Logistics price data processing method and device and electronic equipment

Abstract

The invention provides a logistics price data processing method and apparatus, and an electronic device, relates to the technical field of logistics data, and solves the technical problem of low logistics data processing efficiency for a logistics platform at present. The method comprises the steps of preprocessing price data, service data and aging data of a plurality of logistics platforms through a specified preprocessing mode to obtain target data; training the initial prediction model by using an artificial intelligence algorithm based on the target data to obtain a logistics platform data prediction model; and in response to a selection request for logistics services corresponding to the plurality of target logistics platforms, comparing the logistics prices, the logistics services and the logistics timeliness of the plurality of target logistics platforms by using the logistics platform data prediction model, and automatically matching in the plurality of target logistics platforms through a comparison result and a dynamic planning algorithm according to the selection request. And determining a first target logistics platform of which the matching degree with the selection request is higher than a preset matching degree in the plurality of target logistics platforms.

Description

Technical Field

[0001] The present application relates to the field of logistics data technology, and in particular to a logistics price data processing method, device and electronic equipment. Background Art

[0002] At present, in the traditional logistics industry, due to the differences in prices, services, timeliness, etc. of different express companies and other logistics platforms, users often need to make many comparisons when choosing a logistics platform. However, this process often requires users to do it manually, which is time-consuming, labor-intensive, and prone to errors. Users cannot determine the most suitable logistics platform, resulting in low efficiency in logistics data processing for logistics platforms. Summary of the invention

[0003] The purpose of the present invention is to provide a logistics price data processing method, device and electronic device to solve the current technical problem of low logistics data processing efficiency for logistics platforms.

[0004] In a first aspect, an embodiment of the present application provides a method for processing logistics price data, the method comprising:

[0005] Obtain price data, service data, and timeliness data from multiple logistics platforms;

[0006] Preprocessing the price data, the service data and the timeliness data by a specified preprocessing method to obtain target data; wherein the specified preprocessing method includes any one or more of data cleaning, data screening, data deduplication, data filling missing values, and data removal of outliers;

[0007] Based on the target data, an initial prediction model is trained using an artificial intelligence algorithm to obtain a logistics platform data prediction model;

[0008] In response to a selection request for logistics services corresponding to multiple target logistics platforms, the logistics prices, logistics services and logistics timeliness of the multiple target logistics platforms are compared using the logistics platform data prediction model to obtain a comparison result, and according to the selection request, the multiple target logistics platforms are automatically matched through the comparison result and a dynamic programming algorithm to determine a first target logistics platform among the multiple target logistics platforms whose matching degree with the selection request is higher than a preset matching degree; wherein the selection request includes user price requirements, user service requirements and user timeliness requirements;

[0009] In response to an adding operation and / or a deleting operation on the logistics project conditions corresponding to the plurality of the first target logistics platforms, according to the adding operation and / or the deleting operation, a final first target logistics platform selected by the selection request is screened from the plurality of the first target logistics platforms;

[0010] In response to the feedback data of the selection request corresponding to the client to the final first target logistics platform, the logistics platform data prediction model is adjusted and optimized according to the feedback data.

[0011] In a possible implementation, the logistics platform data prediction model is used to compare the logistics prices of the multiple target logistics platforms to obtain a comparison result, including:

[0012] Acquire historical logistics and transportation data of the multiple target logistics platforms;

[0013] Based on the historical logistics transportation data, the AI ​​system corresponding to the logistics platform data prediction model is used to analyze the logistics transportation speed, logistics transportation route, storage environment excellence of the transit warehouse, and logistics transportation safety of each of the multiple target logistics platforms;

[0014] Based on the logistics transportation speeds, the logistics transportation routes, the storage environment of the transit warehouse, and the logistics transportation safety levels of each of the multiple target logistics platforms, the logistics prices of the multiple target logistics platforms are compared to obtain a comparison result; wherein, in the comparison result, the slower the logistics transportation speed, the longer the logistics transportation route, the better the storage environment of the transit warehouse and / or the lower the logistics transportation safety level, the lower the logistics price of the target logistics platform.

[0015] In a possible implementation, it also includes:

[0016] Acquire item property data and historical sales data for target type goods in the logistics platform; the item property data includes item storage temperature and / or item storage humidity;

[0017] Based on the historical sales data, determine a first region where the historical sales volume is greater than a first preset sales volume from among the multiple regions to which the target type of goods are sold;

[0018] According to the historical sales data of the target type of goods and the item storage temperature and / or the item storage humidity, determine the location of the logistics transfer warehouse for the target type of goods through the AI ​​system, so that the location of the logistics transfer warehouse is as close to the first region as possible under storage conditions that meet the item storage temperature and / or the item storage humidity;

[0019] The distribution logistics price of the target type of goods in the logistics platform is adjusted according to the setting position of the logistics transit warehouse to obtain the adjusted price data of the logistics platform.

[0020] In a possible implementation, after obtaining the historical sales data of the target type of goods in the logistics platform, the method further includes:

[0021] Determining, based on the historical sales data, a sales peak time period during which the historical sales volume of the target type of goods is greater than a second preset sales volume;

[0022] Determine, from the multiple regions to which the target type of goods are sold, a second region whose peak sales time period is greater than a preset time period, and a third region whose peak sales time period is less than or equal to the preset time period;

[0023] Adjusting the delivery area priority of the target type of goods to obtain an adjusted delivery area priority result, so that the delivery priority of the target type of goods to the second area is greater than the delivery priority to the third area;

[0024] The distribution logistics price of the target type of goods in the logistics platform is adjusted according to the distribution area priority result to obtain the adjusted price data of the logistics platform; the higher the distribution area priority result, the higher the distribution logistics price.

[0025] In a possible implementation, the number of the logistics transfer warehouse setting locations includes multiple; and the adjusting the distribution logistics price of the target type of goods according to the logistics transfer warehouse setting locations includes:

[0026] Obtaining the warehouse usage price of each logistics transit warehouse setting location;

[0027] Determining the warehouse storage cost of the target type of goods according to the storage temperature of the goods and / or the storage humidity of the goods;

[0028] Determine the comprehensive total logistics cost corresponding to the location of the logistics transit warehouse according to the warehouse usage price, the warehouse storage cost and the transportation distance logistics cost based on the location of the logistics transit warehouse;

[0029] Compare the multiple comprehensive total logistics costs corresponding to the multiple logistics transfer warehouse setting locations to obtain a comparison result, and determine the multiple first logistics transfer warehouse setting locations whose comprehensive total logistics costs are lower than the preset logistics cost in the comparison result as the candidate logistics transfer warehouse setting locations for the target type of goods;

[0030] Acquire first historical sales data and user feedback data of the target type of goods within a preset distance range around the location where the alternative logistics transfer warehouse is set;

[0031] Determine a target candidate logistics transfer warehouse setting location with the highest first historical sales data and the highest user feedback data from a plurality of candidate logistics transfer warehouse setting locations, and determine the target candidate logistics transfer warehouse setting location as the final logistics transfer warehouse setting location;

[0032] According to the final comprehensive total logistics cost corresponding to the final logistics transit warehouse setting location, the distribution logistics price of the target type of goods in the logistics platform is adjusted to obtain the adjusted price data of the logistics platform.

