Rare earth ore deep processing grading packaging and cross-border logistics integration method
By optimizing cross-border rare earth mineral business data processing through functional model layering and knowledge graphs, the problems of cumbersome customs clearance procedures and inconsistent grading standards have been solved, intelligent management and efficient logistics of cross-border rare earth mineral trade have been realized, and customs clearance efficiency and corporate competitiveness have been improved.
Patent Information
- Application Number
- CN202510790934.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-13
- Publication Date
- 2025-09-26
AI Technical Summary
In existing technologies, the customs clearance process for cross-border trade of rare earth minerals is cumbersome, information islands are serious, and grading standards are not unified, resulting in low customs clearance efficiency, increased costs and frequent trade disputes.
Through hierarchical processing of functional models and the construction of data interaction interfaces, intelligent management of cross-border rare earth mineral business data is achieved. By combining knowledge graphs and reasoning rule sets, customs clearance processes and logistics routes are optimized, providing intelligent decision-making support.
It has achieved standardization and intelligentization of customs clearance processes, reduced manual operations, shared information among multiple entities, ensured product quality consistency, optimized logistics routes, reduced costs and risks, and enhanced corporate competitiveness.
Smart Images
Figure FDA0005448425190000011 
Figure FDA0005448425190000021 
Figure FDA0005448425190000022
Abstract
Description
Technical Field
[0001] The present invention relates to the field of packaging and transportation technology, and in particular to a method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores. Background Art
[0002] Rare earths, the "vitamin" of modern industry, hold an irreplaceable strategic position in electronics, new energy, aerospace, and other fields. With the increasing global trade in rare earths, the efficient integration of rare earth ore processing, grading, packaging, and cross-border logistics has become crucial for ensuring a stable supply chain and enhancing international competitiveness. However, significant technical bottlenecks in customs clearance procedures and product grading standards currently hinder the international development of the rare earth industry.
[0003] In terms of customs clearance procedures for cross-border transportation, the traditional customs clearance system for rare earth mineral cross-border trade relies heavily on manual labor and paper document transfers, involving information exchange and business collaboration among multiple parties, including customs, inspection and quarantine, and businesses. Customs clearance policies, declaration procedures, and regulatory requirements vary significantly across countries and regions. Businesses must prepare separate declaration materials for different trading partners, requiring repeated information entry, resulting in cumbersome and inefficient customs clearance procedures. Furthermore, information sharing among all parties involved is limited, leading to severe information silos. Customs struggles to quickly obtain complete and accurate product information for verification, and businesses are unable to keep up to date on customs clearance progress and potential issues. This leads to cargo delays, increased logistics costs, and even trade disputes.
[0004] There's no unified, authoritative global standard for the grading of rare earth minerals. Different countries, companies, and industry organizations develop grading standards based on their own needs and technical capabilities, resulting in significant discrepancies in rare earth element content determination, impurity limits, and physical property indexes. This lack of uniformity makes it difficult to accurately assess the quality and value of rare earth minerals during further processing, trade, and application, increasing transaction costs and communication barriers. Summary of the Invention
[0005] In view of this, the embodiments of the present invention hope to provide a method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.
[0006] To solve the above technical problems, the technical solution adopted in this application is: a method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores, the method comprising:
[0007] The cross-border business data of rare earth mines is processed by functional model layering to form a functional module call relationship network; the functional model layering process divides the business data into the main function layer F of rare earth enterprises e and rare earth business function layer Fb , and build data interaction interface between functional modules I e-b ;
[0008] Based on the function module call relationship network, process template construction is performed to obtain the dynamic process assembly rule library R p The process template is constructed based on the function call relationship to design the rare earth mining business declaration process P d and exception handling process system P e ;
[0009] Implement service tracking processing on the dynamic process assembly rule base to generate user behavior analysis data set D u ; The service embedding process is at the key process node N k Set up tracking points to collect user operation behavior data D a , rare earth business data change data D c and process execution status data D s ;
[0010] The user behavior analysis data set is processed to construct a guidance strategy and build a service guidance rule base R g The guiding strategy construction process is based on the user behavior pattern design operation prompt H o , formulate exception handling suggestions e and personalized guidance plan H p ;
[0011] The knowledge extraction algorithm is used to construct the knowledge graph of the service guidance rule base to obtain the rare earth business knowledge reasoning rule set R k The knowledge graph construction process includes extracting rare earth business entity E r , build a relationship network G r , discover knowledge rules R kr and establish a causal chain C r ;
[0012] Based on the rare earth business knowledge reasoning rule set, rare earth mine cross-border business data processing is carried out to generate the port business intelligent decision-making solution S d The cross-border business data processing covers the optimization of rare earth mine customs clearance process. c , Logistics Route Planning l , Risk level assessment A r and customs clearance time prediction P t .
[0013] As a further preferred embodiment of the present technical solution: the cross-border business data of rare earth mines is subjected to functional model hierarchical processing to form a functional module call relationship network; the functional model hierarchical processing divides the business data into a rare earth enterprise main function layer and a rare earth business function layer, and constructs a data interaction interface between the functional modules, including: the cross-border business data of rare earth mines is subjected to rare earth enterprise main body classification processing to obtain a rare earth enterprise basic information set E info ={e1,e2,...,e n}, and based on the basic information set of rare earth enterprises, the main function layer of rare earth enterprises is constructed through the following formula:
[0014] Among them, Map is the attribute mapping function, Attr e is a collection of enterprise entity attributes;
[0015] Carry out the filing qualification processing for the main functional layer of the rare earth enterprise and obtain the rare earth enterprise qualification certificate set C cert ={c1,c2,...,c m}, and authorize the rare earth enterprise qualification certificate set, and obtain the rare earth enterprise function authorization table through the following formula:
[0016] A e ={(e i ,c j ,Auth(e i ,c j ))|e i ∈E info ,c j ∈C cert}, where Auth is the authorization function and returns a Boolean value indicating whether authorization is granted;
[0017] The cross-border business data of rare earth mines is classified by business functions to obtain the rare earth business function element set B ele ={b1,b2,...,b k}, and construct the rare earth business function layer based on the rare earth business function element set through the following formula:
[0018] Among them, Combine is the function combination function, Rel b A set of business function relationships;
[0019] The rare earth business function layer is configured with the rare earth mine customs clearance service function to obtain the rare earth mine customs clearance business process set P cs ={p1,p2,...,p l}, and perform inspection declaration, manifest, transit and logistics service function configuration processing on the rare earth mine customs clearance business process set, and obtain the rare earth business service function set through the following algorithm:
[0020] The data interaction interface design and processing are performed on the rare earth enterprise main function layer and the rare earth business function layer to obtain the function interaction interface table. The function interaction interface table is then processed with interface rule configuration to obtain the data interaction interface using the following formula:
[0021] I e-b ={(i,Rule(i))|i∈I table}, where Rule is the interface rule configuration function;
[0022] Through module association analysis, the data interaction interface is processed by call relationship construction to form a function module call relationship network N f , where the nodes are functional modules and the edges are call relationships:
[0023] N f =(V,E), where V = F e ∪F b ,E={(v i ,v j )|There exists an interactive interface i∈I e-b Connect v i and v j .
