CN117787838B - Logistics digital management system and method based on AI large model - Google Patents
Logistics digital management system and method based on AI large model Download PDFInfo
- Publication number
- CN117787838B CN117787838B CN202410211203.9A CN202410211203A CN117787838B CN 117787838 B CN117787838 B CN 117787838B CN 202410211203 A CN202410211203 A CN 202410211203A CN 117787838 B CN117787838 B CN 117787838B
- Authority
- CN
- China
- Prior art keywords
- time
- data
- logistics
- aware
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 230000004044 response Effects 0.000 claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 230000008859 change Effects 0.000 claims abstract description 9
- 238000007726 management method Methods 0.000 claims description 42
- 238000012098 association analyses Methods 0.000 claims description 25
- 238000013507 mapping Methods 0.000 claims description 20
- 238000013468 resource allocation Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 230000035945 sensitivity Effects 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 6
- 238000013439 planning Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 5
- 125000004122 cyclic group Chemical group 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 229910000831 Steel Inorganic materials 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000010959 steel Substances 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of electric digital data processing, in particular to a logistics digital management system and method based on an AI large model. The method specifically comprises the following steps: firstly, preprocessing original logistics data, converting the preprocessed logistics data into a high-dimensional feature space, analyzing time sequence association of data features, and extracting information affecting decision; then, a time-aware multi-layer circulation network model is constructed, and decision information is obtained through a time-aware gating unit, a multi-layer circulation structure, multi-element feature fusion and a weighting mechanism. The problems of insufficient prediction accuracy, low resource utilization efficiency, slow response speed to market change, decision making based on experience instead of data driving, limited risk management and emergency response capability and lack of continuous learning and self-optimizing capability in the prior art are solved.
Description
Technical Field
The invention relates to the field of electric digital data processing, in particular to a logistics digital management system and method based on an AI large model.
Background
In the modern logistics industry, with the rapid development of globalization and electronic commerce, logistics systems face increasing complexity and dynamics. Such environments require logistics management systems that are not only efficient and reliable, but also have the ability to process large amounts of dynamic data, respond quickly to market changes, and make accurate decisions. However, conventional logistics management methods often rely on empirical judgment and manual operation, lack efficient processing capability and flexibility for complex data, and are difficult to cope with increasingly complex and changing market demands.
With the development of artificial intelligence technology, the progress of big data processing, machine learning and deep learning provides a new solution for a logistics management system. By utilizing the techniques, a large amount of logistics data can be processed and analyzed more effectively, so that prediction accuracy is improved, resource allocation is optimized, risk management capability is enhanced, customer service level is improved, and more intelligent and automatic logistics management is realized.
Chinese patent application number: CN202310936680.7, publication date: 2023.11.03 discloses a logistics digital management system of a whole iron and steel plant based on coordination, which comprises a client, a coordination platform and an analysis management platform; the client is used for registering, logging in, inquiring information and grading authority of the collaboration platform and the analysis management platform; the collaboration platform is used for inputting and updating logistics information; the analysis management platform is used for database storage, index calculation, index analysis and logistics operation feedback. The invention can lead the steel enterprise to carry out real-time, comprehensive and accurate control on logistics information, can effectively support the instantaneous intelligent decision of the logistics supply chain of the steel enterprise, and plays a positive role in improving logistics efficiency.
However, the above technology has at least the following technical problems: the problems of insufficient prediction accuracy, low resource utilization efficiency, slow response market change speed, decision making depending on experience rather than data driving, limited risk management and emergency response capability, unstable customer service quality and lack of continuous learning and self-optimizing capability in the prior art mainly result from the limited capability of the traditional logistics system for large data processing and complex pattern recognition and poor adaptability to dynamic market environment.
Disclosure of Invention
The invention provides a logistics digital management system and method based on an AI large model, which solve the problems of insufficient prediction accuracy, low resource utilization efficiency, slow response market change speed, decision making depending on experience instead of data driving, limited risk management and emergency response capability and lack of continuous learning and self-optimizing capability in the prior art, wherein the defects mainly result from limited capability of a traditional logistics system for large data processing and complex pattern recognition and weak adaptability to dynamic market environment. The logistics digital management system based on the AI large model can effectively improve the accuracy of logistics prediction, optimize resource utilization, accelerate market response speed and support data-driven decision making.
