Logistics quotation management method and system

Abstract

The invention discloses a logistics quotation management method and system, and belongs to the technical field of logistics quotation management, and the method specifically comprises the steps: collecting the historical behavior data of the logistics quotation of a user, building a user behavior model based on the historical behavior data, enabling the user behavior model to be used for representing the game behavior of the user, and obtaining the logistics quotation of the user according to the user behavior model. The method comprises the following steps: identifying a behavior mode of a user influencing an initial quotation strategy, generating a corresponding disturbance factor, adjusting the initial quotation strategy based on the disturbance factor, obtaining a quotation result containing user behavior disturbance, and dynamically updating a user behavior model and the disturbance factor according to a deviation between an order performance condition and a user actual behavior; according to the invention, active identification and suppression of user behavior disturbance can be realized in a quotation generation process, so that quotation calculation has adaptability and stability, and processing consistency and response efficiency in a complex interaction scene are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of logistics quotation management, and in particular relates to a logistics quotation management method and system. Background Art

[0002] Logistics quotation management is a crucial component of logistics information systems. Its primary function is to provide users with appropriate transportation pricing solutions based on factors such as transportation routes, storage locations, cargo characteristics, and delivery times. Existing logistics quotation management systems generally output quotation results based on historical transportation costs, market pricing rules, and storage inventory status, combined with pre-set calculation models.

[0003] In practice, the logistics quotation process relies not only on internal system data calculations but also on user interactions during the quotation phase. For example, some users frequently initiate quotation requests within a short period of time, change cargo splitting strategies, select specific time windows for order placement, or even circumvent the system's default quotation path through repeated trial and error. These behaviors can lead to price fluctuations or policy imbalances during system operation.

[0004] Existing logistics quotation management methods typically modify quotes through fixed rules, simple parameter weight adjustments, or the introduction of compensation factors in the later stages of calculation. However, these approaches struggle to accurately identify and predict complex user behavior patterns and lack dynamic adjustment mechanisms for behavioral disturbances. When a competitive relationship forms between quotation strategies and user behavior, stability and computational consistency are easily compromised, leading to multiple rounds of unnecessary recalculations, increased computing resource utilization, and prolonged response times. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the present invention proposes a logistics quotation management method and system.

[0006] To achieve the above object, the present invention provides the following technical solutions: A logistics quotation management method, comprising: Collecting historical behavior data of user logistics quotations, and establishing a user behavior model based on the historical behavior data, wherein the user behavior model is used to characterize the user's gaming behavior; Based on the user behavior model, identify the user's behavior patterns that affect the initial bidding strategy and generate corresponding disturbance factors; Adjust the initial bidding strategy based on the disturbance factor to obtain a bidding result that includes user behavior disturbance; Dynamically update the user behavior model and disturbance factor based on the deviation between order fulfillment and actual user behavior.

[0007] Specifically, collecting historical behavior data of user logistics quotations and establishing a user behavior model based on the historical behavior data includes: Collect historical behavior data on user logistics quotes, including refresh frequency, order splitting operations, order time selection, and route preferences; Identify the target user ID, associate historical order records and quotation request records with the corresponding user account, and build a behavior tracking sequence; Semantically classify the actions in the behavior tracking sequence and mark them with preset behavior labels, including browsing operations, comparison operations, avoidance operations, repetitive operations, and time-point decision operations; Based on the temporal distribution characteristics between operation tags, the behavior transfer pattern is extracted, and the user behavior model is constructed based on the operation nodes.

[0008] Specifically, the method of identifying the user's behavior pattern that affects the initial bidding strategy based on the user behavior model and generating the corresponding disturbance factor includes: Extract the target user's decision node sequence in the user behavior model and cluster the operation jump patterns between adjacent nodes; The node combinations within each cluster are traced back in reverse order to identify the user's behavioral segments that actively skip the recommended strategy or repeat the trial path during the quotation process; Based on the degree of cross-overlap between the behavior segments among users, construct an intervention behavior similarity matrix; The intervention behavior similarity matrix is ​​mapped to a multidimensional behavior intervention space, and a disturbance factor representing the disturbance tendency of user behavior is generated by locating dense trajectory clusters in the frequent disturbance area.

[0009] Specifically, constructing an intervention behavior similarity matrix based on the degree of overlap of the behavior segments between users includes: Encode each behavior fragment into a fragment identification string according to the node type and operation order; Retrieving the segment identification string in the behavior sequences of different users, and recording the set of user identifications in which the segment identification string appears; Calculate the intersection of the user ID sets of any two segment ID strings to form a segment association pair; According to the intersection scale of the fragment association pairs and the difference of the operation sequence, a corresponding similarity value is generated, and the value is filled into the corresponding position of the intervention behavior similarity matrix to construct the intervention behavior similarity matrix.