[0024] As a further preferred embodiment of the present technical solution: the process template construction process is performed based on the function module call relationship network to obtain a dynamic process assembly rule library; the process template construction process is designed based on the function call relationship to design a rare earth mining business declaration process and an exception handling process system, including: the function module call relationship network N f Analyze and process the rare earth mining business declaration process to obtain the declaration process element set P ele ={p e1 ,p e2 ,...,p em}, and based on the above declaration process element set, design the rare earth mining business declaration process through the following algorithm:
[0025] Perform abnormal type identification on the rare earth mining business declaration process and obtain an abnormal situation list L e ={e1,e2,...,e n}, and based on the abnormal situation list, build an exception handling process system through the following formula:
[0026] Among them, CreateFlow is the process creation function, Handler i To handle exceptions i A collection of methods;
[0027] The rare earth mining business declaration process and exception handling process system are integrated with process rules to obtain the process assembly specification table T as ={(p i ,r j )|p i ∈P d ∪P e ,r j ∈Rules}, and dynamically configure the rules of the process assembly specification table to obtain the candidate process set through the following algorithm:
[0028] The candidate process set is subjected to rule assembly processing through process rule mapping to obtain a dynamic process assembly rule library R p :
[0029] R p ={(p, RuleSet(p))|p∈inC p}, where RuleSet is a rule mapping function that returns the rule set corresponding to process p.
[0030] As a further preferred embodiment of the present technical solution: implementing service tracking processing on the dynamic process assembly rule base to generate a user behavior analysis data set; the service tracking processing sets tracking points at key process nodes to collect user operation behavior data, rare earth business data change data and process execution status data, including: p Perform key node analysis and processing to obtain the business key node table N k ={n1,n2,...,n t}, and set the tracking location based on the business key node table, and obtain the key node tracking distribution map through the following formula:
[0031] M d ={(n i ,Position(n i ),Metrics(n i ))|n i ∈inN k}, where Position is the node position function and Metrics is the collection indicator function;
[0032] Based on the key node buried point distribution map, the page access records are collected to obtain the user operation behavior data D a ={a1,a2,...,a s}, and perform operation trajectory annotation processing on the user operation behavior data, and obtain the operation trajectory feature set through the following algorithm: perform function usage data statistical processing on the operation trajectory feature set to obtain the node operation frequency table F n ={(ni ,Frequency(n i ))|n i ∈N k}, and perform rare earth business data change monitoring processing on the node operation frequency table, and obtain rare earth business data change data through the following formula:
[0033] D c ={Δd i |Δd i =d i+1 -d i ,d i ∈D b ,i=1,2,...,u-1}, where D b For business data sets;
[0034] The rare earth business data change data is collected and processed to obtain the process execution status data D s ={s1,s2,...,s v}, and perform key node monitoring processing on the process execution status data, and obtain the node status sequence table through the following algorithm:
[0035] Perform abnormal point identification processing on the node state sequence table to obtain the abnormal event feature set E f ={e1,e2,...,e w}, and perform process jam warning analysis on the abnormal event feature set, and obtain the process warning indicator table through the following formula:
[0036] A t ={(e i ,Severity(e i ),Probability(e i ))|e i ∈E f}, where Severity is the severity assessment function and Probability is the occurrence probability assessment function;
[0037] The user operation behavior data, rare earth business data change data and process execution status data are integrated and processed through a time series feature analysis algorithm to generate a user behavior analysis data set:
[0038] D u =Integrate(D a ,D c ,D s ,TimeFeatures), where Integrate is the data integration function and TimeFeatures is the time series feature extraction function.
[0039] As a further preferred embodiment of the present invention: the user behavior analysis data set is processed for guiding strategy construction to construct a service guiding rule base; the guiding strategy construction process is based on the user behavior pattern to design operation prompts, formulate abnormality handling suggestions and personalized guiding plans, including: u Perform behavior pattern feature extraction to obtain user behavior pattern feature table T b ={(u i ,Pattern(u i ))|u i ∈Users}, and based on the user behavior pattern feature table, generate an operation prompt rule set through the following formula:
[0040] R o ={GenerateRule(p j ,Hint(p j ))|p j ∈Patterns(T b )}, where GenerateRule is
[0041] Rule generation function, Hint is the hint generation function;
[0042] Perform intelligent prompt configuration processing on the operation prompt rule set to obtain the filling guidance rule table T f ={(f i ,Guide(f i ))|f i ∈Fields}, and perform error reminder rule configuration processing on the filling guidance rule table, and obtain the error reminder scheme through the following algorithm:
[0043] The error reminder solution is processed to generate business suggestions to obtain a business suggestion set S a ={s1,s2,...,s x}, and prepare an exception handling suggestion for the business suggestion set, and obtain the exception handling suggestion through the following formula:
[0044] H e ={Handle(e k ,Recommend(e k ))|e k ∈Exceptions}, where Handle is the processing function and Recommend is the recommendation solution generation function;
[0045] Perform optimal path analysis on the exception handling suggestions to obtain a recommended process list L r={l1,l2,...,l y}, and configure the operation steps of the process recommendation list, and obtain the operation step prompts through the following algorithm:
[0046] Perform business-related analysis on the operation step prompts to obtain a personalized guidance plan H p ={(u i ,Plan(u i ))|u i ∈Users}, and perform guidance rule aggregation processing on the personalized guidance scheme to obtain a guidance rule collection:
[0047] Among them, Aggregate is a rule aggregation function;
[0048] The guidance rule set is integrated through rule mapping to build a service guidance rule library:
[0049] R g =IntegrateRules(G r ,Priority), where IntegrateRules is the rule integration function and Priority is the priority sorting function.