The invention provides a logistics digital management system and method based on an AI large model, which concretely comprises the following technical scheme:
logistics digital management system based on AI large model includes following parts:
The system comprises a preprocessing module, a multidimensional mapping module, a correlation analysis module, an extraction module and a time perception multi-layer circulation module;
The preprocessing module is used for carrying out format conversion and standardized preprocessing on the original logistics data, and is connected with the multidimensional mapping module and the time-aware multilayer circulation module in a data transmission mode;
The multidimensional mapping module is used for converting the preprocessed data into a high-dimensional feature space and is connected with the association analysis module in a data transmission mode;
the association analysis module is used for analyzing the time sequence association of the multidimensional data features in the high-dimensional feature space to obtain a dynamic association analysis result, and the association analysis module is connected with the extraction module in a data transmission mode;
The extraction module is used for extracting data features for predicting logistics demands and optimizing resource allocation from dynamic association analysis results, and is connected with the time-aware multi-layer circulation module in a data transmission mode;
The time-aware multi-layer circulation module is used for constructing a time-aware multi-layer circulation network model, introducing sensitivity to time variation by using a time-aware gating unit, processing and analyzing time variation data by using a multi-layer circulation structure, fusing data features from different layers by using a multi-element feature fusion and weighting mechanism, and converting the fused features into decisions of resource allocation, path planning or demand prediction.
A logistics digital management method based on an AI large model comprises the following steps:
s1, preprocessing original logistics data, converting the preprocessed logistics data into a high-dimensional feature space, analyzing time sequence association of data features, and extracting information affecting decision;
S2, constructing a time-aware multi-layer circulation network model, and obtaining decision information through a time-aware gating unit, a multi-layer circulation structure, multi-element feature fusion and a weighting mechanism.
Preferably, the S1 specifically includes:
Scaling the original logistics data by using a logarithmic function in the pretreatment process; and converting the preprocessed logistics data into a high-dimensional feature space through multi-dimensional mapping to obtain a feature set obtained through multi-dimensional mapping.
Preferably, the S1 further includes:
and analyzing the time sequence association of the data features in the feature set obtained by multidimensional mapping to obtain a dynamic association analysis result.
Preferably, the S1 further includes:
and extracting information influencing the decision from the dynamic association analysis result, and identifying data features influencing the predicted logistics demand and the optimized resource allocation.
Preferably, the S2 specifically includes:
the core of the time-aware multi-layer cyclic network model is a time-aware gating unit, and sensitivity to time variation is introduced into the time-aware multi-layer cyclic network model.
Preferably, the S2 further includes:
And capturing and analyzing data characteristics of at least two layers of information over time, including cargo flow and supply chain states in the logistics, by adopting a multi-layer circulating structure.
Preferably, the S2 further includes:
And introducing a multi-feature fusion and weighting mechanism into the time-aware multi-layer cyclic network model, and fusing the data features from different layers.
Preferably, the S2 further includes:
And converting the fused features into prediction results, and converting the fused features into decision information of resource allocation, path planning or demand prediction in a logistics digital management system.
The technical scheme of the invention has the beneficial effects that:
1. By utilizing a time-aware multilayer circulation network model and combining data processing and analysis technology, key indexes such as logistics demand, resource allocation, transportation route selection and the like are accurately predicted, so that logistics management is more effective, and market change response is quicker; according to the prediction result, the inventory level and the production scheduling are optimized, the resource waste is reduced, the transportation efficiency can be maximized, the cost is reduced, and the customer requirements are met in time;
2. In a rapidly-changing market environment, it is important to rapidly respond to customer demands and market changes, and the high-efficiency data processing capacity and accurate prediction result of the system allow rapid decision making, so that the overall logistics response speed is improved; by combining multidimensional data analysis and a complex algorithm model, data-driven decision support is provided for a manager, uncertainty of intuitive or experience-driven decision is reduced, and reliability of the decision is improved; by analyzing and predicting market trends, supply chain outage risks, etc., the manager is aided in developing more efficient risk management policies and emergency response plans.
