CN111222675B - Logistics path intelligent optimization method, device, system, medium and equipment - Google Patents
Logistics path intelligent optimization method, device, system, medium and equipment Download PDFInfo
- Publication number
- CN111222675B CN111222675B CN201911003482.5A CN201911003482A CN111222675B CN 111222675 B CN111222675 B CN 111222675B CN 201911003482 A CN201911003482 A CN 201911003482A CN 111222675 B CN111222675 B CN 111222675B
- Authority
- CN
- China
- Prior art keywords
- goods
- quality
- logistics path
- distribution
- distribution vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, a system, a medium and equipment for intelligently optimizing a logistics path. The method can detect the quality of the goods in real time according to the quality data of the goods on the delivery vehicle, thereby determining whether the goods are deteriorated or possibly deteriorated, and adjusting the logistics path of the delivery vehicle according to the quality of the goods and the current position of the delivery vehicle, so that the goods can be redirected to a more suitable delivery station, and the loss of the goods such as fresh goods in the delivery process is reduced.
Description
Technical Field
The invention relates to the technical field of intelligent logistics management, in particular to a method, a device, a system, a medium and equipment for intelligently optimizing a logistics path.
Background
With the rise of cold-chain logistics and fresh electricity suppliers, the requirements of logistics transportation are more and more strict, and ensuring the quality of goods and reducing the loss of the goods are important problems to be solved by logistics transportation enterprises.
Conventional logistics transportation is generally performed by manually inspecting and monitoring the quality of goods from a distribution center to a destination, and the transportation route is constant. The logistics transportation in this way has the following disadvantages: 1) The quality of goods cannot be monitored in real time; 2) The inability to dynamically adjust the logistics route and destination for each batch of goods based on the quality of the goods results in high goods loss, for example, when a temperature rise or a deterioration of the goods is detected in real time, the logistics route and destination should be adjusted to divert to a closer destination to prevent further loss of the fresh goods.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an intelligent optimization method for a logistics path, which can monitor the quality of goods in real time, adjust the logistics path according to the quality of the goods and reduce the loss of the fresh goods and the like in distribution.
The second purpose of the invention is to provide a logistics path intelligent optimization device.
The invention also provides a system for intelligently optimizing the logistics path.
A fourth object of the present invention is to provide a storage medium.
It is a fifth object of the invention to provide a computing device.
The first purpose of the invention is realized by the following technical scheme: an intelligent optimization method for a logistics path comprises the following steps:
acquiring quality data of goods with known quality collected on a distribution vehicle as a training sample;
training the neural network by taking the training sample as the input of the neural network and the quality of the goods corresponding to the training sample as a label to obtain a quality detection model of the goods;
acquiring quality data of goods collected on a distribution vehicle for goods distribution as a test sample;
inputting the test sample into a cargo quality detection model to detect the quality of the cargo;
acquiring the current position of a distribution vehicle;
and adjusting the logistics path for the distribution vehicle according to the quality of the goods and the current position of the distribution vehicle.
Preferably, the quality data of the goods comprises the temperature, the humidity and the illumination intensity of the environment in which the goods are located and the photos of the goods;
the quality data of the goods corresponding to the training samples and the testing samples are respectively input into the neural network and the goods quality detection model after being preprocessed, wherein the preprocessing process comprises the following steps:
carrying out image segmentation on the photo of the goods, and segmenting the image into m x n blocks; calculating a Census conversion value of each block, and calculating a cumulative histogram of the Census conversion values of each block to obtain a 256-dimensional characteristic value of each block; cascading the characteristic values of all the blocks to form an image characteristic value with m x n x 256 dimensions;
and cascading the temperature, the humidity and the illumination intensity of the environment where the goods are located and the acquired m, n, 256-dimensional image characteristic values to form (m, n, 256+ 3) -dimensional characteristic vectors which are used as the input of a neural network or a goods quality detection model.
Preferably, the neural network is a multilayer convolution CNN neural network, a deep residual error network and a hybrid neural network;
and aiming at the goods with the quality detected by the goods quality detection model, the quality data of the goods are used as training samples, and the current goods quality detection model is subjected to incremental learning.
Preferably, the specific process of adjusting the logistics path for the delivery vehicle is as follows:
after the current quality of the goods is detected by the goods quality detection model, determining whether the goods are in a deterioration state or not according to the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are in a deterioration possibility or not according to a comparison result;
if not, the logistics path of the delivery vehicle is not changed;
if so, acquiring the current position of the distribution vehicle, determining the logistics path of the distribution vehicle by adopting a logistics path selection strategy with a time window, and selecting a distribution station which has the lowest distribution cost and meets the requirement of the time window from the current position of the distribution vehicle.