[0050] As a further preferred embodiment of the present technical solution: the use of the knowledge extraction algorithm to construct a knowledge graph for the service guidance rule base to obtain a rare earth business knowledge reasoning rule set; the knowledge graph construction process includes extracting rare earth business entities, building a relationship network, discovering knowledge rules and establishing a causal relationship chain, including: using the knowledge extraction algorithm to construct the service guidance rule base R g Perform rare earth business entity extraction and processing to obtain entity feature set E f ={e1,e2,...,e m}, and perform rare earth business entity attribute labeling on the entity feature set, and obtain the rare earth business entity dictionary through the following formula:
[0051] D e ={(e i ,Attributes(e i ))|e i ∈E f}, where Attributes is the attribute annotation function;
[0052] The rare earth business entity dictionary is processed by relationship network construction to obtain the initial relationship graph G i =(V i ,E i), and the initial relationship graph is processed to calculate the strength of the association between entities, and the relationship network is obtained by the following algorithm:
[0053] Perform knowledge rule extraction on the relationship network to obtain the rule candidate set C r ={r1,r2,...,r n}, and perform rule verification on the rule candidate set to obtain the knowledge rule through the following formula:
[0054] R kr ={r i |Validate(r i ),r i ∈C r}, where Validate is the rule validation function;
[0055] The knowledge rules are processed into a causal chain to obtain the causal relationship:
[0056] T c ={(c i ,Effect(c i ),Cause(c i ))|c i ∈CausalEvents}, and perform causal strength evaluation on the causal relationship table, and obtain the causal relationship chain through the following algorithm:
[0057] The knowledge rules and causal relationship chains are processed by rule induction algorithm to generate inference rules, and the basic inference rule set R is obtained. b ={r1,r2,...,r p}, and perform rule completeness verification on the basic inference rule set, and obtain a rule verification report through the following formula:
[0058] R v =VerifyCompleteness(R b ,Requirements), where VerifyCompleteness is
[0059] Completeness check function, Requirements is a set of business requirements;
[0060] The rule verification report is subjected to rule supplementation processing to obtain a rare earth business knowledge reasoning rule set:
[0061] R k =R b ∪Supplement(R v ), where Supplement is the rule supplement function.
[0062] As a further preferred embodiment of the present technical solution: the cross-border business data processing of rare earth mines is carried out based on the rare earth business knowledge reasoning rule set to generate an intelligent decision-making plan for port business; the cross-border business data processing covers rare earth mine customs clearance process optimization, logistics path planning, risk level assessment and customs clearance time prediction, including: the rare earth business knowledge reasoning rule set R k Analyze the rare earth ore customs clearance business process and obtain the process bottleneck point set B p ={b1,b2,...,b q}, and optimize the customs clearance process for the set of process bottleneck points, and obtain the customs clearance process candidate solutions through the following algorithm:
[0063] Perform process node configuration processing on the candidate solution of the customs clearance process to obtain the customs clearance business flow diagram G c =(V c ,E c ), and perform path deviation analysis on the customs clearance business flow diagram, and obtain the customs clearance process benchmark path through the following formula:
[0064] P base =OptimizePath(G c ,Constraints), where OptimizePath is the path optimization function and Constraints is the set of constraints; perform logistics resource allocation processing on the customs clearance process benchmark path to obtain the logistics resource distribution map M r ={(l i ,Resources(l i ))|l i ∈Locations}, and perform logistics path planning on the logistics resource distribution map, and obtain the logistics path planning solution through the following algorithm:
[0065] The logistics path planning scheme is evaluated for transport timeliness to obtain a transport timeliness evaluation table T a ={(p i ,Time(p i ),Reliability(p i ))|p i ∈P l}, and perform logistics node optimization processing on the transportation time evaluation table, and obtain the logistics distribution route map through the following formula:
[0066] G d =OptimizeNodes(P l,TimeConstraints) Among them, OptimizeNodes is the node optimization function, TimeConstraints is the time constraint condition;
[0067] Perform risk factor identification on the logistics distribution route map to obtain a risk factor list R l ={r1,r2,...,r s}, and perform risk level assessment on the risk factor list, and obtain a risk level assessment report through the following algorithm:
[0068] The risk level assessment report is processed to extract the customs clearance time factor and obtain the time influencing factor table T f ={(f i ,Weight(f i ))|f i ∈Factors}, and perform customs clearance time prediction processing on the time influencing factor table, and obtain the customs clearance time prediction result through the following formula:
[0069] P t =PredictTime(T f ,CurrentState,Model), where PredictTime is the time prediction function, CurrentState is the current state, and Model is the prediction model;
[0070] The customs clearance process benchmark path, logistics distribution path map and customs clearance time prediction results are integrated to obtain the decision candidate solution set C d ={c1,c2,...,c t}, and perform feasibility evaluation on the decision candidate solution set, and obtain a solution evaluation report through the following algorithm:
[0071] The intelligent decision-making process is performed on the program evaluation report to obtain the intelligent decision-making program for port business: S d =SelectBest(R e ,Objectives), where SelectBest is the optimal solution selection function and Objectives is the decision target set.
[0072] The embodiment of the present invention adopts the above technical solution, which has the following advantages:
[0073] 1. This invention standardizes and intelligentizes complex customs clearance processes through functional model layering and dynamic process assembly, reducing manual operations and repeated declarations. It also enables multi-party information sharing through data interaction interfaces, breaking down information silos. Customs can conduct rapid verification, and enterprises can grasp progress in real time, significantly shortening customs clearance time, and reducing logistics costs and the risk of trade disputes.
