User behavior-based instant preferential pushing method and device, equipment and storage medium

By collecting and analyzing user behavior data and tracking location information in real time, personalized promotional information is generated, solving the problems of wasted marketing resources and delayed demand response in traditional express delivery services. This enables precise marketing and instant demand response, improving user satisfaction and marketing efficiency.

CN119047946APending Publication Date: 2024-11-29SHANGHAI DONGPU INFORMATION TECH CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411066268.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The traditional express delivery service industry lacks precise target positioning and personalized content, resulting in wasted marketing resources, low marketing efficiency, difficulty in improving user conversion rates, and an inability to respond to consumers' immediate needs in a timely manner, thus reducing customer satisfaction.

Method used

By collecting users' historical behavior data, analyzing potential demand using user behavior prediction models, tracking the location of couriers and users in real time, generating personalized discount information, and receiving client response information to optimize the model, personalized recommendations and instant demand response can be achieved.

Benefits of technology

It enables accurate prediction of user needs, improves marketing effectiveness and advertising conversion rates, enhances customer satisfaction, and optimizes the accuracy and responsiveness of marketing strategies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047946A_ABST
    Figure CN119047946A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of information processing, in particular to a user behavior-based instant preferential pushing method, device and equipment and a storage medium, and the method comprises the steps: collecting historical behavior data of a user, analyzing the historical behavior data through a preset user behavior prediction model, recognizing potential demands and consumption habit information in an analysis result, and transmitting the potential demands and consumption habit information to the user; matching a corresponding pushing strategy according to the potential demand and consumption habit information, tracking the first position information of the courier and the second position information of the user in real time, when the second position information is within the coverage range of the first position information, generating personalized preferential information according to the pushing strategy, and sending the personalized preferential information to the user. The personalized preferential information is sent to the client corresponding to the user, so that the user demand can be accurately predicted, the personalized recommendation is realized, the marketing effect and the effective conversion rate of the advertisement are improved, the instant demand of the consumer can be timely responded, and the customer satisfaction is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method, device, equipment and storage medium for pushing instant discounts based on user behavior. Background Art

[0002] In the traditional express delivery service industry, marketing strategies usually adopt a "cast-a-net" approach with wide publicity and coverage. Although this method can increase brand exposure to a certain extent, due to the lack of precise target positioning and personalized content, it cannot accurately predict user needs, has poor flexibility, and cannot achieve personalized recommendations, resulting in a large amount of marketing resources being wasted on potential customers who are not interested or do not currently need services. Blind push without understanding the target customers' interest preferences and consumption habits cannot guarantee the effective conversion of advertisements, which in turn results in low marketing efficiency and difficulty in significantly improving user conversion rates. In addition, after the marketing information is pushed, couriers are often unable to respond to consumers' immediate needs in a timely manner, which in turn reduces customer satisfaction and leads to customer churn. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a method, device, equipment and storage medium for pushing instant discounts based on user behavior, which can accurately predict user needs, realize personalized recommendations, improve marketing effects and the effective conversion rate of advertisements, respond to consumers' immediate needs in a timely manner, and improve customer satisfaction.

[0004] The first aspect of the present invention provides a method for pushing instant discounts based on user behavior, including: collecting historical behavior data of users, analyzing the historical behavior data using a preset user behavior prediction model to obtain analysis results; identifying potential demand and consumption habit information in the analysis results, and matching corresponding push strategies according to the potential demand and consumption habit information; tracking the courier's first location information and the user's second location information in real time to determine whether the second location information is within the coverage of the first location information; if so, generating personalized discount information according to the push strategy, and sending the personalized discount information to the client corresponding to the user; receiving response information from the client to the sent content, and optimizing the user behavior prediction model according to the response information.

[0005] Optionally, in a first implementation method of the first aspect of the present invention, the user's historical behavior data is collected, and the historical behavior data is analyzed using a preset user behavior prediction model to obtain analysis results, including: collecting the user's historical behavior data on the express service provider platform, the historical behavior data including historical purchase records, browsing behavior records, evaluation content records, and GPS positioning trajectory records reflecting daily activity range and travel habits; cleaning the historical behavior data to obtain cleaned data; converting the cleaned data into a target format to obtain standard format data; and analyzing the standard format data using a preset user behavior prediction model to obtain analysis results.

