Logistics order notification optimization method and device, equipment and medium

Abstract

The invention provides a notification optimization method and device for a logistics order, equipment and a medium. The method comprises the steps of obtaining user basic data based on a logistics system, user account information and a third-party social platform; preprocessing the obtained user basic data to obtain preprocessed user basic data; constructing a logistics order notification model; obtaining a notification plan by using a logistics order notification model based on the preprocessed user basic data; monitoring the current scene in real time, and dynamically adjusting the notification plan based on the current scene monitored in real time; the logistics order notification model comprises a user behavior prediction model and a notification effect optimization model, the current user behavior prediction model is utilized to predict a user receiving time window, then the notification effect optimization model is utilized to analyze the response probability of the user to different notification channels, and the notification channel with the highest response probability is identified. According to the method, accurate prediction of the user preference and the optimal notification time is realized, so that the reaching rate of the notification and the satisfaction degree of the user are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics order notification optimization, and in particular to a logistics order notification optimization method, device, equipment and medium. Background Art

[0002] With the booming development of e-commerce, the volume of express delivery business has increased dramatically, but the delivery notification arrival rate and user experience have become pain points in the industry. Traditional notification methods such as SMS and phone calls often fail due to user rejection, message blocking, number change and other issues. Therefore, a more intelligent, personalized and efficient express delivery notification solution is urgently needed. Summary of the invention

[0003] The main purpose of the present invention is to solve the problem of low arrival rate of express delivery notification in the prior art.

[0004] A first aspect of the present invention provides a notification optimization method for a logistics order, comprising:

[0005] Obtain basic user data based on logistics systems, user account information, and third-party social platforms;

[0006] Preprocessing the acquired user basic data to obtain preprocessed user basic data;

[0007] Build a logistics order notification model;

[0008] Based on the pre-processed user basic data, the notification plan is obtained using the logistics order notification model;

[0009] Monitor the current situation in real time and dynamically adjust the notification plan based on the current situation monitored in real time;

[0010] The logistics order notification model includes a user behavior prediction model and a notification effect optimization model. The current user behavior prediction model is used to predict the user's delivery time window, and then the notification effect optimization model is used to analyze the user's response probability to different notification channels, and identify the notification channel with the highest response probability.

[0011] Optionally, in a first implementation of the first aspect of the present invention, the obtaining of basic logistics data based on a logistics system, user account information, and a third-party social platform includes:

[0012] Based on the logistics system, the logistics system obtains courier delivery records, recipient basic information, historical delivery addresses, and package status update logs;

[0013] Based on the user account information, preferred delivery time, common contact information, and notification preference settings are obtained;

[0014] Based on the third-party social platform, the user's active time period, interest tags and social relationships are obtained.

[0015] Optionally, in a second implementation manner of the first aspect of the present invention, preprocessing the acquired user basic data to obtain the preprocessed user basic data includes:

[0016] Cleaning the acquired user basic data to obtain cleaned user basic data;

[0017] The cleaning process includes: removing duplicate data, filling missing values, processing outliers and unifying formats;

[0018] The cleaned user basic data is desensitized using data desensitization technology to obtain the desensitized user basic data;

[0019] Formatting the user basic data after the desensitization process to obtain the formatted user basic data;

[0020] The formatting process includes: data type conversion and data standardization process.

[0021] Optionally, in a third implementation of the first aspect of the present invention, the construction of the logistics order notification model includes: a user behavior prediction model and a notification effect optimization model;

[0022] The user behavior prediction model uses time series analysis to predict the user's receipt time window;

[0023] The notification effect optimization model uses a gradient boosting tree to analyze the user's response probability to different notification channels and identifies the notification channel with the highest response probability;

[0024] The notification plan is obtained based on the predicted user receipt time window and the notification channel with the highest probability.

[0025] Optionally, in a fourth implementation of the first aspect of the present invention, real-time monitoring of the current scenario and dynamically adjusting the notification plan based on the real-time monitored current scenario includes:

[0026] Real-time monitoring includes user geographic location, weather conditions, and current social events; and dynamically adjust notification plans based on the current real-time monitoring, including user geographic location, weather conditions, and current social events;

[0027] And automatically generate notification text according to the current notification plan.