[0033] In a possible implementation, it also includes:

[0034] Obtaining an actual return rate of logistics goods on the logistics platform by a first user belonging to a fourth region;

[0035] If the actual return rate is greater than or equal to the preset return rate, acquiring the regional environment data of the fourth region and the user habit data of the first user;

[0036] The logistics configuration items delivered to the fourth region are adjusted according to the regional environment data and the user habit data to obtain the logistics configuration results of the adjusted logistics configuration items; wherein the logistics configuration items include any one or more of the storage temperature configured in the logistics process, the preference type corresponding to the logistics object that can be adjusted, and the quality type corresponding to the logistics object that can be adjusted; the preference type includes any one or more of the taste preference, temperature preference, color preference, shape preference, and size preference;

[0037] The logistics price of the distribution to the fourth region in the logistics platform is adjusted according to the logistics configuration result to obtain the adjusted price data of the logistics platform.

[0038] In a possible implementation, it also includes:

[0039] Obtaining repurchase rates and user evaluation data of logistics goods on the logistics platform by users in multiple regions;

[0040] Analyze the user's tolerance for goods through an AI system based on the repurchase rate and user evaluation data;

[0041] For the fifth region corresponding to the second user whose cargo tolerance is lower than the first preset tolerance, the delivery priority level of the logistics cargo delivered to the fifth region is increased, and for the sixth region corresponding to the third user whose cargo tolerance is higher than the second preset tolerance, the delivery priority level of the logistics cargo delivered to the sixth region is decreased;

[0042] The distribution logistics prices for the fifth and sixth regions in the logistics platform are adjusted according to the adjusted delivery priority levels to obtain adjusted price data of the logistics platform; the higher the adjusted delivery priority level, the higher the distribution logistics price, and the lower the adjusted delivery priority level, the lower the distribution logistics price.

[0043] In a second aspect, a logistics price data processing device is provided, the device comprising:

[0044] The acquisition module is used to obtain price data, service data and timeliness data from multiple logistics platforms;

[0045] A preprocessing module, used to preprocess the price data, the service data and the timeliness data by a specified preprocessing method to obtain target data; wherein the specified preprocessing method includes any one or more of data cleaning, data screening, data deduplication, data filling missing values, and data removal of abnormal values;

[0046] A training module, used to train the initial prediction model based on the target data using an artificial intelligence algorithm to obtain a logistics platform data prediction model;

[0047] A matching module, for responding to a selection request for logistics services corresponding to a plurality of target logistics platforms, using the logistics platform data prediction model to compare the logistics prices, logistics services and logistics timeliness of the plurality of target logistics platforms, obtaining a comparison result, and automatically matching the plurality of target logistics platforms according to the selection request through the comparison result and a dynamic programming algorithm, and determining a first target logistics platform among the plurality of target logistics platforms whose matching degree with the selection request is higher than a preset matching degree; wherein the selection request includes user price requirements, user service requirements and user timeliness requirements;

[0048] A screening module, configured to respond to an adding operation and / or a deleting operation on the logistics project conditions corresponding to the plurality of the first target logistics platforms, and to screen the final first target logistics platform that the selection request finally corresponds to and is selected from the plurality of the first target logistics platforms according to the adding operation and / or the deleting operation;

[0049] The adjustment module is used to respond to the feedback data of the client corresponding to the selection request on the final first target logistics platform, and adjust and optimize the logistics platform data prediction model according to the feedback data.

[0050] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0051] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method described in the first aspect above.

[0052] The embodiments of the present application bring the following beneficial effects:

[0053] A logistics price data processing method, device and electronic device provided in the embodiments of the present application can obtain price data, service data and timeliness data of multiple logistics platforms; pre-process the price data, service data and timeliness data by a specified pre-processing method to obtain target data; wherein the specified pre-processing method includes any one or more of data cleaning, data screening, data deduplication, data filling missing values, and data removal of outliers; based on the target data, an initial prediction model is trained using an artificial intelligence algorithm to obtain a logistics platform data prediction model; in response to a selection request for logistics services corresponding to multiple target logistics platforms, the logistics prices, logistics services and logistics timeliness of the multiple target logistics platforms are compared using the logistics platform data prediction model to obtain a comparison result, and According to the selection request, the comparison result and the dynamic programming algorithm are used to automatically match the multiple target logistics platforms, and determine the first target logistics platform whose matching degree with the selection request is higher than the preset matching degree among the multiple target logistics platforms; wherein the selection request includes user price requirements, user service requirements and user time requirements; in response to the addition operation and / or deletion operation of the logistics project conditions corresponding to the multiple first target logistics platforms, according to the addition operation and / or the deletion operation, the final first target logistics platform corresponding to the selection request is screened among the multiple first target logistics platforms; in response to the feedback data of the client corresponding to the selection request on the final first target logistics platform, the logistics platform data prediction model is adjusted and optimized according to the feedback data. In this scheme, the comparison and matching of the logistics platform related data by the logistics platform data prediction model can provide users with a simple, intuitive and efficient express selection scheme, while ensuring the service quality and meeting the personalized needs of users, improving the user experience, helping to distinguish the existing comparison scheme and the selection scheme of the logistics platform, improving the user experience and satisfaction, enabling users to quickly and accurately find the logistics platform that meets their personalized needs, and solving the current technical problem of low efficiency in logistics data processing for the logistics platform.