Drawings
FIG. 1 is a block diagram of a large AI-model-based logistics digital management system according to one embodiment of the present invention;
fig. 2 is a flowchart of a logistics digitalized management method based on an AI large model according to an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the logistics digital management system and method based on the AI large model provided by the invention with reference to the drawings.
Referring to fig. 1, a block diagram of a large AI model-based logistics digital management system according to an embodiment of the present invention is shown, the system includes:
The system comprises a preprocessing module, a multidimensional mapping module, a correlation analysis module, an extraction module and a time perception multi-layer circulation module;
The preprocessing module is used for preprocessing the original logistics data, comprises format conversion and standardization processing, and is used for reducing the influence of extreme values, and is connected with the multidimensional mapping module and the time perception multi-layer circulation module in a data transmission mode;
The multidimensional mapping module is used for converting the preprocessed data into a high-dimensional feature space, revealing hidden association and mode among the data, and is connected with the association analysis module in a data transmission mode;
The association analysis module is used for analyzing the time sequence association of the multidimensional data features in the high-dimensional feature space, capturing the data features evolving along with time to obtain a dynamic association analysis result, and is connected with the extraction module in a data transmission mode;
The extraction module is used for extracting critical information for decision, such as predicting logistics requirements and optimizing key data characteristics of resource allocation, from dynamic association analysis results, and is connected with the time-aware multi-layer circulation module in a data transmission mode;
The time-aware multi-layer circulation module is used for constructing a time-aware multi-layer circulation network model and improving the accuracy and efficiency of logistics data processing; the sensitivity of time change is introduced by using a time perception gating unit, multi-layer time change data is processed and analyzed through a multi-layer circulating structure, and the data features from different layers are fused by using a multi-element feature fusion and weighting mechanism, so that the fused features are converted into various decisions such as resource allocation, path planning or demand prediction.
Referring to fig. 2, a flowchart of a method for digitally managing a logistics based on an AI large model according to an embodiment of the present invention is shown, the method includes the following steps:
s1, preprocessing original logistics data, converting the preprocessed logistics data into a high-dimensional feature space, analyzing time sequence association of data features, and extracting information affecting decision;
an efficient logistics data collection and arrangement mechanism is established, and information can be collected from a plurality of data sources and effectively arranged and stored aiming at processing large-scale dynamic logistics data. In processing large-scale dynamic logistics data, it is necessary to convert the raw logistics data collected into a format more suitable for analysis and processing. The raw stream data is pre-processed to reduce the impact of extremes on analysis and to make raw stream data from different sources and scales comparable.
In the data preprocessing stage, the preprocessing module scales the original logistics data by using a logarithmic function, and the specific formula is as follows:
Wherein, Representing the pretreated logistics data,/>Representing the ith data point in the original stream data,/>AndThe mean value and standard deviation of the original logistics data are respectively used for standardized processing of the data. The use of logarithmic functions reduces the effects of extremes, making the data distribution smoother.
The multidimensional mapping module converts the preprocessed logistics data into a high-dimensional feature space to reveal hidden associations and modes among the logistics data. The formula of the multidimensional mapping transformation is:
Wherein, Representing the feature set obtained by the multidimensional mapping, reflecting the physical distribution data attribute and structure in the high-dimensional space,And/>Scaling factors and power exponentiations for each data point determine the mapping mode; /(I)And/>Is an adjustment parameter for adjusting the sensitivity and degree of nonlinearity of the map.
To capture complex dynamic relationships between data, an associative analysis module analyzes the time-series associations of multi-dimensional data features, understanding how the data features evolve over time, and revealing patterns and trends behind the evolution. The formula of the correlation analysis is:
Wherein, Representing dynamic association analysis results,/>Represents j-th dimensional data extracted from a feature set of a multidimensional map,/>Is a dynamic association weight matrix used for weighting the association between different features; /(I)Is a balance parameter for adjusting the focus of the analysis.
