| CN113537574B (en) | Service processing aging pushing method and device, storage medium and computer equipment |
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 |