Logistics service quality index data management method and device, equipment and storage medium

Abstract

The invention relates to the technical field of logistics information management, and discloses a logistics service quality index data management method and device, equipment and a storage medium. The method comprises the following steps: reading original logistics data related to logistics service quality from a pre-connected data source; performing cleaning and format conversion processing on the original logistics data to obtain preprocessed logistics data; respectively calculating the preprocessed logistics data according to different preset algorithm formulas and network models, and outputting corresponding logistics service quality index data; and converting the logistics service quality index data into a chart type, and displaying the chart type to a user through a display interface. According to the method, automatic management of the logistics service quality index data is realized, the working efficiency is effectively improved, the probability of human errors is reduced, and logistics enterprises can know the service quality condition more timely and accurately and then take corresponding measures to improve the service quality.

Description

Technical Field

[0001] The present invention relates to the field of logistics service technology, and in particular to a logistics service quality indicator data management method, device, equipment and storage medium. Background Art

[0002] With the rapid development of the logistics industry, customers have higher and higher requirements for the quality of logistics services. In order to meet customer needs and improve their own competitiveness, logistics companies must strictly control service quality. Traditional quality control methods often rely on manual statistics and analysis, which is not only inefficient but also prone to errors.

[0003] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0004] The main purpose of the present invention is to solve the problem that existing logistics service quality control methods often rely on manual statistics and analysis, which is not only inefficient but also prone to errors.

[0005] A first aspect of the present invention provides a method for managing logistics service quality indicator data, comprising: reading original logistics data related to logistics service quality from a pre-connected data source; cleaning and format conversion processing the original logistics data to obtain pre-processed logistics data; calculating the pre-processed logistics data according to different preset algorithm formulas and network models, and outputting corresponding logistics service quality indicator data, the logistics service quality indicator data including: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transport full load rate; converting the logistics service quality indicator data into a chart type, and displaying the chart type to a user through a display interface.

[0006] Optionally, in a first implementation method of the first aspect of the present invention, original logistics data related to the quality of logistics services is read from a pre-connected data source, including the steps of: pre-connecting the data source, the data source including a logistics system API interface, a logistics database, and logistics vehicle-mounted sensors; using a polling mechanism or an event-driven mechanism to read original logistics data related to the quality of logistics services from the data source, the original logistics data including: transportation cost records, records of the integrity of goods for each delivery, customer evaluation texts, inventory quantities and in-and-out time records, and vehicle loading and capacity for each transportation.

[0007] Optionally, in a second implementation method of the first aspect of the present invention, the original logistics data is cleaned and format-converted to obtain preprocessed logistics data, including the steps of: detecting whether there are null values ​​in the original logistics data, and if so, directly deleting the null values ​​or filling the null values ​​with the mean; detecting whether there are abnormal values ​​in the original logistics data, and if so, directly deleting the abnormal values ​​or correcting the abnormal values; after the null values ​​and abnormal values ​​in the original logistics data are processed, the original logistics data is converted into a numerical type with a unified format.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the pre-processed logistics data are calculated respectively according to different preset algorithm formulas and network models, and corresponding logistics service quality index data are output, wherein the logistics service quality index data include: scheduled collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transport full load rate, including the steps of: pre-designing an algorithm formula for logistics service quality index data, wherein, scheduled collection rate = number of express deliveries collected within the specified time / total number of express deliveries × 100%; delivery rate = number of express deliveries successfully delivered within the specified time / number of all express deliveries attempted to be delivered × 1 00%; Goods integrity rate = quantity of intact goods delivered / total quantity of goods delivered × 100%; Inventory turnover rate = sales cost / average inventory × 100%; Transport full load rate = actual vehicle load / rated vehicle load × 100%; Obtain customer evaluation text from the customer feedback system; Pre-design a network model for logistics service quality indicator data, wherein the network model is used to receive customer evaluation text and output corresponding sentiment tendency categories, and the sentiment tendency categories include customer satisfaction and customer dissatisfaction; Input the pre-processed logistics data into the preset algorithm formula and algorithm model accordingly, and output corresponding logistics service quality indicator data.

[0009] Optionally, in a fourth implementation method of the first aspect of the present invention, a network model for logistics service quality index data is pre-designed, wherein the network model is used to receive customer evaluation texts and output corresponding sentiment tendency categories, wherein the sentiment tendency categories include customer satisfaction and customer dissatisfaction, and comprises the steps of: cleaning and formatting the collected customer evaluation texts to obtain preprocessed customer evaluation text data; annotating the preprocessed customer evaluation texts with sentiment tendencies, and dividing the customer evaluation text data into two categories: customer satisfaction and customer dissatisfaction; constructing an initial network recognition model comprising an embedding layer, an LSTM layer, and a fully connected layer, and setting hyperparameters of the initial network recognition model, wherein the hyperparameters include learning rate, batch size, and number of training rounds; training the initial network recognition model using the annotated preprocessed customer evaluation texts, and updating the parameters of the initial network recognition model through a back-propagation algorithm and a gradient descent optimizer to obtain a trained network recognition model; preprocessing the customer evaluation text to be predicted and inputting it into the trained network recognition model to output a sentiment tendency prediction type.

[0010] Optionally, in the fifth implementation method of the first aspect of the present invention, after outputting the corresponding logistics service quality index data, it also includes the steps of: using a filtering algorithm to denoise the logistics service quality index data; using an exponential smoothing method to smooth the logistics service quality index data.

[0011] Optionally, in a sixth implementation method of the first aspect of the present invention, the logistics service quality indicator data is converted into chart data, and the chart data is displayed to a user through a display interface, including the steps of: converting the logistics service quality indicator data into chart data according to the characteristics and display requirements of the logistics service quality indicator data, wherein the types of the chart data include line charts, bar charts or pie charts; pre-designing the overall layout of the display interface, and embedding the generated chart data into the corresponding position of the display interface to display it to the user.

[0012] The second aspect of the present invention provides a logistics service quality indicator data management device, including: a reading module, used to read original logistics data related to logistics service quality from a pre-connected data source; a processing module, used to clean and convert the original logistics data to obtain pre-processed logistics data; a calculation module, used to calculate the pre-processed logistics data according to different preset algorithm formulas and network models, and output corresponding logistics service quality indicator data, the logistics service quality indicator data including: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transport full load rate; a display module, used to convert the logistics service quality indicator data into a chart type, and display the chart type to the user through a display interface.

[0013] Optionally, in a first implementation manner of the second aspect of the present invention, the reading module includes: a connection unit, used to pre-connect to a data source, wherein the data source includes a logistics system API interface, a logistics database, and a logistics vehicle-mounted sensor; a reading unit, used to read original logistics data related to the quality of logistics services from the data source using a polling mechanism or an event-driven mechanism, wherein the original logistics data includes: transportation cost records, records of the integrity of goods for each delivery, customer evaluation texts, inventory quantity and in-and-out time records, and vehicle loading and capacity for each transportation.

[0014] Optionally, in a second implementation method of the second aspect of the present invention, the processing module includes: a first detection unit, used to detect whether there are null values ​​in the original logistics data, and if so, directly delete the null values ​​or fill the null values ​​with the mean; a second detection unit, used to detect whether there are abnormal values ​​in the original logistics data, and if so, directly delete the abnormal values ​​or correct the abnormal values; a conversion unit, used to convert the original logistics data into a numerical type with a unified format after the null values ​​and abnormal values ​​in the original logistics data are processed.

[0015] Optionally, in a third implementation method of the second aspect of the present invention, the calculation module includes: a formula design unit, used to pre-design an algorithm formula for logistics service quality index data, wherein, scheduled collection rate = number of express deliveries collected within the specified time / total number of express deliveries × 100%; delivery rate = number of express deliveries successfully delivered within the specified time / number of all express deliveries attempted to be delivered × 100%; cargo integrity rate = number of intact delivered goods / total number of delivered goods × 100%; inventory turnover rate = sales cost / average inventory × 100%; transport full load rate = actual vehicle load / rated vehicle load × 100%; obtaining customer evaluation text from a customer feedback system; a model design unit, used to pre-design a network model for logistics service quality index data, wherein the network model is used to receive customer evaluation texts and output corresponding sentiment tendency categories, the sentiment tendency categories including customer satisfaction and customer dissatisfaction; an output unit, used to input the pre-processed logistics data into a preset algorithm formula and an algorithm model, and output corresponding logistics service quality index data.

[0016] Optionally, in a fourth implementation of the second aspect of the present invention, the model design unit includes: a preprocessing subunit, which is used to clean and format-convert the collected customer evaluation text to obtain preprocessed customer evaluation text data; a labeling subunit, which is used to label the preprocessed customer evaluation text with sentiment tendency, and divide the customer evaluation text data into two categories: customer satisfaction and customer dissatisfaction; a construction subunit, which is used to construct an initial network recognition model including an embedding layer, an LSTM layer and a fully connected layer, and set hyperparameters of the initial network recognition model, wherein the hyperparameters include learning rate, batch size, and number of training rounds; a training subunit, which is used to train the initial network recognition model using the labeled preprocessed customer evaluation text, and update the parameters of the initial network recognition model through a back-propagation algorithm and a gradient descent optimizer to obtain a trained network recognition model; a prediction subunit, which is used to preprocess the customer evaluation text to be predicted and input it into the trained network recognition model, and output a sentiment tendency prediction type.

[0017] Optionally, in the fifth implementation method of the second aspect of the present invention, it also includes: an indicator processing module, which is used to use a filtering algorithm to denoise the logistics service quality indicator data; and use an exponential smoothing method to smooth the logistics service quality indicator data.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the display module includes: a chart conversion unit, used to convert the logistics service quality indicator data into chart data according to the characteristics and display requirements of the logistics service quality indicator data, and the types of the chart data include line charts, bar charts or pie charts; a chart display unit, used to pre-design the overall layout of the display interface, and embed the generated chart data into the corresponding position of the display interface to display it to the user.

[0019] The third aspect of the present invention provides a logistics service quality indicator data management device, comprising: a memory and at least one processor, the memory storing computer-readable instructions, the memory and the at least one processor being interconnected through a line; the at least one processor calls the computer-readable instructions in the memory so that the logistics service quality indicator data management device executes the various steps of the logistics service quality indicator data management method as described above.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium, in which computer-readable instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the various steps of the logistics service quality indicator data management method as described above.

[0021] Beneficial effects: The technical solution of the present invention reads the original logistics data related to the logistics service quality from the pre-connected data source; cleans and converts the original logistics data to obtain pre-processed logistics data; calculates the pre-processed logistics data according to different preset algorithm formulas and network models, and outputs corresponding logistics service quality index data, which include: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate; converts the logistics service quality index data into a chart type, and displays the chart type to the user through a display interface. The method of the present invention realizes the automated management of logistics service quality index data, effectively improves work efficiency, reduces the probability of human error, and enables logistics companies to understand the service quality status more timely and accurately, and then take corresponding measures to improve service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A first flow chart of the logistics service quality indicator data management method provided by an embodiment of the present invention;

[0023] Figure 2 A second flow chart of the logistics service quality indicator data management method provided by an embodiment of the present invention;

[0024] Figure 3 A third flow chart of the logistics service quality indicator data management method provided by an embodiment of the present invention;

[0025] Figure 4 A fourth flow chart of the logistics service quality indicator data management method provided by an embodiment of the present invention;

[0026] Figure 5 A fifth flow chart of the logistics service quality indicator data management method provided by the embodiment of the present invention;

[0027] Figure 6 A sixth flow chart of the logistics service quality indicator data management method provided by an embodiment of the present invention;

[0028] Figure 7 A seventh flow chart of the logistics service quality indicator data management method provided by the embodiment of the present invention;

[0029] Figure 8 A schematic diagram of the structure of a logistics service quality indicator data management device provided by an embodiment of the present invention;

[0030] Fig. 9 Another structural schematic diagram of the logistics service quality index data management device provided by an embodiment of the present invention;

[0031] Fig.10A schematic diagram of the structure of a logistics service quality indicator data management device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The embodiment of the present invention provides a method, device, equipment and storage medium for managing logistics service quality indicator data, which reads original logistics data related to logistics service quality from a pre-connected data source; cleans and converts the original logistics data to obtain pre-processed logistics data; calculates the pre-processed logistics data according to different preset algorithm formulas and network models, and outputs corresponding logistics service quality indicator data, which includes: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate; converts the logistics service quality indicator data into a chart type, and displays the chart type to the user through a display interface. The method of the present invention realizes the automated management of logistics service quality indicator data, effectively improves work efficiency, reduces the probability of human error, and enables logistics companies to understand the service quality status more timely and accurately, and then take corresponding measures to improve service quality.

[0033] The terms "first", "second", "third", "fourth", etc. (if any) 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 interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the logistics service quality index data management method in the embodiment of the present invention includes:

[0035] S100, reading raw logistics data related to logistics service quality from a pre-connected data source;

[0036] Specifically, the quality of logistics services is crucial to logistics companies. By collecting and analyzing relevant raw logistics data, companies can continuously optimize logistics service processes and improve service quality, thereby improving customer satisfaction, enhancing market competitiveness, reducing operating costs and promoting supply chain collaboration. This embodiment can automatically obtain data and reduce manual operations through pre-set data source connections; extract data from multiple data sources to ensure the comprehensiveness and accuracy of the data, providing a data basis for subsequent analysis.

[0037] S200, cleaning and format conversion processing are performed on the original logistics data to obtain pre-processed logistics data;

[0038] In this embodiment, the original logistics data is cleaned and formatted to ensure data accuracy and consistency, providing a reliable basis for subsequent calculations and analysis. The unified data format can improve the efficiency of subsequent calculations and analysis.

[0039] S300, calculating the pre-processed logistics data respectively according to different preset algorithm formulas and network models, and outputting corresponding logistics service quality index data, wherein the logistics service quality index data includes: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate;

[0040] In this embodiment, according to business needs, the algorithm formula of each logistics service quality indicator is defined. Specifically, the calculation function of programming languages ​​such as Python and R or the database can be used to calculate the pre-processed logistics data according to the defined algorithm formula, and the data of each logistics service quality indicator is automatically obtained; for indicators such as customer satisfaction that require complex calculations, machine learning models (such as neural networks, decision trees, etc.) can be introduced for prediction and calculation. These models can be trained and optimized based on historical data and customer feedback. This embodiment uses scientific algorithm formulas and network models for calculation to ensure the accuracy and credibility of the indicator data. According to business changes and data feedback, the algorithm formula and network model can be continuously optimized to improve the accuracy and practicality of the indicator data.

[0041] In this embodiment, the on-time collection rate can directly reflect the response speed and execution ability of the logistics service provider, and is an important indicator for measuring its service efficiency; a high on-time collection rate means that customers can deliver goods to the logistics service provider more promptly, thereby shortening waiting time and improving customer satisfaction; by improving the on-time collection rate, the logistics service provider can better plan transportation routes and vehicle scheduling, optimize resource allocation, and reduce costs.

[0042] Delivery rate usually refers to the ratio of suppliers to deliver goods on time, and is an important indicator to measure suppliers' delivery performance. A high delivery rate means that suppliers can deliver goods according to the agreed time and quantity, ensuring the stable operation of the supply chain; an increase in delivery rate helps reduce additional costs caused by delays or out-of-stocks, such as loss of sales opportunities and increased inventory costs; a supplier's high delivery rate can enhance the purchaser's trust and reliance on it, and promote long-term cooperation between the two parties.

[0043] The cargo integrity rate refers to the proportion of cargo that is not damaged, lost or destroyed during transportation. The cargo integrity rate is one of the important indicators for evaluating the quality of transportation services, which can ensure the safety of cargo during transportation; cargo damage or loss will cause direct economic losses to customers and the supply chain, so ensuring the cargo integrity rate is of great significance to reducing economic losses; a high cargo integrity rate can enhance the corporate image of logistics service providers and enhance customer trust and satisfaction.

[0044] Customer satisfaction refers to the degree to which customers are satisfied with the service quality and efficiency provided by logistics service providers. Customer satisfaction is an important indicator for measuring the service quality of logistics service providers, which can directly reflect customers' feelings and expectations. By collecting and analyzing customer satisfaction data, logistics service providers can understand customer needs and dissatisfaction points, so as to make targeted service improvements. High customer satisfaction can enhance customer loyalty and dependence on logistics service providers, and promote long-term cooperation and word-of-mouth communication.

[0045] Inventory turnover rate refers to the turnover rate of inventory used by an enterprise to sell goods or provide services, usually expressed as the ratio of sales to average inventory within a certain period of time (such as one year). Inventory turnover rate can reflect the inventory management level and efficiency of an enterprise, and is one of the important indicators to measure the management level of an enterprise; a high inventory turnover rate means that an enterprise can convert inventory into sales more quickly, thereby improving the efficiency of capital utilization; by optimizing inventory turnover rate, an enterprise can better control the inventory level of each link in the supply chain and avoid excessive backlogs or out-of-stock phenomena.

[0046] The transport full load rate refers to the ratio of the actual loading capacity of a transport vehicle to its theoretical loading capacity, reflecting the utilization of the transport vehicle. A high transport full load rate means that the transport vehicle is fully utilized, which can reduce empty driving and waiting time and improve transportation efficiency; by increasing the transport full load rate, enterprises can reduce the transportation cost per unit of goods, thereby improving overall profitability; a high transport full load rate helps reduce energy consumption and environmental pollution, and promotes environmental protection and sustainable development of enterprises.

[0047] The on-time collection rate, delivery rate, intact cargo rate, customer satisfaction, inventory turnover rate, and transportation full load rate and other logistics service quality index data play an important role in measuring logistics service efficiency, ensuring supply chain stability, ensuring cargo safety, reflecting service quality, measuring inventory management efficiency, and improving transportation efficiency. This embodiment can achieve efficient and accurate acquisition of these index data, thereby helping logistics service providers to better meet customer needs, reduce costs, improve efficiency, and promote sustainable development of enterprises.

[0048] S400: Convert the logistics service quality indicator data into a chart type, and display the chart type to the user through a display interface.

[0049] Specifically, this embodiment can select a suitable chart type for display according to the characteristics of the indicator data and user needs. For example, for proportional indicators such as the scheduled collection rate and the delivery rate, a pie chart or a bar chart can be selected for display; for scoring indicators such as customer satisfaction, a line chart or a scatter chart can be selected for display. Specifically, you can use Python's Matplotlib, Seaborn and other libraries or JavaScript's ECharts, Highcharts and other libraries to generate corresponding charts according to the selected chart type. At the same time, a user-friendly display interface is designed, the generated charts are embedded into the interface, and necessary interactive functions are provided. This embodiment displays the indicator data through charts, making the data more intuitive and easy to understand, so that users can quickly understand the quality of logistics services; interactive functions are provided to allow users to filter, sort and export data according to their needs, thereby improving user participation and satisfaction.

[0050] The method of the present invention realizes the automated management of logistics service quality index data, effectively improves work efficiency, reduces the probability of human error, and enables logistics companies to understand the service quality status more timely and accurately, and then take corresponding measures to improve service quality.

[0051] See also Figure 2 The second embodiment of the logistics service quality index data management method in the embodiment of the present invention includes:

[0052] S110, pre-connecting a data source, wherein the data source includes a logistics system API interface, a logistics database, and a logistics vehicle-mounted sensor;

[0053] S120. Use a polling mechanism or an event-driven mechanism to read original logistics data related to logistics service quality from the data source, where the original logistics data includes: transportation cost records, records of the integrity of goods for each delivery, customer evaluation texts, inventory quantity and in-and-out time records, and vehicle loading and capacity for each transportation.

[0054] Specifically, the data sources that need to be connected are clearly defined, including the logistics system API interface, logistics database, and logistics vehicle sensors; and the corresponding connection parameters are configured according to the type and characteristics of the data source. For example, for the API interface, you need to obtain the API key and endpoint URL; for the database, you need to configure the database address, user name, password, etc.; for the vehicle sensor, you need to configure the sensor's data transmission protocol and receiving end. For the logistics system API interface: Use the API key and endpoint URL to establish a connection with the logistics system through HTTP requests. You can use the HTTP client library in the programming language (such as Python, Java, etc.) to send requests and receive responses. For the logistics database: Use a database connection pool (such as DBCP, C3P0, etc.) or a database connection framework (such as JDBC, ODBC, etc.) to establish a connection with the logistics database, and configure the connection pool parameters (such as the minimum number of connections, the maximum number of connections, waiting timeout, etc.) to ensure the stability and efficiency of the database connection. For the logistics vehicle sensor: According to the sensor's data transmission protocol (such as MQTT, HTTP, etc.), configure the data receiving end (such as server, cloud platform, etc.) to receive the data sent by the sensor. You can use an IoT platform (such as Alibaba Cloud IoT Platform, Huawei Cloud IoT Platform, etc.) to simplify the data reception and processing of sensors. After the connection is established, perform a connection test to ensure that the data source can respond and transmit data normally.

[0055] By pre-connecting the data source, this embodiment can ensure that data can be quickly and stably acquired in the subsequent data reading process, thereby improving the efficiency and accuracy of data reading; using a database connection pool can avoid frequent opening and closing of database connections, save system resources, and improve the performance of database access.

[0056] This embodiment can select a polling mechanism or an event-driven mechanism according to actual needs and the characteristics of the data source. For the polling mechanism, it is necessary to set a suitable polling interval (such as every second, every minute, etc.) according to the frequency of data updates and real-time requirements; its logic is to trigger a data reading operation when the polling interval arrives to obtain data from the data source. The advantage of selecting a polling mechanism is that it is simple and easy to implement. It is suitable for scenarios with low data update frequency or low real-time requirements. By setting a reasonable polling interval, the real-time nature of data reading and the consumption of system resources can be balanced.

[0057] For the event-driven mechanism, it is necessary to register the corresponding event listener (such as database trigger, API callback function, etc.) according to the event type supported by the data source; its logic is to trigger the event processing logic when the event occurs and obtain data from the data source. According to the selected mechanism, read the original logistics data related to the quality of logistics services from the data source, including: transportation cost records, records of the integrity of goods delivered each time, customer evaluation texts, inventory quantity and in and out time records, vehicle load and vehicle capacity for each transportation, etc.; store the read data in a suitable storage medium (such as database, file system, cloud storage, etc.), and perform necessary data processing and analysis. The advantage of the event-driven mechanism is high real-time performance, which can obtain data immediately when the data is updated, and is suitable for scenarios with high requirements for data real-time performance; it avoids the problem of resource waste in the polling mechanism and improves the performance and efficiency of the system.

[0058] This embodiment can realize real-time acquisition and processing of logistics data by pre-connecting to the data source and using a polling mechanism or an event-driven mechanism to read the original logistics data from the data source, thereby providing strong support for subsequent logistics service quality analysis and optimization.

[0059] See also Figure 3 The third embodiment of the logistics service quality index data management method in the embodiment of the present invention includes:

[0060] S210, detecting whether there is a null value in the original logistics data, and if so, directly deleting the null value or filling the null value with a mean value;

[0061] S220, detecting whether there are abnormal values ​​in the original logistics data, and if so, directly deleting the abnormal values ​​or correcting the abnormal values;

[0062] S230. After the null values ​​and abnormal values ​​in the original logistics data are processed, the original logistics data is converted into a numerical type with a unified format.

[0063] Specifically, traverse the original logistics data and check whether there are null values ​​in each field. As an example, you can use the null value detection function in the programming language (such as is None or ==np.nan in Python) to perform detection. If the proportion of null values ​​is low and has little impact on subsequent analysis, you can choose to directly delete the records containing null values; if the null values ​​need to be filled to maintain the integrity of the data, you can calculate the mean of the field and use the mean to fill the null values. This embodiment can improve the accuracy of the data by detecting and processing null values, and avoid null values ​​from interfering with subsequent data analysis and model training. Mean filling can maintain the integrity of the data and avoid the reduction of data volume due to the deletion of null values, and will not introduce too much noise.

[0064] This embodiment can use statistical methods (such as the 3σ principle, box plots, etc.) to detect outliers in the original logistics data, and set a reasonable outlier detection threshold based on business logic and actual conditions. If the outliers have a large impact on subsequent analysis and cannot be reasonably corrected, you can choose to delete the records containing the outliers; if the outliers can be corrected through business logic (such as anomalies caused by data entry errors), perform correction operations. This embodiment can improve the accuracy and reliability of data by detecting and processing outliers, and avoid misleading subsequent data analysis and model training by outliers. Correcting outliers can preserve the integrity of the data while improving the quality of the data, providing stronger support for subsequent analysis and modeling.

[0065] According to the needs of subsequent analysis and modeling, determine the numerical type (such as integer, floating point, etc.) that needs to be converted for each field. As an example, the data type conversion function in the programming language (such as int(), float(), etc. in Python) can be used to convert data. For fields that need to retain decimal points, you can choose to convert to a floating point type; for fields that only need the integer part, you can choose to convert to an integer type. Make sure that all fields of the same type have the same format (such as decimal places, thousands separators, etc.). This embodiment can facilitate subsequent data processing and model training by converting data into a numerical type with a unified format, and improve the readability and processability of the data; the unified format can ensure the consistency and accuracy of the data during the analysis and modeling process, and avoid errors and deviations caused by inconsistent data formats.

[0066] This embodiment can improve the accuracy, reliability and readability of data by detecting and processing null values ​​and abnormal values ​​in the original logistics data, and converting the data into a numerical type with a unified format, thereby providing stronger support for subsequent data analysis and model training.

[0067] See also Figure 4 The fourth embodiment of the method for managing the logistics service quality index data of express delivery in the embodiment of the present invention includes:

[0068] S310. Pre-design an algorithm formula for logistics service quality index data, where: scheduled collection rate = number of express parcels collected within the specified time / total number of express parcels × 100%; delivery rate = number of express parcels successfully delivered within the specified time / total number of express parcels attempted to be delivered × 100%; intact rate of goods = number of intact delivered goods / total number of delivered goods × 100%; inventory turnover rate = sales cost / average inventory × 100%; transportation full load rate = actual vehicle load / vehicle rated load × 100%; obtain customer evaluation text from the customer feedback system;

[0069] S320, pre-designing a network model of logistics service quality index data, wherein the network model is used to receive customer evaluation texts and output corresponding sentiment tendency categories, wherein the sentiment tendency categories include customer satisfaction and customer dissatisfaction;

[0070] S330. Input the pre-processed logistics data into the preset algorithm formula and algorithm model accordingly, and output corresponding logistics service quality indicator data.

[0071] Specifically, according to the needs of logistics service quality evaluation, the indicators such as scheduled collection rate, delivery rate, cargo integrity rate, inventory turnover rate and transportation full load rate are defined, and the algorithm formula is designed: Scheduled collection rate: the number of express deliveries collected within the specified time / the total number of express deliveries × 100%. The scheduled collection rate is calculated by counting the number of express deliveries collected within the specified time and the total number of express deliveries. Delivery rate: the number of express deliveries successfully delivered within the specified time / the number of all express deliveries attempted to be delivered × 100%. The delivery rate is calculated by counting the number of express deliveries successfully delivered within the specified time and the number of all express deliveries attempted to be delivered. Cargo integrity rate: the number of intact goods delivered / the total number of delivered goods × 100%. The cargo integrity rate is calculated by counting the number of intact goods delivered and the total number of delivered goods. Inventory turnover rate: sales cost / average inventory × 100%. The inventory turnover rate is calculated by counting the sales cost and the average inventory. Transportation full load rate: actual vehicle load / rated vehicle load × 100%. The transportation full load rate is calculated by counting the actual vehicle load and the rated vehicle load.

[0072] This embodiment can quantify the logistics service quality indicators by designing an algorithm formula, providing an objective basis for subsequent evaluation and improvement. Indicators such as the on-time collection rate and the delivery rate can reflect the efficiency and punctuality of the logistics service, helping customers better understand the level of logistics services.

[0073] Pre-design the network model of logistics service quality indicator data, obtain customer evaluation text from the customer feedback system, and perform preprocessing (such as word segmentation, removal of stop words, etc.); select a suitable text classification algorithm to build the network model; design the input layer, hidden layer and output layer structure of the network model according to the characteristics of the customer evaluation text and classification requirements; use the labeled customer evaluation text data set to train the model, and adjust the model parameters to improve classification accuracy; input the preprocessed customer evaluation text into the trained network model, and output the corresponding sentiment tendency category (customer satisfaction or customer dissatisfaction).

[0074] By designing a network model, we can automatically analyze the sentiment of customer evaluation texts and improve the efficiency and accuracy of customer feedback processing. Timely understanding of customer satisfaction and dissatisfaction can help logistics service providers improve service quality and increase customer satisfaction.

[0075] Clean, convert and format the original logistics data to ensure that the data meets the input requirements of the algorithm formula and network model, and input the pre-processed logistics data into the preset algorithm formula and network model accordingly; according to the calculation results of the algorithm formula and network model, output the corresponding logistics service quality indicator data (such as on-time collection rate, delivery rate, cargo integrity rate, etc.) and emotional tendency category (customer satisfaction or customer dissatisfaction).

[0076] This embodiment can automatically calculate the logistics service quality index and analyze the customer feedback sentiment tendency by inputting the pre-processed logistics data into the preset algorithm formula and network model, thereby improving the evaluation efficiency and accuracy. The output index data can be used to monitor and improve the logistics service quality, helping customers to better understand the level of logistics services and existing problems. At the same time, the output of sentiment tendency categories helps logistics service providers to understand customer needs in a timely manner and improve service quality.

[0077] This embodiment pre-designs the algorithm formula and network model of logistics service quality index data, and inputs the pre-processed logistics data into these formulas and models accordingly, so as to realize the automatic evaluation of logistics service quality and the emotional tendency analysis of customer feedback. This helps to improve the efficiency and quality of logistics services and enhance customer satisfaction.

[0078] See also Figure 5 The fifth embodiment of the logistics service quality indicator data management in the embodiment of the present invention includes:

[0079] S321, after cleaning and format conversion of the collected customer evaluation text, pre-processed customer evaluation text data is obtained;

[0080] S322, marking the sentiment tendency of the pre-processed customer evaluation text, and dividing the customer evaluation text data into two categories: customer satisfaction and customer dissatisfaction;

[0081] S323, constructing an initial network recognition model including an embedding layer, an LSTM layer and a fully connected layer, and setting hyperparameters of the initial network recognition model, wherein the hyperparameters include, for example, a learning rate, a batch size, and a number of training rounds;

[0082] S324, using the annotated pre-processed customer evaluation text to train the initial network recognition model, updating the parameters of the initial network recognition model through a back propagation algorithm and a gradient descent optimizer, and obtaining a trained network recognition model;

[0083] S325, pre-processing the customer evaluation text to be predicted and inputting it into the trained network recognition model to output the sentiment tendency prediction type.

[0084] Specifically, first, clean the collected customer review texts, for example, remove irrelevant characters in the customer review texts, such as punctuation marks, special symbols, HTML tags, etc.; handle spelling mistakes and grammar mistakes in the texts to restore the true review intention as much as possible; remove stop words, that is, those high-frequency words that contribute nothing to the text sentiment analysis, such as "de", "le", "zai", etc. After that, convert the texts into a unified encoding format, such as UTF-8; perform word segmentation on the texts to cut the continuous texts into independent words or phrases; according to needs, convert the texts into a format suitable for model input, such as word vectors or sentence vectors. The cleaned text data is cleaner and more accurate, which can reduce the impact of noise on subsequent analysis; the text data after format conversion is more unified and standardized, facilitating the subsequent processing and analysis of the model.

[0085] In this embodiment, professional personnel can be invited or a crowdsourcing platform can be used to label the sentiment of the preprocessed customer review texts. During the labeling process, it is necessary to ensure the consistency and accuracy of the labeling to avoid ambiguity or errors. After that, the labeled customer review text data is divided into a training set and a test set for subsequent model training and verification. Through sentiment labeling, accurate training data can be obtained, providing a reliable basis for model training. Data division helps to evaluate the generalization ability of the model and ensure the performance of the model in actual applications.

[0086] In this embodiment, use a deep learning framework (such as TensorFlow, PyTorch, etc.) to build an initial network recognition model including an embedding layer, an LSTM layer, and a fully connected layer. The embedding layer is used to convert the text into word vectors, the LSTM layer is used to capture the temporal dependencies in the text, and the fully connected layer is used to output the sentiment category. According to the requirements of the model and the characteristics of the data, set appropriate hyperparameters, such as learning rate, batch size, number of training epochs, etc. The setting of hyperparameters has an important impact on the performance and training speed of the model, and sufficient experiments and adjustments are required. By building a deep learning model, the feature representation in the text can be automatically learned, improving the accuracy of sentiment analysis. Appropriate hyperparameter settings can accelerate the training process of the model, improving the convergence speed and performance of the model.

[0087] Next, convert the labeled preprocessed customer review texts into the input format required by the model, and use the backpropagation algorithm and gradient descent optimizer to train the initial network recognition model; during the training process, monitor indicators such as the loss function and accuracy of the model, and adjust the model parameters and training strategies in a timely manner; use the test set to verify the trained model and evaluate the generalization ability and actual application effect of the model. Through the training process, the model can learn the sentiment feature in the text, improving the accuracy of sentiment analysis; the backpropagation algorithm and gradient descent optimizer can ensure that the model parameters are updated in the correct direction, accelerating the convergence process of the model.

[0088] Finally, the customer evaluation text to be predicted is cleaned, formatted and converted to obtain an input format consistent with the training data; the preprocessed customer evaluation text is input into the trained network recognition model to obtain the sentiment tendency prediction type (customer satisfaction or customer dissatisfaction); according to the prediction results of the model, the corresponding sentiment tendency category and confidence level are output. Through the preprocessing operation, the consistency of the input data and the training data can be ensured, and the prediction accuracy of the model can be improved. The trained network recognition model can quickly and accurately output the sentiment tendency prediction type, providing timely customer feedback information for logistics service providers. This helps logistics service providers to understand customer needs and improve service quality in a timely manner, thereby enhancing customer satisfaction and loyalty.

[0089] See also Figure 6 The sixth embodiment of the logistics service quality indicator data management in the embodiment of the present invention includes:

[0090] S401, using a filtering algorithm to perform denoising on the logistics service quality index data;

[0091] S402: Smoothing the logistics service quality index data using an exponential smoothing method.

[0092] Specifically, according to the characteristics and noise type of the logistics service quality index data, select the appropriate filtering algorithm, such as mean filtering, median filtering, Gaussian filtering, etc. First, according to the actual situation of the data and the filtering requirements, determine the parameters of the filtering algorithm, such as window size, threshold, etc.; input the logistics service quality index data into the selected filtering algorithm to denoise the data; the filtering algorithm will traverse the data, smooth and denoise the data according to the set parameters and rules; obtain the denoised logistics service quality index data for subsequent analysis and processing. Through the processing of the filtering algorithm, the noise and outliers in the logistics service quality index data can be effectively removed, and the accuracy and reliability of the data can be improved. The denoised data is smoother and more stable, which helps to more accurately reflect the actual quality and level of logistics services; improve the accuracy and reliability of subsequent data analysis, and provide more accurate decision support for logistics service providers.

[0093] This embodiment also uses exponential smoothing to smooth the logistics service quality index data. Specifically, according to the characteristics of the logistics service quality index data and the smoothing requirements, a suitable smoothing coefficient α (0<α<1) is selected. The smoothing coefficient α determines the degree of smoothing. The larger the α, the more obvious the smoothing effect, but at the same time, some detailed information may be lost. Usually, the first data point is used as the initial smoothing value, or it is set according to the average value of the first few data points; the exponential smoothing formula is used to smooth the data. The formula is generally: St =α*Y t +(1-α)*S t -1, where S t is the smoothed value of the tth period, Y t is the original data of the tth period, α is the smoothing coefficient; traverse the entire data set and calculate the smoothing value of each data point in turn; obtain the smoothed logistics service quality index data for subsequent analysis and display. Through the processing of exponential smoothing, random fluctuations and short-term changes in the data can be eliminated, and the long-term trends and laws of the data can be highlighted. The smoothed data is easier to understand and analyze, which helps logistics service providers better grasp the changing trends and laws of logistics service quality.

[0094] This embodiment uses filtering algorithm and exponential smoothing method to process logistics service quality index data, which can effectively improve the accuracy and reliability of data.

[0095] See also Figure 7 The seventh embodiment of the logistics service quality indicator data management in the embodiment of the present invention includes:

[0096] S410, converting the logistics service quality indicator data into chart data according to the characteristics and display requirements of the logistics service quality indicator data, wherein the types of the chart data include line charts, bar charts or pie charts;

[0097] S420, pre-designing the overall layout of the display interface, embedding the generated chart data into the corresponding position of the display interface to display it to the user.

[0098] Specifically, first collect and organize the data of logistics service quality indicators such as the scheduled collection rate, delivery rate, intact cargo rate, customer satisfaction, inventory turnover rate, and transportation full load rate; according to the nature of the data and the display requirements, classify the data into time series data (such as the changes in the scheduled collection rate and inventory turnover rate over time), classification data (such as the delivery rate in different months, the intact cargo rate of different products), or proportion data (such as the proportion of different evaluation levels in customer satisfaction, and the proportion of different full load levels in transportation full load rate). For time series data, select a line chart to show the trend of data changes, such as the changes in the scheduled collection rate and inventory turnover rate over time. For classification data, select a bar chart to compare data of different categories, such as the delivery rate in different months or the intact cargo rate of different products. For proportion data, select a pie chart to show the proportion of each part, such as the proportion of different evaluation levels in customer satisfaction or the proportion of different full load levels in transportation full load rate.

[0099] Perform necessary cleaning, format conversion and preprocessing on the raw data to ensure the accuracy and consistency of the data. Use chart generation tools (such as Excel, Tableau, Python's matplotlib, etc.) to generate charts according to the selected chart type. When generating charts, pay attention to setting parameters such as axes, titles, legends, colors, etc. to ensure the clarity and readability of the charts. According to the characteristics of the data and display requirements, further optimize the generated charts, such as adjusting the size, scale, font, etc. of the charts to improve the visual effect and attractiveness of the charts.

[0100] This embodiment converts the logistics service quality index data into chart data, which can intuitively display the data change trend, compare different categories of data, and display the proportion of each part, which helps users to quickly understand and analyze the data. Different chart types can highlight different aspects of the displayed data, meet the diverse display needs of users, and improve the usability and value of the data.

[0101] This embodiment can also design the overall layout of the display interface according to user needs and display content. The layout should be concise and clear, and easy for users to browse and operate. You can consider using grid layout, card layout or flow layout, etc. Determine the theme, style, color, etc. of the display interface to create a comfortable visual effect, and you can choose colors and elements related to logistics services to enhance the professionalism and attractiveness of the interface. Embed the generated chart data into the corresponding position of the display interface, and adjust the size, position, arrangement, etc. of the chart according to the layout and display requirements to ensure that the chart is consistent with other elements of the interface. Add necessary instructions and annotations to the chart, such as titles, axis labels, legends, etc., to help users better understand the content and meaning of the chart. Further, according to needs, interactive functions can be added to the display interface, such as hovering the mouse to display data details, clicking on the chart to filter or jump data, etc. The interactive function can enhance the user's sense of participation and experience, so that users can have a deeper understanding and grasp of the logistics service quality indicator data. You can consider adding data filtering, sorting, exporting and other functions to meet the different needs and operating habits of users. By pre-designing the overall layout of the display interface, it is possible to ensure that the display content is clear, orderly and beautiful, and improve the user's browsing experience. The rationality and professionalism of the layout can also enhance users' trust and recognition of logistics services. Embedding the generated chart data into the corresponding position of the display interface can facilitate users to directly view and analyze the data without additional data processing and conversion steps. This helps to improve the availability and value of data, allowing users to make decisions and take actions faster. Adding interactive functions can enhance user participation and interactivity, allowing users to have a deeper understanding and grasp of the logistics service quality indicator data. Interactive functions can also meet the different needs and operating habits of users, and improve user satisfaction and loyalty.

[0102] This embodiment can display the logistics service quality index data to users in an intuitive, clear and interactive way, improve the availability and value of the data, and enhance the user experience and satisfaction. This helps logistics service providers better understand and grasp the quality and efficiency of logistics services.

[0103] The above describes the logistics service quality index data management method in the embodiment of the present invention. The following describes the logistics service quality index data management device in the embodiment of the present invention. Figure 8 In one embodiment of the present invention, a logistics service quality index data management device includes:

[0104] A reading module 10, used for reading raw logistics data related to logistics service quality from a pre-connected data source;

[0105] The processing module 20 is used to clean and format the raw logistics data to obtain pre-processed logistics data;

[0106] The calculation module 30 is used to calculate the pre-processed logistics data according to different preset algorithm formulas and network models, and output corresponding logistics service quality index data, wherein the logistics service quality index data includes: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate;

[0107] The display module 40 is used to convert the logistics service quality indicator data into a chart type and display the chart type to the user through a display interface.

[0108] The present invention realizes the automated management of logistics service quality index data, effectively improves work efficiency, reduces the probability of human error, and enables logistics companies to understand the service quality status more timely and accurately, and then take corresponding measures to improve service quality.

[0109] See also Fig. 9 Another embodiment of the logistics service quality index data management device in the embodiment of the present invention includes:

[0110] A reading module 10, used for reading raw logistics data related to logistics service quality from a pre-connected data source;

[0111] The processing module 20 is used to clean and format the raw logistics data to obtain pre-processed logistics data;

[0112] The calculation module 30 is used to calculate the pre-processed logistics data according to different preset algorithm formulas and network models, and output corresponding logistics service quality index data, wherein the logistics service quality index data includes: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate;

[0113] The display module 40 is used to convert the logistics service quality indicator data into a chart type and display the chart type to the user through a display interface.

[0114] In this embodiment, the reading module 10 includes:

[0115] A connection unit 11 is used to pre-connect a data source, wherein the data source includes a logistics system API interface, a logistics database, and a logistics vehicle-mounted sensor;

[0116] The reading unit 12 is used to read the original logistics data related to the logistics service quality from the data source using a polling mechanism or an event-driven mechanism, wherein the original logistics data includes: transportation cost records, records of the integrity of goods for each delivery, customer evaluation texts, inventory quantity and in-and-out time records, and vehicle loading and capacity for each transportation.

[0117] In this embodiment, the processing module 20 includes:

[0118] The first detection unit 21 is used to detect whether there is a null value in the original logistics data. If so, the null value is directly deleted or filled with a mean value;

[0119] A second detection unit 22 is used to detect whether there are abnormal values ​​in the original logistics data, and if so, directly delete the abnormal values ​​or correct the abnormal values;

[0120] The conversion unit 23 is used to convert the original logistics data into a numerical type with a unified format after the null values ​​and abnormal values ​​in the original logistics data are processed.

[0121] In this embodiment, the calculation module 30 includes:

[0122] The formula design unit 31 is used to pre-design the algorithm formula of the logistics service quality index data, wherein, the scheduled collection rate = the number of express deliveries collected within the specified time / the total number of express deliveries × 100%; the delivery rate = the number of express deliveries successfully delivered within the specified time / the number of all express deliveries attempted to be delivered × 100%; the intact rate of goods = the number of intact delivered goods / the total number of delivered goods × 100%; the inventory turnover rate = the sales cost / the average inventory × 100%; the transport full load rate = the actual load of the vehicle / the rated load of the vehicle × 100%; obtain the customer evaluation text from the customer feedback system;

[0123] A model design unit 32 is used to pre-design a network model of logistics service quality index data, wherein the network model is used to receive customer evaluation texts and output corresponding sentiment tendency categories, wherein the sentiment tendency categories include customer satisfaction and customer dissatisfaction;

[0124] The output unit 33 is used to input the pre-processed logistics data into the preset algorithm formula and algorithm model, and output corresponding logistics service quality indicator data.

[0125] In this embodiment, the model design unit 32 includes:

[0126] The preprocessing subunit 321 is used to clean and format the collected customer evaluation text to obtain preprocessed customer evaluation text data;

[0127] The annotation subunit 322 is used to perform sentiment orientation annotation on the pre-processed customer evaluation text, and divide the customer evaluation text data into two categories: customer satisfaction and customer dissatisfaction;

[0128] A construction subunit 323 is used to construct an initial network recognition model including an embedding layer, an LSTM layer, and a fully connected layer, and set hyperparameters of the initial network recognition model, including, for example, a learning rate, a batch size, and a number of training rounds;

[0129] The training subunit 324 is used to train the initial network recognition model using the annotated pre-processed customer evaluation text, and update the parameters of the initial network recognition model through the back propagation algorithm and the gradient descent optimizer to obtain the trained network recognition model;

[0130] The prediction subunit 325 is used to pre-process the customer evaluation text to be predicted and then input it into the trained network recognition model to output the sentiment tendency prediction type.

[0131] In this embodiment, it also includes: an indicator processing module 35, which is used to use a filtering algorithm to perform denoising on the logistics service quality indicator data; and use an exponential smoothing method to smooth the logistics service quality indicator data.

[0132] In this embodiment, the display module 40 includes:

[0133] A chart conversion unit 41, configured to convert the logistics service quality indicator data into chart data according to the characteristics and display requirements of the logistics service quality indicator data, wherein the types of the chart data include a line chart, a bar chart or a pie chart;

[0134] The chart display unit 42 is used to pre-design the overall layout of the display interface and embed the generated chart data into the corresponding position of the display interface to display it to the user.

[0135] The present invention realizes the automated management of logistics service quality index data, effectively improves work efficiency, reduces the probability of human error, and enables logistics companies to understand the service quality status more timely and accurately, and then take corresponding measures to improve service quality.

[0136] above Figure 8 and Fig. 9 The logistics service quality indicator data management device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The logistics service quality indicator data management device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0137] Fig.10 It is a structural diagram of a logistics service quality index data management device provided by an embodiment of the present invention. The logistics service quality index data management device 100 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 11 (for example, one or more processors) and a memory 12, and one or more storage media 13 (for example, one or more massive storage devices) storing application programs 133 or data 132. Among them, the memory 12 and the storage medium 13 can be short-term storage or permanent storage. The program stored in the storage medium 13 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the logistics service quality index data management device 100. Furthermore, the processor 11 can be configured to communicate with the storage medium 13 to execute a series of instruction operations in the storage medium 13 on the logistics service quality index data management device 100.

[0138] The logistics service quality index data management device 100 may also include one or more power supplies 14, one or more wired or wireless network interfaces 15, one or more input and output interfaces 16, and / or one or more operating systems 131, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Fig.10 The device structure shown does not constitute a limitation on the logistics service quality indicator data management device 100, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0139] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the logistics service quality indicator data management method.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0141] If the integrated unit 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 invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0142] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for managing logistics service quality indicator data, characterized in that: The method for managing logistics service quality indicator data includes: Reading raw logistics data related to logistics service quality from pre-connected data sources; Cleaning and format conversion processing are performed on the original logistics data to obtain pre-processed logistics data; The pre-processed logistics data are calculated respectively according to different preset algorithm formulas and network models, and corresponding logistics service quality index data are output, wherein the logistics service quality index data include: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate; The logistics service quality indicator data is converted into a chart type, and the chart type is displayed to the user through a display interface.

2. The method for managing logistics service quality index data according to claim 1, characterized in that: Reading raw logistics data related to logistics service quality from a pre-connected data source includes the following steps: Pre-connecting data sources, including logistics system API interface, logistics database, and logistics vehicle-mounted sensors; The original logistics data related to the logistics service quality is read from the data source using a polling mechanism or an event-driven mechanism, wherein the original logistics data includes: transportation cost records, records of the integrity of goods for each delivery, customer evaluation texts, inventory quantity and in-and-out time records, and vehicle loading and capacity for each transportation.

3. The method for managing logistics service quality index data according to claim 1, characterized in that: The raw logistics data is cleaned and format converted to obtain pre-processed logistics data, including the following steps: Detect whether there is a null value in the original logistics data, and if so, directly delete the null value or fill the null value with a mean value; Detect whether there are abnormal values ​​in the original logistics data, and if so, directly delete the abnormal values ​​or correct the abnormal values; After the null values ​​and abnormal values ​​in the original logistics data are processed, the original logistics data is converted into a numerical type with a unified format.

4. The method for managing logistics service quality index data according to claim 1, characterized in that: The pre-processed logistics data are calculated respectively according to different preset algorithm formulas and network models, and corresponding logistics service quality index data are output, wherein the logistics service quality index data include: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate, including the steps of: The algorithm formula for logistics service quality index data is designed in advance, among which, the on-time collection rate = the number of express parcels collected within the specified time / the total number of express parcels × 100%; the delivery rate = the number of express parcels successfully delivered within the specified time / the number of all express parcels attempted to be delivered × 100%; the rate of intact goods = the number of intact goods delivered / the total number of goods delivered × 100%; the inventory turnover rate = the cost of sales / the average inventory × 100%; the transport full load rate = the actual load of the vehicle / the rated load of the vehicle × 100%; obtain the customer evaluation text from the customer feedback system; Pre-designing a network model of logistics service quality index data, wherein the network model is used to receive customer evaluation texts and output corresponding sentiment tendency categories, wherein the sentiment tendency categories include customer satisfaction and customer dissatisfaction; The pre-processed logistics data is input into the preset algorithm formula and algorithm model accordingly, and the corresponding logistics service quality indicator data is output.

5. The method for managing logistics service quality index data according to claim 4, characterized in that: A network model of logistics service quality index data is pre-designed, wherein the network model is used to receive customer evaluation texts and output corresponding sentiment tendency categories, wherein the sentiment tendency categories include customer satisfaction and customer dissatisfaction, and includes the steps of: After cleaning and format conversion of the collected customer evaluation texts, pre-processed customer evaluation text data is obtained; Performing sentiment labeling on the preprocessed customer evaluation text, and dividing the customer evaluation text data into two categories: customer satisfaction and customer dissatisfaction; Construct an initial network recognition model including an embedding layer, an LSTM layer, and a fully connected layer, and set hyperparameters of the initial network recognition model, including learning rate, batch size, and number of training rounds; The initial network recognition model is trained using the annotated pre-processed customer evaluation texts, and the parameters of the initial network recognition model are updated through the back propagation algorithm and the gradient descent optimizer to obtain the trained network recognition model; The customer evaluation text to be predicted is preprocessed and then input into the trained network recognition model to output the sentiment tendency prediction type.

6. The method for managing logistics service quality index data according to claim 1, characterized in that: After outputting the corresponding logistics service quality indicator data, the following steps are also included: Using a filtering algorithm to perform denoising on the logistics service quality indicator data; The exponential smoothing method is used to smooth the logistics service quality index data.

7. The method for managing logistics service quality index data according to claim 1, characterized in that: Converting the logistics service quality indicator data into chart data, and displaying the chart data to the user through a display interface, comprises the steps of: According to the characteristics and display requirements of the logistics service quality indicator data, the logistics service quality indicator data is converted into chart data, and the types of the chart data include line charts, bar charts or pie charts; The overall layout of the display interface is designed in advance, and the generated chart data is embedded in the corresponding position of the display interface to be displayed to the user.

8. A logistics service quality index data management device, characterized in that: include: A reading module, used for reading raw logistics data related to logistics service quality from a pre-connected data source; A processing module, used for cleaning and format conversion of the raw logistics data to obtain pre-processed logistics data; A calculation module, used to calculate the pre-processed logistics data according to different preset algorithm formulas and network models, and output corresponding logistics service quality index data, wherein the logistics service quality index data includes: on-time collection rate, delivery rate, cargo integrity rate, customer satisfaction, inventory turnover rate, and transportation full load rate; The display module is used to convert the logistics service quality indicator data into a chart type and display the chart type to the user through a display interface.

9. A logistics service quality index data management device, characterized in that: comprising a memory and at least one processor, wherein the memory has computer-readable instructions stored therein; The at least one processor calls the computer-readable instructions in the memory to execute the various steps of the logistics service quality indicator data management method as described in any one of claims 1-7.

10. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the various steps of the logistics service quality indicator data management method as described in any one of claims 1-7 are implemented.

Images