[0074] Second, this invention addresses the challenge of inconsistent standards by establishing a globally unified digital system for rare earth ore grading. Intelligent detection and automated grading ensure product quality consistency, while visually tracing grading information throughout the entire process facilitates quality assessment and accountability, safeguarding the rights and interests of all parties involved in the supply chain and promoting standardization in the rare earth industry.
[0075] 3. This invention uses knowledge graphs and reasoning rule sets to conduct in-depth analysis of cross-border trade data, realize intelligent decision-making such as customs clearance process optimization and logistics route planning, accurately predict risks and timeliness, provide scientific decision-making basis for enterprises, and enhance enterprises' adaptability and competitiveness in the global rare earth trade.
[0076] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the following detailed description. DETAILED DESCRIPTION
[0077] The following is a detailed description in conjunction with the embodiments of the present disclosure.
[0078] It should be clear that the following embodiments of the present disclosure are described through specific concrete examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.
[0079] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.
[0080] A method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores, comprising:
[0081] The cross-border business data of rare earth mines is processed by functional model layering to form a functional module call relationship network; the functional model layering process divides the business data into the main function layer F of rare earth enterprises e and rare earth business function layer F b , and build data interaction interface between functional modules I e-b ;
[0082] Based on the function module call relationship network, process template construction is performed to obtain the dynamic process assembly rule library R p The process template is constructed based on the function call relationship to design the rare earth mining business declaration process P d and exception handling process system P e ;
[0083] Implement service tracking processing on the dynamic process assembly rule base to generate user behavior analysis data set D u ; The service embedding process is at the key process node N k Set up tracking points to collect user operation behavior data D a , rare earth business data change data D c and process execution status data D s ;
[0084] The user behavior analysis data set is processed to construct a guidance strategy and build a service guidance rule base R g The guiding strategy construction process is based on the user behavior pattern design operation prompt H o , formulate exception handling suggestions e and personalized guidance plan H p ;
[0085] The knowledge extraction algorithm is used to construct the knowledge graph of the service guidance rule base to obtain the rare earth business knowledge reasoning rule set Rk The knowledge graph construction process includes extracting rare earth business entity E r , build relationship network G r , discover knowledge rules R kr and establish a causal chain C r ;
[0086] Based on the rare earth business knowledge reasoning rule set, rare earth mine cross-border business data processing is carried out to generate the port business intelligent decision-making solution S d The cross-border business data processing covers the optimization of rare earth mine customs clearance process. c , Logistics Route Planning l , Risk level assessment A r and customs clearance time prediction P t .
[0087] As a further preferred embodiment of the present technical solution: the cross-border business data of rare earth mines is subjected to functional model hierarchical processing to form a functional module call relationship network; the functional model hierarchical processing divides the business data into a rare earth enterprise main function layer and a rare earth business function layer, and constructs a data interaction interface between the functional modules, including: the cross-border business data of rare earth mines is subjected to rare earth enterprise main body classification processing to obtain a rare earth enterprise basic information set E info ={e1,e2,...,e n}, and based on the basic information set of rare earth enterprises, the main function layer of rare earth enterprises is constructed through the following formula:
[0088] Among them, Map is the attribute mapping function, Attr e is a collection of enterprise entity attributes;
[0089] Carry out the filing qualification processing for the main functional layer of the rare earth enterprise and obtain the rare earth enterprise qualification certificate set C cert ={c1,c2,...,c m}, and authorize the rare earth enterprise qualification certificate set, and obtain the rare earth enterprise function authorization table through the following formula:
[0090] A e ={(e i ,c j ,Auth(e i ,c j ))|e i ∈E info ,c j ∈C cert}, where Auth is the authorization function and returns a Boolean value indicating whether authorization is granted;
[0091] The cross-border business data of rare earth mines is classified by business functions to obtain the rare earth business function element set B ele ={b1,b2,...,b k}, and construct the rare earth business function layer based on the rare earth business function element set through the following formula:
[0092] Among them, Combine is the function combination function, Rel b A set of business function relationships;
[0093] The rare earth business function layer is configured with the rare earth mine customs clearance service function to obtain the rare earth mine customs clearance business process set P cs ={p1,p2,...,p l}, and perform inspection declaration, manifest, transit and logistics service function configuration processing on the rare earth mine customs clearance business process set, and obtain the rare earth business service function set through the following algorithm:
[0094] The data interaction interface design and processing are performed on the rare earth enterprise main function layer and the rare earth business function layer to obtain the function interaction interface table. The function interaction interface table is then processed with interface rule configuration to obtain the data interaction interface using the following formula:
[0095] I e-b ={(i,Rule(i))|i∈I table}, where Rule is the interface rule configuration function;
[0096] Through module association analysis, the data interaction interface is processed by call relationship construction to form a function module call relationship network N f , where the nodes are functional modules and the edges are call relationships:
[0097] N f =(V,E), where V = F e ∪F b ,E={(v i ,v j )|There exists an interactive interface i∈I e-b Connect v i and v j .
[0098] As a further preferred embodiment of the present technical solution: the process template construction process is performed based on the function module call relationship network to obtain a dynamic process assembly rule library; the process template construction process is designed based on the function call relationship to design a rare earth mining business declaration process and an exception handling process system, including: the function module call relationship network N f Analyze and process the rare earth mining business declaration process to obtain the declaration process element set Pele ={p e1 ,p e2 ,...,p em}, and based on the above declaration process element set, design the rare earth mining business declaration process through the following algorithm:
[0099] Perform abnormal type identification on the rare earth mining business declaration process and obtain an abnormal situation list L e ={e1,e2,...,e n}, and based on the abnormal situation list, build an exception handling process system through the following formula:
[0100] Among them, CreateFlow is the process creation function, Handler i To handle exceptions i A collection of methods;
[0101] The rare earth mining business declaration process and exception handling process system are integrated with process rules to obtain the process assembly specification table T as ={(p i ,r j )|p i ∈P d ∪P e ,r j ∈Rules}, and dynamically configure the rules of the process assembly specification table to obtain the candidate process set through the following algorithm:
[0102] The candidate process set is subjected to rule assembly processing through process rule mapping to obtain a dynamic process assembly rule library R p :
[0103] R p ={(p, RuleSet(p))|p∈inC p}, where RuleSet is a rule mapping function that returns the rule set corresponding to process p.