[0010] Specifically, the intervention behavior similarity matrix is ​​mapped to a multidimensional behavior intervention space, and by locating dense trajectory clusters in the frequently disturbed area, a disturbance factor representing the disturbance tendency of the user behavior is generated, including: Assign corresponding multidimensional space coordinates to each behavior segment in the intervention behavior similarity matrix, where the coordinate dimension corresponds to the preset intervention feature category; The spatial coordinates of all behavior segments are combined to form a behavior intervention point set, and a neighborhood search is performed in the point set to determine the candidate trajectory cluster; Perform sequence analysis on the point sets in each candidate trajectory cluster to screen out the trajectory sets with cross-node jump characteristics; Based on the density of node distribution and the cross-hop frequency in the trajectory set, a corresponding disturbance factor is generated.

[0011] Specifically, adjusting the initial bidding strategy based on the disturbance factor to obtain a bidding result that includes user behavior disturbance includes: Identify behavioral category labels in perturbation factors and map them to a preset set of quote adjustment parameters; In the quotation calculation process, insert the quotation adjustment parameter set during the parameter initialization phase to replace or modify the original parameter values; In the middle stage of quotation calculation, the parameter branch corresponding to the disturbance factor is called for the calculation nodes involved in path selection, warehouse allocation and time window matching; Before generating the quotation results, a global consistency check based on the disturbance factor is performed on the output of all computing nodes, and the necessary quotation recalculation process is retriggered based on the check results.

[0012] Specifically, in the intermediate stage of the quotation calculation, the parameter branch corresponding to the disturbance factor is called for the calculation nodes involved in path selection, warehouse allocation, and time window matching, including: Determine the set of computing nodes that are within the path selection, warehouse allocation, and time window matching range in the current quotation calculation process; For each node in the set of computing nodes, retrieving a perturbation factor type label associated with the node; According to the perturbation factor type label, load the corresponding parameter branch configuration from the preset parameter branch library; Injecting the parameter branch configuration into the corresponding computing node operation process to replace the original parameter set of the node; For the calculation nodes after parameter replacement, subsequent calculations are completed according to the preset execution order.

[0013] Specifically, dynamically updating the user behavior model and disturbance factor based on the deviation between the order fulfillment status and the user's actual behavior includes: Extract the fulfillment path data, delivery timing data, and warehouse call data corresponding to the target order from the fulfillment records; Aligning the fulfillment path data with the user's actual behavior sequence from order placement to fulfillment completion to generate a behavior-fulfillment mapping table; In the behavior-performance mapping table, calculating the deviation index between the performance execution node and the corresponding user operation node; Map the deviation indicators to the corresponding characteristic parameters of the user behavior model, and dynamically update the user behavior model and disturbance factors.

[0014] A logistics quotation management system, used to implement the logistics quotation management method, comprising: a model generation module, a disturbance module, a quotation module and a dynamic update module; The model generation module is used to collect historical behavior data of user logistics quotations and establish a user behavior model based on the historical behavior data; The perturbation module is used to identify the user's behavior pattern that affects the initial bidding strategy based on the user behavior model and generate a corresponding perturbation factor; The quotation module is used to adjust the initial quotation strategy based on the disturbance factor to obtain a quotation result including the user behavior disturbance; The dynamic update module is used to dynamically update the user behavior model and the disturbance factor according to the deviation between the order fulfillment situation and the actual user behavior.

[0015] Specifically, the quotation module includes: a mapping unit, an adjustment unit and a verification unit; The mapping unit is used to identify the behavior category label in the disturbance factor and map it to a preset quote adjustment parameter set; The adjustment unit is used to adjust the quotation parameters during the quotation calculation stage; The verification unit is used to perform a global consistency check on the outputs of all computing nodes based on the disturbance factor before generating the quotation result, and to re-trigger the necessary quotation recalculation process according to the check result.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a logistics quotation management method and system. By collecting multi-dimensional historical behavior data of users in the logistics quotation process, a user behavior model with game attributes is constructed, and based on the model, the disturbance behavior that users may cause to the quotation strategy is predicted, and the corresponding disturbance factor is generated. In the intermediate link of the quotation calculation, the disturbance factor is dynamically introduced into key calculation nodes such as path selection, warehouse allocation and time window matching, and the quotation result is output. After the order fulfillment is completed, the user behavior model and the disturbance factor are updated in a closed loop according to the deviation between the fulfillment data and the actual behavior of the user. This method can realize the active identification and suppression of user behavior disturbances in the quotation generation process, so that the quotation calculation has adaptability and stability, thereby improving the processing consistency and response efficiency in complex interactive scenarios, and reducing the burden of repeated calculations and resource usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Flowchart provided for the present invention; Figure 2 This is a diagram of the system architecture provided by the present invention. DETAILED DESCRIPTION

[0018] The present application is described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but are not intended to limit the present application in any form. It should be noted that those skilled in the art may make several variations and improvements without departing from the scope of the present application. These all fall within the scope of protection of the present application.