[0028] Optionally, in a sixth implementation of the first aspect of the present invention, the method further comprises: when the order status is updated or the package is signed for, triggering the automatic sending of the notification copy;

[0029] During the sending process, record the sending log and notification effect;

[0030] The notification effect is evaluated by setting key performance indicators, wherein the key performance indicators include: notification arrival rate, user satisfaction score and complaint rate;

[0031] The recorded notification effects are used to optimize the logistics order notification model parameters.

[0032] Optionally, in a sixth implementation of the first aspect of the present invention, the method further includes: optimizing the logistics order notification model parameters according to user feedback;

[0033] The user feedback is to obtain user comments, and use text mining technology to analyze the obtained user comments to extract sentiment tendencies and improvement suggestions;

[0034] The logistics order notification model parameters are optimized based on the extracted sentiment tendencies and improvement suggestions.

[0035] A second aspect of the present invention provides a notification optimization device for a logistics order, comprising:

[0036] The data acquisition module is used to obtain basic user data based on the logistics system, user account information and third-party social platforms;

[0037] A preprocessing module, used to preprocess the acquired user basic data to obtain preprocessed user basic data;

[0038] Build a model module to build a logistics order notification model;

[0039] The notification plan acquisition module is used to obtain the notification plan based on the pre-processed user basic data using the logistics order notification model;

[0040] A dynamic adjustment module, used to monitor the current situation in real time and dynamically adjust the notification plan based on the current situation monitored in real time;

[0041] The logistics order notification model includes a user behavior prediction model and a notification effect optimization model. The current user behavior prediction model is used to predict the user's delivery time window, and then the notification effect optimization model is used to analyze the user's response probability to different notification channels, and identify the notification channel with the highest response probability.

[0042] Optionally, in a first implementation of the second aspect of the present invention, the data acquisition module includes:

[0043] Used to obtain express delivery records, recipient basic information, historical delivery addresses and package status update logs based on the logistics system;

[0044] Used to obtain preferred delivery time, common contact information, and notification preference settings based on the user account information;

[0045] Used to obtain the user's active time period, interest tags and social relationships based on the third-party social platform.

[0046] Optionally, in a second implementation of the second aspect of the present invention, the preprocessing module includes:

[0047] The data cleaning submodule is used to clean the acquired user basic data to obtain the cleaned user basic data;

[0048] The cleaning process includes: removing duplicate data, filling missing values, processing outliers and unifying formats;

[0049] The data desensitization submodule is used to perform data desensitization on the cleaned user basic data using data desensitization technology to obtain the desensitized user basic data;

[0050] The data formatting submodule is used to format the user basic data after the desensitization process to obtain the formatted user basic data;

[0051] The formatting process includes: data type conversion and data standardization process.

[0052] Optionally, in a third implementation of the second aspect of the present invention, the construction of the logistics order notification model includes: a user behavior prediction model and a notification effect optimization model;

[0053] The user behavior prediction model uses time series analysis to predict the user's receipt time window;

[0054] The notification effect optimization model uses a gradient boosting tree to analyze the user's response probability to different notification channels and identifies the notification channel with the highest response probability;

[0055] The notification plan is obtained based on the predicted user receipt time window and the notification channel with the highest probability.

[0056] Optionally, in a fourth implementation of the second aspect of the present invention, the dynamic adjustment module includes: for real-time monitoring of the user's geographic location, weather conditions, and current social events; and dynamically adjusting the notification plan based on the current real-time monitoring of the user's geographic location, weather conditions, and current social events;

[0057] And automatically generate notification text according to the current notification plan.

[0058] Optionally, in a sixth implementation of the second aspect of the present invention, the device further includes: an automatic sending module, configured to trigger automatic sending of the notification copy when the order status is updated or the package is signed for;

[0059] During the sending process, record the sending log and notification effect;

[0060] The notification effect is evaluated by setting key performance indicators, wherein the key performance indicators include: notification arrival rate, user satisfaction score and complaint rate;

[0061] The recorded notification effects are used to optimize the logistics order notification model parameters.