Further, the specific steps of determining the logistics path of the delivery vehicle by adopting the logistics path selection strategy with the time window are as follows:
setting a path from the current position of the vehicle to an original distribution station as a current logistics path;
calculating the cost of each reachable distribution station inserted into the current logistics path, selecting the reachable distribution station with the lowest cost to insert into the current logistics path, judging whether the distribution station can insert into the current logistics path under the constraint condition of a time window or not, if so, inserting the distribution station into the current path, and updating the logistics path; if not, keeping the current logistics path unchanged.
Preferably, for the distribution vehicle which is carrying out goods distribution, the quality data of the goods collected on the distribution vehicle is acquired in a timing and/or alarm triggering mode;
the alarm triggering mode is to acquire the quality data acquired by the delivery vehicle when the quality data acquired by the delivery vehicle exceeds a certain threshold.
The second purpose of the invention is realized by the following technical scheme: a logistics path intelligent optimization apparatus, the apparatus comprising:
the system comprises a training sample acquisition module, a quality analysis module and a quality analysis module, wherein the training sample acquisition module is used for acquiring quality data of goods with known quality acquired on a distribution vehicle as training samples;
the cargo quality detection model building module is used for taking the training samples as the input of the neural network, taking the cargo quality corresponding to the training samples as the label, and training the neural network to obtain a cargo quality detection model;
the system comprises a test sample acquisition module, a quality analysis module and a quality analysis module, wherein the test sample acquisition module is used for acquiring quality data of goods collected on a distribution vehicle for goods distribution as a test sample;
the goods quality detection module is used for inputting the test samples into the goods quality detection model to detect the quality of the goods;
the distribution vehicle position acquisition module is used for acquiring the position of a distribution vehicle;
and the logistics path optimization module is used for adjusting the logistics path for the delivery vehicle according to the quality of the goods and the current position of the delivery vehicle.
The third purpose of the invention is realized by the following technical scheme: an intelligent logistics path optimization system comprises a terminal data acquisition device and an intelligent logistics path optimization device; the terminal data acquisition device is connected with the logistics path intelligent optimization device through a wireless network;
the terminal data acquisition device is used for acquiring quality data of goods on a distribution vehicle and sending the data to the logistics path intelligent optimization device;
the intelligent logistics path optimization device is used for achieving the intelligent logistics path optimization method for the first purpose of the invention.
The fourth purpose of the invention is realized by the following technical scheme: a storage medium stores a program, and when the program is executed by a processor, the method for intelligently optimizing a logistics path according to the first object of the invention is realized.
The fifth purpose of the invention is realized by the following technical scheme: the computing equipment comprises a processor and a memory for storing a program executable by the processor, and when the processor executes the program stored by the memory, the intelligent logistics path optimization method achieves the first aim of the invention.
Compared with the prior art, the invention has the following advantages and effects:
(1) In the intelligent logistics path optimization method, firstly, a goods quality detection model is trained through quality data of goods with known quality acquired from a delivery vehicle, then, the quality data of the goods are acquired aiming at the delivery vehicle which is delivering the goods, the quality data of the goods are input into the goods quality detection model to detect the quality of the goods, and then, the logistics path is adjusted for the delivery vehicle according to the quality of the goods and the current position of the delivery vehicle. Therefore, the method can detect the quality of the goods in real time according to the quality data of the goods on the delivery vehicle, so as to determine whether the goods are deteriorated or possibly deteriorated, and adjust the logistics path of the delivery vehicle according to the quality of the goods and the current position of the delivery vehicle, so that the goods can be redirected to a more suitable delivery station, and the loss of the goods such as fresh goods in the delivery process is reduced.
(2) In the logistics path intelligent optimization method, the quality data of the goods with the quality detected by the goods quality detection model is used as a training sample, and the current goods quality detection model is subjected to incremental learning so as to improve the quality detection precision of the goods quality detection model.