[0019] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0020] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flow chart. In addition, the " The words "first", "second", "third", etc. do not limit the data and execution order, but only distinguish the same or similar items with basically the same functions and effects.

[0021] Unless otherwise defined, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification and in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" as used in this specification includes any and all combinations of one or more of the relevant listed items.

[0022] Example 1 See also Figure 1 The present invention provides an embodiment: a logistics quotation management method, comprising the following specific steps: Step S1: Collect historical behavior data of user logistics quotations, and establish a user behavior model based on the historical behavior data. The user behavior model is used to characterize the user's gaming behavior.

[0023] The specific steps of step S1 are: Step S101: Collect historical behavior data of user logistics quotations, including refresh frequency, order splitting operations, order time selection, and route preference.

[0024] Step S102: Identify the target user ID, associate historical order records and quotation request records with the corresponding user account, and build a behavior tracking sequence.

[0025] In this embodiment, based on the target user's unique account ID on the quotation platform, the user's historical order records and historical quotation request records are retrieved from the data storage module. The historical order records include fields such as order number, cargo type, originating warehouse, destination, transportation route identifier, and order time; the quotation request records include fields such as the quotation request time, the selected parameter configuration requested, and the quotation solution identifier returned by the system. Subsequently, the above two types of records are uniformly sorted along the timeline and associated based on the account ID to generate a chronological sequence of behavioral events. Finally, each record in the event sequence is annotated with a corresponding behavioral type tag, such as quotation query, order confirmation, order modification, etc.

[0026] Step S103: semantically classify the operations in the behavior tracking sequence and mark them as preset behavior labels, including browsing operation, comparison operation, avoidance operation, repetitive operation, and time-point decision operation.

[0027] In this embodiment, first, all event records in the behavior tracking sequence generated in step S102 are read, and the operation type, trigger condition, and context parameters of each event are extracted; then, the semantic classification module is called to match the extracted event attributes with the preset behavior label classification rules. The label rules are classification mapping tables established by analyzing historical user behavior characteristics, which include browsing operations, comparison operations, avoidance operations, repetitive operations, and time-point decision operations. For example, if continuous quotation query events occur repeatedly with a small parameter change, they are marked as comparison operations; if orders are submitted in a concentrated manner at a specific time point to avoid time period surcharges, they are marked as time-point decision operations; after matching is completed, each event is assigned a corresponding label, and the original event type field is replaced with the label in the behavior tracking sequence to obtain a behavior sequence with semantic annotations.

[0028] Step S104: Based on the temporal distribution characteristics between the operation tags, the behavior transfer pattern is extracted, and the user behavior model is constructed based on the operation nodes.

[0029] In this embodiment, the behavior tracking sequence marked with semantic tags in step S103 is read, and the distribution of each operation tag on the time axis is analyzed, including the order of appearance of adjacent tags, the appearance interval, and the position characteristics in the sequence; then, the jump relationship between each tag is used as a candidate behavior transfer unit, and these units are classified and counted according to the tag combination type to obtain the transfer probability distribution and common jump path set between tags; on this basis, each tag is regarded as an operation node in the user behavior model, and the jump relationship between different tags is used as a directed connection edge between nodes to form a user behavior model based on the operation node.

[0030] Step S2: Based on the user behavior model, identify the user's behavior pattern that affects the initial bidding strategy and generate a corresponding disturbance factor.

[0031] The specific steps of step S2 are: Step S201: extracting the decision node sequence of the target user in the user behavior model, and clustering the operation jump patterns between adjacent nodes.

[0032] In this embodiment, all operation nodes corresponding to the target user identifier are retrieved from the constructed user behavior model, and a decision node sequence is extracted according to the temporal connection relationship of the nodes in the model; the decision node sequence reflects the user's behavior path in a specific quotation process; then, the operation difference features between adjacent nodes are calculated, including changes in label categories, time intervals between nodes, and strategy branch identifiers of the previous and next nodes; then, these adjacent node pairs are regarded as basic units of jump patterns, all jump patterns are feature encoded, and cluster analysis is performed on them based on similarity metrics; the final clustering results are used to characterize the distribution of user operation switching patterns at different behavior stages.

[0033] Step S202: tracing back the node combinations in each cluster in reverse order to identify the behavior segments in which the user actively skips the recommendation strategy or repeats the trial path during the quotation process.