[0104] As a further preferred embodiment of the present technical solution: implementing service tracking processing on the dynamic process assembly rule base to generate a user behavior analysis data set; the service tracking processing sets tracking points at key process nodes to collect user operation behavior data, rare earth business data change data and process execution status data, including: p Perform key node analysis and processing to obtain the business key node table N k ={n1,n2,...,n t}, and set the tracking location based on the business key node table, and obtain the key node tracking distribution map through the following formula:
[0105] M d ={(n i ,Position(n i ),Metrics(n i ))|n i ∈inN k}, where Position is the node position function and Metrics is the collection indicator function;
[0106] Based on the key node buried point distribution map, the page access records are collected to obtain the user operation behavior data D a ={a1,a2,...,a s}, and perform operation trajectory annotation processing on the user operation behavior data, and obtain the operation trajectory feature set through the following algorithm: perform function usage data statistical processing on the operation trajectory feature set to obtain the node operation frequency table F n ={(n i ,Frequency(n i ))|n i ∈N k}, and perform rare earth business data change monitoring processing on the node operation frequency table, and obtain rare earth business data change data through the following formula:
[0107] D c ={Δd i |Δd i =d i+1 -d i ,d i ∈D b ,i=1,2,...,u-1}, where D b For business data sets;
[0108] The rare earth business data change data is collected and processed to obtain the process execution status data D s ={s1,s2,...,s v}, and perform key node monitoring processing on the process execution status data, and obtain the node status sequence table through the following algorithm:
[0109] Perform abnormal point identification processing on the node state sequence table to obtain the abnormal event feature set E f ={e1,e2,...,e w}, and perform process jam warning analysis on the abnormal event feature set, and obtain the process warning indicator table through the following formula:
[0110] A t ={(e i ,Severity(e i),Probability(e i ))|e i ∈E f}, where Severity is the severity assessment function and Probability is the occurrence probability assessment function;
[0111] The user operation behavior data, rare earth business data change data and process execution status data are integrated and processed through a time series feature analysis algorithm to generate a user behavior analysis data set:
[0112] D u =Integrate(D a ,D c ,D s ,TimeFeatures), where Integrate is the data integration function and TimeFeatures is the time series feature extraction function.
[0113] As a further preferred embodiment of the present invention: the user behavior analysis data set is processed for guiding strategy construction to construct a service guiding rule base; the guiding strategy construction process is based on the user behavior pattern to design operation prompts, formulate abnormality handling suggestions and personalized guiding plans, including: u Perform behavior pattern feature extraction to obtain user behavior pattern feature table T b ={(u i ,Pattern(u i ))|u i ∈Users}, and based on the user behavior pattern feature table, generate an operation prompt rule set through the following formula:
[0114] R o ={GenerateRule(p j ,Hint(p j ))|p j ∈Patterns(T b )}, where GenerateRule is
[0115] Rule generation function, Hint is the hint generation function;
[0116] Perform intelligent prompt configuration processing on the operation prompt rule set to obtain the filling guidance rule table T f ={(f i ,Guide(f i ))|f i ∈Fields}, and perform error reminder rule configuration processing on the filling guidance rule table, and obtain the error reminder scheme through the following algorithm:
[0117] The error reminder solution is processed to generate business suggestions to obtain a business suggestion set S a ={s1,s2,...,s x}, and prepare an exception handling suggestion for the business suggestion set, and obtain the exception handling suggestion through the following formula:
[0118] H e ={Handle(e k ,Recommend(e k ))|e k ∈Exceptions}, where Handle is the processing function and Recommend is the recommendation solution generation function;
[0119] Perform optimal path analysis on the exception handling suggestions to obtain a recommended process list L r ={l1,l2,...,l y}, and configure the operation steps of the process recommendation list, and obtain the operation step prompts through the following algorithm:
[0120] Perform business-related analysis on the operation step prompts to obtain a personalized guidance plan H p ={(u i ,Plan(u i ))|u i ∈Users}, and perform guidance rule aggregation processing on the personalized guidance scheme to obtain a guidance rule collection:
[0121] Among them, Aggregate is a rule aggregation function;
[0122] The guidance rule set is integrated through rule mapping to build a service guidance rule library:
[0123] R g =IntegrateRules(G r ,Priority), where IntegrateRules is the rule integration function and Priority is the priority sorting function.
[0124] As a further preferred embodiment of the present technical solution: the use of the knowledge extraction algorithm to construct a knowledge graph for the service guidance rule base to obtain a rare earth business knowledge reasoning rule set; the knowledge graph construction process includes extracting rare earth business entities, building a relationship network, discovering knowledge rules and establishing a causal relationship chain, including: using the knowledge extraction algorithm to construct the service guidance rule base R g Perform rare earth business entity extraction and processing to obtain entity feature set Ef ={e1,e2,...,e m}, and perform rare earth business entity attribute labeling on the entity feature set, and obtain the rare earth business entity dictionary through the following formula:
[0125] D e ={(e i ,Attributes(e i ))|e i ∈E f}, where Attributes is the attribute annotation function;
[0126] The rare earth business entity dictionary is processed by relationship network construction to obtain the initial relationship graph G i =(V i ,E i ), and the initial relationship graph is processed to calculate the strength of the association between entities, and the relationship network is obtained by the following algorithm:
[0127] Perform knowledge rule extraction on the relationship network to obtain the rule candidate set C r ={r1,r2,...,r n}, and perform rule verification on the rule candidate set to obtain the knowledge rule through the following formula:
[0128] R kr ={r i |Validate(r i ),r i ∈C r}, where Validate is the rule validation function;
[0129] The knowledge rules are processed into a causal chain to obtain the causal relationship:
[0130] T c ={(c i ,Effect(c i ),Cause(c i ))|c i ∈CausalEvents}, and perform causal strength evaluation on the causal relationship table, and obtain the causal relationship chain through the following algorithm:
[0131] The knowledge rules and causal relationship chains are processed by rule induction algorithm to generate inference rules, and the basic inference rule set R is obtained. b ={r1,r2,...,r p}, and perform rule completeness verification on the basic inference rule set, and obtain a rule verification report through the following formula:
[0132] R v =VerifyCompleteness(R b ,Requirements), where VerifyCompleteness is
[0133] Completeness check function, Requirements is a set of business requirements;
[0134] The rule verification report is subjected to rule supplementation processing to obtain a rare earth business knowledge reasoning rule set:
[0135] R k =R b ∪Supplement(R v ), where Supplement is the rule supplement function.