(3) In the logistics path intelligent optimization method, after the current quality of the goods is detected by the goods quality detection model, whether the goods are deteriorated or not is determined according to the current quality of the goods, and/or the current quality of the goods is compared with the quality before a certain time period, and whether the possibility of deterioration exists or not is determined according to the comparison result; if not, the goods quality is normal, the logistics path of the distribution vehicle is not changed, if the goods are possibly deteriorated or deteriorated, the logistics path of the distribution vehicle is adjusted, a distribution station which is the lowest in distribution cost from the current position and meets the time window requirement is selected for the distribution vehicle, and the logistics path of the distribution vehicle is determined according to the station, so that the loss of the goods on the distribution vehicle is reduced as much as possible.
(4) In the logistics path intelligent optimization method, for a distribution vehicle which is carrying out cargo distribution, quality data of cargos collected on the distribution vehicle is acquired in a timing and/or alarm triggering mode. The quality of the goods can be monitored in a timing mode when the quality data of the goods are acquired in a timing mode, and the quality of the goods is basically unchanged in a short time without being monitored uninterruptedly, so that the problem that the calculation amount is increased and calculation resources are wasted due to uninterrupted monitoring all the time can be solved under the condition that the real-time monitoring of the quality of the goods is ensured; when an alarm triggering mode is adopted, namely when the collected quality data exceeds a certain threshold value, for example, the temperature exceeds a certain threshold value, the quality data is obtained to carry out quality detection, and the emergency situation of the goods can be monitored in time so as to effectively and quickly solve the problem.
Drawings
FIG. 1 is a flow chart of the intelligent optimization method of the logistics path.
Fig. 2 is a block diagram of the structure of the intelligent logistics path optimization device.
FIG. 3 is a block diagram of the intelligent optimization system for logistics path according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Example 1
The embodiment discloses an intelligent optimization method for a logistics path, which comprises the following steps as shown in fig. 1:
s1, acquiring quality data of goods with known quality collected on a distribution vehicle, and taking the data as a training sample; in this embodiment, the quality data of the cargo includes the temperature, humidity, and illumination intensity of the environment where the cargo is located and the photograph of the cargo, and the quality data of the cargo may be collected by the temperature sensor, the humidity sensor, the illumination intensity sensor, and the camera on the delivery vehicle, respectively.
S2, taking the training sample as the input of the neural network, taking the quality of the goods corresponding to the training sample as a label, and training the neural network to obtain a goods quality detection model; in this embodiment, the neural network may adopt a multilayer convolutional CNN neural network, a deep residual error network, a hybrid neural network, and the like.
In this embodiment, the quality data of the goods corresponding to the training samples is input to the neural network after being preprocessed, wherein the preprocessing process is as follows:
carrying out image segmentation on the photo of the goods, and segmenting the image into m x n blocks; calculating a Census conversion value of each block, and calculating a cumulative histogram of the Census conversion values of each block to obtain a 256-dimensional characteristic value of each block; cascading the characteristic values of all the blocks to form an image characteristic value with m x n x 256 dimensions;
and cascading the temperature, the humidity and the illumination intensity of the environment where the goods are located and the acquired m, n, 256-dimensional image characteristic values to form (m, n, 256+ 3) -dimensional characteristic vectors which are used as the input of a neural network or a goods quality detection model.
And S3, acquiring the quality data of the goods collected on the delivery vehicle for the delivery of the goods as a test sample.
In the embodiment, the quality data of the goods collected on the delivery vehicle is acquired in a timing and/or alarm triggering mode; the timing mode comprises the following steps: acquiring quality data of goods collected by a distribution vehicle at regular intervals; the alarm triggering method is a method of acquiring quality data acquired by a distribution vehicle when the quality data acquired by the distribution vehicle exceeds an alarm value which is a predetermined threshold value, for example, an alarm is generated when a temperature detected by a temperature sensor exceeds a predetermined value, and quality data of goods acquired by the distribution vehicle is acquired when the occurrence of the alarm is detected.
In the embodiment, timing and alarm triggering can be simultaneously selected to acquire the quality data of the goods, and the two modes are combined to monitor the quality of the goods timely and monitor the condition of the goods during the sudden quality change.
S4, inputting the test sample into a cargo quality detection model to detect the quality of the cargo; in this embodiment, for the goods whose quality is detected by the goods quality detection model, the quality data is used as a training sample, and the incremental learning is performed on the current goods quality detection model to obtain the incrementally learned goods quality detection model for use in the next detection.