[0054] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 A flow chart of a logistics price data processing method provided in an embodiment of the present application;

[0057] Figure 2 A schematic diagram of a graphical user interface for logistics platform recommendation results in the logistics price data processing method provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of a graphical user interface in which a user can perform a new / modify operation in the logistics price data processing method provided in an embodiment of the present application;

[0059] Figure 4 A schematic diagram of another graphical user interface in which a user can perform a new / modify operation in the logistics price data processing method provided in an embodiment of the present application;

[0060] Figure 5 A schematic diagram of another graphical user interface in which a user can perform a new / modify operation in the logistics price data processing method provided in an embodiment of the present application;

[0061] Figure 6 A schematic diagram of another graphical user interface in which a user can perform a new / modify operation in the logistics price data processing method provided in an embodiment of the present application;

[0062] Figure 7 A schematic diagram of another graphical user interface in which a user can perform a new / modify operation in the logistics price data processing method provided in an embodiment of the present application;

[0063] Figure 8 A schematic diagram of the structure of a logistics price data processing device provided in an embodiment of the present application;

[0064] Fig. 9 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0066] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0067] At present, users are often unable to determine the most suitable courier company, because the weights of factors such as price, service, and timeliness may be different for different users. Specifically, due to the differences in price, service, and timeliness of different courier companies, users often need to make multi-faceted comparisons when choosing a courier company. This process is time-consuming, labor-intensive, and error-prone, because it is difficult for users to fully understand the service quality and timeliness of all courier companies. Moreover, each user may have different weights on factors such as price, service, and timeliness. Therefore, it is difficult for users to find a courier company that fully meets their personalized needs, resulting in the inability to meet personalized needs. Furthermore, due to the inconsistent price and service standards of major courier companies, it is difficult for users to find a unified standard to compare the advantages and disadvantages of various courier companies, resulting in a lack of a unified comparison standard. It can be seen that the current logistics data processing efficiency for logistics platforms is low.

[0068] Based on this, the embodiments of the present application provide a logistics price data processing method, device and electronic device, through which the current technical problem of low logistics data processing efficiency for logistics platforms can be solved.

[0069] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0070] Figure 1 A flow chart of a logistics price data processing method provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0071] Step S110, obtaining price data, service data and time efficiency data of multiple logistics platforms.

[0072] As an optional implementation method, the price data, service data and time efficiency data of multiple logistics platforms can be obtained through data collection. Specifically, by establishing cooperative relationships with major express delivery companies, relevant data such as prices, services, and time efficiency of major express delivery companies are collected. These data include but are not limited to the express delivery companies' freight, delivery time, network coverage, complaint rate, etc.

[0073] To obtain price data, the average price, price range and price change trend of each express company can be obtained through the official website of the express company, third-party price comparison platform or market research. To obtain service data, user evaluation platforms, social media, questionnaires and other methods can be used to collect users' service evaluation of express companies, including service attitude, professionalism, problem-solving ability, etc. To obtain delivery speed data, the average delivery time and punctuality rate of each express company can be calculated through the timeliness data provided by the express company, user feedback and data from third-party monitoring agencies. To obtain complaint rate data, the number of complaints and complaint rates of each express company can be obtained from channels such as consumer associations, express company customer service departments, and complaint platforms, and the types of complaints and their resolution can be analyzed.

[0074] Step S120, preprocessing the price data, service data and timeliness data by a specified preprocessing method to obtain target data.

[0075] The specified preprocessing method includes any one or more of data cleaning, data screening, data deduplication, data filling of missing values, and data removal of outliers.

[0076] In a possible implementation, the data preprocessing process can use big data technology to process the collected data, including data cleaning, data preprocessing and other operations to ensure the accuracy and availability of the data. During the data preprocessing process, the data can be screened, deduplicated, missing values ​​filled, outliers removed and other operations to improve the training effect of the model. Among them, data cleaning can include removing duplicate, erroneous or invalid data to ensure the accuracy and consistency of the data.

[0077] In the process of data preprocessing, since data of different dimensions may have different dimensions and magnitudes, the data can be standardized for unified comparison and analysis. The collected data can also be classified and sorted according to dimensions such as express companies and time periods for subsequent analysis.

[0078] Step S130, training the initial prediction model using an artificial intelligence algorithm based on the target data to obtain a logistics platform data prediction model.

[0079] Regarding the model training process, it should be noted that artificial intelligence algorithms (such as neural networks, decision trees, etc.) can be used to train the processed data to obtain a prediction model between the price, service, and timeliness of each express company. During the model training process, different features can be combined and optimized to obtain the best prediction effect. As an example, for the distribution of weights in the model, different weights can be assigned to price, service evaluation, delivery speed, complaint rate, etc. according to the importance of each dimension of data. The distribution of weights can be based on expert scoring, user surveys, or historical data analysis. For the calculation of the comprehensive score in the model, the weighted average method or other appropriate mathematical models can be used to weight the data of each dimension and sum them to obtain the comprehensive score of each express company.

[0080] Step S140, in response to a selection request for logistics services corresponding to multiple target logistics platforms, the logistics prices, logistics services and logistics timeliness of the multiple target logistics platforms are compared using a logistics platform data prediction model to obtain a comparison result, and according to the selection request, the comparison result and a dynamic programming algorithm are used to automatically match the multiple target logistics platforms to determine the first target logistics platform among the multiple target logistics platforms whose matching degree with the selection request is higher than a preset matching degree.

[0081] The selection request includes the user's price requirements, service requirements, and time requirements. In a possible implementation, when the user selects a logistics platform (express delivery service), the system can automatically match the most suitable logistics platform (express delivery company) according to the user's personalized requirements (such as price, service, time efficiency, etc.) through the price comparison module. Figure 2 As shown, the recommended results of the logistics platform after price comparison are displayed to the user. The implementation of the price comparison module can be based on the prediction model and dynamic programming algorithm, and can provide the best matching solution according to the personalized needs of the user and the actual situation of the logistics platform (express company). For example, the express companies can also be ranked and compared based on the comprehensive score, and the advantages and disadvantages of each company can be analyzed. For example, the performance changes of each express company in different time periods can be observed and its development trend can be analyzed through methods such as time series analysis. The evaluation results can also be displayed in an intuitive way using visualization tools such as charts and maps to achieve visual display, which is convenient for users to understand and use.

[0082] In an optional implementation, the most suitable courier company can be automatically matched according to the personalized needs of the user. Exemplarily, based on the user demand analysis and multi-dimensional data evaluation results, an intelligent matching algorithm is developed, which can automatically select several options that best meet the user's needs from a large number of courier companies according to the user's personalized needs, and sort them according to the degree of matching. Furthermore, considering that user needs and market conditions may change at any time, the intelligent matching algorithm should have the ability to adjust dynamically. By real-time monitoring of user behavior and market data, and regularly updating the courier company evaluation results, a dynamic adjustment strategy is implemented to ensure the timeliness and accuracy of the algorithm.

[0083] For the analysis process of various aspects of user needs, for example, a complete user needs analysis system is established, which can identify and analyze user behavior on the platform, including search history, screening conditions, purchase records, etc., to gain a deep understanding of user preferences and needs in terms of price, service, timeliness, etc. For the specific analysis logic of user needs, for example, the specific logic of establishing a complete user needs analysis system can follow the following steps and principles to ensure that the system can comprehensively and accurately capture and understand user needs:

[0084] First, clarify the goal and scope of the demand analysis. First determine the project goal, that is, first clarify the overall goal of the project or product, that is, what problems to solve and what user needs to meet. Define the scope of demand: Based on the project goals, define the specific scope of the demand analysis, including which functional modules, business processes and user groups, etc.