[0136] As a further preferred embodiment of the present technical solution: the cross-border business data processing of rare earth mines is carried out based on the rare earth business knowledge reasoning rule set to generate an intelligent decision-making plan for port business; the cross-border business data processing covers rare earth mine customs clearance process optimization, logistics path planning, risk level assessment and customs clearance time prediction, including: the rare earth business knowledge reasoning rule set R k Analyze the rare earth ore customs clearance business process and obtain the process bottleneck point set B p ={b1,b2,...,b q}, and optimize the customs clearance process for the set of process bottleneck points, and obtain the customs clearance process candidate solutions through the following algorithm:
[0137] Perform process node configuration processing on the candidate solution of the customs clearance process to obtain the customs clearance business flow diagram G c =(V c ,E c ), and perform path deviation analysis on the customs clearance business flow diagram, and obtain the customs clearance process benchmark path through the following formula:
[0138] P base =OptimizePath(G c ,Constraints), where OptimizePath is the path optimization function and Constraints is the set of constraints; perform logistics resource allocation processing on the customs clearance process benchmark path to obtain the logistics resource distribution map M r ={(l i ,Resources(l i ))|l i ∈Locations}, and perform logistics path planning on the logistics resource distribution map, and obtain the logistics path planning solution through the following algorithm:
[0139] The logistics path planning scheme is evaluated for transport timeliness to obtain a transport timeliness evaluation table T a ={(p i ,Time(p i ),Reliability(p i ))|p i ∈P l}, and perform logistics node optimization processing on the transportation time evaluation table, and obtain the logistics distribution route map through the following formula:
[0140] G d =OptimizeNodes(P l ,TimeConstraints) Among them, OptimizeNodes is the node optimization function, TimeConstraints is the time constraint condition;
[0141] Perform risk factor identification on the logistics distribution route map to obtain a risk factor list R l ={r1,r2,...,r s}, and perform risk level assessment on the risk factor list, and obtain a risk level assessment report through the following algorithm:
[0142] The risk level assessment report is processed to extract the customs clearance time factor and obtain the time influencing factor table T f ={(f i ,Weight(f i ))|f i ∈Factors}, and perform customs clearance time prediction processing on the time influencing factor table, and obtain the customs clearance time prediction result through the following formula:
[0143] P t =PredictTime(T f ,CurrentState,Model), where PredictTime is the time prediction function, CurrentState is the current state, and Model is the prediction model;
[0144] The customs clearance process benchmark path, logistics distribution path map and customs clearance time prediction results are integrated to obtain the decision candidate solution set C d ={c1,c2,...,c t}, and perform feasibility evaluation on the decision candidate solution set, and obtain a solution evaluation report through the following algorithm:
[0145] The intelligent decision-making process is performed on the program evaluation report to obtain the intelligent decision-making program for port business: S d =SelectBest(R e ,Objectives), where SelectBest is the optimal solution selection function and Objectives is the decision target set.
[0146] To solve the above technical problems, another technical solution adopted in this application is: a computer device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of the high-precision motion capture real-time calibration method based on multi-sensor fusion as described above.
[0147] In the present disclosure, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "including," "comprising," "having," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.
[0148] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.
[0149] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.
Claims
1. A method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores, characterized in that: The method comprises: The cross-border business data of rare earth mines is processed by functional model layering to form a functional module call relationship network; the functional model layering process divides the business data into the main function layer F of rare earth enterprises e and rare earth business function layer F b , and build data interaction interface between functional modules I e-b ; Based on the function module call relationship network, process template construction is performed to obtain the dynamic process assembly rule library R p The process template is constructed based on the function call relationship to design the rare earth mining business declaration process P d and exception handling process system P e ; Implement service tracking processing on the dynamic process assembly rule base to generate user behavior analysis data set D u ; The service embedding process is at the key process node N k Set up tracking points to collect user operation behavior data D a , rare earth business data change data D c and process execution status data D s ; The user behavior analysis data set is processed to construct a guidance strategy and build a service guidance rule base R g The guiding strategy construction process is based on the user behavior pattern design operation prompt H o , formulate exception handling suggestions e and personalized guidance plan H p ; The knowledge extraction algorithm is used to construct the knowledge graph of the service guidance rule base to obtain the rare earth business knowledge reasoning rule set R k The knowledge graph construction process includes extracting rare earth business entity E r , build a relationship network G r , discover knowledge rules R kr and establish a causal chain C r ; Based on the rare earth business knowledge reasoning rule set, rare earth mine cross-border business data processing is carried out to generate the port business intelligent decision-making solution S d The cross-border business data processing covers the optimization of rare earth mine customs clearance process. c , Logistics Route Planning l , Risk level assessment A r and customs clearance time prediction P t .