The extraction module extracts information influencing decision from the dynamic association analysis result, identifies data features having important influences on predicting logistics demands, optimizing resource allocation and the like, and adopts an extraction formula as follows:
Wherein, Is information which is extracted from dynamic association analysis results and is critical to decisions, is a quantitative representation of the importance of different decisions (such as demand prediction, resource allocation, risk management and the like) in a logistics digital management system, and is a method for optimizing the importance of the decisions in the logistics digital management systemAnd/>Is the weight and bias of the extraction structure. By combining the hyperbolic sine function and the logarithmic function, a nonlinear extraction structure is created to improve the recognition capability of key information.
S2, constructing a time-aware multi-layer circulation network model, and obtaining decision information through a time-aware gating unit, a multi-layer circulation structure, multi-element feature fusion and a weighting mechanism.
When the logistics digital management system based on the AI large model is designed, the time-aware multi-layer circulation module builds a time-aware multi-layer circulation network model, and accuracy and efficiency of logistics data processing are improved. The core of the time-aware multi-layer cyclic network model is a time-aware gating unit, which introduces sensitivity to time variations in the network model, and in logistic data analysis, time factors are critical to understanding cargo flow and supply chain reactions. For this purpose, the following formula was designed:
Wherein, Representing the output value of a time-aware gating cell,/>Representing a Sigmoid activation function for mapping input values to fixed intervals (0 to 1),/>Representing the current time step, is the response of the time sensing gating unit to the change of the pretreated logistics data along with time,/>Is an index representing the point in time,/>Is an index for adjusting the influence of time values,/>And/>Is the weight and bias parameters of the time-aware gating cell. By combining linear and nonlinear time features (such as sine, cosine and logarithmic functions), the time-aware gating unit can accurately model the effect of time on the processed logistics data.
In order to process multi-level information in the stream data, a multi-layer circulation structure is adopted. In the logistics digital management system, from the position of a single package to the dynamic state of the whole supply chain, the logistics digital management system comprises a plurality of layers of information, and captures and analyzes the data characteristics of time variation of the multi-layer information, such as the goods flow, the supply chain state and the like in logistics, wherein the specific formulas are as follows:
Wherein, Represents the/>Output state of layer at time t,/>Represents the/>Layer at time/>Output state of/>Is a parameter for adjusting interaction effect and is used for adjusting the influence degree of information interaction between different layers,/>Refers to a unit or layer of a recurrent neural network for processing input data and combining previous output states/>A new output state for the current time step is generated. By combining the hyperbolic tangent function, the exponential function, and the logarithmic function, each layer is enabled to learn and maintain the flow of information from the output of the previous layer, thereby enabling better processing and understanding of complex logistic data.
In the time-aware multi-layer circulation network model, a multi-feature fusion and weighting mechanism is introduced to fuse data features from different layers, so that a comprehensive data view is provided for logistics decision. The formula is as follows:
Wherein, Representing the fused feature representation,/>Representing extraction of information critical to decision from dynamic association analysis results,/>And/>Representing the output states of the last layer and each layer respectively,/>Representing the last layer,/>Is a learning parameter for adjusting fusion proportion,/>Is a weight parameter used to emphasize the importance of the different layer outputs.
And converting the fused features into specific prediction results, and converting the fused features into various decision information such as resource allocation, path planning or demand prediction in a logistics digital management system. The formula is as follows:
Wherein, Representing the final prediction output,/>Representing weight parameters,/>Is a constant for preventing denominator from being 0,/>Is a bias parameter.
The predicted output comprises probability distribution of key decision points in the logistics digital management system, wherein the key decision points refer to cargo demand prediction, resource allocation optimization, transportation route selection, expected delivery time, inventory management and the like. Taking the cargo demand prediction as one specific embodiment, the cargo demand prediction result may include demand prediction of different time points, places or product categories, and the inventory level is adjusted according to the prediction result. For example, if a region is expected to increase in demand within the coming weeks, the inventory of the region may be increased in advance to reduce transportation delays and meet demand. And in coordination with the production department, the production plan is adjusted according to the demand forecast. Under the condition that the predicted demand is increased, the production speed is increased; conversely, production is slowed down when demand falls to reduce excess inventory. And optimizing the distribution route and the time table according to the prediction result. More frequent dispensing is performed in areas of high demand while reducing the frequency of dispensing in areas of low demand to improve overall shipping efficiency.