[0062] Optionally, in a sixth implementation of the second aspect of the present invention, the device further includes: a model optimization module, configured to optimize the logistics order notification model parameters according to user feedback;

[0063] The user feedback is to obtain user comments, and use text mining technology to analyze the obtained user comments to extract sentiment tendencies and improvement suggestions;

[0064] The logistics order notification model parameters are optimized based on the extracted sentiment tendencies and improvement suggestions.

[0065] A third aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for optimizing the notification of logistics orders.

[0066] A fourth aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-mentioned method for optimizing the notification of logistics orders.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. The present invention obtains user data from multiple sources such as logistics systems, user account information, and third-party social platforms; uses historical data to train user behavior prediction models and notification effect optimization models; generates personalized notification plans based on user characteristics and current situations; and continuously adjusts and optimizes model parameters based on notification effects and user feedback to improve notification reach and user experience;

[0069] 2. The present invention achieves accurate prediction of user preferences and optimal notification time, thereby significantly improving notification reach and user satisfaction;

[0070] 3. The present invention continuously optimizes model parameters through notification effects and user feedback, thereby improving notification trigger rate and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0072] Figure 1 A first flow chart of a notification optimization method for logistics orders provided by an embodiment of the present invention;

[0073] Figure 2 A second flow chart of the notification optimization method for logistics orders provided by an embodiment of the present invention;

[0074] Figure 3 A schematic diagram of the structure of a notification optimization device for logistics orders provided by an embodiment of the present invention;

[0075] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The embodiment of the present invention provides a notification optimization method, device, equipment and medium for logistics orders, which obtains user basic data based on the logistics system, user account information and third-party social platforms; pre-processes the obtained user basic data to obtain the pre-processed user basic data; constructs a logistics order notification model, which includes a user behavior prediction model and a notification effect optimization model, uses the current user behavior prediction model to predict the user's delivery time window, and then uses the notification effect optimization model to analyze the user's response probability to different notification channels, and identifies the notification channel with the highest response probability; based on the pre-processed user basic data, uses the logistics order notification model to obtain a notification plan; monitors the current scenario in real time, and dynamically adjusts the notification plan based on the current scenario monitored in real time; and then continuously adjusts the optimization model parameters according to the notification effect and user feedback. The present invention solves the problem of low arrival rate of express delivery notifications in the prior art.

[0077] 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.

[0078] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the notification optimization method for logistics orders in the embodiment of the present invention includes:

[0079] 101. Obtain basic user data based on logistics systems, user account information, and third-party social platforms;

[0080] In this embodiment, the logistics system obtains express delivery records, recipient basic information, historical delivery addresses, and package status update logs, which are helpful for understanding the user's receiving habits and package circulation conditions;

[0081] Based on the user account information, the preferred delivery time, common contact information and notification preference settings are obtained, which directly reflects the user's basic needs and expectations;

[0082] Based on the third-party social platform, the user's active time periods, interest tags, and social relationships are obtained, and the user builds a more three-dimensional user portrait.

[0083] 102. Preprocess the acquired user basic data to obtain preprocessed user basic data;

[0084] In this embodiment, the acquired user basic data is cleansed to obtain cleaned user basic data;

[0085] The cleaning process includes: removing duplicate data, filling missing values, processing outliers and unifying formats;

[0086] The cleaned user basic data is desensitized using data desensitization technology to obtain the desensitized user basic data;

[0087] Formatting the user basic data after the desensitization process to obtain the formatted user basic data;

[0088] The formatting process includes: data type conversion and data standardization process.

[0089] This embodiment uniformly formats and integrates data from different sources to facilitate subsequent analysis.

[0090] 103. Build a logistics order notification model;

[0091] In this embodiment, the construction of the logistics order notification model includes: a user behavior prediction model and a notification effect optimization model;

[0092] The user behavior prediction model uses time series analysis to predict the user's receipt time window;

[0093] The notification effect optimization model uses a gradient boosting tree to analyze the user's response probability to different notification channels and identifies the notification channel with the highest response probability;

[0094] The notification plan is obtained based on the predicted user receipt time window and the notification channel with the highest probability.