In this embodiment, the quality data of the goods corresponding to the test sample is input to the goods quality inspection model after being preprocessed, wherein the preprocessing process is as follows:
carrying out image segmentation on the photo of the goods, and segmenting the image into m x n blocks; calculating a Census conversion value of each block, and calculating a cumulative histogram of the Census conversion values of each block to obtain a 256-dimensional characteristic value of each block; cascading the characteristic values of all the blocks to form m × n × 256-dimensional image characteristic values;
and cascading the temperature, the humidity and the illumination intensity of the environment where the goods are located and the acquired m, n, 256-dimensional image characteristic values to form (m, n, 256+ 3) -dimensional characteristic vectors which are used as the input of a neural network or a goods quality detection model.
S5, acquiring the current position of a distribution vehicle; and adjusting the logistics path for the distribution vehicle according to the quality of the goods and the current position of the distribution vehicle. The specific process is as follows:
after the current quality of the goods is detected by the goods quality detection model, determining whether the goods are in a deterioration state or not according to the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are in a deterioration possibility or not according to a comparison result;
if not, namely under the condition that the goods are not deteriorated or possible to be deteriorated, the logistics path of the distribution vehicle is not changed; in this embodiment, a threshold X for determining whether or not the quality of the goods at one node is deteriorated may be set according to the type and kind of the goods, and the quality detected by the goods quality detection model may be compared with the threshold X. For example, at several time points in sequence, the quality of the goods detected at the time point t1 is a1, the quality of the goods detected at the time point t2 is a2, the quality of the goods detected at the time point t3 is a3, the current quality of the goods detected at the current time point t4 is a4, and if the quality a3 and the quality a4 are both lower than the threshold value X but the difference between the quality a4 and the quality a3 exceeds a certain value, it is determined that the goods are likely to be deteriorated, and the operation in the following "yes" case is performed.
If so, namely under the condition that the goods are deteriorated and/or possibly deteriorated, the current position of the distribution vehicle is obtained, the logistics path of the distribution vehicle is determined by adopting a logistics path selection strategy with a time window, and the next distribution station which has the lowest distribution cost and meets the requirement of the time window is selected for the distribution vehicle from the current position, and the specific steps are as follows:
setting a path from the current position of the vehicle to an original distribution station as a current logistics path;
calculating the cost of each reachable distribution station inserted into the current logistics path, selecting the reachable distribution station with the lowest cost to insert into the current logistics path, judging whether the distribution station can insert into the current logistics path under the constraint condition of a time window or not, if so, inserting the distribution station into the current path, and updating the logistics path; if not, keeping the current logistics path unchanged. In this embodiment, the constraint of the time window refers to the time: depending on the current quality of the goods, the latest time to deliver the goods to the respective delivery site is required, which is determined depending on the goods type or kind.
Example 2
The embodiment discloses a logistics path intelligent optimization device, as shown in fig. 2, the device includes:
the system comprises a training sample acquisition module, a quality analysis module and a quality analysis module, wherein the training sample acquisition module is used for acquiring quality data of goods with known quality acquired on a distribution vehicle as training samples; wherein the quality data include the temperature, humidity and illumination intensity of the environment in which the goods are located and the photos of the goods, and the quality data of the goods can be respectively collected by a temperature sensor, a humidity sensor, an illumination intensity sensor and a camera on the distribution vehicle.
The cargo quality detection model building module is used for taking the training samples as the input of the neural network, taking the cargo quality corresponding to the training samples as the label, and training the neural network to obtain a cargo quality detection model; in this embodiment, the neural network may adopt a multilayer convolutional CNN neural network, a deep residual error network, a hybrid neural network, and the like.
And the test sample acquisition module is used for acquiring the quality data of the goods collected on the distribution vehicle for the goods distribution as a test sample. In this embodiment, the test sample acquisition module acquires quality data of the goods collected on the delivery vehicle by a timed and/or alarm triggering manner.
And the cargo quality detection module inputs the test sample into the cargo quality detection model to detect the quality of the cargo.
The distribution vehicle position acquisition module is used for acquiring the position of a distribution vehicle; the distribution vehicle is provided with a GPS module, and the position of the distribution vehicle is determined by positioning the position of the distribution vehicle through the GPS module on the distribution vehicle.
And the logistics path optimization module is used for adjusting the logistics path for the distribution vehicle according to the quality of the goods and the current position of the distribution vehicle.
This embodiment commodity circulation route intelligent optimization device still includes:
and the cargo quality detection model optimization module is used for aiming at the cargos of which the quality is detected by the cargo quality detection model, using the quality data as training samples, performing incremental learning on the current cargo quality detection model to obtain the incrementally learned cargo quality detection model, and using the model for the next detection.