[0085] Then, collect user needs. This can be done through user interviews, and the interviewees should cover users with different backgrounds, roles, and needs. It can also be done through questionnaire surveys. Detailed questionnaires can be designed and distributed to target user groups online or offline to collect a large number of user feedback and opinions. During the competitive product analysis process, analyze the functions, advantages and disadvantages, user reviews, etc. of similar products on the market to understand industry trends and user preferences. During the data analysis process, use existing data (such as user behavior data, transaction data, etc.) to mine and analyze to discover potential user needs and problems.

[0086] After that, we will analyze and organize the needs. The first step is to classify the collected needs according to the dimensions of functional modules, business processes, user groups, etc. The next step is to prioritize the needs according to factors such as the urgency, importance, and difficulty of implementation. The next step is to verify and revise the needs through prototype design, user testing, etc. to ensure the accuracy and feasibility of the needs.

[0087] In the process of establishing the requirements specification, the requirements specification is written, that is, the analyzed and sorted requirements are recorded in the form of a document, including the requirements description, functional requirements, performance indicators, constraints, etc. During the review and confirmation, relevant personnel are organized to review and confirm the requirements specification to ensure that all parties have a consistent understanding of the requirements.

[0088] Tracking and change management of user requirements. During the requirements tracking, during the project development process, continuously track the realization of requirements to ensure that the development results are consistent with the requirements specification. For changes in requirements, establish a strict change management process, including change application, evaluation, approval, implementation and verification.

[0089] As an example, technical and tool support can also be introduced. For example, by using demand analysis software, professional demand analysis software (such as C / S structured software) can be used to improve the efficiency and accuracy of demand analysis. These software usually contain functional modules such as system management, project view, demand type view and demand view. For automated tools, automated tools (such as data mining tools, user behavior analysis tools, etc.) are used to assist demand analysis work and improve the efficiency and accuracy of data processing. For continuous optimization and iteration, user feedback can be collected first. After the product is launched, user feedback and opinions can be continuously collected to understand user usage and demand changes. Then, demand iteration is performed, and product functions are continuously optimized and iterated according to user feedback and market changes to meet users' changing needs. Through the above steps and principles, a complete user demand analysis system can be established to ensure that the project or product can accurately capture and meet user needs, and improve product competitiveness and user satisfaction.

[0090] In one possible implementation, data from multiple dimensions (including price, service evaluation, delivery speed, complaint rate, etc.) can be integrated to conduct a comprehensive evaluation of major express delivery companies, thereby achieving multi-dimensional data evaluation. These data can be obtained through cooperation with express delivery companies, or collected through user feedback, third-party evaluation, etc.

[0091] Step S150, in response to the adding operation and / or deleting operation of the logistics project conditions corresponding to the multiple first target logistics platforms, the final first target logistics platform corresponding to the selected request is screened and selected from the multiple first target logistics platforms according to the adding operation and / or deleting operation.

[0092] like Figure 2As shown in the figure, based on the user's browsing history and purchase behavior, the system can recommend the courier company (first target logistics platform) that best meets the user's needs. The implementation of the recommendation module is based on the collaborative filtering algorithm, which can recommend the most suitable courier company (first target logistics platform) based on the user's interests and behavior data. Then, the user can also manually add or delete certain conditions to filter among multiple first target logistics platforms, such as Figure 3 , Figure 4 , Figure 5 , Figure 6 and Figure 7 As shown, further filtering is performed by adding operations and / or removing operations.

[0093] In an optional implementation, the user's browsing history and purchasing behavior on the platform can be tracked by technical means, including the courier companies viewed, service types, price ranges, etc., as well as the final purchase decisions, to achieve user behavior tracking. Based on user behavior data, a user portrait can be constructed. By analyzing the user's browsing and purchasing habits, identifying the user's preferences and needs, and potential changes in needs, the construction of the user portrait can be achieved. Based on the user portrait and historical data, a personalized recommendation algorithm can be designed. The algorithm can predict which courier companies the user may be interested in and the user's possible choices in a specific situation. When displaying personalized recommendation results on the user interface, the recommendation results may include courier companies similar to the user's historical choices, high-quality options that meet the user's current needs, etc. At the same time, flexible filtering and sorting functions are provided so that users can adjust according to their needs to achieve personalized recommendation display.

[0094] Specifically, the specific implementation process of the above-mentioned user behavior tracking may include the following specific contents: the system can track the mailing behavior. For the ordering method, track whether the user places the order through the official website, APP, mini program or third-party platform. For the mailing frequency, analyze the user's mailing frequency to understand the user's mailing habits and needs. For the mailing type, distinguish whether it is personal mailing or corporate mailing, as well as the type and characteristics of the mailed items. Furthermore, the system can also track the query behavior. For the query method, track whether the user inquires about the logistics information through the official website, APP, SMS, phone or third-party platform. For the query frequency, analyze the frequency of the user's query of logistics information to understand the user's attention to the package. For the query result feedback, collect the user's satisfaction and feedback on the query results. In addition, the system can also track the complaint behavior. For the complaint channel, track whether the user complains through the official customer service, social media, complaint platform or other channels. For the complaint reason, analyze the specific reasons for the user's complaint, such as package loss, delay, damage, etc. For complaint handling, record the process and results of complaint handling, and evaluate the efficiency and effectiveness of complaint handling

[0095] Specifically, the detailed construction process of the above-mentioned user portrait construction may include the following steps: First, data collection. For user data, basic information of users (such as age, gender, geographic location, etc.), historical behavior data (such as browsing history, purchase history, click history, etc.) and user feedback data (such as ratings, comments, etc.) are collected. For item data, attribute information of items (such as price, brand, category, description, etc.) and association information between items (such as similarity, complementarity, etc.) are collected. Then, data preprocessing is performed. For data cleaning, duplicate, erroneous or invalid data is removed to ensure the accuracy and consistency of the data. For data standardization, data from different sources and formats are uniformly processed for subsequent analysis. For feature extraction, features useful for recommendation are extracted from the original data, such as user interest preferences, item popularity, etc. After that, algorithm selection and design are performed. Based on the user's historical behavior data, other users or items with similar interests to the target user are found, so as to recommend similar items to the target user. Collaborative filtering algorithms include user-based collaborative filtering and item-based collaborative filtering to implement collaborative filtering algorithms. By analyzing the content information of items (such as text descriptions, tags, etc.) and the user's historical preferences, we recommend items similar to those that the user liked before, and implement a content-based recommendation algorithm. Combining the advantages of collaborative filtering and content-based recommendation algorithms, we improve the accuracy and diversity of recommendations through weighting, fusion, and other methods to implement a hybrid recommendation algorithm. Using deep learning technologies such as deep neural networks, we automatically extract the features of users and items, and perform complex nonlinear relationship modeling to achieve more accurate recommendations and implement a deep learning recommendation algorithm. Then comes model training and optimization, training data division, that is, dividing the collected data into training sets and test sets for model training and evaluation; model training is to use the training set data to train the recommendation algorithm model and adjust the model parameters to optimize the recommendation effect; model evaluation is to use the test set data to evaluate the trained model, and measure the recommendation effect through indicators such as recall rate, accuracy, coverage, and novelty; model optimization is to iteratively optimize the model based on the evaluation results, including adjusting algorithm parameters, improving feature extraction methods, and introducing new data sources. Finally, the recommendation results are generated and displayed. For recommendation list generation, a recommendation list is generated for the user based on the trained recommendation algorithm model, including recommended items, reasons for recommendation, etc. For recommendation result sorting, the items in the recommendation list are sorted, and the items that the user is most likely to be interested in are placed in front.

