CN117474299A - Prediction method, device and equipment for cold transport supply and demand - Google Patents
Prediction method, device and equipment for cold transport supply and demand Download PDFInfo
- Publication number
- CN117474299A CN117474299A CN202311817343.2A CN202311817343A CN117474299A CN 117474299 A CN117474299 A CN 117474299A CN 202311817343 A CN202311817343 A CN 202311817343A CN 117474299 A CN117474299 A CN 117474299A
- Authority
- CN
- China
- Prior art keywords
- cold
- time
- demand
- supply
- time sequence
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000000452 restraining effect Effects 0.000 claims abstract description 3
- 230000008569 process Effects 0.000 claims description 13
- 238000001816 cooling Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000013519 translation 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a prediction method, a device and equipment for cold transport supply and demand, belonging to the technical field of intelligent cold transport prediction, wherein the method comprises the following steps: acquiring the main delivery quantity of the cold cargos and the quantity of drivers participating in cold chain transportation based on the time sequence, and defining the cold transport supply-demand ratio based on the time sequence; the method comprises the steps of taking the influence of holidays on a time sequence into consideration by acquiring an overall trend curve of the time sequence and a time periodicity rule representing seasonality, introducing error items, and restraining the time sequence; according to the cold transport supply and demand ratio corresponding to the constrained time sequence, predicting cold transport supply and demand corresponding to the next time node of the current time node by acquiring the current time node; the prediction technology for the cold transportation supply and demand provided by the invention comprises nonlinear trends such as year, month, day periodicity, holiday influence and the like, and the strong seasonal influence factors of the cold transportation are fully considered, so that the invention can better predict the cold transportation supply and demand.
Description
Technical Field
The invention relates to the technical field of intelligent prediction of cold transport, in particular to a prediction method, a device and equipment for cold transport supply and demand.
Background
Cold chain transportation (Cold-chain transportation) refers to transportation in which the transported goods always maintain a certain temperature in the whole transportation process, regardless of the links of loading, unloading, transporting, changing transportation modes, changing packaging equipment and the like; along with the improvement of the living standard of people, the demand of people for fresh agricultural and sideline products is higher and higher, and the freshness of foods is also more and more critical, so that higher requirements for cold chain transportation are provided.
The real-time problem of cold chain transportation can be effectively solved by predicting cold transportation supply and demand through an artificial intelligence algorithm, but the conventional prediction algorithm generally adopts a moving average method or ARIMA model (Autoregressive Integrated Moving Average model) to do time sequence prediction, and also uses a Long Short-Term Memory (LSTM) network; however, the moving average method or ARIMA model is only suitable for short-time prediction, and does not consider periodicity, holidays or other factors, so that the accuracy of prediction is poor, LSTM cannot predict for a long time, the model is complex, and the speed is low when large data volume is calculated; therefore, it is urgently required to design a new prediction technique for cooling supply and demand to improve accuracy of prediction of cooling supply and demand.
Disclosure of Invention
In order to solve the problems, the invention aims to provide a prediction technology for cold transport supply and demand, which can predict the supply and demand ratio in the cold transport market in a future period of time, thereby helping to regulate the market balance, promote the matching efficiency and promote the success.
In order to achieve the above technical object, the present application provides a prediction method for cooling supply and demand, including the steps of:
acquiring the main delivery quantity of the cold cargos and the quantity of drivers participating in cold chain transportation based on the time sequence, and defining the cold transport supply-demand ratio based on the time sequence;
the method comprises the steps of taking the influence of holidays on a time sequence into consideration by acquiring an overall trend curve of the time sequence and a time periodicity rule representing seasonality, introducing error items, and restraining the time sequence;
and predicting the cold supply and demand corresponding to the next time node of the current time node by acquiring the current time node according to the cold supply and demand ratio corresponding to the constrained time sequence.
Preferably, in defining the time series-based cold transport supply-demand ratio, a time series is formed by a time period corresponding to the history data based on the history data of the number of cold transport main shipments and the number of drivers involved in cold chain transportation;
based on the time series, the supply quantity of the cold operation divided by the demand quantity of the cold operation is defined as a cold operation supply-demand ratio based on the time series.
Preferably, in the process of acquiring the overall trend curve of the time sequence, acquiring the overall trend curve according to the variation trend of the time sequence on the non-periodic surface;
the overall trend curve includes a nonlinear trend term and a linear trend term, wherein the nonlinear trend term is expressed as:
wherein, C is the upper limit of the numerical value, k represents the linear increasing rate, m represents the offset parameter, and t represents the time;
the linear trend term is expressed as:
k is the linear growth rate.