[0095] In this embodiment, the notification effect optimization model is a regression model that establishes the relationship between notification delivery rate, opening rate, user feedback and notification strategy. An A / B testing strategy is adopted to conduct a small-scale verification of the optimal notification solution predicted by the model and collect actual effect data.

[0096] 104. Based on the pre-processed user basic data, the notification plan is obtained using the logistics order notification model;

[0097] 105. Monitor the current situation in real time and dynamically adjust the notification plan based on the current situation monitored in real time;

[0098] In this embodiment, real-time monitoring includes user geographic location, weather conditions, and current social events; and the notification plan is dynamically adjusted based on the current real-time monitoring including user geographic location, weather conditions, and current social events; for example: adjusting notification content and timing due to large-scale events to ensure the timeliness and relevance of the notification.

[0099] And automatically generate notification text according to the current notification plan.

[0100] This embodiment can achieve accurate prediction of user preferences and optimal notification time, thereby significantly improving the notification delivery rate and user satisfaction.

[0101] See also Figure 2 The second embodiment of the notification optimization method for logistics orders in the embodiment of the present invention includes:

[0102] 201. Obtaining basic user data based on logistics systems, user account information, and third-party social platforms;

[0103] In this embodiment, logistics system data: including express delivery records, recipient basic information, historical delivery addresses, package status update logs, etc., these data are helpful to understand the user's receiving habits and package circulation. User account information: user registration information on the express company's official website or APP, such as preferred delivery time, common contact information, notification preference settings, etc., directly reflects the user's basic needs and expectations. Third-party social platform data: access to social platforms such as WeChat and Weibo through legal and compliant data sharing agreements, collect users' active time periods, interest tags, social relationships, etc., to build a more three-dimensional user portrait. Public data sources: such as weather forecasts, holiday arrangements, etc., these external factors may affect users' receiving habits and notification acceptance.

[0104] 202. Clean the acquired user basic data to obtain cleaned user basic data;

[0105] In this embodiment, the collected data is deduplicated, outliers are processed, and missing values ​​are filled to ensure data quality. Data desensitization technology is used to protect user privacy, such as anonymizing sensitive information. A data warehouse is built to uniformly format and integrate data from different sources for subsequent analysis.

[0106] 203. Build a logistics order notification model;

[0107] In this embodiment, the logistics order notification model includes: a user behavior prediction model and a notification effect optimization model;

[0108] Specifically, we use time series analysis to predict the user's possible future time window for receiving emails; we use the gradient boosting tree to analyze the user's response probability to different notification channels and identify the most effective notification method;

[0109] At the same time, sentiment analysis technology can be combined to predict the impact of specific notification content on user emotions and avoid negative experiences.

[0110] Among them, the notification effect optimization model is a regression model that establishes the relationship between notification delivery rate, opening rate, user feedback and notification strategy. Using the A / B testing strategy, the optimal notification solution predicted by the model is verified on a small scale to collect actual effect data.

[0111] Ensemble learning methods fuse multiple weak models to improve prediction accuracy and robustness.

[0112] Through in-depth analysis of user behavior patterns, such as differences in receiving preferences on weekdays and weekends, special needs of urgent packages, etc., clustering algorithms are used to divide users into different groups, such as immediate response type, evening peak preference type, etc., and specific strategies are formulated for each group.

[0113] 204. Based on the pre-processed user basic data, a notification plan is obtained using a logistics order notification model;

[0114] 205. Monitor the current situation in real time and dynamically adjust the notification plan based on the current situation monitored in real time;

[0115] In this embodiment, the user's geographic location, weather conditions, etc. are monitored in real time to dynamically adjust the notification strategy. For example, indoor receiving point notifications are recommended first on rainy days. The notification content and timing are adjusted in conjunction with current social events (such as large-scale events) to ensure the timeliness and relevance of the notification.

[0116] Customized notification content: Automatically generate notification text containing personalized information based on user preferences and context, such as "Zhang San, your express delivery has arrived at the smart cabinet at the entrance of the community, please check it."