Logistics path intelligent optimization device specifically includes rotten decision module of goods and route optimization module in this embodiment, wherein:
and the goods deterioration judging module is used for determining whether the goods are deteriorated according to the current quality of the goods after the goods quality detecting model detects the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are possibly deteriorated according to the comparison result.
In this embodiment, a threshold X may be set according to the type and kind of the goods, and the goods deterioration determination module compares the quality detected by the goods quality detection model with the threshold X, and if the quality does not exceed the threshold X, it indicates that the goods are not deteriorated, and the distribution vehicle may travel along the originally planned logistics route. In addition, the goods deterioration judging module may also detect whether the quality of the goods has changed significantly within a certain time period, so as to determine whether the goods are likely to be deteriorated, for example, at several time points in sequence, where the quality of the goods detected at time point t1 is a1, the quality of the goods detected at time point t2 is a2, the quality of the goods detected at time point t3 is a3, the current quality of the goods detected at current time point t4 is a4, and if the qualities a3 and a4 are both lower than the threshold X, but the difference between a4 and a3 exceeds a certain value, it is determined that the goods are likely to be deteriorated.
And the path optimization module is used for determining the logistics path of the distribution vehicle by adopting a logistics path selection strategy with a time window when the goods deterioration judgment module judges that the goods deteriorate or the deterioration is possible, and selecting the next distribution station which has the lowest distribution cost and meets the time window requirement from the current position for the distribution vehicle. The next station of the distribution vehicle arrives at the distribution station to carry out corresponding treatment, and further deterioration and damage of goods on the distribution vehicle are avoided.
The intelligent logistics path optimization device in this embodiment corresponds to the intelligent logistics path optimization method in embodiment 1, and therefore specific implementation of each module can be referred to above in embodiment 1, and is not described in detail herein; it should be noted that, the apparatus provided in this embodiment is only illustrated by dividing the functional modules, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure is divided into different functional modules to complete all or part of the functions described above. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Example 3
The embodiment discloses an intelligent logistics path optimization system, which comprises a terminal data acquisition device and an intelligent logistics path optimization device, as shown in fig. 3; the terminal data acquisition device is connected with the logistics path intelligent optimization device through a wireless network;
and the terminal data acquisition device is used for acquiring quality data of goods on the distribution vehicle and sending the data to the logistics path intelligent optimization device.
The intelligent logistics path optimization device is used for realizing the intelligent logistics path optimization method in embodiment 1, and comprises the following steps:
s1, acquiring quality data of goods with known quality collected on a distribution vehicle, and taking the data as a training sample;
s2, taking the training sample as the input of the neural network, taking the quality of the goods corresponding to the training sample as a label, and training the neural network to obtain a goods quality detection model;
s3, acquiring quality data of the goods collected on a distribution vehicle for goods distribution as a test sample;
s4, inputting the test sample into a goods quality detection model to detect the quality of goods;
and S5, acquiring the current position of the distribution vehicle, and adjusting a logistics path for the distribution vehicle according to the quality of the goods and the current position of the distribution vehicle. The specific process is as follows:
after the current quality of the goods is detected by the goods quality detection model, determining whether the goods are in a deterioration state or not according to the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are in a deterioration possibility or not according to a comparison result;
if not, the logistics path of the delivery vehicle is not changed;
if so, acquiring the current position of the distribution vehicle, determining the logistics path of the distribution vehicle by adopting a logistics path selection strategy with a time window, and selecting the next distribution station which has the lowest distribution cost and meets the time window requirement from the current position of the distribution vehicle.
In this embodiment, the terminal data acquisition device is arranged on the distribution vehicle and comprises a temperature sensor, a humidity sensor, an illumination intensity sensor, a camera and a microcontroller; wherein temperature sensor, humidity transducer, illumination intensity sensor, camera set up on the distribution vehicle and connect microcontroller respectively, and microcontroller can use chips such as singlechip.
The logistics path intelligent optimization device is arranged at a remote end, such as a logistics general monitoring room. The intelligent logistics path optimization device comprises a processor, and specifically, the intelligent logistics path optimization method described in embodiment 1 can be implemented by directly adopting a computer and utilizing the data processing function of the computer.