In summary, the logistics digital management system and method based on the AI large model are completed.
The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (5)
1. The logistics digital management method based on the AI large model is characterized by comprising the following steps:
S1, preprocessing original logistics data, converting the preprocessed logistics data into a high-dimensional feature space through multi-dimensional mapping to obtain a feature set obtained through multi-dimensional mapping, and analyzing time sequence association of data features in the feature set obtained through multi-dimensional mapping, wherein a formula for time sequence association analysis is as follows:
Wherein/> Representing dynamic association analysis results,/>Represents j-th dimensional data extracted from a feature set of a multidimensional map,/>Is a dynamic association weight matrix; /(I)Is a balance parameter; extracting information influencing decision from the dynamic association analysis result;
S2, constructing a time-aware multi-layer circulation network model, wherein the core of the time-aware multi-layer circulation network model is a time-aware gating unit, and the sensitivity to time change is introduced into the time-aware multi-layer circulation network model; the following formula was designed:
Wherein/> Representing the output value of a time-aware gating cell,/>Representing a Sigmoid activation function,/>Representing the current time step, is the response of the time sensing gating unit to the change of the pretreated logistics data along with time,/>Is an index representing the point in time,/>Is an index,/>And/>Is the weight and bias parameters of the time-aware gating cell; introducing a multi-layer circulating structure, capturing and analyzing data characteristics of at least two layers of information and time variation, wherein the specific formula is as follows:
Wherein/> Represents the/>Output state of layer at time t,/>Represents the/>Layer at time/>Output state of/>Is a parameter for adjusting interaction effects,/>Refers to a unit or layer of a recurrent neural network; and introducing a multi-element feature fusion and weighting mechanism to fuse the data features from different layers, wherein the specific formula is as follows:
Wherein/> Representing the fused feature representation,/>Representing extraction of information critical to decision from dynamic association analysis results,/>Representing the output state of the last layer at time t,/>Representing the last layer,/>Is a learning parameter for adjusting fusion proportion,/>Is a weight parameter; the decision information is further obtained through conversion by a time perception gating unit, a multi-layer circulating structure, multi-element feature fusion and a weighting mechanism.
2. The AI-large-model-based logistics digital management method as set forth in claim 1, wherein S1 specifically includes:
during the preprocessing, the raw stream data is scaled using a logarithmic function.
3. The AI-large-model-based logistics digital management method of claim 1, wherein S1 further comprises:
and extracting information influencing the decision from the dynamic association analysis result, and identifying data features influencing the predicted logistics demand and the optimized resource allocation.
4. The AI-large-model-based logistics digital management method as set forth in claim 1, wherein S2 further includes:
And converting the fused features into prediction results, and converting the fused features into decision information of resource allocation, path planning or demand prediction in a logistics digital management system.
5. The logistics digital management system based on the AI large model is applied to the logistics digital management method based on the AI large model as set forth in claim 1, and is characterized by comprising the following parts:
The system comprises a preprocessing module, a multidimensional mapping module, a correlation analysis module, an extraction module and a time perception multi-layer circulation module;
The preprocessing module is used for carrying out format conversion and standardized preprocessing on the original logistics data, and is connected with the multidimensional mapping module and the time-aware multilayer circulation module in a data transmission mode;
The multidimensional mapping module is used for converting the preprocessed data into a high-dimensional feature space and is connected with the association analysis module in a data transmission mode;
the association analysis module is used for analyzing the time sequence association of the multidimensional data features in the high-dimensional feature space to obtain a dynamic association analysis result, and the association analysis module is connected with the extraction module in a data transmission mode;
The extraction module is used for extracting data features for predicting logistics demands and optimizing resource allocation from dynamic association analysis results, and is connected with the time-aware multi-layer circulation module in a data transmission mode;