[0034] In this embodiment, for each jump pattern cluster obtained in step S201, the node combinations in each cluster are traversed in turn, and the temporal order of the node combinations is reversed to form a reverse node chain; then, the reverse chain is traced back from the end node to analyze the connection relationship between the nodes and the associated quotation strategy identifiers; when it is detected in the backtracking process that there is a jump in the node combination that bypasses the system recommended path, or there are multiple cyclic switches to and from the same path node, this part of the node chain is intercepted as a behavior fragment.

[0035] Step S203: constructing an intervention behavior similarity matrix based on the degree of cross-overlap of the behavior segments between users.

[0036] The specific steps of step S203 are: Step S2031: Encode each behavior segment into a segment identification string according to the node type and operation sequence.

[0037] Step S2032: searching for the segment identification string in the behavior sequences of different users, and recording the set of user identifications in which the segment identification string appears.

[0038] In this embodiment, a behavior segment identification string generated by the previous processing step is received, and the identification string is obtained by combining the label sequence of each operation node in the segment and the connection order thereof; then, the multi-user historical behavior sequences stored in the behavior data set are traversed, and a sliding window search is performed on each behavior sequence in chronological order to compare whether the operation label combination in the window is completely consistent with the target identification string; if a match is successful, the user unique identifier corresponding to the behavior sequence is read and added to the user identifier set corresponding to the segment identification string; after the retrieval is completed, a mapping table of the user identifier set and the number of occurrences is established for each segment identification string.

[0039] Step S2033: Calculate the intersection of the user identification sets of any two segment identification strings to form a segment association pair.

[0040] In this embodiment, the user identification set corresponding to each fragment identification string is read from the result of step S2032; then, in the set list of all fragment identification strings, any two different fragment identification strings are selected in turn in a combination manner, and a set intersection operation is performed on their respective user identification sets to obtain a user identification list included in both sets; then, the user identification list is recorded together with the corresponding two fragment identification strings to form a fragment association pair, and a unique association pair number is assigned to it; finally, all generated fragment association pairs are stored in the fragment association relationship table.

[0041] Step S2034: Generate corresponding similarity values ​​based on the intersection size of the segment association pairs and the difference between the operation sequences, and fill the values ​​into corresponding positions of the intervention behavior similarity matrix to construct the intervention behavior similarity matrix.

[0042] In this embodiment, for each fragment association pair generated in step S2033, the intersection scale of the corresponding user identification set and the operation sequence information of the two fragment identification strings in the association pair are read; then, the difference index between the two operation sequences is calculated, and the difference is composed of the difference in operation node type and the difference in node order; then, the intersection scale and the difference are converted into similarity values ​​according to the preset numerical mapping rules, and the value range of the similarity corresponds to the matrix index; finally, the similarity value is filled into the intervention behavior similarity matrix with the two fragment identification strings as row and column indexes, until the similarities of all fragment association pairs are filled in, thereby constructing a complete intervention behavior similarity matrix.

[0043] Step S204: Mapping the intervention behavior similarity matrix to a multi-dimensional behavior intervention space, and generating a disturbance factor for representing the user behavior disturbance tendency by locating dense trajectory clusters in the frequent disturbance area.

[0044] The specific steps of step S204 are: Step S2041: assigning corresponding multi-dimensional space coordinates to each behavior segment in the intervention behavior similarity matrix, where the coordinate dimensions correspond to preset intervention feature categories.

[0045] In this embodiment, all behavior fragment identifiers in the intervention behavior similarity matrix are read, and the intervention feature data related to each fragment is retrieved. The intervention feature categories include but are not limited to time sensitivity, path deviation, node repetition rate, strategy avoidance intensity, and cross-stage switching frequency; then, a coordinate dimension is assigned to each intervention feature category, and the feature value of the fragment is mapped to the numerical coordinate position of the dimension according to a preset numerical standard; then, the coordinate values ​​of all dimensions are combined into the multidimensional space coordinates of the behavior fragment, and stored in the intervention feature space data table.

[0046] Step S2042: combining the spatial coordinates of all behavior segments to form a behavior intervention point set, and performing a neighborhood search in the point set to determine a candidate trajectory cluster.

[0047] In this embodiment, the multidimensional spatial coordinates of all the behavior fragments generated in step S2041 are read in sequence and combined according to the spatial coordinate values ​​to form a behavior intervention point set, where each point in the point set corresponds to a multidimensional feature representation of a behavior fragment. Subsequently, based on a preset spatial neighborhood radius parameter, a neighborhood search operation is performed on the point set to identify a set of points that are spatially close to each other. During the neighborhood search process, the spatial distance between each point and the surrounding points is calculated, and the number of neighboring points whose distance does not exceed the radius is counted. If the number of neighbors of a fragment point exceeds a preset threshold, the point and its neighboring points in the neighborhood are classified as the same candidate trajectory cluster. After the traversal is completed, the data set of all candidate trajectory clusters is output.