[0096] Specifically, for the flexible filtering and sorting functions mentioned above, first conduct a demand analysis to clarify the user's specific needs for filtering and sorting. This usually includes: filtering function, that is, users may need to filter express services according to different conditions (such as express companies, estimated delivery time, price range, whether cash on delivery is supported, etc.); sorting function, that is, users may want to arrange the filtering results according to a certain order (such as price from low to high, estimated delivery time from short to long, evaluation score from high to low, etc.). Then comes the database and data model design. For database design, ensure that the database can store all necessary express service information, including express companies, prices, estimated delivery times, user reviews, etc.; for data models, build a reasonable data model to support efficient query and filtering operations. For example, you can use indexes to speed up queries, or store commonly used filtering conditions as separate fields to reduce the amount of calculations. For back-end development, in the API design part, design a RESTful API or other form of interface to receive the filtering and sorting requests sent by the front-end and return the corresponding results; in the query optimization part, use SQL query statements or NoSQL query languages ​​to retrieve data according to the query conditions. In order to improve query efficiency, you can optimize the query statements and use indexes, joint queries and other technologies. In the sorting algorithm part, implement the sorting algorithm on the back-end to sort the data according to the sorting fields and order selected by the user. This can be achieved through the built-in sorting function of the database (such as the ORDER BY clause of SQL), or you can sort the data in memory before returning it to the front-end. For front-end development, in the user interface design, design an intuitive and easy-to-use user interface, including a filter condition input box, a sorting option drop-down menu, etc.; for the interactive logic, write JavaScript code to handle the user's filtering and sorting operations. When the user changes the filtering condition or sorting option, the front-end sends a corresponding request to the back-end and updates the page to display the new results. For data display, use tables, lists or other suitable controls to display the filtered and sorted express service information. In order to improve the user experience, you can add functions such as paging and loading prompts. Finally, in terms of testing and optimization, functional testing is a comprehensive test of the filtering and sorting functions to ensure that they can correctly respond to user operations and return expected results; performance testing: testing the performance of the system when processing large amounts of data, including response time, throughput, etc.; if the performance is poor, optimization is required; in terms of user feedback, user feedback is collected and the functions are iterated and optimized based on user feedback.

[0097] Step S160, in response to the feedback data of the client corresponding to the selection request to the final first target logistics platform, the logistics platform data prediction model is adjusted and optimized according to the feedback data.

[0098] Users can evaluate and provide feedback on the recommended express companies so that the express platform can continuously optimize the recommendation algorithm and improve service quality. The feedback module is implemented based on user evaluation and feedback data, which can collect user opinions and suggestions in a timely manner, adjust and optimize the recommendation algorithm, and achieve continuous optimization and feedback. Specifically, first perform user feedback collection, regularly collect user feedback on the evaluation results, and understand user needs and expectations; then, model optimization, that is, continuously optimize and improve the evaluation model based on user feedback and actual conditions, to improve the accuracy and reliability of the evaluation; finally, data update, that is, regularly update the data of each dimension to ensure the timeliness and accuracy of the evaluation results.

[0099] By comparing and matching the relevant data of logistics platforms (express companies) through the logistics platform data prediction model, users can be provided with a simple, intuitive and efficient express selection solution, while ensuring service quality and meeting the personalized needs of users, improving the user experience, helping to distinguish between existing comparison solutions and logistics platform selection solutions, improving user experience and satisfaction, and enabling users to quickly and accurately find logistics platforms that meet their personalized needs, while increasing the business volume and reputation of logistics platforms. The implementation of this function not only improves the user experience, but also improves the service quality of express companies, and solves the current technical problem of low efficiency in logistics data processing for logistics platforms.

[0100] In the embodiment of the present application, users can search for services of multiple express delivery companies on one platform at the same time, without logging into the websites or APPs of different express delivery companies separately, saving time and energy, and realizing the convenience and speed of user use. It also provides more diverse express delivery options, and users can choose the most suitable express delivery company according to their needs and preferences, which allows users to make wise choices according to their own circumstances. Different express delivery companies may have differences in speed, price, service scope, etc. In addition, it also provides a comparison function in terms of express delivery fees, and users can directly compare the prices of different express delivery companies on one page and choose the service with the highest cost performance. This can not only help users save costs, but also provide more room for competition between express delivery companies. Furthermore, based on the user's browsing history and purchasing behavior, the system can recommend to users the express delivery company that best meets their personalized needs. This personalized recommendation function can improve the user's experience and enable users to more conveniently choose the express delivery service that best meets their needs. In addition, users can also evaluate and feedback the recommended express delivery companies so that the system can continuously optimize the recommendation algorithm and improve the service quality. This feedback mechanism can improve users' trust and satisfaction with the platform. Through the comparison function and personalized recommendation provided, more users can be attracted to use the platform and choose the appropriate express delivery company, thereby improving the business volume and reputation of the express delivery company. To sum up, the system's comparison function for logistics prices and other aspects has achieved convenient and fast query, more diverse choices, price comparison advantages, personalized recommendations, user feedback, and increased express company business volume and reputation, bringing more convenience and value to users and logistics platforms such as express companies.

[0101] The above steps are described in detail below.

[0102] In some embodiments, the logistics platform data prediction model is used to compare the logistics prices of multiple target logistics platforms in the above step S140 to obtain a comparison result, which may specifically include the following steps:

[0103] Obtain historical logistics and transportation data of multiple target logistics platforms; analyze the historical logistics and transportation data through the AI ​​system corresponding to the logistics platform data prediction model to obtain the logistics and transportation speed, logistics and transportation routes, the excellence of the storage environment of the transit warehouse, and the logistics and transportation safety of each of the multiple target logistics platforms;

[0104] Based on the logistics transportation speeds, logistics transportation routes, transit warehouse storage environments, and logistics transportation safety levels of multiple target logistics platforms, the logistics prices of multiple target logistics platforms are compared to obtain comparison results; wherein, in the comparison results, the slower the logistics transportation speed, the longer the logistics transportation route, the better the transit warehouse storage environment and / or the lower the logistics transportation safety level, the lower the logistics price of the target logistics platform.