The microcontroller of the terminal data acquisition device is connected with the intelligent logistics path optimization device through a wireless communication network, and the intelligent logistics path optimization device acquires quality data, collected by the terminal data acquisition device, of distribution vehicles through the wireless communication network. A logistics path intelligent optimization device can be connected with terminal data acquisition devices on one or more distribution vehicles through a wireless communication network.
In this embodiment, the intelligent logistics path optimization device acquires quality data of the goods collected by the delivery vehicle by means of timing and/or alarm triggering, where the timing acquisition refers to: the processor acquires the quality data acquired by the terminal data acquisition device at regular time, and the specific implementation method can be as follows: the processor sends corresponding instructions to a microcontroller of the terminal data acquisition device at regular time, and the microcontroller sends quality data acquired by a temperature sensor, a humidity sensor, an illumination intensity sensor and a camera to the processor after receiving the corresponding instructions sent by the processor; wherein when the alarm triggers acquisition of the finger: when the quality data collected on the distribution vehicle exceeds a certain threshold value, namely an alarm value, the quality data collected on the distribution vehicle is obtained; the specific implementation mode can be as follows: the microcontroller of the terminal data acquisition device receives the quality data sent by each sensor, compares the received quality data with each set threshold value, and if the received quality data do not meet the requirements after comparison, the microcontroller sends an alarm signal to trigger the terminal data acquisition device to send each quality data to the processor; for example, the microcontroller receives a temperature signal sent by a temperature sensor, compares the temperature sensing signal with a set temperature threshold, and if the temperature sensing signal exceeds the temperature threshold, the microcontroller generates an alarm and sends each received quality data to the processor.
The distribution vehicle is provided with a GPS module, the GPS module is connected to the logistics path intelligent optimization device through a wireless network, and in the embodiment, the logistics path intelligent optimization device positions the distribution vehicle through the GPS module on the distribution vehicle to determine the position of the distribution vehicle.
Example 4
The embodiment discloses a storage medium, which stores a program, and when the program is executed by a processor, the method for intelligently optimizing a logistics path according to embodiment 4 is implemented as follows:
s1, acquiring quality data of goods with known quality collected on a distribution vehicle, and taking the data as a training sample;
s2, taking the training sample as the input of the neural network, taking the quality of the goods corresponding to the training sample as a label, and training the neural network to obtain a goods quality detection model;
s3, acquiring quality data of the goods collected on a distribution vehicle for goods distribution as a test sample;
s4, inputting the test sample into a cargo quality detection model to detect the quality of the cargo;
s5, obtaining the current position of the distribution vehicle, and adjusting a logistics path for the distribution vehicle according to the quality of goods and the current position of the distribution vehicle, wherein the specific process is as follows:
after the current quality of the goods is detected by the goods quality detection model, determining whether the goods are in a deterioration state or not according to the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are in a deterioration possibility or not according to a comparison result;
if not, the logistics path of the delivery vehicle is not changed.
If so, acquiring the current position of the distribution vehicle, determining the logistics path of the distribution vehicle by adopting a logistics path selection strategy with a time window, and selecting the next distribution station which has the lowest distribution cost and meets the time window requirement from the current position of the distribution vehicle.
In the present embodiment, the storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server, a data center, etc. that is integrated with one or more available media, and the available media may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD).
Example 5
The embodiment discloses a computing device, which includes a processor and a memory for storing an executable program of the processor, and when the processor executes the program stored in the memory, the method for intelligently optimizing a logistics path according to embodiment 1 is implemented as follows:
s1, acquiring quality data of goods with known quality collected on a distribution vehicle, and taking the data as a training sample;
s2, taking the training sample as the input of the neural network, taking the quality of the goods corresponding to the training sample as a label, and training the neural network to obtain a goods quality detection model;
s3, acquiring quality data of the goods collected on a distribution vehicle for goods distribution as a test sample;
s4, inputting the test sample into a goods quality detection model to detect the quality of goods;
and S5, acquiring the current position of the distribution vehicle, and adjusting a logistics path for the distribution vehicle according to the quality of the goods and the current position of the distribution vehicle. The specific process is as follows:
after the current quality of the goods is detected by the goods quality detection model, determining whether the goods are in a deterioration state or not according to the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are in a deterioration possibility or not according to a comparison result;
if not, the logistics path of the distribution vehicle is not changed.
If so, acquiring the current position of the distribution vehicle, determining the logistics path of the distribution vehicle by adopting a logistics path selection strategy with a time window, and selecting the next distribution station which has the lowest distribution cost and meets the time window requirement from the current position of the distribution vehicle.