The time-aware multi-layer circulation module is used for constructing a time-aware multi-layer circulation network model, introducing sensitivity to time variation by using a time-aware gating unit, processing and analyzing time variation data by using a multi-layer circulation structure, fusing data features from different layers by using a multi-element feature fusion and weighting mechanism, and converting the fused features into decisions of resource allocation, path planning or demand prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410211203.9A CN117787838B (en) | 2024-02-27 | 2024-02-27 | Logistics digital management system and method based on AI large model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410211203.9A CN117787838B (en) | 2024-02-27 | 2024-02-27 | Logistics digital management system and method based on AI large model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117787838A CN117787838A (en) | 2024-03-29 |
| CN117787838B true CN117787838B (en) | 2024-05-28 |
Family
ID=90393059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410211203.9A Active CN117787838B (en) | 2024-02-27 | 2024-02-27 | Logistics digital management system and method based on AI large model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117787838B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439045A (en) * | 2022-07-14 | 2022-12-06 | 西北师范大学 | Logistics storage demand prediction method based on MAGRU |
| CN117533356A (en) * | 2024-01-09 | 2024-02-09 | 北京市北太机电设备工贸有限公司 | Intelligent driving assistance system and method |
-
2024
- 2024-02-27 CN CN202410211203.9A patent/CN117787838B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439045A (en) * | 2022-07-14 | 2022-12-06 | 西北师范大学 | Logistics storage demand prediction method based on MAGRU |
| CN117533356A (en) * | 2024-01-09 | 2024-02-09 | 北京市北太机电设备工贸有限公司 | Intelligent driving assistance system and method |
Non-Patent Citations (2)
| Title |
|---|
| 基于多因素分析的区域物流需求径向基函数网络预测;周泰;基于多因素分析的区域物流需求径向基函数网络预测;20090904;第389卷(第389期);2-3 * |
| 基于遗传算法优化支持向量回归机的区域物流需求预测;曹志强;杨筝;刘放;;***科学学报;20180810(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117787838A (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | An overall review of research on prefabricated construction supply chain management | |
| CN112561156A (en) | Short-term power load prediction method based on user load mode classification | |
| CN102402716B (en) | Intelligent production decision support system | |
| CN116485576A (en) | Intelligent manufacturing management platform for brain data with known source in aviation manufacturing industry | |
| CN112785427B (en) | Enterprise credit analysis system based on power data | |
| Raju et al. | An approach for demand forecasting in steel industries using ensemble learning | |
| CN112530559A (en) | Intelligent medical material allocation system for sudden public health event | |
| Kim et al. | Role and challenge of technology toward a smart sustainable city: Topic modeling, classification, and time series analysis using information and communication technology patent data | |
| Kwon et al. | Identification of promising inventions considering the quality of knowledge accumulation: A machine learning approach | |
| CN116703303A (en) | Warehouse visual supervision system and method based on multi-layer perceptron and RBF | |
| Bakhshi-Khaniki et al. | Integrated Dynamic Cellular Manufacturing Systems and Hierarchical Production Planning with Worker Assignment and Stochastic Demand | |
| CN117787838B (en) | Logistics digital management system and method based on AI large model | |
| CN108492013A (en) | A kind of manufacture system scheduling model validation checking method based on quality control | |
| Xia et al. | Research on short-term load forecasting of power system based on gradient lifting tree | |
| CN112508276B (en) | Power grid rapid diagnosis and optimization system and optimization method | |
| CN112381396B (en) | Integrated management method and system for serving enterprise development planning | |
| CN114185957B (en) | Intelligent mining method suitable for power big data service requirements | |
| CN117807114B (en) | Logistics information intelligent retrieval method, system, equipment and storage medium | |
| Castro et al. | Development and Analysis of Predictive Models for Industry 4.0 with an Open-Source Tool | |
| INGKAPRADIT et al. | Model of Big Data Application for Performance Improvement to Smart Factory in Thailand | |
| Cao | Towards Promoting the Efficiency of Enterprise Investment Management with Artificial Intelligence | |
| Zhang et al. | Design of Financial Modeling System Based on Decision Tree Analysis | |
| Wei et al. | Intelligent manufacturing: bridging the gap between the Internet of Things and machinery to achieve optimized operations | |
| Liu et al. | Path identification and effect assessment of digital economy-driven manufacturing quality development in the context of big data analysis | |
| Wang et al. | Forecast of Production Quantity of General-Purpose Parts Based on Customized Production |
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 |