Preferably, in the process of acquiring the time periodicity law representing the season, the time periodicity law of the time sequence is acquired through the fourier series, wherein the time periodicity law is expressed as:
where P represents a period, N represents the number of approximation terms, a n And b n Is a parameter to be learned, a n And b n The vector representation is β= [ a 1 ,b 1 ,a 2 ,b2,……a n ,b n ] T ；
The beta-coincidence normal distribution is expressed as:
where σ is the variance of the normal distribution.
Preferably, in the process of acquiring the effect of holidays on time series, the holidays are unithermally encoded, and the holiday effect is expressed as:
wherein L represents the number of holidays, D i The date set representing the holiday in the past and in the future, K conforms to a normal distribution, and the variance v of the normal distribution represents the holiday influence parameter.
Preferably, in the process of constraining the time series, the constrained time series is expressed as:
wherein t represents time and y (t) is the final predicted value; g (t) is a trend term representing the overall trend curve of the time series; s (t) is a time periodicity term representing a seasonal periodicity law; h (t) is a holiday term representing the effect of holidays on the time series;is an error term.
Preferably, in the process of predicting the cold supply and demand, the problem is converted into an optimization problem according to a method for estimating MAP by a maximum posterior, the constrained time sequence is solved by using an L-BFGS quasi-Newton method, the cold supply and demand ratio is adjusted according to the solved result, and the cold supply and demand of the next time node is predicted by acquiring the cold supply and demand ratio of the current time node.
The invention discloses a prediction device for cold transport supply and demand, which comprises:
the cold transport data acquisition module is used for acquiring the main delivery quantity of the cold transport goods and the quantity of drivers participating in cold chain transport based on the time sequence;
the cold transport supply and demand ratio definition module is used for defining the cold transport supply and demand ratio based on the time sequence according to the main delivery quantity of the cold transport corresponding to the time sequence and the quantity of drivers participating in cold chain transportation;
the cold operation time constraint module is used for considering the influence of holidays on the time sequence by acquiring an overall trend curve of the time sequence and a time periodicity rule representing seasonality, introducing an error term and constraining the time sequence;
and the cold supply and demand prediction module is used for predicting the cold supply and demand corresponding to the next time node of the current time node by acquiring the current time node according to the cold supply and demand ratio corresponding to the constrained time sequence.
The invention discloses the following technical effects:
the prediction technology for the cold transportation supply and demand provided by the invention comprises nonlinear trends such as year, month, day periodicity, holiday influence and the like, and the strong seasonal influence factors of the cold transportation are fully considered, so that the invention can better predict the cold transportation supply and demand;
the invention is based on statistics, can learn from a small amount of data, has high efficiency and can predict for a long time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the method of the invention.
Description of the embodiments
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
As shown in FIG. 1, the invention fully considers nonlinear trends including year, month, day periodicity, holiday influence and the like, and aims at the characteristic that cold transport has strong seasonal influence, and the invention provides a prediction technology for cold transport supply and demand, which can predict the supply and demand ratio in the cold transport market in a future period of time, thereby helping to regulate market balance, promote matching efficiency and promote success, and the specific technical process comprises the following steps:
1. historical data preparation:
1. the city-separated goods classification counts the historical main shipment quantity of the cold transportation goods according to the day. The shipping quantity of the cold carrier represents the required portion of the market. If there are duplicate shipping cases, the duplication should be removed to better express the real needs of the market. The longer the history period, the better the time period trend can be calculated better.
2. The number of drivers in the history is counted according to the day by day according to the city classification. The number of drivers represents the supply portion of the market, and statistics are made based on the driver's expressed willingness to transport cold goods to better express the actual supply of the market. The longer the history period, the better, preferably consistent with the cold shipment volume time period.
3. The supply number divided by the demand number is the supply-demand ratio.
The following prediction method is adopted to respectively predict the number of the goods finding drivers and the number of the duplicate removal shipments, so as to obtain the predicted supply-demand ratio.
2. The method comprises the following steps:
1. the method is an addition model of a time sequence, and mainly comprises a trend term, periodicity, holidays and an error term.
；
Wherein t represents time and y (t) is the final predicted value; g (t) is a trend term representing the overall trend curve of the time series; s (t) is a time periodicity term representing a seasonal, such as a month periodicity, a week periodicity, or a day periodicity law; h (t) is a holiday term representing the effect of holidays on the time series;is an error term.