[0048] Step S2043: performing sequence analysis on the point sets in each candidate trajectory cluster to screen out trajectory sets with cross-node jump features.

[0049] In this embodiment, for each candidate trajectory cluster obtained in step S2042, the original behavior segment sequence data corresponding to all points in the cluster is read; then, the segments within the same trajectory cluster are sorted according to their occurrence order in the original user behavior sequence, and the jump relationship and jump direction between nodes are recorded; then, cross-node jump detection is performed on the sorted sequence, specifically to identify operation modes that jump directly to non-adjacent nodes without passing through consecutive adjacent nodes in the model; if multiple segments with similar cross-node jump patterns are found in the same trajectory cluster, these segments are integrated into a trajectory set, and a unique identifier is assigned to the set.

[0050] Step S2044: Generate a corresponding disturbance factor based on the density of node distribution and the cross-hop frequency in the trajectory set.

[0051] In this embodiment, for each trajectory set obtained in step S2043, the distribution density of each node in the set in the user behavior model is calculated. The distribution density is determined by the ratio of the number of times a node appears in the trajectory set to the total number of paths that the node can reach in the model. Subsequently, the frequency of cross-node jump events in the trajectory set is calculated. The frequency is the ratio of the number of jump events to the total number of events in the trajectory set. Finally, the values ​​of the node distribution density and the cross-jump frequency are input into the disturbance factor generation module, converted into disturbance factor values ​​according to a preset mapping rule, and a unique corresponding disturbance factor identifier is generated for each trajectory set.

[0052] Step S3: Adjust the initial bidding strategy based on the disturbance factor to obtain a bidding result that includes user behavior disturbance.

[0053] The specific steps of step S3 are: Step S301: Identify the behavior category label in the disturbance factor and map it to a preset quotation adjustment parameter set.

[0054] In this embodiment, the disturbance factor data structure generated in the previous step is read, and the behavior category label associated with the factor is parsed therefrom, the label including but not limited to price trial, path avoidance, time window concentration, repeated quotation and warehouse switching; then, the quotation adjustment parameter mapping table stored in the parameter configuration library is accessed, in which each type of behavior label corresponds to a set of adjustment parameters that can be used for quotation calculation, and the adjustment parameter set may include basic freight correction coefficient, path weight adjustment value, time window priority parameter and inventory call threshold, etc.; then, the parsed behavior category label is matched with the entry in the mapping table, the corresponding quotation adjustment parameter set is extracted, and the set is bound to the unique identifier of the disturbance factor.

[0055] Step S302: In the quotation calculation process, insert the quotation adjustment parameter set during the parameter initialization phase to replace or modify the original parameter values.

[0056] In this embodiment, when the quotation engine starts the quotation calculation process, it locates the parameter initialization stage, which is used to load initial parameters for each calculation module, including basic freight, path cost weight, warehouse call priority, time window additional coefficient, etc.; then, all parameter items are read from the quotation adjustment parameter set bound in step S301, and compared with the original parameters loaded in the initialization stage item by item. When it is detected that the corresponding parameter item already exists, the original parameter value is directly replaced with the value in the adjustment parameter set; if the corresponding parameter item does not exist, the adjustment parameter is inserted as a new item into the parameter list. After completing the replacement and insertion operations, the parameter configuration file of the initialization stage is regenerated and passed to the subsequent quotation calculation.

[0057] Step S303: In the intermediate stage of quotation calculation, for the calculation nodes involved in path selection, warehouse allocation and time window matching, the parameter branch corresponding to the disturbance factor is called.

[0058] The specific steps of step S303 are: Step S3031: Determine the set of computing nodes that are within the scope of path selection, warehouse allocation, and time window matching in the current quotation calculation process.

[0059] In this embodiment, the execution schedule of the current task is read in the calculation link of the quotation engine. The schedule lists all computing nodes involved in the quotation calculation and their functional types in module order. Subsequently, based on the functional identification of the node, the nodes with functional types of path selection, warehouse allocation and time window matching are screened out, and the reference addresses of the nodes that meet the conditions are stored in a node set structure. For the case of nodes with composite functions, such as nodes involving path selection and warehouse allocation at the same time, multi-label marking is performed in the set to facilitate the call of corresponding functional logic separately in subsequent processing. Finally, the generated computing node set is used as the target set input for subsequent parameter calls and strategy adjustment steps.

[0060] Step S3032: For each node in the computing node set, retrieve the disturbance factor type label associated with the node.

[0061] In this embodiment, the computing node set generated in step S3031 is read, and each node in the set is traversed in turn. For each node, its node identification information and function type identification are obtained, and the disturbance factor index table is accessed. Subsequently, in the disturbance factor index table, the node identification information is used as the search key to query the disturbance factor record associated with the node, and the disturbance factor type label in the record is parsed. If a node is associated with multiple disturbance factors, all type labels are stored in the associated label field of the node in the form of a list; after the traversal is completed, a mapping table of node identification-disturbance factor type label set is formed.

[0062] Step S3033: According to the disturbance factor type label, the corresponding parameter branch configuration is loaded from the preset parameter branch library.

[0063] In this embodiment, the node identification-disturbance factor type label set mapping table generated in step S3032 is read, and the disturbance factor type label of each node is traversed in turn. For each type label, the preset parameter branch library is accessed. The library is partitioned according to the behavior intervention category, and several parameter branch configuration files are stored in each partition. Subsequently, the corresponding parameter branch configuration file is retrieved in the partition matching the label, and all parameter items of the configuration file are loaded into a temporary cache area. If a node is associated with multiple disturbance factor type labels, the corresponding parameter branches are loaded in sequence according to the label order, and the parameter items are merged or overwritten in the cache area. After loading is completed, the parameter branch configuration of the node is cached to the node execution context.

[0064] Step S3034: inject the parameter branch configuration into the corresponding computing node operation process to replace the original parameter set of the node.

[0065] In this embodiment, the parameter branch configuration loaded in step S3033 is read and located at the compute node to which it is bound. Subsequently, during the parameter loading phase before the computational process for that compute node is started, the node's original parameter set is copied to a temporary buffer for backtracking. Next, the node's original parameter set is replaced item by item using the parameter values ​​in the parameter branch configuration. Fields not present in the original parameter set are directly appended to the parameter structure and registered as valid compute variables in the node's execution context. After completing the parameter replacement and append operations, the updated parameter set is written back to the node's runtime environment.

[0066] Step S3035: For the computing nodes after parameter replacement, subsequent calculations are completed according to the preset execution order.

[0067] In this embodiment, for the computing node that has completed parameter replacement in step S3034, its sequential index value in the execution plan table is read, and the node's dependency on subsequent nodes in the computing link is determined; then, according to the preset execution sequence control table, the computing process of each dependent node is triggered in sequence starting from the current node, wherein the current node first executes the calculation logic such as path selection, warehouse allocation or time window matching according to the injected new parameter set, and writes the result data into the intermediate result cache; then, the downstream nodes that depend on the output of the node obtain the intermediate results in sequence, and continue to execute their corresponding computing operations until all nodes in the branch link complete the computing task; finally, the result data of the computing link is submitted to the global summary.

[0068] Step S304: Before generating the quotation result, a global consistency check based on the disturbance factor is performed on the output of all computing nodes, and the necessary quotation recalculation process is retriggered according to the check result.

[0069] In this embodiment, before the quotation calculation process enters the result aggregation stage, all computing node outputs in the global output data buffer are retrieved, and their positions and dependencies in the link are determined according to the node execution plan table; then, all disturbance factors involved in the calculation and their type labels are read from the disturbance factor index table, and compared one by one with the outputs of the corresponding computing nodes. For nodes associated with disturbance factors, consistency verification logic is executed, including but not limited to: value range check of key fields before and after parameter adjustment, cross-node data format matching verification, and numerical balance check within the link. If the verification result shows that there is a deviation exceeding the threshold or a dependency conflict, the node and its downstream links are marked as requiring recalculation in the execution control module; then, the corresponding quotation recalculation process is retriggered based on the marked status, and only the affected node links are recalculated, and the new result data is updated to the global output buffer after completion.

[0070] Step S4: Dynamically update the user behavior model and disturbance factor based on the deviation between the order fulfillment status and the user's actual behavior.

[0071] The specific steps of step S4 are: Step S401: Extract the fulfillment path data, delivery timing data and warehouse call data corresponding to the target order from the fulfillment record.

[0072] Step S402: Align the fulfillment path data with the actual behavior sequence of the user in the entire process from order placement to fulfillment completion to generate a behavior-fulfillment mapping table.

[0073] In this embodiment, the fulfillment path data of the target order is obtained. The path data consists of multiple fulfillment nodes, and each node contains information such as node identification, completion timestamp, and processing action type. Subsequently, the user behavior sequence associated with the order is extracted. The sequence covers the entire process from the user initiating the order request to the completion of the fulfillment, and is arranged in chronological order. Then, the fulfillment path nodes and user behavior events are aligned one by one with the timestamp as the primary key, and a one-to-one mapping relationship is established for records with time overlap or intervals within a preset threshold. For cases where multiple stages or multiple behaviors correspond to the same fulfillment node, they are recorded in the mapping table as a behavior set. Finally, the behavior-fulfillment mapping table formed contains the pairing information of the fulfillment path nodes and the corresponding user behaviors, and retains the relative order and context identification of the behaviors.

[0074] Step S403: In the behavior-performance mapping table, the deviation index between the performance execution node and the corresponding user operation node is calculated.

[0075] In this embodiment, the behavior-performance mapping table generated in step S402 is read, and the mapping records therein are traversed one by one. For each record, the key indicator data of the performance execution node is extracted, including the node completion time, processing time, number of state changes, etc., and the characteristic data of the corresponding user operation node is extracted at the same time, including the operation trigger time, continuous operation interval, behavior frequency, etc.; then, according to the preset deviation calculation rules, the difference values ​​of the performance node and the user operation node in dimensions such as time, number and behavior density are compared to generate a multi-dimensional deviation vector; if a certain performance node corresponds to multiple user operation nodes, the user operation data is aggregated during the calculation to ensure that it is under the same comparison benchmark as the indicators of the performance node; finally, a deviation indicator is generated.

[0076] Step S404: Map the deviation index to the corresponding characteristic parameter of the user behavior model, and dynamically update the user behavior model and the disturbance factor.

[0077] In this embodiment, the deviation index table generated in step S403 is read, and the corresponding characteristic parameter position in the user behavior model is located according to the fulfillment node identifier and the user operation node identifier in the deviation index record. Subsequently, each dimension of the deviation index vector is mapped one-to-one with the predefined characteristic parameters in the user behavior model, for example, the time difference dimension is mapped to the response delay parameter of the model, the frequency difference dimension is mapped to the interaction stability parameter, and the behavior density dimension is mapped to the attention concentration parameter; after the mapping is completed, the parameter values ​​in the model are corrected according to the preset dynamic update rules; the correction methods include direct replacement of the parameter values, proportional increase or decrease, or smooth update based on historical trends; then, the disturbance factor weights bound to these characteristic parameters are recalculated.

[0078] Example 2 See also Figure 2 , another embodiment provided by the present invention: a logistics quotation management system, comprising: a model generation module, a disturbance module, a quotation module and a dynamic update module; The model generation module is used to collect historical behavior data of user logistics quotations and establish a user behavior model based on the historical behavior data; The perturbation module is used to identify the user's behavior pattern that affects the initial bidding strategy based on the user behavior model and generate a corresponding perturbation factor; The quotation module is used to adjust the initial quotation strategy based on the disturbance factor to obtain a quotation result including the user behavior disturbance; The dynamic update module is used to dynamically update the user behavior model and the disturbance factor according to the deviation between the order fulfillment situation and the actual user behavior.

[0079] The quotation module includes: a mapping unit, an adjustment unit and a verification unit; The mapping unit is used to identify the behavior category label in the disturbance factor and map it to a preset quote adjustment parameter set; The adjustment unit is used to adjust the quotation parameters during the quotation calculation stage; The verification unit is used to perform a global consistency check on the outputs of all computing nodes based on the disturbance factor before generating the quotation result, and to re-trigger the necessary quotation recalculation process according to the check result.

[0080] In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0081] The above-described specific embodiments further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is merely a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A logistics quotation management method, characterized in that: include: Collecting historical behavior data of user logistics quotations, and establishing a user behavior model based on the historical behavior data, wherein the user behavior model is used to characterize the user's gaming behavior; Based on the user behavior model, identify the user's behavior patterns that affect the initial bidding strategy and generate corresponding disturbance factors; Adjust the initial bidding strategy based on the disturbance factor to obtain a bidding result that includes user behavior disturbance; Dynamically update the user behavior model and disturbance factor based on the deviation between order fulfillment and actual user behavior.

2. A logistics quotation management method according to claim 1, characterized in that: The collecting of historical behavior data of user logistics quotations and establishing a user behavior model based on the historical behavior data includes: Collect historical behavior data on user logistics quotes, including refresh frequency, order splitting operations, order time selection, and route preferences; Identify the target user ID, associate historical order records and quotation request records with the corresponding user account, and build a behavior tracking sequence; Semantically classify the actions in the behavior tracking sequence and mark them with preset behavior labels, including browsing operations, comparison operations, avoidance operations, repetitive operations, and time-point decision operations; Based on the temporal distribution characteristics between operation tags, the behavior transfer pattern is extracted, and the user behavior model is constructed based on the operation nodes.

3. A logistics quotation management method according to claim 2, characterized in that: The method of identifying the user's behavior pattern that affects the initial bidding strategy based on the user behavior model and generating the corresponding disturbance factor includes: Extract the target user's decision node sequence in the user behavior model and cluster the operation jump patterns between adjacent nodes; The node combinations within each cluster are traced back in reverse order to identify the user's behavioral segments that actively skip the recommended strategy or repeat the trial path during the quotation process; Based on the degree of cross-overlap between the behavior segments among users, construct an intervention behavior similarity matrix; The intervention behavior similarity matrix is ​​mapped to a multidimensional behavior intervention space, and a disturbance factor representing the disturbance tendency of user behavior is generated by locating dense trajectory clusters in the frequent disturbance area.

4. A logistics quotation management method according to claim 3, characterized in that: The constructing of an intervention behavior similarity matrix based on the degree of overlap of the behavior segments between users includes: Encode each behavior fragment into a fragment identification string according to the node type and operation order; Retrieving the segment identification string in the behavior sequences of different users, and recording the set of user identifications in which the segment identification string appears; Calculate the intersection of the user ID sets of any two segment ID strings to form a segment association pair; According to the intersection scale of the fragment association pairs and the difference of the operation sequence, a corresponding similarity value is generated, and the value is filled into the corresponding position of the intervention behavior similarity matrix to construct the intervention behavior similarity matrix.

5. A logistics quotation management method according to claim 4, characterized in that: The intervention behavior similarity matrix is ​​mapped to a multidimensional behavior intervention space. By locating dense trajectory clusters in the frequently disturbed area, a disturbance factor representing the disturbance tendency of the user behavior is generated, including: Assign corresponding multidimensional space coordinates to each behavior segment in the intervention behavior similarity matrix, where the coordinate dimension corresponds to the preset intervention feature category; The spatial coordinates of all behavior segments are combined to form a behavior intervention point set, and a neighborhood search is performed in the point set to determine the candidate trajectory cluster; Perform sequence analysis on the point sets in each candidate trajectory cluster to screen out the trajectory sets with cross-node jump characteristics; Based on the density of node distribution and the cross-hop frequency in the trajectory set, a corresponding disturbance factor is generated.

6. A logistics quotation management method according to claim 5, characterized in that: The step of adjusting the initial bidding strategy based on the disturbance factor to obtain a bidding result including the user behavior disturbance includes: Identify behavioral category labels in perturbation factors and map them to a preset set of quote adjustment parameters; In the quotation calculation process, insert the quotation adjustment parameter set during the parameter initialization phase to replace or modify the original parameter values; In the middle stage of quotation calculation, the parameter branch corresponding to the disturbance factor is called for the calculation nodes involved in path selection, warehouse allocation and time window matching; Before generating the quotation results, a global consistency check based on the disturbance factor is performed on the output of all computing nodes, and the necessary quotation recalculation process is retriggered based on the check results.

7. A logistics quotation management method according to claim 6, characterized in that: In the intermediate stage of the quotation calculation, the parameter branch corresponding to the disturbance factor is called for the calculation nodes involved in path selection, warehouse allocation, and time window matching, including: Determine the set of computing nodes that are within the path selection, warehouse allocation, and time window matching range in the current quotation calculation process; For each node in the set of computing nodes, retrieving a perturbation factor type label associated with the node; According to the perturbation factor type label, load the corresponding parameter branch configuration from the preset parameter branch library; Injecting the parameter branch configuration into the corresponding computing node operation process to replace the original parameter set of the node; For the calculation nodes after parameter replacement, subsequent calculations are completed according to the preset execution order.

8. A logistics quotation management method according to claim 7, characterized in that: Dynamically updating the user behavior model and disturbance factor based on the deviation between order fulfillment and actual user behavior includes: Extract the fulfillment path data, delivery timing data, and warehouse call data corresponding to the target order from the fulfillment records; Aligning the fulfillment path data with the user's actual behavior sequence from order placement to fulfillment completion to generate a behavior-fulfillment mapping table; In the behavior-performance mapping table, calculating the deviation index between the performance execution node and the corresponding user operation node; Map the deviation indicators to the corresponding characteristic parameters of the user behavior model, and dynamically update the user behavior model and disturbance factors.

9. A logistics quotation management system, used to implement a logistics quotation management method according to any one of claims 1 to 8, characterized in that: include: Model generation module, perturbation module, quotation module and dynamic update module; The model generation module is used to collect historical behavior data of user logistics quotations and establish a user behavior model based on the historical behavior data; The perturbation module is used to identify the user's behavior pattern that affects the initial bidding strategy based on the user behavior model and generate a corresponding perturbation factor; The quotation module is used to adjust the initial quotation strategy based on the disturbance factor to obtain a quotation result including the user behavior disturbance; The dynamic update module is used to dynamically update the user behavior model and the disturbance factor according to the deviation between the order fulfillment situation and the actual user behavior.

10. A logistics quotation management system according to claim 9, characterized in that: The quotation module includes: a mapping unit, an adjustment unit and a verification unit; The mapping unit is used to identify the behavior category label in the disturbance factor and map it to a preset quote adjustment parameter set; The adjustment unit is used to adjust the quotation parameters during the quotation calculation stage; The verification unit is used to perform a global consistency check on the outputs of all computing nodes based on the disturbance factor before generating the quotation result, and to re-trigger the necessary quotation recalculation process according to the check result.

Images