2. The method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores according to claim 1, characterized in that: The cross-border business data of rare earth mines is subjected to functional model hierarchical processing to form a functional module call relationship network; The functional model hierarchical processing divides the business data into the rare earth enterprise main function layer and the rare earth business function layer, and constructs the data interaction interface between the functional modules, including: classifying the rare earth enterprise main body of the rare earth mine cross-border business data to obtain the rare earth enterprise basic information set E info ={e1,e2,...,e n }, and based on the basic information set of rare earth enterprises, the main function layer of rare earth enterprises is constructed through the following formula: Among them, Map is the attribute mapping function, Attr e is a collection of enterprise entity attributes; Carry out the filing qualification processing for the main functional layer of the rare earth enterprise and obtain the rare earth enterprise qualification certificate set C cert ={c1,c2,...,c m }, and authorize the rare earth enterprise qualification certificate set, and obtain the rare earth enterprise function authorization table through the following formula: A e ={(e i ,c j ,Auth(e i ,c j ))|e i ∈E info ,c j ∈C cert }, where Auth is the authorization function and returns a Boolean value indicating whether authorization is granted; The cross-border business data of rare earth mines is classified by business functions to obtain the rare earth business function element set B ele ={b1,b2,...,b k }, and construct the rare earth business function layer based on the rare earth business function element set through the following formula: Among them, Combine is the function combination function, Rel b A set of business function relationships; The rare earth business function layer is configured with the rare earth mine customs clearance service function to obtain the rare earth mine customs clearance business process set P cs ={p1,p2,...,p l }, and perform inspection declaration, manifest, transit and logistics service function configuration processing on the rare earth mine customs clearance business process set, and obtain the rare earth business service function set through the following algorithm: The data interaction interface design and processing are performed on the rare earth enterprise main function layer and the rare earth business function layer to obtain the function interaction interface table. The function interaction interface table is then processed with interface rule configuration to obtain the data interaction interface using the following formula: I e-b ={(i,Rule(i))|i∈I table }, where Rule is the interface rule configuration function; Through module association analysis, the data interaction interface is processed by call relationship construction to form a function module call relationship network N f , where the nodes are functional modules and the edges are call relationships: N f =(V,E), where V = F e ∪F b ,E={(v i ,v j )|There exists an interactive interface i∈I e-b Connect v i and v j .
3. The method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores according to claim 2, characterized in that: The process template is constructed based on the function module call relationship network to obtain a dynamic process assembly rule library; The process template construction process designs the rare earth mining business declaration process and exception handling process system based on the function call relationship, including: calling the relationship network N of the function module f Analyze and process the rare earth mining business declaration process to obtain the declaration process element set P ele ={p e1 ,p e2 ,...,p em }, and based on the above declaration process element set, design the rare earth mining business declaration process through the following algorithm: Perform abnormal type identification on the rare earth mining business declaration process and obtain an abnormal situation list L e ={e1,e2,...,e n }, and based on the abnormal situation list, build an exception handling process system through the following formula: Among them, CreateFlow is the process creation function, Handler i To handle exception e i A collection of methods; The rare earth mining business declaration process and exception handling process system are integrated with process rules to obtain the process assembly specification table T as ={(p i ,r j )|p i ∈P d ∪P e ,r j ∈Rules}, and dynamically configure the rules of the process assembly specification table to obtain the candidate process set through the following algorithm: The candidate process set is subjected to rule assembly processing through process rule mapping to obtain a dynamic process assembly rule library R p : R p ={(p, RuleSet(p))|p∈inC p }, where RuleSet is a rule mapping function that returns the rule set corresponding to process p.
4. The method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores according to claim 3, characterized in that: Implementing service tracking processing on the dynamic process assembly rule library to generate a user behavior analysis data set; The service tracking point processing sets tracking points at key process nodes to collect user operation behavior data, rare earth business data change data and process execution status data, including: assembling the rule base R of the dynamic process p Perform key node analysis and processing to obtain the business key node table N k ={n1,n2,...,n t }, and set the tracking location based on the business key node table, and obtain the key node tracking distribution map through the following formula: M d ={(n i ,Position(n i ),Metrics(n i ))|n i ∈inN k }, where Position is the node position function and Metrics is the collection indicator function; Based on the key node buried point distribution map, the page access records are collected to obtain the user operation behavior data D a ={a1,a2,...,a s }, and perform operation trajectory annotation processing on the user operation behavior data, and obtain the operation trajectory feature set through the following algorithm: perform function usage data statistical processing on the operation trajectory feature set to obtain the node operation frequency table F n ={(n i ,Frequency(n i ))|n i ∈N k }, and perform rare earth business data change monitoring processing on the node operation frequency table, and obtain rare earth business data change data through the following formula: D c ={Δd i |Δd i =d i+1 -d i ,d i ∈D b ,i=1,2,...,u-1}, where D b For business data sets; The rare earth business data change data is collected and processed to obtain the process execution status data D s ={s1,s2,...,s v }, and perform key node monitoring processing on the process execution status data, and obtain the node status sequence table through the following algorithm: Perform abnormal point identification processing on the node state sequence table to obtain the abnormal event feature set E f ={e1,e2,...,e w }, and perform process jam warning analysis on the abnormal event feature set, and obtain the process warning indicator table through the following formula: A t ={(e i ,Severity(e i ),Probability(e i ))|e i ∈E f }, where Severity is the severity assessment function and Probability is the occurrence probability assessment function; The user operation behavior data, rare earth business data change data and process execution status data are integrated and processed through a time series feature analysis algorithm to generate a user behavior analysis data set: D u =Integrate(D a ,D c ,D s ,TimeFeatures), where Integrate is the data integration function and TimeFeatures is the time series feature extraction function.