2. The trend term g (t) is calculated. It shows the trend of the time series over the non-period. The trend terms are divided into a nonlinear trend term g1 (t) and a linear trend term g2 (t).
Formula of nonlinear trend term
；
Where C is an upper numerical limit and k represents a linear growth rate or slope, and when k >0, the trend is upward, whereas downward, the greater k indicates the faster the trend. When k >0, with increasing time t, exp (-k (t-m)) tends to be 0, g1 (t) tends to be C, m is an offset parameter, and represents a turning point where the slope of the trend term changes, the left-right translation of the curve can be adjusted.
Linear trend term formula:
；
k is the linear growth rate or slope and m is the offset parameter.
3. The time periodicity term s (t) is calculated. The time periodicity includes changes in years, months, weeks, days, etc. due to time changes, and has a periodicity law. The fourier series is used here to model the periodicity of the time series.
；
Where P represents a period (the annual period is 365 and the week is 7), N represents the number of approximation items, and N is finer as it is larger. a, a n And b n Is a parameter that needs to be learned. a, a n And b n The vector representation is β= [ a 1 ,b 1 ,a 2 ,b 2 ,……a n ,b n ] T Beta corresponds to a normal distribution, expressed as:
；
the variance of the normal distribution is σ. The effect of the time periodicity on the prediction result can be adjusted by the parameter sigma, the larger this value is, the larger the effect of the time periodicity is, the smaller this value is, the smaller the effect of the time periodicity is. The time periodicity term may be selected from two formulas, an addition or a multiplication.
4. And calculating holiday term h (t). In the real world, there are legal holidays in addition to Saturday and sunday. The supply and demand of the cold market is greatly affected by holidays during which the shipment and the number of drivers are greatly reduced, so that the holiday term is a very important factor.
The legal holidays vary in the day of the year and accurate recording of the day of the year is required. Some special holidays such as spring festival are included, the legal date is generally 7 days, but in the cold transport market, the period of time before and after spring festival is still the valley period. Therefore, the date of the spring festival is prolonged for 7 days before and after the spring festival.
In the calculation of the method, each holiday is used as an independent model, and the model of the working day is not affected:
；
；
assume a total of L holidays, D i A date set representing the holiday in the past and in the future, and the holiday is encoded with one-hot encoding, i.e. if the date is the holiday, the corresponding value of the date is 1, and if not the holiday, the corresponding value of the date is 0; the variance v of the normal distribution is the holiday influence parameter, when the parameter value is larger, the influence of the holiday on the model is larger, and when the value is smaller, the influence of the holiday on the model is smaller, and the parameter can be adjusted according to actual conditions. Holiday terms may also be selected from two formulas, either additive or multiplicative.
5. The next step is training of the model. The super parameters to be trained by the model are K, m in trend term, beta in season term, K in holiday term and error term. The true value in the training data is the a priori distribution, expressed by the formula y (t) =g (t) +s (t) +h (t) +i>The posterior probability distribution is obtained, the problem is converted into an optimization problem according to the maximum posterior MAP estimation method, and the L-BFGS quasi-Newton method is used for solving.
6. And respectively training two time sequence prediction models of the number of the goods finding drivers and the number of the goods removing and returning to obtain the prediction results of the two groups of values. Dividing the predicted number of the goods finding drivers by the predicted number of the goods removing and re-sending to obtain the predicted supply-demand ratio.
。
Embodiments of the present application also provide a computer system device having a processor, a memory, and the like. The device stores a computer program which performs the following task steps:
firstly, acquiring historical cold shipment data and the number of finding drivers, and storing the data on a memory;
then, running a cold transport supply and demand prediction method program to respectively predict the cold transport shipping number and the goods finding driver number of 7 days in the future;
and finally, calculating the cold transport supply and demand ratio by using the predicted result data.
Aiming at holiday conditions, the invention focuses on treating window periods before and after spring and delays holiday effect. Meanwhile, the parameter can be adjusted to be addition or multiplication, so that the method has higher flexibility. Therefore, when the delivery amount and the number of drivers in the cold transport market are predicted, the holiday term adjustment is better utilized, so that the prediction result is more accurate.
The invention has higher prediction accuracy of the cold transport supply-demand ratio, the index for measuring the accuracy is MAPE (Mean Absolute Percentage Error, average absolute percentage error), and the calculation formula is
Wherein M is MAPE, n is the number of samples, t is the time series {1,2,3 … …, n }, A t Is the true value at time t, F t Is the predicted value at time t.
Compared with the actual value, the average MAPE of 7 days for the repeated delivery number and the average MAPE of 7 days for the delivery number is 0.08, the average MAPE of 7 days for the delivery number is 0.03, the error is within 0.1, and the supply and demand ratio of the cold transport duration can be predicted well. For the network freight platform, the supply-demand ratio can be predicted in advance, and market operators can be helped to actively take measures to adjust market balance, so that the achievement of drivers and owners of goods is promoted.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A method for predicting cooling supply and demand, comprising the steps of:
acquiring the main delivery quantity of the cold cargos and the quantity of drivers participating in cold chain transportation based on the time sequence, and defining the cold transport supply-demand ratio based on the time sequence;
the method comprises the steps of obtaining an overall trend curve of the time sequence and a time periodicity rule representing seasonality, considering the influence of holidays on the time sequence, introducing error items, and restraining the time sequence;
and predicting the cold supply and demand corresponding to the next time node of the current time node by acquiring the current time node according to the cold supply and demand ratio corresponding to the constrained time sequence.
2. A method of predicting cooling supply and demand according to claim 1, wherein:
in the process of defining the cold transport supply-demand ratio based on the time sequence, forming the time sequence through a time period corresponding to the historical data based on the historical data of the main delivery quantity of the cold transport and the quantity of drivers participating in cold chain transportation;
based on the time series, dividing the supply quantity of cold operation by the demand quantity of cold operation is defined as a cold operation supply-demand ratio based on the time series.
3. A method of predicting cooling supply and demand according to claim 2, wherein:
in the process of acquiring the overall trend curve of the time sequence, acquiring the overall trend curve according to the variation trend of the time sequence on the non-periodic surface;
the overall trend curve includes a nonlinear trend term and a linear trend term, wherein the nonlinear trend term is expressed as:
，
wherein, C is the upper limit of the numerical value, k represents the linear increasing rate, m represents the offset parameter, and t represents the time;
the linear trend term is expressed as:
，
k is the linear growth rate.
4. A method of predicting cooling supply and demand according to claim 3, wherein:
in the process of acquiring the time periodicity law representing the season, acquiring the time periodicity law of the time sequence through a Fourier series, wherein the time periodicity law is expressed as:
，
where P represents a period, N represents the number of approximation terms, a n And b n Is a parameter to be learned, a n And b n The vector representation is β= [ a 1 ,b 1 ,a 2 ,b 2 ,……a n ,b n ] T ；
The beta-coincidence normal distribution is expressed as:
，
where σ is the variance of the normal distribution.
5. A method of predicting cooling supply and demand according to claim 4, wherein:
in the process of acquiring the influence of holidays on the time sequence, the holidays are subjected to one-time coding, and the holiday influence is expressed as:
，
wherein L represents the number of holidays, D i The date set representing the holiday in the past and in the future, K conforms to a normal distribution, and the variance v of the normal distribution represents the holiday influence parameter.
6. A method of predicting cooling supply and demand according to claim 5, wherein:
in the process of constraining the time series, the constrained time series is expressed as:
，
wherein t represents time and y (t) is the final predicted value; g (t) is a trend term representing the overall trend curve of the time series; s (t) is a time periodic term representing seasonalA periodicity law; h (t) is a holiday term representing the effect of holidays on the time series;is an error term.
7. A method of predicting cooling supply and demand according to claim 6, wherein:
in the process of predicting the cold supply and demand, the problem is converted into an optimization problem according to a MAP maximum posterior estimation method, the constrained time sequence is solved by using an L-BFGS quasi-Newton method, the cold supply and demand ratio is adjusted according to the solved result, and the cold supply and demand of the next time node is predicted by acquiring the cold supply and demand ratio of the current time node.
8. A predictive device for cooling supply and demand, comprising:
the cold transport data acquisition module is used for acquiring the main delivery quantity of the cold transport goods and the quantity of drivers participating in cold chain transport based on the time sequence;
the cold transport supply and demand ratio definition module is used for defining the cold transport supply and demand ratio based on the time sequence according to the main delivery quantity of the cold transport corresponding to the time sequence and the quantity of drivers participating in cold chain transportation;
the cold operation time constraint module is used for constraining the time sequence by acquiring an overall trend curve of the time sequence and a time periodicity rule representing seasonality and considering the influence of holidays on the time sequence and introducing error items;
and the cold supply and demand prediction module is used for predicting the cold supply and demand corresponding to the next time node of the current time node by acquiring the current time node according to the cold supply and demand ratio corresponding to the constrained time sequence.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.
10. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311817343.2A CN117474299B (en) | 2023-12-27 | 2023-12-27 | Prediction method, device and equipment for cold transport supply and demand |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311817343.2A CN117474299B (en) | 2023-12-27 | 2023-12-27 | Prediction method, device and equipment for cold transport supply and demand |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117474299A true CN117474299A (en) | 2024-01-30 |
| CN117474299B CN117474299B (en) | 2024-02-27 |
Family
ID=89626089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311817343.2A Active CN117474299B (en) | 2023-12-27 | 2023-12-27 | Prediction method, device and equipment for cold transport supply and demand |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474299B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN114169568A (en) * | 2021-11-03 | 2022-03-11 | 国网浙江省电力有限公司瑞安市供电公司 | Prophet model-based power distribution line current prediction and heavy overload early warning and system |
| CN115081681A (en) * | 2022-05-25 | 2022-09-20 | 四川大学 | Prophet algorithm-based wind power prediction method |
| CN116205329A (en) * | 2022-12-13 | 2023-06-02 | 贵州智诚科技有限公司 | Holiday passenger flow prediction method |
-
2023
- 2023-12-27 CN CN202311817343.2A patent/CN117474299B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657831A (en) * | 2017-10-11 | 2019-04-19 | 顺丰科技有限公司 | A kind of Traffic prediction method, apparatus, equipment, storage medium |
| CN114169568A (en) * | 2021-11-03 | 2022-03-11 | 国网浙江省电力有限公司瑞安市供电公司 | Prophet model-based power distribution line current prediction and heavy overload early warning and system |
| CN115081681A (en) * | 2022-05-25 | 2022-09-20 | 四川大学 | Prophet algorithm-based wind power prediction method |
| CN116205329A (en) * | 2022-12-13 | 2023-06-02 | 贵州智诚科技有限公司 | Holiday passenger flow prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117474299B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lai et al. | Valuation of storage at a liquefied natural gas terminal | |
| US11361276B2 (en) | Analysis and correction of supply chain design through machine learning | |
| CN109636826A (en) | Live pig weight method for measurement, server and computer readable storage medium | |
| Han et al. | Forecasting dry bulk freight index with improved SVM | |
| CN109829758A (en) | Sales Volume of Commodity prediction technique and system towards more duration of insurances | |
| CN111079989A (en) | Water supply company water supply amount prediction device based on DWT-PCA-LSTM | |
| CN117474299B (en) | Prediction method, device and equipment for cold transport supply and demand | |
| CN114241230A (en) | Target detection model pruning method and target detection method | |
| CN115409563A (en) | Multi-factor-influenced agricultural equipment inventory demand prediction method | |
| CN114942951A (en) | Fishing vessel fishing behavior analysis method based on AIS data | |
| Kronbak | The dynamics of an open-access fishery: Baltic Sea cod | |
| CN107169532A (en) | A kind of car networking fuel consumption data method for evaluating quality based on wavelet analysis and semi-supervised learning | |
| CN110415835B (en) | Method and device for predicting residual life of mechanical equipment | |
| CN108090785B (en) | Method and device for determining user behavior decline tendency and electronic equipment | |
| CN113592153B (en) | Goods distribution method, device, medium and computer equipment | |
| CN112712251B (en) | Ship intelligent scheduling method applied to barge management system | |
| Boyko | Data Interpretation Algorithm for Adaptive Methods of Modeling and Forecasting Time Series | |
| Artemenkov et al. | Population Dynamics of Atlantic Chub Mackerel Scomber colias at the Multispecies Fishery | |
| CN116579508B (en) | Fish prediction method, device, equipment and storage medium | |
| Zhabitskii et al. | A Digital Twin of Intensive Aquabi-otechnological Production Based on a Closed Ecosystem Modeling & Simulation | |
| Ramshorst | Forecasting Transportation Volumes at Farm Trans | |
| CN116502850B (en) | Cabin position distribution method, device and equipment | |
| CN116863276A (en) | Preparation method and system for realizing selenium-enriched livestock products | |
| US20230090377A1 (en) | System and Method for Optimizing Backhaul Loads in Transportation System | |
| Gaida et al. | The decision making mechanisms in sea container traffic management |
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 |