The computing device in this embodiment may be a desktop computer, a notebook computer, a smart phone, a PDA handheld terminal, or a tablet computer.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such modifications are intended to be included in the scope of the present invention.
Claims (7)
1. An intelligent optimization method for a logistics path is characterized by comprising the following steps:
acquiring quality data of goods with known quality collected on a distribution vehicle as a training sample; the quality data of the goods comprises the temperature, the humidity and the illumination intensity of the environment where the goods are located and the photos of the goods;
the quality data of the goods corresponding to the training samples and the testing samples are respectively input into the neural network and the goods quality detection model after being preprocessed, wherein the preprocessing process comprises the following steps:
carrying out image segmentation on the photo of the goods, and segmenting the image into m x n blocks; calculating a Census conversion value of each block, and calculating a cumulative histogram of the Census conversion values of each block to obtain a 256-dimensional characteristic value of each block; cascading the characteristic values of all the blocks to form m × n × 256-dimensional image characteristic values;
cascading the temperature, the humidity and the illumination intensity of the environment where the goods are located and the acquired m x n 256-dimensional image characteristic values to form (m x n 256+ 3) -dimensional characteristic vectors which are used as the input of a neural network or a goods quality detection model;
training the neural network by taking the training sample as the input of the neural network and the quality of the goods corresponding to the training sample as a label to obtain a quality detection model of the goods;
acquiring quality data of goods collected on a distribution vehicle for goods distribution as a test sample;
inputting the test sample into a cargo quality detection model to detect the quality of the cargo;
acquiring the current position of a distribution vehicle;
adjusting a logistics path for a distribution vehicle according to the quality of the goods and the current position of the distribution vehicle; the specific process of adjusting the logistics path for the delivery vehicle is as follows:
after the current quality of the goods is detected by the goods quality detection model, determining whether the goods are in a deterioration state or not according to the current quality of the goods, and/or comparing the current quality of the goods with the quality before a certain time period, and determining whether the goods are in a deterioration possibility or not according to a comparison result;
if not, the logistics path of the distribution vehicle is not changed;
if so, acquiring the current position of the distribution vehicle, determining the logistics path of the distribution vehicle by adopting a logistics path selection strategy with a time window, and selecting a distribution station which has the lowest distribution cost and meets the requirement of the time window from the current position of the distribution vehicle;
the specific steps of determining the logistics path of the distribution vehicle by adopting the logistics path selection strategy with the time window are as follows:
setting a path from the current position of the vehicle to an original distribution station as a current logistics path;
calculating the cost of each reachable distribution station inserted into the current logistics path, selecting the reachable distribution station with the lowest cost to insert into the current logistics path, judging whether the distribution station can insert into the current logistics path under the constraint condition of a time window or not, if so, inserting the distribution station into the current path, and updating the logistics path; if not, keeping the current logistics path unchanged.
2. The intelligent logistics path optimization method of claim 1, wherein the neural network is a multilayer Convolutional (CNN) neural network, a deep residual error network and a hybrid neural network;
and aiming at the goods with the quality detected by the goods quality detection model, the quality data of the goods are used as training samples, and the current goods quality detection model is subjected to incremental learning.
3. The intelligent logistics path optimization method of claim 1, wherein the quality data of the collected goods on the distribution vehicle is acquired in a timed and/or alarm triggering mode aiming at the distribution vehicle carrying out goods distribution;
the alarm triggering mode is to acquire the quality data acquired by the delivery vehicle when the quality data acquired by the delivery vehicle exceeds a certain threshold.
4. An intelligent optimization device for logistics paths, which is applied to the intelligent optimization method for logistics paths of any one of claims 1-3, the device comprising:
the system comprises a training sample acquisition module, a quality analysis module and a quality analysis module, wherein the training sample acquisition module is used for acquiring quality data of goods with known quality acquired on a distribution vehicle as training samples;
the cargo quality detection model building module is used for taking the training samples as the input of the neural network, taking the cargo quality corresponding to the training samples as the label, and training the neural network to obtain a cargo quality detection model;
the system comprises a test sample acquisition module, a data acquisition module and a data processing module, wherein the test sample acquisition module is used for acquiring quality data of goods acquired by a delivery vehicle for delivering the goods as a test sample;
the goods quality detection module is used for inputting the test samples into the goods quality detection model to detect the quality of the goods;
the distribution vehicle position acquisition module is used for acquiring the position of a distribution vehicle;
and the logistics path optimization module is used for adjusting the logistics path for the distribution vehicle according to the quality of the goods and the current position of the distribution vehicle.