5. The method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores according to claim 4, characterized in that: Performing guidance strategy construction processing on the user behavior analysis data set to build a service guidance rule library; The guidance strategy construction process designs operation prompts based on user behavior patterns, formulates abnormality handling suggestions and personalized guidance plans, including: analyzing the user behavior data set D u Perform behavior pattern feature extraction to obtain user behavior pattern feature table T b ={(u i ,Pattern(u i ))|u i ∈Users}, and based on the user behavior pattern feature table, generate an operation prompt rule set through the following formula: R o ={GenerateRule(p j ,Hint(p j ))|p j ∈Patterns(T b )}, where GenerateRule is Rule generation function, Hint is the hint generation function; Perform intelligent prompt configuration processing on the operation prompt rule set to obtain the filling guidance rule table T f ={(f i ,Guide(f i ))|f i ∈Fields}, and perform error reminder rule configuration processing on the filling guidance rule table, and obtain the error reminder scheme through the following algorithm: The error reminder solution is processed to generate business suggestions to obtain a business suggestion set S a ={s1,s2,...,s x }, and prepare an exception handling suggestion for the business suggestion set, and obtain the exception handling suggestion through the following formula: H e ={Handle(e k ,Recommend(e k ))|e k ∈Exceptions}, where Handle is the processing function and Recommend is the recommendation solution generation function; Perform optimal path analysis on the exception handling suggestions to obtain a recommended process list L r ={l1,l2,...,l y }, and configure the operation steps of the process recommendation list, and obtain the operation step prompts through the following algorithm: Perform business-related analysis on the operation step prompts to obtain a personalized guidance plan H p ={(u i ,Plan(u i ))|u i ∈Users}, and perform guidance rule aggregation processing on the personalized guidance scheme to obtain a guidance rule collection: Among them, Aggregate is a rule aggregation function; The guidance rule set is integrated through rule mapping to build a service guidance rule library: R g =IntegrateRules(G r ,Priority), where IntegrateRules is the rule integration function and Priority is the priority sorting function.
6. The method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores according to claim 5, characterized in that: The method uses the knowledge extraction algorithm to construct a knowledge graph for the service guidance rule base to obtain a rare earth business knowledge reasoning rule set; the knowledge graph construction process includes extracting rare earth business entities, building a relationship network, discovering knowledge rules and establishing a causal relationship chain, including: using the knowledge extraction algorithm to construct the service guidance rule base R g Perform rare earth business entity extraction and processing to obtain entity feature set E f ={e1,e2,...,e m }, and perform rare earth business entity attribute labeling on the entity feature set, and obtain the rare earth business entity dictionary through the following formula: D e ={(e i ,Attributes(e i ))|e i ∈E f }, where Attributes is the attribute annotation function; The rare earth business entity dictionary is processed by relationship network construction to obtain the initial relationship graph G i =(V i ,E i ), and the initial relationship graph is processed to calculate the strength of the association between entities, and the relationship network is obtained by the following algorithm: Perform knowledge rule extraction on the relationship network to obtain the rule candidate set C r ={r1,r2,...,r n }, and perform rule verification on the rule candidate set to obtain the knowledge rule through the following formula: R kr ={r i |Validate(r i ),r i ∈C r }, where Validate is the rule validation function; The knowledge rules are processed into a causal chain to obtain the causal relationship: T c ={(c i ,Effect(c i ),Cause(c i ))|c i ∈CausalEvents}, and perform causal strength evaluation on the causal relationship table, and obtain the causal relationship chain through the following algorithm: The knowledge rules and causal relationship chains are processed by rule induction algorithm to generate inference rules, and the basic inference rule set R is obtained. b ={r1,r2,...,r p }, and perform rule completeness verification on the basic inference rule set, and obtain a rule verification report through the following formula: R v = VerifyCompleteness(R b , Requirements), where VerifyCompleteness is Completeness check function, Requirements is a set of business requirements; The rule verification report is subjected to rule supplementation processing to obtain a rare earth business knowledge reasoning rule set: R k =R b ∪Supplement(R v ), where Supplement is the rule supplement function.
7. The method for integrating deep processing, grading, packaging and cross-border logistics of rare earth ores according to claim 6, characterized in that: The rare earth business knowledge reasoning rule set is used to carry out rare earth mine cross-border business data processing and generate an intelligent decision-making plan for port business; The cross-border business data processing covers rare earth mine customs clearance process optimization, logistics route planning, risk level assessment and customs clearance time prediction, including: the rare earth business knowledge reasoning rule set R k Analyze the rare earth ore customs clearance business process and obtain the process bottleneck point set B p ={b1,b2,...,b q }, and optimize the customs clearance process for the set of process bottleneck points, and obtain the customs clearance process candidate solutions through the following algorithm: Perform process node configuration processing on the candidate solution of the customs clearance process to obtain the customs clearance business flow diagram G c =(V c ,E c ), and perform path deviation analysis on the customs clearance business flow diagram, and obtain the customs clearance process benchmark path through the following formula: P base =OptimizePath(G c ,Constraints), where OptimizePath is the path optimization function and Constraints is the set of constraints; perform logistics resource allocation processing on the customs clearance process benchmark path to obtain the logistics resource distribution map M r ={(l i ,Resources(l i ))|l i ∈Locations}, and perform logistics path planning on the logistics resource distribution map, and obtain the logistics path planning solution through the following algorithm: The logistics path planning scheme is evaluated for transport timeliness to obtain a transport timeliness evaluation table T a ={(p i ,Time(p i ),Reliability(p i ))|p i ∈P l }, and perform logistics node optimization processing on the transportation time evaluation table, and obtain the logistics distribution route map through the following formula: G d =OptimizeNodes(P l ,TimeConstraints) Among them, OptimizeNodes is the node optimization function, TimeConstraints is the time constraint condition; Perform risk factor identification on the logistics distribution route map to obtain a risk factor list R l ={r1,r2,...,r s }, and perform risk level assessment on the risk factor list, and obtain a risk level assessment report through the following algorithm: The risk level assessment report is processed to extract the clearance time factor and obtain the time factor influencing table T f ={(f i ,Weight(f i ))|f i ∈Factors}, and perform customs clearance time prediction processing on the time influencing factor table, and obtain the customs clearance time prediction result through the following formula: P t =PredictTime(T f ,CurrentState,Model), where PredictTime is the time prediction function, CurrentState is the current state, and Model is the prediction model; The customs clearance process benchmark path, logistics distribution path map and customs clearance time prediction results are integrated to obtain the decision candidate solution set C d ={c1,c2,...,c t }, and perform feasibility evaluation on the decision candidate solution set, and obtain a solution evaluation report through the following algorithm: The program evaluation report is processed for intelligent decision-making to obtain an intelligent decision-making program for port operations: S d =SelectBest(R e ,Objectives), where SelectBest is the optimal solution selection function and Objectives is the decision target set.