[0105] For the price adjustment process of each express company (logistics platform), for example, the price can be adjusted according to the warehouse location, shipping distance, and trunk road conditions of the transportation route. For example, through a detailed comparison by the AI ​​system, if a certain express company's transportation speed is slow, the price of the express company can be reduced; if a certain express company's transportation speed is fast, the price of the express company can be increased. This logistics price processing method makes the processing result of logistics prices more reasonable and improves user experience.

[0106] In some embodiments, the method may further include the following steps:

[0107] Acquire item property data and historical sales data for target type goods in the logistics platform; the item property data includes item storage temperature and / or item storage humidity; determine a first region where the historical sales volume is greater than a first preset sales volume from a plurality of regions to which the target type goods are sold based on the historical sales data;

[0108] Based on the historical sales data of the target type of goods and the item storage temperature and / or item storage humidity, the AI ​​system is used to determine the location of the logistics transit warehouse for the target type of goods, so that the location of the logistics transit warehouse is as close to the first region as possible under storage conditions that meet the item storage temperature and / or item storage humidity; the distribution logistics price of the target type of goods in the logistics platform is adjusted according to the location of the logistics transit warehouse to obtain adjusted price data of the logistics platform.

[0109] As an optional implementation method, the logistics and warehouse quotation fusion system can be used to select transit warehouses and delivery priorities in other regions through the AI ​​system according to the local nature and sales of a certain type of goods, and then adjust the logistics price according to the location of the transit warehouse. This logistics price processing method makes the processing results of logistics prices more reasonable and improves user experience.

[0110] In some embodiments, after obtaining historical sales data for the target type of goods in the logistics platform, the method may further include the following steps:

[0111] Determine, based on the historical sales data, a sales peak time period in which the historical sales quantity of the target type of goods is greater than a second preset sales quantity; determine, from among the multiple regions to which the target type of goods are sold, a second region in which the sales peak time period is greater than the preset time period, and a third region in which the sales peak time period is less than or equal to the preset time period;

[0112] Adjusting the delivery area priority of the target type of goods to obtain an adjusted delivery area priority result, so that the delivery priority of the target type of goods to the second area is greater than the delivery priority to the third area;

[0113] The distribution logistics price of the target type of goods in the logistics platform is adjusted according to the distribution area priority result to obtain the adjusted price data of the logistics platform; the higher the distribution area priority result, the higher the distribution logistics price.

[0114] As an example, based on the local sales of a certain type of goods, the AI ​​system selects transit warehouses and delivery priorities in other regions. For example, for goods such as ice cream that are sold in large quantities during hot weather, the preferred delivery area is southern cities; during periods of large climate differences in different regions (such as September when it snows in the Northeast and Sichuan is hot), ice cream is preferably shipped from warehouses in the Northeast to avoid long-term accumulation of goods due to local sales conditions, and finally calculate the corresponding goods storage and logistics prices. This logistics price processing method makes the logistics price processing results more reasonable and improves user experience.

[0115] In some embodiments, the number of locations where the logistics transit warehouse is set includes multiple; the process of adjusting the distribution logistics price of the target type of goods according to the location where the logistics transit warehouse is set may specifically include the following steps:

[0116] Obtain the warehouse usage price of each logistics transit warehouse setting location; determine the warehouse storage cost of the target type of goods based on the item storage temperature and / or item storage humidity; determine the comprehensive total logistics cost corresponding to the logistics transit warehouse setting location based on the warehouse usage price, warehouse storage cost and the transportation distance logistics cost based on the logistics transit warehouse setting location;

[0117] Compare multiple comprehensive total logistics costs corresponding to multiple logistics transfer warehouse setting locations to obtain comparison results, and determine multiple first logistics transfer warehouse setting locations whose comprehensive total logistics costs are lower than the preset logistics costs in the comparison results as candidate logistics transfer warehouse setting locations for the target type of goods;

[0118] Obtaining first historical sales data and user feedback data of target type goods within a preset distance range around the candidate logistics transfer warehouse setting location; determining a target candidate logistics transfer warehouse setting location with the highest first historical sales data and user feedback data from multiple candidate logistics transfer warehouse setting locations, and determining the target candidate logistics transfer warehouse setting location as the final logistics transfer warehouse setting location;

[0119] According to the final comprehensive total logistics cost corresponding to the final logistics transit warehouse setting location, the distribution logistics price of the target type of goods in the logistics platform is adjusted to obtain the adjusted price data of the logistics platform.

[0120] Exemplary, first determine whether it is fresh cold chain goods (special storage temperature requirements for items), if so, confirm to set up ordinary warehouses in low temperature climate areas, instead of low temperature functional warehouses in other areas, to reduce warehouse storage costs. Furthermore, it is also possible to compare and comprehensively judge through the AI ​​system: search the quotation of local warehouses through the system (set up the system interface with the local house rental system for data communication to realize the inquiry and quotation of warehouse rental in a certain place), calculate the first comprehensive logistics total cost based on the warehouse quotation, warehouse storage cost and transportation distance logistics cost, and compare the second comprehensive logistics total cost of warehousing and storing goods in other regions through the AI ​​system, select the goods storage location corresponding to the lower comprehensive logistics total cost as the final goods storage method, and calculate the logistics price corresponding to the final goods storage method. In the embodiment of the present application, it is also possible to combine the types of goods, regional warehouse data, logistics transportation data, goods sales data and user feedback data, perform data comparison through IA, and perform data balancing algorithm through IA based on logistics costs and user experience results, and select the optimal logistics method and final logistics price for goods. Through this logistics price processing method, the adjustment result of the logistics price is more reasonable and the user experience is improved.

[0121] In some embodiments, the method may further include the following steps:

[0122] Obtaining an actual return rate of logistics goods on the logistics platform by a first user belonging to a fourth region; if the actual return rate is greater than or equal to a preset return rate, obtaining regional environment data of the fourth region and user habit data of the first user;

[0123] The logistics configuration items for delivery to the fourth region are adjusted according to the regional environmental data and the user habit data to obtain the logistics configuration results of the adjusted logistics configuration items; wherein the logistics configuration items include any one or more of the storage temperature configured in the logistics process, the adjustable preference type corresponding to the logistics object, and the adjustable quality type corresponding to the logistics object; the preference type includes any one or more of the taste preference, temperature preference, color preference, shape preference, and size preference; according to the logistics configuration results, the delivery logistics price for delivery to the fourth region in the logistics platform is adjusted to obtain the adjusted price data of the logistics platform.

[0124] As an optional implementation, shipments are made based on the regional environmental data, user habit data, and user return rate of each region. For example, if the user return rate of a region is higher than a preset value (such as the user return rate of users in a certain region is high), priority is given to sending high-quality goods of the same type to users in that region; if the user return rate of a region is lower than or equal to a preset value (such as the user return rate of users in a certain region is low), priority is given to sending low-quality goods of the same type to users in that region. This logistics price processing method makes the adjustment results of logistics prices more reasonable and improves user experience.

[0125] In some embodiments, the method may further include the following steps:

[0126] Obtain the repurchase rate and user evaluation data of logistics goods on the logistics platform from users in multiple regions; analyze the user's tolerance for goods through the AI ​​system based on the repurchase rate and user evaluation data;

[0127] For the fifth region corresponding to the second user whose cargo tolerance is lower than the first preset tolerance, the delivery priority level of the logistics cargo delivered to the fifth region is increased, and for the sixth region corresponding to the third user whose cargo tolerance is higher than the second preset tolerance, the delivery priority level of the logistics cargo delivered to the sixth region is decreased;

[0128] According to the adjusted delivery priority level, the delivery logistics prices to the fifth and sixth regions in the logistics platform are adjusted to obtain the adjusted price data of the logistics platform; the higher the adjusted delivery priority level, the higher the delivery logistics price, and the lower the adjusted delivery priority level, the lower the delivery logistics price.

[0129] For example, first read the repurchase rate and evaluation, and then determine the user's tolerance for goods through the AI ​​system based on the repurchase rate and evaluation: if the tolerance is low, it will be shipped first, that is, the delivery speed will be adjusted faster; if the tolerance is high, the delivery priority will be reduced, the delivery speed will be adjusted slower, and the user will be sent a gift after a preset period of time to weigh the user's tolerance balance point, and then calculate the corresponding goods storage and logistics prices. This logistics price processing method makes the adjustment result of the logistics price more reasonable and improves the user experience.

[0130] Figure 8 A schematic diagram of the structure of a logistics price data processing device is provided. Figure 8 As shown, the logistics price data processing device 800 includes:

[0131] The acquisition module 801 is used to acquire price data, service data and time efficiency data of multiple logistics platforms;

[0132] A preprocessing module 802 is used to preprocess the price data, the service data and the timeliness data by a specified preprocessing method to obtain target data; wherein the specified preprocessing method includes any one or more of data cleaning, data screening, data deduplication, data filling missing values, and data removal of abnormal values;

[0133] A training module 803 is used to train the initial prediction model based on the target data using an artificial intelligence algorithm to obtain a logistics platform data prediction model;

[0134] The matching module 804 is used to respond to the selection request for the corresponding logistics services of multiple target logistics platforms, compare the logistics prices, logistics services and logistics timeliness of the multiple target logistics platforms using the logistics platform data prediction model, obtain the comparison result, and automatically match the multiple target logistics platforms according to the selection request through the comparison result and the dynamic programming algorithm, and determine the first target logistics platform among the multiple target logistics platforms whose matching degree with the selection request is higher than the preset matching degree; wherein the selection request includes the user price requirement, the user service requirement and the user timeliness requirement;

[0135] A screening module 805 is used for responding to an adding operation and / or a deleting operation on the logistics project conditions corresponding to the plurality of first target logistics platforms, and screening the final first target logistics platform that the selection request finally corresponds to and is selected from the plurality of first target logistics platforms according to the adding operation and / or the deleting operation;

[0136] The adjustment module 806 is used to respond to the feedback data of the client corresponding to the selection request on the final first target logistics platform, and adjust and optimize the logistics platform data prediction model according to the feedback data.

[0137] The logistics price data processing device provided in the embodiment of the present application has the same technical features as the logistics price data processing method provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0138] An electronic device provided in an embodiment of the present application is Fig. 9 As shown, the electronic device 900 includes a processor 902 and a memory 901, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the above embodiment when executing the computer program.

[0139] See also Fig. 9The electronic device further includes: a bus 903 and a communication interface 904, a processor 902, a communication interface 904 and a memory 901 are connected via the bus 903; the processor 902 is used to execute an executable module stored in the memory 901, such as a computer program.

[0140] The memory 901 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 904 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0141] The bus 903 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0142] Among them, the memory 901 is used to store programs, and the processor 902 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 902 or implemented by the processor 902.

[0143] The processor 902 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 902. The above processor 902 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor are combined to execute. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 901, and the processor 902 reads the information in the memory 901 and completes the steps of the above method in combination with its hardware.

[0144] Corresponding to the above-mentioned logistics price data processing method, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned logistics price data processing method.

[0145] The logistics price data processing device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. It can be clearly understood by technicians in the relevant field that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0146] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0147] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0148] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0149] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0150] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the logistics price data processing method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0151] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0152] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A logistics price data processing method, characterized in that: The method comprises: Obtain price data, service data, and timeliness data from multiple logistics platforms; Preprocessing the price data, the service data and the timeliness data by a specified preprocessing method to obtain target data; wherein the specified preprocessing method includes any one or more of data cleaning, data screening, data deduplication, data filling missing values, and data removal of outliers; Based on the target data, an initial prediction model is trained using an artificial intelligence algorithm to obtain a logistics platform data prediction model; In response to a selection request for logistics services corresponding to multiple target logistics platforms, the logistics prices, logistics services and logistics timeliness of the multiple target logistics platforms are compared using the logistics platform data prediction model to obtain a comparison result, and according to the selection request, the multiple target logistics platforms are automatically matched through the comparison result and a dynamic programming algorithm to determine a first target logistics platform among the multiple target logistics platforms whose matching degree with the selection request is higher than a preset matching degree; wherein the selection request includes user price requirements, user service requirements and user timeliness requirements; In response to an adding operation and / or a deleting operation on the logistics project conditions corresponding to the plurality of the first target logistics platforms, according to the adding operation and / or the deleting operation, a final first target logistics platform selected by the selection request is screened from the plurality of the first target logistics platforms; In response to the feedback data of the selection request corresponding to the client to the final first target logistics platform, the logistics platform data prediction model is adjusted and optimized according to the feedback data.

2. The method according to claim 1, characterized in that The logistics platform data prediction model is used to compare the logistics prices of the multiple target logistics platforms to obtain comparison results, including: Acquire historical logistics and transportation data of the multiple target logistics platforms; Based on the historical logistics transportation data, the AI ​​system corresponding to the logistics platform data prediction model is used to analyze the logistics transportation speed, logistics transportation route, storage environment excellence of the transit warehouse, and logistics transportation safety of each of the multiple target logistics platforms; Based on the logistics transportation speeds, the logistics transportation routes, the storage environment of the transit warehouse, and the logistics transportation safety levels of each of the multiple target logistics platforms, the logistics prices of the multiple target logistics platforms are compared to obtain a comparison result; wherein, in the comparison result, the slower the logistics transportation speed, the longer the logistics transportation route, the better the storage environment of the transit warehouse and / or the lower the logistics transportation safety level, the lower the logistics price of the target logistics platform.

3. The method according to claim 1, characterized in that Also includes: Acquire item property data and historical sales data for target type goods in the logistics platform; the item property data includes item storage temperature and / or item storage humidity; Based on the historical sales data, determine a first region where the historical sales volume is greater than a first preset sales volume from among the multiple regions to which the target type of goods are sold; According to the historical sales data of the target type of goods and the item storage temperature and / or the item storage humidity, determine the location of the logistics transfer warehouse for the target type of goods through the AI ​​system, so that the location of the logistics transfer warehouse is as close to the first region as possible under storage conditions that meet the item storage temperature and / or the item storage humidity; The distribution logistics price of the target type of goods in the logistics platform is adjusted according to the setting position of the logistics transit warehouse to obtain the adjusted price data of the logistics platform.

4. The method according to claim 3, characterized in that: After obtaining the historical sales data of the target type of goods in the logistics platform, it also includes: Determining, based on the historical sales data, a sales peak time period during which the historical sales volume of the target type of goods is greater than a second preset sales volume; Determine, from the multiple regions to which the target type of goods are sold, a second region whose peak sales time period is greater than a preset time period, and a third region whose peak sales time period is less than or equal to the preset time period; Adjusting the delivery area priority of the target type of goods to obtain an adjusted delivery area priority result, so that the delivery priority of the target type of goods to the second area is greater than the delivery priority to the third area; The distribution logistics price of the target type of goods in the logistics platform is adjusted according to the distribution area priority result to obtain the adjusted price data of the logistics platform; the higher the distribution area priority result, the higher the distribution logistics price.

5. The method according to claim 3, characterized in that: The number of the logistics transfer warehouse setting locations includes multiple; the distribution logistics price of the target type of goods is adjusted according to the logistics transfer warehouse setting locations, including: Obtaining the warehouse usage price of each logistics transit warehouse setting location; Determining the warehouse storage cost of the target type of goods according to the storage temperature of the goods and / or the storage humidity of the goods; Determine the comprehensive total logistics cost corresponding to the location of the logistics transit warehouse according to the warehouse usage price, the warehouse storage cost and the transportation distance logistics cost based on the location of the logistics transit warehouse; Compare the multiple comprehensive total logistics costs corresponding to the multiple logistics transfer warehouse setting locations to obtain a comparison result, and determine the multiple first logistics transfer warehouse setting locations whose comprehensive total logistics costs are lower than the preset logistics cost in the comparison result as the candidate logistics transfer warehouse setting locations for the target type of goods; Acquire first historical sales data and user feedback data of the target type of goods within a preset distance range around the location where the alternative logistics transfer warehouse is set; Determine a target candidate logistics transfer warehouse setting location with the highest first historical sales data and the highest user feedback data from a plurality of candidate logistics transfer warehouse setting locations, and determine the target candidate logistics transfer warehouse setting location as the final logistics transfer warehouse setting location; According to the final comprehensive total logistics cost corresponding to the final logistics transit warehouse setting location, the distribution logistics price of the target type of goods in the logistics platform is adjusted to obtain the adjusted price data of the logistics platform.

6. The method according to claim 1, characterized in that Also includes: Obtaining an actual return rate of logistics goods on the logistics platform by a first user belonging to a fourth region; If the actual return rate is greater than or equal to the preset return rate, acquiring the regional environment data of the fourth region and the user habit data of the first user; The logistics configuration items delivered to the fourth region are adjusted according to the regional environment data and the user habit data to obtain the logistics configuration results of the adjusted logistics configuration items; wherein the logistics configuration items include any one or more of the storage temperature configured in the logistics process, the preference type corresponding to the logistics object that can be adjusted, and the quality type corresponding to the logistics object that can be adjusted; the preference type includes any one or more of the taste preference, temperature preference, color preference, shape preference, and size preference; The logistics price of the distribution to the fourth region in the logistics platform is adjusted according to the logistics configuration result to obtain the adjusted price data of the logistics platform.

7. The method according to claim 1, characterized in that Also includes: Obtaining repurchase rates and user evaluation data of logistics goods on the logistics platform by users in multiple regions; Analyze the user's tolerance for goods through an AI system based on the repurchase rate and user evaluation data; For the fifth region corresponding to the second user whose cargo tolerance is lower than the first preset tolerance, the delivery priority level of the logistics cargo delivered to the fifth region is increased, and for the sixth region corresponding to the third user whose cargo tolerance is higher than the second preset tolerance, the delivery priority level of the logistics cargo delivered to the sixth region is decreased; The distribution logistics prices for the fifth and sixth regions in the logistics platform are adjusted according to the adjusted delivery priority levels to obtain adjusted price data of the logistics platform; the higher the adjusted delivery priority level, the higher the distribution logistics price, and the lower the adjusted delivery priority level, the lower the distribution logistics price.

8. A logistics price data processing device, characterized in that: The device comprises: The acquisition module is used to obtain price data, service data and timeliness data from multiple logistics platforms; A preprocessing module, used to preprocess the price data, the service data and the timeliness data by a specified preprocessing method to obtain target data; wherein the specified preprocessing method includes any one or more of data cleaning, data screening, data deduplication, data filling missing values, and data removal of abnormal values; A training module, used to train the initial prediction model based on the target data using an artificial intelligence algorithm to obtain a logistics platform data prediction model; A matching module, for responding to a selection request for logistics services corresponding to a plurality of target logistics platforms, using the logistics platform data prediction model to compare the logistics prices, logistics services and logistics timeliness of the plurality of target logistics platforms, obtaining a comparison result, and automatically matching the plurality of target logistics platforms according to the selection request through the comparison result and a dynamic programming algorithm, and determining a first target logistics platform among the plurality of target logistics platforms whose matching degree with the selection request is higher than a preset matching degree; wherein the selection request includes user price requirements, user service requirements and user timeliness requirements; A screening module, configured to respond to an adding operation and / or a deleting operation on the logistics project conditions corresponding to the plurality of the first target logistics platforms, and to screen the final first target logistics platform that the selection request finally corresponds to and is selected from the plurality of the first target logistics platforms according to the adding operation and / or the deleting operation; The adjustment module is used to respond to the feedback data of the client corresponding to the selection request on the final first target logistics platform, and adjust and optimize the logistics platform data prediction model according to the feedback data.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 7.

Images