5. An intelligent logistics path optimization system is characterized by comprising a terminal data acquisition device and an intelligent logistics path optimization device; the terminal data acquisition device is connected with the logistics path intelligent optimization device through a wireless network;
the terminal data acquisition device is used for acquiring quality data of goods on a distribution vehicle and sending the data to the logistics path intelligent optimization device;
the intelligent logistics path optimization device is used for realizing the intelligent logistics path optimization method of any one of claims 1 to 3.
6. A storage medium storing a program, wherein the program, when executed by a processor, implements the method for intelligently optimizing a logistics path of any one of claims 1 to 3.
7. A computing device comprising a processor and a memory for storing a processor-executable program, wherein the processor, when executing the program stored in the memory, implements the intelligent logistics path optimization method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911003482.5A CN111222675B (en) | 2019-10-22 | 2019-10-22 | Logistics path intelligent optimization method, device, system, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911003482.5A CN111222675B (en) | 2019-10-22 | 2019-10-22 | Logistics path intelligent optimization method, device, system, medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111222675A CN111222675A (en) | 2020-06-02 |
| CN111222675B true CN111222675B (en) | 2023-04-07 |
Family
ID=70805813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911003482.5A Active CN111222675B (en) | 2019-10-22 | 2019-10-22 | Logistics path intelligent optimization method, device, system, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222675B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815249B (en) * | 2020-08-31 | 2021-01-01 | 北京每日优鲜电子商务有限公司 | Distribution management method |
| CN112950131A (en) * | 2021-04-21 | 2021-06-11 | 辽宁工程技术大学 | Transportation path optimization system and method of logistics management system |
| CN114386897B (en) * | 2021-12-21 | 2022-10-21 | 中武(福建)跨境电子商务有限责任公司 | Supply chain logistics distribution system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103903117A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Logistics intelligent conveying supervision method |
| CN108416561A (en) * | 2018-05-03 | 2018-08-17 | 闽南师范大学 | A kind of fresh commodity distribution control method and system |
-
2019
- 2019-10-22 CN CN201911003482.5A patent/CN111222675B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103903117A (en) * | 2014-03-22 | 2014-07-02 | 哈尔滨工程大学 | Logistics intelligent conveying supervision method |
| CN108416561A (en) * | 2018-05-03 | 2018-08-17 | 闽南师范大学 | A kind of fresh commodity distribution control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111222675A (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111222675B (en) | Logistics path intelligent optimization method, device, system, medium and equipment | |
| US8751414B2 (en) | Identifying abnormalities in resource usage | |
| CN112348428B (en) | Container monitoring method, device, server and storage medium | |
| US20060074828A1 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| US11508163B2 (en) | Method and apparatus for training lane line identifying model, device, and storage medium | |
| US10885620B2 (en) | Neural network image processing system | |
| US10679064B2 (en) | Optimized classifier update | |
| US10564195B2 (en) | System and method for energy sample forecasting of HVAC-R systems | |
| US7373332B2 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| CN112433122A (en) | Charging pile available state detection method, device, equipment and storage medium | |
| CN107422715A (en) | The system and device of a kind of storage information | |
| CN115687447A (en) | Marine environment monitoring system and method based on Internet of things | |
| CN111695735B (en) | Flow calculation-based railway bow net real-time early warning method, system and device | |
| Hung et al. | Model-driven traffic data acquisition in vehicular sensor networks | |
| CN115587545B (en) | Parameter optimization method, device and equipment for photoresist and storage medium | |
| CN111640134A (en) | Face tracking method and device, computer equipment and storage device thereof | |
| CN115298705A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN114997310A (en) | Environment-friendly monitoring data processing method and system | |
| US20060074826A1 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| US20060074827A1 (en) | Methods and apparatus for detecting temporal process variation and for managing and predicting performance of automatic classifiers | |
| EP3499419A1 (en) | Information processing method, information processing apparatus, and program | |
| CN114187502A (en) | Vehicle loading rate identification method and device, electronic equipment and storage medium | |
| CN113837173A (en) | Target object detection method and device, computer equipment and storage medium | |
| CN117573153B (en) | Router chip burning method, device, electronic equipment and computer readable medium | |
| CN115017962B (en) | Riding number detection method, target characteristic sequence determination method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |