Order data processing method, device and equipment
By collecting and preprocessing the order data of logistics outlets, and using preset order division methods and algorithms for order division processing, the shortcomings of the performance analysis of order division algorithms and incomplete special order processing in the existing technology are solved, and more accurate order division indicator data and outlet operation status analysis are achieved.
Patent Information
- Application Number
- CN202510084284.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-20
- Publication Date
- 2025-05-13
AI Technical Summary
The existing technology lacks an effective monitoring and reporting system in the logistics industry, making it difficult to deeply analyze the performance of the order-sharing algorithm, and the traditional processing methods do not handle special order situations comprehensively, resulting in inaccurate evaluation results.
By collecting order data from multiple business systems of logistics outlets, pre-processing and order-dividing, use pre-set order-dividing methods and order-dividing algorithms to perform order-dividing, and generate order-dividing results and indicator data to analyze the operating status of outlets.
The accuracy of the order-subdivided index data is improved, and the rapid and accurate analysis of the operating status of logistics outlets is achieved, abnormal states can be identified and the performance of the order-subdivided algorithm is optimized.
Smart Images
Figure CN119990974A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to an order data processing method, device and equipment. Background Art
[0002] In the complex operating environment of the modern logistics industry, the accuracy and efficiency of the order splitting algorithm are crucial to optimizing the logistics distribution process. However, existing technologies face many challenges: The lack of a comprehensive and effective monitoring and reporting system cannot provide sufficient data support for in-depth analysis of the performance of the order splitting algorithm, making it difficult to accurately locate and solve problems at the algorithm level.
[0003] The traditional way of handling special order situations such as empty pickup codes is relatively simple and fixed, failing to fully consider the diverse characteristics of orders and their comprehensive impact on algorithm performance evaluation, resulting in inaccurate and incomplete evaluation results. Summary of the invention
[0004] The present invention provides an order data processing method, device and equipment, which can improve the accuracy of order splitting index data and realize rapid and accurate analysis of the operating status of outlets based on the order splitting index data.
[0005] In one aspect, the present invention provides an order data processing method, the method comprising: Collect logistics order data of logistics outlets in multiple business systems to obtain order data sets; Preprocessing the order data in the order data set to obtain a processed data set; Determine, according to the data attribute information in the processed data set, a preset order splitting method corresponding to the data in the processed data set, and obtain a preset order splitting field corresponding to the preset order splitting method; Using the order splitting algorithm corresponding to the preset order splitting method, the order data is split, and the order splitting result corresponding to the preset order splitting field is obtained; Determine the order splitting index data of the logistics network point according to the order splitting results of each order data in the processed data set; According to the order splitting index data of the logistics network point, it is determined whether the logistics network point is in an abnormal state.
[0006] Exemplarily, the order splitting algorithm corresponding to the preset order splitting method is used to split the order data to obtain the order splitting result corresponding to the preset order splitting field, including: Using sample order data to train the order splitting algorithm corresponding to the preset order splitting method to obtain an order splitting processing model; The order data is input into the order splitting processing model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field.
[0007] Exemplarily, the order splitting processing model includes a decision tree model, a neural network model, and a support vector machine model. The order data is input into the order splitting processing model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field, including: Obtain the number of classification features and data volume corresponding to the order data; When the number of classification features is greater than a preset number and the data volume is greater than a preset threshold, the order data is input into the decision tree model for order splitting processing to obtain order splitting results corresponding to the preset order splitting fields; When the number of classification features is less than or equal to the preset number or the data volume is less than or equal to the preset threshold, the order data is input into the neural network model or the support vector machine model for order splitting processing to obtain the order splitting results corresponding to the preset order splitting fields.
[0008] Exemplarily, the method further includes: If the predicted first-level outlet in the order splitting result is not empty, the first-level outlet identification quantity corresponding to the order data is increased by a preset value to obtain an updated first-level outlet identification quantity; The accuracy of the order splitting processing model is determined based on the matching result between the order splitting result of each order data in the order data set and the actual result.
[0009] Exemplarily, determining whether the logistics network point is in an abnormal state according to the order splitting index data of the logistics network point includes: Obtain at least one order splitting indicator data of the first-level network point accuracy rate, branch network point recognition rate, branch network point accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point; If any order splitting index data is less than or equal to the preset index threshold corresponding to the order splitting index data, it is determined that the logistics network point is in an abnormal state; If the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network are all greater than the preset indicator thresholds corresponding to each order splitting indicator, it is determined that the logistics network is in a normal state.
[0010] Exemplarily, the obtaining of a preset order splitting field corresponding to the preset order splitting method includes: Adopt the first order splitting method of the pickup code keyword to obtain the first order splitting field corresponding to the pickup code keyword; Adopt the second order splitting method of the pickup code electronic fence to obtain the second order splitting field corresponding to the pickup code electronic fence; Adopt the third order splitting method of the pickup code to obtain the third order splitting field corresponding to the pickup code; Using the fourth order division method of the historical full word, obtaining the fourth order division field corresponding to the historical full word; The first order splitting field, the second order splitting field, the third order splitting field and the fourth order splitting field are determined as the preset order splitting fields.
[0011] Exemplarily, the step of inputting the order data into the order splitting processing model for order splitting processing to obtain order splitting results corresponding to the preset order splitting fields includes: Inputting the order data into the order splitting processing model, and extracting time features, geographic features, customer features, and product features corresponding to the order data; Obtaining weights corresponding to the time features, geographic features, customer features, and product features; Determine a weighted fusion feature according to the time feature, geographic feature, customer feature, product feature and the weights corresponding to the time feature, geographic feature, customer feature and product feature; Perform order splitting processing based on the weighted fusion features to obtain order splitting results corresponding to the preset order splitting fields; The method further comprises: Determine the target order splitting algorithm based on the user's report requirements and analysis dimensions; The order data to be analyzed is split according to the target splitting algorithm to obtain target performance indicator data, and a target report is generated according to the target performance indicator data.
[0012] Another aspect provides an order data processing device, the device comprising: The order data collection module is used to collect logistics order data of logistics outlets in multiple business systems to obtain order data sets; A processing module, used for preprocessing the order data in the order data set to obtain a processed data set; A field acquisition module, used to determine the preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and to acquire the preset order splitting field corresponding to the preset order splitting method; An order splitting result determination module is used to use an order splitting algorithm corresponding to a preset order splitting method to split the order data and obtain an order splitting result corresponding to the preset order splitting field; An index data determination module, used to determine the order splitting index data of the logistics network point according to the order splitting results of each order data in the processed data set; The status determination module is used to determine whether the logistics network point is in an abnormal state according to the order distribution index data of the logistics network point.
[0013] Exemplarily, the order splitting result determination module includes: An order splitting processing model training unit is used to train the order splitting algorithm corresponding to the preset order splitting method using sample order data to obtain an order splitting processing model; The order splitting result determination unit is used to input the order data into the order splitting processing model for order splitting processing, and obtain the order splitting result corresponding to the preset order splitting field.
[0014] Exemplarily, the order splitting processing model includes a decision tree model, a neural network model and a support vector machine model, and the order splitting result determination unit is also used to obtain the number of classification features and the data volume corresponding to the order data; when the number of classification features is greater than a preset number and the data volume is greater than a preset threshold, the order data is input into the decision tree model for order splitting processing to obtain the order splitting results corresponding to the preset order splitting fields; when the number of classification features is less than or equal to the preset number or the data volume is less than or equal to the preset threshold, the order data is input into the neural network model or the support vector machine model for order splitting processing to obtain the order splitting results corresponding to the preset order splitting fields.
[0015] Exemplarily, the device further comprises: An updating module, configured to increase the first-level outlet identification quantity corresponding to the order data by a preset value to obtain an updated first-level outlet identification quantity if the first-level outlet predicted in the order splitting result is not empty; The accuracy determination module is used to determine the accuracy of the order splitting processing model according to the matching result of the order splitting result of each order data in the order data set and the actual result.
[0016] Exemplarily, the state determination module is further used to obtain at least one order splitting indicator data of the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point; And if any order splitting index data is less than or equal to the preset index threshold corresponding to the order splitting index data, it is determined that the logistics network point is in an abnormal state; And if the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network are all greater than the preset indicator thresholds corresponding to each order splitting indicator, it is determined that the logistics network is in a normal state.
[0017] Exemplarily, the field acquisition module is also used to: adopt the first order splitting method of the pickup code keyword to obtain the first order splitting field corresponding to the pickup code keyword; adopt the second order splitting method of the pickup code electronic fence to obtain the second order splitting field corresponding to the pickup code electronic fence; adopt the third order splitting method of the pickup code to obtain the third order splitting field corresponding to the pickup code; adopt the fourth order splitting method of the historical full word to obtain the fourth order splitting field corresponding to the historical full word; determine the first order splitting field, the second order splitting field, the third order splitting field and the fourth order splitting field as the preset order splitting fields.
[0018] Exemplarily, the order splitting result determination unit is further used to input the order data into the order splitting processing model, extract the time features, geographic features, customer features and product features corresponding to the order data; obtain the weights corresponding to the time features, geographic features, customer features and product features respectively; determine the weighted fusion features according to the time features, geographic features, customer features, product features and the weights corresponding to the time features, geographic features, customer features and product features respectively; perform order splitting processing based on the weighted fusion features to obtain the order splitting results corresponding to the preset order splitting fields; Exemplarily, the device further comprises: The target algorithm determination module is used to determine the target order splitting algorithm based on the user's report requirements and analysis dimensions; The report generation module is used to process the order data to be analyzed according to the target order splitting algorithm, obtain target performance indicator data, and generate a target report according to the target performance indicator data.
[0019] On the other hand, an electronic device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the order data processing method as described above.
[0020] On the other hand, a computer storage medium is provided, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the order data processing method as described above.
[0021] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the order data processing method as described above.
[0022] The order data processing method, device and equipment provided by the present invention have the following technical effects: The present invention collects logistics order data of logistics outlets in multiple business systems to obtain an order data set; pre-processes order data in the order data set to obtain a processed data set; determines a preset order splitting method corresponding to the data in the processed data set according to data attribute information in the processed data set, and obtains a preset order splitting field corresponding to the preset order splitting method; uses an order splitting algorithm corresponding to the preset order splitting method to split the order data to obtain an order splitting result corresponding to the preset order splitting field; can select an order splitting method to accurately split the order data to obtain an order splitting result; determines order splitting index data of the logistics outlet according to the order splitting result of each order data in the processed data set; thereby improving the accuracy of the order splitting index data; determines whether the logistics outlet is in an abnormal state according to the order splitting index data of the logistics outlet; thereby realizing rapid and accurate analysis of the operation status of the outlet according to the order splitting index data. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions and advantages of the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0024] Figure 1 is a schematic diagram of an order data processing system provided by an embodiment of this specification; Figure 2 It is a flowchart of an order data processing method provided in an embodiment of this specification; Figure 3 It is a flowchart of a method for using an order splitting algorithm corresponding to a preset order splitting method, splitting the order data, and obtaining an order splitting result corresponding to the preset order splitting field, provided in an embodiment of this specification; Figure 4 It is a flowchart of a method provided by an embodiment of this specification for inputting the order data into the order splitting processing model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field; Figure 5 It is a flowchart of a method for generating a target report according to the target performance indicator data provided by an embodiment of this specification; Figure 6 It is a structural diagram of an order data processing device provided in an embodiment of this specification; Figure 7It is a structural diagram of a server provided in an embodiment of this specification. DETAILED DESCRIPTION
[0025] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.
[0027] See also Figure 1 , Figure 1 is a schematic diagram of an order data processing system provided in an embodiment of this specification, such as Figure 1 As shown, the order data processing system may include at least a server 01 and a client 02 .
[0028] Specifically, in the embodiments of this specification, the server 01 may include an independently operated server, or a distributed server, or a server cluster composed of multiple servers, and may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 01 may include a network communication unit, a processor, a memory, and the like. Specifically, the server 01 can be used to collect logistics order data of logistics outlets in multiple business systems to obtain an order data set; pre-process the order data in the order data set to obtain a processed data set; determine the preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and obtain the preset order splitting field corresponding to the preset order splitting method; use the order splitting algorithm corresponding to the preset order splitting method to split the order data to obtain the order splitting results corresponding to the preset order splitting fields; determine the order splitting index data of the logistics outlet according to the order splitting results of each order data in the processed data set; determine whether the logistics outlet is in an abnormal state according to the order splitting index data of the logistics outlet.
[0029] Specifically, in the embodiments of this specification, the client 02 may include physical devices such as smart phones, desktop computers, tablet computers, laptop computers, digital assistants, smart wearable devices, smart speakers, vehicle terminals, smart TVs, etc., and may also include software running in physical devices, such as web pages provided by some service providers to users, or applications provided by these service providers to users. Specifically, the client 02 may be used to display the order splitting index data of logistics outlets.
[0030] The following describes an order data processing method of the present invention. Figure 2 It is a flowchart of an order data processing method provided in an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the method may include: S201: Collect logistics order data of logistics outlets in multiple business systems to obtain an order data set. In the embodiments of this specification, order-related data from different systems are collected through various interfaces and data collection tools, including but not limited to logistics business systems, customer relationship management systems, commodity information systems, etc.
[0031] S203: Preprocess the order data in the order data set to obtain a processed data set.
[0032] In the embodiments of this specification, the collected data is preprocessed, including data cleaning, format conversion, feature extraction and other operations, to improve data quality and usability.
[0033] S205: Determine a preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and obtain a preset order splitting field corresponding to the preset order splitting method.
[0034] In the embodiment of this specification, the order splitting result record: save the full order splitting result and record the result of each order splitting algorithm: Record in separate orders: 4 records for each order, 400,000 orders per day on average, 1.6 million orders per day in total, stored for 30 days. The four ways to split orders are: pick-up code keyword, pick-up code electronic fence, pick-up code, and historical full word (historical salesperson / address salesperson).
[0035] S207: Using an order splitting algorithm corresponding to a preset order splitting method, the order data is split, and an order splitting result corresponding to the preset order splitting field is obtained.
[0036] In the embodiment of this specification, the fields corresponding to the order number may be: shipping order number, partner order number, order number. According to existing rules, a global common value is used to facilitate problem tracing and location.
[0037] S209: Determine order splitting index data of the logistics network point according to the order splitting results of each order data in the processed data set.
[0038] In the embodiments of the present specification, the order splitting index data may include but are not limited to the first-level outlet accuracy rate, branch outlet recognition rate, branch outlet accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate.
[0039] S2011: Determine whether the logistics network is in an abnormal state based on the order distribution index data of the logistics network.
[0040] In the embodiments of this specification, it is possible to evaluate how many first-level outlets the order splitting algorithm cannot output, analyze which first-level outlet recognition rate is low, and determine outlets with recognition rates below a preset threshold as abnormal outlets.
[0041] In the embodiments of this specification, Figure 3 As shown, the order data is processed by using the order splitting algorithm corresponding to the preset order splitting method to obtain the order splitting result corresponding to the preset order splitting field, including: S2071: Using sample order data to train an order splitting algorithm corresponding to the preset order splitting method to obtain an order splitting processing model; S2073: Input the order data into the order splitting processing model for order splitting processing, and obtain the order splitting result corresponding to the preset order splitting field.
[0042] In the embodiments of the present specification, the machine learning model in the intelligent monitoring and analysis module can be used to perform in-depth analysis on the pre-processed data. Specifically, the order splitting algorithm corresponding to the preset order splitting method can be trained using sample order data to obtain an order splitting processing model. The order splitting algorithm can include multiple types, and each preset order splitting method can correspond to an order splitting algorithm. The order splitting algorithm can include algorithms corresponding to decision tree models, neural network models, and support vector machine models.
[0043] In the embodiments of this specification, the fields are as follows: a. Order number: take the waybill number / partner order number / order number; according to existing rules, take the global common value; to facilitate problem tracing and location.
[0044] b. Order splitting algorithm 1: current enumeration value; c. Order splitting algorithm 1-predicted outlet: output outlet code for automatic order splitting d. Order splitting algorithm 1-predicted pickup code: output pickup code for automatic order splitting. If none, this field is empty; e. Order splitting algorithm 1-predicted salesperson: salesperson queried based on outlet + pickup code or salesperson directly returned by the interface; f. Order splitting algorithm; 2: g. Order splitting algorithm 2-predicted outlets: automatically split the order and output the outlet code; h. Order splitting algorithm 2-predicted pickup code: automatically split the order and output the pickup code. If there is no pickup code, this field is empty; i. Order splitting algorithm 2-predicted salesperson: the salesperson queried based on the outlet + pickup code or the salesperson directly returned by the interface; j. Order splitting algorithm N: k. Order splitting algorithm N-prediction point: automatic order splitting and output point code l; Order splitting algorithm N-predicted pickup code: Automatically split the order and output the pickup code. If none, this field is empty. m. Order splitting algorithm N-predicted salesperson: the salesperson queried based on the outlet + pickup code or the salesperson directly returned by the interface.
[0045] In the embodiment of this specification, the order splitting processing model includes a decision tree model, a neural network model and a support vector machine model. Figure 4As shown, the order data is input into the order splitting processing model for order splitting processing, and the order splitting result corresponding to the preset order splitting field is obtained, including: S20731: Obtain the number of classification features and data volume corresponding to the order data; S20733: When the number of classification features is greater than a preset number and the data volume is greater than a preset threshold, input the order data into the decision tree model for order splitting processing to obtain order splitting results corresponding to the preset order splitting fields; S20735: When the number of classification features is less than or equal to the preset number or the data volume is less than or equal to the preset threshold, the order data is input into the neural network model or the support vector machine model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field.
[0046] In the embodiments of this specification, the order splitting processing model includes a decision tree model, a neural network model, and a support vector machine model. According to the characteristics of the data and the purpose of analysis, a suitable machine learning model can be selected or multiple models can be used in combination. When there are a large number of classification features in the order data and the amount of data is relatively small, the decision tree model is used; otherwise, the neural network model or the support vector machine model can be selected for order splitting processing.
[0047] In the embodiment of this specification, the method further includes: If the predicted first-level outlet in the order splitting result is not empty, the first-level outlet identification quantity corresponding to the order data is increased by a preset value to obtain an updated first-level outlet identification quantity; The accuracy of the order splitting processing model is determined based on the matching result between the order splitting result of each order data in the order data set and the actual result.
[0048] In the embodiments of this specification, conventional index calculation: For each order, first perform conventional recognition calculation. If the predicted first-level outlet output for a certain order is not empty, the first-level outlet recognition quantity for this order is +1. At the same time, the accuracy index is calculated. The accuracy calculation is usually based on the matching of the predicted results with the actual results, such as whether the predicted pickup code is consistent with the actual pickup code, whether the predicted salesperson is consistent with the actual salesperson, etc. Conventional indicators are the basis for evaluating the performance of the order splitting algorithm, and can reflect the completion of the order splitting algorithm on basic tasks.
[0049] In the embodiment of this specification, determining whether the logistics network point is in an abnormal state according to the order splitting index data of the logistics network point includes: Obtain at least one order splitting indicator data of the first-level network point accuracy rate, branch network point recognition rate, branch network point accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point; If any order splitting index data is less than or equal to the preset index threshold corresponding to the order splitting index data, it is determined that the logistics network point is in an abnormal state; If the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network are all greater than the preset indicator thresholds corresponding to each order splitting indicator, it is determined that the logistics network is in a normal state.
[0050] In the embodiments of this specification, at least one order splitting index data of the first-level network point accuracy rate, branch network point recognition rate, branch network point accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point can be obtained; and a preset index threshold corresponding to each index can be pre-set. When the preset index threshold is not reached, the logistics network point is considered abnormal. If at least one order splitting index data is less than or equal to the preset index threshold corresponding to the order splitting index data, it is determined that the logistics network point is in an abnormal state; if the first-level network point accuracy rate, branch network point recognition rate, branch network point accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point are all greater than the preset index threshold corresponding to each order splitting index, it is determined that the logistics network point is in a normal state. Thereby, a quick and accurate analysis of the operation status of the network point is achieved based on the order splitting index data.
[0051] In the embodiment of this specification, the obtaining of the preset order splitting field corresponding to the preset order splitting method includes: Adopt the first order splitting method of the pickup code keyword to obtain the first order splitting field corresponding to the pickup code keyword; Adopt the second order splitting method of the pickup code electronic fence to obtain the second order splitting field corresponding to the pickup code electronic fence; Adopt the third order splitting method of the pickup code to obtain the third order splitting field corresponding to the pickup code; Using the fourth order division method of the historical full word, obtaining the fourth order division field corresponding to the historical full word; The first order splitting field, the second order splitting field, the third order splitting field and the fourth order splitting field are determined as the preset order splitting fields.
[0052] In the embodiment of this specification, the four order splitting methods are: pick-up code keyword, pick-up code electronic fence, pick-up code, and historical full word (historical salesperson / address salesperson). Therefore, these order splitting methods can be used to split the order, and the order splitting fields corresponding to each order splitting method can be obtained; finally, each order splitting field is combined into a preset order splitting field.
[0053] In the embodiment of the present specification, the step of inputting the order data into the order splitting processing model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field includes: Inputting the order data into the order splitting processing model, and extracting time features, geographic features, customer features, and product features corresponding to the order data; Obtaining weights corresponding to the time features, geographic features, customer features, and product features; Determine a weighted fusion feature according to the time feature, geographic feature, customer feature, product feature and the weights corresponding to the time feature, geographic feature, customer feature and product feature; The order splitting process is performed based on the weighted fusion feature to obtain the order splitting result corresponding to the preset order splitting field.
[0054] In the embodiments of this specification, in addition to conventional indicators, comprehensive performance indicators are calculated based on the multiple characteristics and dynamic weights of the order. The multiple characteristics of the order include the time characteristics, geographical characteristics, customer characteristics, and product characteristics mentioned above. Dynamic weights are assigned to each feature based on the importance of the feature and the degree of influence on the performance of the order splitting algorithm. For orders of high-value goods, the product value feature may have a higher weight because it is more important to ensure accurate order splitting of such orders; for orders located in remote areas, the remoteness of the region in the geographical feature may have a higher weight because the order splitting of such orders may face more challenges. The comprehensive performance index is obtained by multiplying each feature by its corresponding dynamic weight and combining it with conventional indicators for comprehensive calculation.
[0055] Special order processing: For orders with empty pickup codes, adjust their contribution in the calculation of comprehensive performance indicators according to their dynamic weights. When the pickup code is empty, determine the weight of the order in the calculation of comprehensive performance indicators by analyzing other features of the order, such as the customer's historical ordering behavior, product category, etc. If the order comes from a customer who frequently places orders and has a good reputation, and the product category is ordinary goods, then the weight of the order in the calculation of comprehensive performance indicators may be relatively low, because such orders may have empty pickup codes due to some accidental factors, which has little impact on the overall evaluation of the performance of the order splitting algorithm; on the contrary, if the order comes from a new customer and the product category is high-value or special goods, then the weight of the order in the calculation of comprehensive performance indicators may be relatively high, because the accuracy of the order splitting of such orders is more important, and even if the pickup code is empty, it needs to be given enough attention to ensure that the indicator calculation results can truly reflect the performance of the order splitting algorithm in various complex situations.
[0056] In the embodiments of this specification, Figure 5 As shown, the method also includes: S501: Determine the target order splitting algorithm according to the user's report requirements and analysis dimensions; S503: splitting the order data to be analyzed according to the target order splitting algorithm to obtain target performance indicator data, and generating a target report according to the target performance indicator data.
[0057] In the embodiments of this specification, corresponding data can be obtained from the intelligent monitoring and analysis module according to the report requirements and analysis dimensions set by the user. The user can select different analysis dimensions according to their business needs, such as viewing the performance of the order splitting algorithm in different regions by region, viewing the performance of the order splitting algorithm in different commodity categories by commodity category, and viewing the performance of the order splitting algorithm in different time periods by time period.
[0058] The intelligent monitoring and analysis module extracts relevant data from the analyzed data based on the analysis dimension selected by the user. If the user chooses to view by region, the module will extract order data from different regions and the corresponding order splitting algorithm performance indicator data.
[0059] It can be seen from the technical solutions provided in the above embodiments of this specification that the embodiments of this specification collect logistics order data of logistics outlets in multiple business systems to obtain an order data set; pre-process the order data in the order data set to obtain a processed data set; determine the preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and obtain the preset order splitting field corresponding to the preset order splitting method; use the order splitting algorithm corresponding to the preset order splitting method to split the order data to obtain the order splitting result corresponding to the preset order splitting field; the order splitting method can be selected to accurately split the order data to obtain the order splitting result; determine the order splitting index data of the logistics outlet according to the order splitting result of each order data in the processed data set; thereby improving the accuracy of the order splitting index data; determine whether the logistics outlet is in an abnormal state according to the order splitting index data of the logistics outlet; thereby realizing rapid and accurate analysis of the operating status of the outlet according to the order splitting index data.
[0060] The embodiment of this specification also provides an order data processing device, such as Figure 6 As shown, the device comprises: The order data collection module 610 is used to collect logistics order data of logistics outlets in multiple business systems to obtain an order data set; A processing module 620, configured to pre-process the order data in the order data set to obtain a processed data set; A field acquisition module 630 is used to determine the preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and to acquire the preset order splitting field corresponding to the preset order splitting method; The order splitting result determination module 640 is used to use the order splitting algorithm corresponding to the preset order splitting method to split the order data and obtain the order splitting result corresponding to the preset order splitting field; An index data determination module 650 is used to determine the order splitting index data of the logistics network point according to the order splitting result of each order data in the processed data set; The status determination module 660 is used to determine whether the logistics network point is in an abnormal state according to the order distribution index data of the logistics network point.
[0061] Exemplarily, the order splitting result determination module includes: An order splitting processing model training unit is used to train the order splitting algorithm corresponding to the preset order splitting method using sample order data to obtain an order splitting processing model; The order splitting result determination unit is used to input the order data into the order splitting processing model for order splitting processing, and obtain the order splitting result corresponding to the preset order splitting field.
[0062] Exemplarily, the order splitting processing model includes a decision tree model, a neural network model and a support vector machine model, and the order splitting result determination unit is also used to obtain the number of classification features and the data volume corresponding to the order data; when the number of classification features is greater than a preset number and the data volume is greater than a preset threshold, the order data is input into the decision tree model for order splitting processing to obtain the order splitting results corresponding to the preset order splitting fields; when the number of classification features is less than or equal to the preset number or the data volume is less than or equal to the preset threshold, the order data is input into the neural network model or the support vector machine model for order splitting processing to obtain the order splitting results corresponding to the preset order splitting fields.
[0063] Exemplarily, the device further comprises: An updating module, configured to increase the first-level outlet identification quantity corresponding to the order data by a preset value to obtain an updated first-level outlet identification quantity if the first-level outlet predicted in the order splitting result is not empty; The accuracy determination module is used to determine the accuracy of the order splitting processing model according to the matching result of the order splitting result of each order data in the order data set and the actual result.
[0064] Exemplarily, the state determination module is further used to obtain at least one order splitting indicator data of the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point; And if any order splitting index data is less than or equal to the preset index threshold corresponding to the order splitting index data, it is determined that the logistics network point is in an abnormal state; And if the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network are all greater than the preset indicator thresholds corresponding to each order splitting indicator, it is determined that the logistics network is in a normal state.
[0065] Exemplarily, the field acquisition module is also used to: adopt the first order splitting method of the pickup code keyword to obtain the first order splitting field corresponding to the pickup code keyword; adopt the second order splitting method of the pickup code electronic fence to obtain the second order splitting field corresponding to the pickup code electronic fence; adopt the third order splitting method of the pickup code to obtain the third order splitting field corresponding to the pickup code; adopt the fourth order splitting method of the historical full word to obtain the fourth order splitting field corresponding to the historical full word; determine the first order splitting field, the second order splitting field, the third order splitting field and the fourth order splitting field as the preset order splitting fields.
[0066] Exemplarily, the order splitting result determination unit is further used to input the order data into the order splitting processing model, extract the time features, geographic features, customer features and product features corresponding to the order data; obtain the weights corresponding to the time features, geographic features, customer features and product features respectively; determine the weighted fusion features according to the time features, geographic features, customer features, product features and the weights corresponding to the time features, geographic features, customer features and product features respectively; perform order splitting processing based on the weighted fusion features to obtain the order splitting results corresponding to the preset order splitting fields; Exemplarily, the device further comprises: The target algorithm determination module is used to determine the target order splitting algorithm based on the user's report requirements and analysis dimensions; The report generation module is used to process the order data to be analyzed according to the target order splitting algorithm, obtain target performance indicator data, and generate a target report according to the target performance indicator data.
[0067] The device and method embodiments in the described device embodiments are based on the same inventive concept.
[0068] An embodiment of the present specification provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the order data processing method provided in the above method embodiment.
[0069] An embodiment of the present invention also provides a computer storage medium, which can be set in a terminal to store at least one instruction or at least one program related to an order data processing method in a method embodiment. The at least one instruction or at least one program is loaded and executed by the processor to implement the order data processing method provided by the above method embodiment.
[0070] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the order data processing method provided in the above method embodiment.
[0071] Optionally, in the embodiments of this specification, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.
[0072] The memory described in the embodiments of this specification can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.
[0073] The order data processing method embodiment provided in the embodiments of this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 7 1 is a hardware structure diagram of a server of an order data processing method provided in an embodiment of this specification. Figure 7As shown, the server 700 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 710 (the central processing unit 710 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 730 for storing data, and one or more storage media 720 (such as one or more mass storage devices) for storing application programs 723 or data 722. Among them, the memory 730 and the storage medium 720 can be short-term storage or permanent storage. The program stored in the storage medium 720 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 710 can be configured to communicate with the storage medium 720 and execute a series of instruction operations in the storage medium 720 on the server 700. The server 700 may also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and / or one or more operating systems 721, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.
[0074] The input / output interface 740 may be used to receive or send data via a network. A specific example of the network may include a wireless network provided by a communication provider of the server 700. In one example, the input / output interface 740 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 740 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0075] It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.
[0076] It can be seen from the embodiments of the order data processing method, device, electronic device or storage medium provided by the present invention that the present invention collects logistics order data of logistics outlets in multiple business systems to obtain an order data set; pre-processes the order data in the order data set to obtain a processed data set; determines the preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and obtains the preset order splitting field corresponding to the preset order splitting method; adopts the order splitting algorithm corresponding to the preset order splitting method to split the order data to obtain the order splitting result corresponding to the preset order splitting field; the order splitting method can be selected to accurately split the order data to obtain the order splitting result; determines the order splitting index data of the logistics outlet according to the order splitting result of each order data in the processed data set; thereby improving the accuracy of the order splitting index data; determines whether the logistics outlet is in an abnormal state according to the order splitting index data of the logistics outlet; thereby realizing rapid and accurate analysis of the operating status of the outlet according to the order splitting index data.
[0077] It should be noted that the above sequence of the embodiments of this specification is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0078] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0079] A person skilled in the art will appreciate that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.
[0080] The above description is only a preferred 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 principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for processing order data, characterized in that: The method comprises: Collect logistics order data of logistics outlets in multiple business systems to obtain order data sets; Preprocessing the order data in the order data set to obtain a processed data set; Determine, according to the data attribute information in the processed data set, a preset order splitting method corresponding to the data in the processed data set, and obtain a preset order splitting field corresponding to the preset order splitting method; Using the order splitting algorithm corresponding to the preset order splitting method, the order data is split, and the order splitting result corresponding to the preset order splitting field is obtained; Determine the order splitting index data of the logistics network point according to the order splitting results of each order data in the processed data set; According to the order splitting index data of the logistics network point, it is determined whether the logistics network point is in an abnormal state.
2. The method according to claim 1, characterized in that The order splitting algorithm corresponding to the preset order splitting method is adopted to split the order data to obtain the order splitting result corresponding to the preset order splitting field, including: Using sample order data to train the order splitting algorithm corresponding to the preset order splitting method to obtain an order splitting processing model; The order data is input into the order splitting processing model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field.
3. The method according to claim 2, characterized in that The order splitting processing model includes a decision tree model, a neural network model and a support vector machine model. The order data is input into the order splitting processing model for order splitting processing to obtain the order splitting result corresponding to the preset order splitting field, including: Obtain the number of classification features and data volume corresponding to the order data; When the number of classification features is greater than a preset number and the data volume is greater than a preset threshold, the order data is input into the decision tree model for order splitting processing to obtain order splitting results corresponding to the preset order splitting fields; When the number of classification features is less than or equal to the preset number or the data volume is less than or equal to the preset threshold, the order data is input into the neural network model or the support vector machine model for order splitting processing to obtain the order splitting results corresponding to the preset order splitting fields.
4. The method according to claim 3, characterized in that: The method further comprises: If the predicted first-level outlet in the order splitting result is not empty, the first-level outlet identification quantity corresponding to the order data is increased by a preset value to obtain an updated first-level outlet identification quantity; The accuracy of the order splitting processing model is determined based on the matching result between the order splitting result of each order data in the order data set and the actual result.
5. The method according to claim 4, characterized in that The determining whether the logistics network point is in an abnormal state according to the order splitting index data of the logistics network point includes: Obtain at least one order splitting indicator data of the first-level network point accuracy rate, branch network point recognition rate, branch network point accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network point; If any order splitting index data is less than or equal to the preset index threshold corresponding to the order splitting index data, it is determined that the logistics network point is in an abnormal state; If the first-level network accuracy rate, branch network recognition rate, branch network accuracy rate, pickup code recognition rate, pickup code accuracy rate, salesperson recognition rate, and salesperson accuracy rate corresponding to the logistics network are all greater than the preset indicator thresholds corresponding to each order splitting indicator, it is determined that the logistics network is in a normal state.
6. The method according to claim 1, characterized in that The obtaining of the preset order splitting field corresponding to the preset order splitting method includes: Adopt the first order splitting method of the pickup code keyword to obtain the first order splitting field corresponding to the pickup code keyword; Adopt the second order splitting method of the pickup code electronic fence to obtain the second order splitting field corresponding to the pickup code electronic fence; Adopt the third order splitting method of the pickup code to obtain the third order splitting field corresponding to the pickup code; Using the fourth order division method of the historical full word, obtaining the fourth order division field corresponding to the historical full word; The first order splitting field, the second order splitting field, the third order splitting field and the fourth order splitting field are determined as the preset order splitting fields.
7. The method according to claim 2, characterized in that: The step of inputting the order data into the order splitting processing model for order splitting processing to obtain order splitting results corresponding to the preset order splitting fields includes: Inputting the order data into the order splitting processing model, and extracting time features, geographic features, customer features, and product features corresponding to the order data; Obtaining weights corresponding to the time features, geographic features, customer features, and product features; Determine a weighted fusion feature according to the time feature, geographic feature, customer feature, product feature and the weights corresponding to the time feature, geographic feature, customer feature and product feature; Perform order splitting processing based on the weighted fusion features to obtain order splitting results corresponding to the preset order splitting fields; The method further comprises: Determine the target order splitting algorithm based on the user's report requirements and analysis dimensions; The order data to be analyzed is split according to the target splitting algorithm to obtain target performance indicator data, and a target report is generated according to the target performance indicator data.
8. An order data processing device, characterized in that: The device comprises: The order data collection module is used to collect logistics order data of logistics outlets in multiple business systems to obtain order data sets; A processing module, used for preprocessing the order data in the order data set to obtain a processed data set; A field acquisition module, used to determine the preset order splitting method corresponding to the data in the processed data set according to the data attribute information in the processed data set, and to acquire the preset order splitting field corresponding to the preset order splitting method; An order splitting result determination module is used to use an order splitting algorithm corresponding to a preset order splitting method to split the order data and obtain an order splitting result corresponding to the preset order splitting field; An index data determination module, used to determine the order splitting index data of the logistics network point according to the order splitting results of each order data in the processed data set; The status determination module is used to determine whether the logistics network point is in an abnormal state according to the order distribution index data of the logistics network point.
9. An electronic device, characterized in that: The device includes: a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the order data processing method as described in any one of claims 1-7.
10. A computer storage medium, characterized in that: The computer storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the order data processing method as described in any one of claims 1-7.