[0117] 206. Continuously adjust and optimize model parameters based on notification effects and user feedback;

[0118] In this embodiment, key performance indicators (KPIs) are set up, such as notification arrival rate, user satisfaction score, complaint rate, etc., to regularly evaluate the effectiveness of the notification strategy. A real-time monitoring system is implemented to capture abnormal notification events, such as high frequency of unread notifications, and intervene and adjust in time.

[0119] User feedback mechanism: Establish convenient user feedback channels to encourage users to provide direct feedback on notification services, such as one-click evaluation and suggestion submission functions. Use text mining technology to analyze user comments, extract sentiment tendencies and improvement suggestions as the basis for model optimization.

[0120] Parameter tuning and model iteration: Based on feedback data, use online learning algorithms to gradually adjust model parameters to achieve self-optimization. Regularly review model performance, introduce new feature variables or algorithm models, and maintain technological cutting-edge capabilities to respond to changes in user habits and new market demands.

[0121] In this embodiment, the new automatic sending configuration is added to set the sending time interval, the sending time interval on holidays, and whether to resend the SMS the next day.

[0122] Sending interval: Select by time, sending start time options: 7:30, 8:30, 9:30, sending end time, 7:30-24 o'clock, one option every 5 minutes.

[0123] Holiday sending interval: (optional) Select by time, sending start time options: 7:30, 8:30, 9:30, sending end time, 7:30-24:00, one option every 5 minutes.

[0124] Reissue during non-sending period: The default setting is "No". After reissue is set, the order number distributed or received during non-sending period will be reissued the next day.

[0125] The above describes the notification optimization method for logistics orders in the embodiment of the present invention. The following describes the notification optimization device for logistics orders in the embodiment of the present invention. Figure 3 In one embodiment of the present invention, a notification optimization device for logistics orders includes:

[0126] The data acquisition module 301 is used to acquire basic user data based on the logistics system, user account information and a third-party social platform;

[0127] Specifically, the data acquisition module 301 includes:

[0128] The logistics system obtains data including courier delivery records, recipient basic information, historical delivery addresses, and package status update logs, which are helpful for understanding user delivery habits and package circulation conditions;

[0129] Based on the user account information, the preferred delivery time, common contact information and notification preference settings are obtained, which directly reflects the user's basic needs and expectations; in this embodiment, it can be obtained through the user's registration information on the express company's official website or APP.

[0130] Based on the third-party social platform, the user's active time period, interest tags and social relationships are obtained, and the user builds a more three-dimensional user portrait; in this embodiment, social platforms such as WeChat and Weibo are accessed through legal and compliant data sharing agreements to collect relevant user data;

[0131] In this embodiment, other public data sources are also included, such as weather forecasts, holiday schedules, etc., and these data may affect the user's receiving habits and notification acceptance.

[0132] A preprocessing module 302 is used to preprocess the acquired user basic data to obtain preprocessed user basic data;

[0133] Specifically, the preprocessing module 302 includes:

[0134] The data cleaning submodule 3021 is used to clean the acquired user basic data to obtain the cleaned user basic data;

[0135] The cleaning process includes: removing duplicate data, filling missing values, processing outliers and unifying formats;

[0136] The data desensitization submodule 3022 is used to perform data desensitization processing on the cleaned user basic data using data desensitization technology to obtain the desensitized user basic data;

[0137] The data formatting submodule 3023 is used to format the user basic data after the desensitization process to obtain the formatted user basic data;

[0138] The formatting process includes: data type conversion and data standardization process.

[0139] This embodiment uniformly formats and integrates data from different sources to facilitate subsequent analysis.

[0140] A model building module 303 is used to build a logistics order notification model;

[0141] Specifically, the model building module 303 includes:

[0142] User behavior prediction model and notification effect optimization model;

[0143] The user behavior prediction model uses time series analysis to predict the user's receipt time window;

[0144] The notification effect optimization model uses a gradient boosting tree to analyze the user's response probability to different notification channels and identifies the notification channel with the highest response probability;

[0145] The notification plan is obtained based on the predicted user receipt time window and the notification channel with the highest probability.

[0146] In this embodiment, the notification effect optimization model is a regression model that establishes the relationship between notification delivery rate, opening rate, user feedback and notification strategy. An A / B testing strategy is adopted to conduct a small-scale verification of the optimal notification solution predicted by the model and collect actual effect data.

[0147] In this embodiment, the ensemble learning method fuses multiple weak models to improve prediction accuracy and robustness.

[0148] In this embodiment, a clustering algorithm is used to divide users into different groups, such as immediate response type, evening peak preference type, etc., and a specific strategy is formulated for each group.

[0149] The notification plan acquisition module 304 is used to obtain the notification plan based on the pre-processed user basic data using the logistics order notification model;

[0150] A dynamic adjustment module 305, for monitoring the current scenario in real time and dynamically adjusting the notification plan based on the current scenario monitored in real time;

[0151] Specifically, the dynamic adjustment module 305 includes:

[0152] Real-time monitoring includes user geographic location, weather conditions, and current social events; and dynamically adjust notification plans based on the current real-time monitoring, including user geographic location, weather conditions, and current social events; for example: adjust notification content and timing due to large-scale events to ensure the timeliness and relevance of notifications.

[0153] Automatic sending module 306, used to trigger the automatic sending of notification text when the order status is updated or the package is signed for;

[0154] During the sending process, record the sending log and notification effect;

[0155] The notification effect is evaluated by setting key performance indicators, wherein the key performance indicators include: notification arrival rate, user satisfaction score and complaint rate;

[0156] The recorded notification effects are used to optimize the logistics order notification model parameters.

[0157] At the same time, a real-time monitoring system is implemented to capture abnormal notification events, such as a high frequency of unread notifications, and to intervene and adjust in a timely manner.

[0158] More specifically, during the automatic sending process, configure the sending time interval, the holiday sending time interval, and set whether to resend the SMS the next day;

[0159] Among them, configuring the sending time interval allows users to configure the specific sending time range every day to ensure that the SMS is sent within the specified time;

[0160] For example: Select by time, the sending start time options are: 7:30, 8:30, 9:30, and the sending end time is 7:30-24 o'clock, with an option every 5 minutes.

[0161] Configure the holiday sending time range to set the holiday sending time range to ensure that SMS messages can be sent according to user requirements during holidays;

[0162] For example: Select by time, the sending start time options are: 7:30, 8:30, 9:30, and the sending end time is 7:30-24 o'clock, with an option every 5 minutes.

[0163] Set whether to resend SMS the next day, the default is "No". After setting resend, the order number that is distributed or signed for outside the sending time period will be resent the next day.

[0164] Model optimization module 307, used to optimize the logistics order notification model parameters according to user feedback;

[0165] The user feedback is to obtain user comments, and use text mining technology to analyze the obtained user comments to extract sentiment tendencies and improvement suggestions;

[0166] The logistics order notification model parameters are optimized based on the extracted sentiment tendencies and improvement suggestions.

[0167] User feedback mechanism: Establish convenient user feedback channels to encourage users to provide direct feedback on notification services, such as one-click evaluation and suggestion submission functions. Use text mining technology to analyze user comments, extract sentiment tendencies and improvement suggestions as the basis for model optimization.

[0168] Parameter tuning and model iteration: Based on feedback data, use online learning algorithms to gradually adjust model parameters to achieve self-optimization. Regularly review model performance, introduce new feature variables or algorithm models, and maintain technological cutting-edge capabilities to respond to changes in user habits and new market demands.

[0169] This embodiment can continuously optimize model parameters, improve notification reach and user experience, and achieve accurate prediction of user preferences and optimal notification time.

[0170] above Figure 3 The notification optimization device for logistics orders in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0171] Figure 4 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing unit, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 (for example, one or more mass storage devices) storing application programs 733 or data 732. Among them, the memory 720 and the storage medium 730 can be temporary storage or permanent storage. The program stored in the storage medium 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of instruction operations in the storage medium 730 on the electronic device 700.

[0172] The electronic device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input and output interfaces 750, and / or one or more operating systems 731, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 4 The structure of the electronic device shown does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0173] 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 method for notifying an optimization device for logistics orders.

[0174] 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.

[0175] 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 several instructions for 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.

[0176] 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 notification optimization method for logistics orders, characterized in that: include: Obtain basic user data based on logistics systems, user account information, and third-party social platforms; Preprocessing the acquired user basic data to obtain preprocessed user basic data; Build a logistics order notification model; Based on the pre-processed user basic data, the notification plan is obtained using the logistics order notification model; Monitor the current situation in real time and dynamically adjust the notification plan based on the current situation monitored in real time; The logistics order notification model includes a user behavior prediction model and a notification effect optimization model. The current user behavior prediction model is used to predict the user's delivery time window, and then the notification effect optimization model is used to analyze the user's response probability to different notification channels, and identify the notification channel with the highest response probability.

2. The notification optimization method for logistics orders according to claim 1, characterized in that: The basic logistics data obtained based on the logistics system, user account information and third-party social platforms include: Based on the logistics system, the logistics system obtains the express delivery records, basic information of the recipient, historical delivery addresses and package status update logs; Based on the user account information, preferred delivery time, common contact information, and notification preference settings are obtained; Based on the third-party social platform, the user's active time period, interest tags and social relationships are obtained.

3. The notification optimization method for logistics orders according to claim 1, characterized in that: The preprocessing of the acquired user basic data to obtain the preprocessed user basic data includes: Cleaning the acquired user basic data to obtain cleaned user basic data; The cleaning process includes: removing duplicate data, filling missing values, processing outliers and unifying formats; The cleaned user basic data is desensitized using data desensitization technology to obtain the desensitized user basic data; Formatting the user basic data after the desensitization process to obtain the formatted user basic data; The formatting process includes: data type conversion and data standardization process.

4. The notification optimization method for logistics orders according to claim 1, characterized in that: The construction of the logistics order notification model includes: a user behavior prediction model and a notification effect optimization model; The user behavior prediction model uses time series analysis to predict the user's receipt time window; The notification effect optimization model uses a gradient boosting tree to analyze the user's response probability to different notification channels and identifies the notification channel with the highest response probability; The notification plan is obtained based on the predicted user receipt time window and the notification channel with the highest probability.

5. The notification optimization method for logistics orders according to claim 1, characterized in that: The real-time monitoring of the current situation and dynamically adjusting the notification plan based on the real-time monitored current situation include: Real-time monitoring includes user geographic location, weather conditions, and current social events; and dynamically adjust notification plans based on the current real-time monitoring, including user geographic location, weather conditions, and current social events; And automatically generate notification text according to the current notification plan.

6. The notification optimization method for logistics orders according to claim 5 is characterized in that: The method further includes: when the order status is updated or the package is signed for, triggering the automatic sending of the notification copy; During the sending process, record the sending log and notification effect; The notification effect is evaluated by setting key performance indicators, wherein the key performance indicators include: notification arrival rate, user satisfaction score and complaint rate; The recorded notification effects are used to optimize the logistics order notification model parameters.

7. The notification optimization method for logistics orders according to claim 6, characterized in that: The method further includes: optimizing the logistics order notification model parameters according to user feedback; The user feedback is to obtain user comments, and use text mining technology to analyze the obtained user comments to extract sentiment tendencies and improvement suggestions; The logistics order notification model parameters are optimized based on the extracted sentiment tendencies and improvement suggestions.

8. A notification optimization device for logistics orders, characterized in that: include: The data acquisition module is used to obtain basic user data based on the logistics system, user account information and third-party social platforms; A preprocessing module, used to preprocess the acquired user basic data to obtain preprocessed user basic data; Build a model module to build a logistics order notification model; The notification plan acquisition module is used to obtain the notification plan based on the pre-processed user basic data using the logistics order notification model; A dynamic adjustment module, used to monitor the current situation in real time and dynamically adjust the notification plan based on the current situation monitored in real time; The logistics order notification model includes a user behavior prediction model and a notification effect optimization model. The current user behavior prediction model is used to predict the user's delivery time window, and then the notification effect optimization model is used to analyze the user's response probability to different notification channels, and identify the notification channel with the highest response probability.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the notification optimization method for logistics orders described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the notification optimization method for logistics orders described in any one of claims 1 to 7 are implemented.

Images