[0006] Optionally, in a second implementation method of the first aspect of the present invention, the identifying of potential demand and consumption habit information in the analysis results, and matching corresponding push strategies according to the potential demand and consumption habit information, include: constructing a user portrait according to the analysis results; based on the user portrait, using a collaborative filtering algorithm to identify similarities between users in a user-express service interaction matrix; determining potential demand and consumption habit information according to the similarities between users; and calling a preset strategy library, and matching a push strategy in the strategy library that has a mapping relationship with the potential demand and consumption habit information.

[0007] Optionally, in a third implementation method of the first aspect of the present invention, the real-time tracking of the courier's first location information and the user's second location information, and determining whether the second location information is within the coverage of the first location information, includes: real-time tracking of the courier's first location information and the user's second location information; calculating the real-time distance between the first location information and the second location information by using the Haversine formula; calculating the real-time coverage of the courier based on the first location information, and setting a virtual boundary of the real-time coverage using geo-fence technology; and determining whether the second location information is within the virtual boundary based on the real-time distance.

[0008] Optionally, in a fourth implementation method of the first aspect of the present invention, if so, generating personalized discount information according to the push strategy, and sending the personalized discount information to the client corresponding to the user, including: if so, generating personalized discount information according to the push strategy, the personalized discount information including the express service type and exclusive discount; obtaining a personalized push template, filling the personalized discount information into the graphic position corresponding to the personalized push template, and obtaining a personalized discount table; sending the personalized discount table to the client corresponding to the user, so that the client generates and displays a discount page based on the personalized discount table.

[0009] Optionally, in a fifth implementation method of the first aspect of the present invention, the receiving of response information of the client to the sent content and optimizing the user behavior prediction model according to the response information include: receiving response information of the client to the sent content, the response information including click-through rate information, conversion rate information and user direct feedback information; feeding back the response information to the user behavior prediction model, and adjusting the parameters of the user behavior prediction model using online learning technology to obtain an iterated user behavior prediction model; and deploying the iterated user behavior prediction model.

[0010] Optionally, in a sixth implementation method of the first aspect of the present invention, after receiving the response information of the client to the sent content and optimizing the user behavior prediction model according to the response information, it also includes: generating an instant discount push record and obtaining a timestamp from a timestamp service platform; determining whether the time interval between two consecutive instant discount push records corresponding to the user is greater than a preset threshold; if so, generating a frequent push record, and using the public key in a preset key pair to encrypt the frequent push record to obtain a frequent push encrypted record; uploading the frequent push encrypted record to the blockchain, and sending the private key in the key pair to the management end, so that the management end uses the private key to decrypt the frequent push encrypted record.

[0011] The second aspect of the present invention provides an instant discount push device based on user behavior, including: a collection and analysis module, used to collect historical behavior data of users, and use a preset user behavior prediction model to analyze the historical behavior data to obtain analysis results; an identification and matching module, used to identify potential demand and consumption habit information in the analysis results, and match corresponding push strategies according to the potential demand and consumption habit information; a tracking and judgment module, used to track the courier's first location information and the user's second location information in real time, and judge whether the second location information is within the coverage of the first location information; a generation and sending module, used to generate personalized discount information according to the push strategy if so, and send the personalized discount information to the client corresponding to the user; a receiving and optimization module, used to receive response information of the client to the sent content, and optimize the user behavior prediction model according to the response information.

[0012] Optionally, in a first implementation method of the second aspect of the present invention, the collection and analysis module includes: a collection unit, used to collect historical behavior data of users on the express service provider platform, the historical behavior data including historical purchase records, browsing behavior records, evaluation content records, and GPS positioning trajectory records reflecting daily activity range and travel habits; a cleaning unit, used to clean the historical behavior data to obtain cleaned data; a conversion unit, used to convert the cleaned data into a target format to obtain standard format data; and an analysis unit, used to analyze the standard format data using a preset user behavior prediction model to obtain analysis results.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the identification and matching module includes: a construction unit, used to construct a user portrait based on the analysis results; an identification unit, used to identify the similarities between users in the user and express service interaction matrix based on the user portrait and using a collaborative filtering algorithm; a determination unit, used to determine potential demand and consumption habit information based on the similarities between users; and a calling matching unit, used to call a preset strategy library to match a push strategy in the strategy library that has a mapping relationship with the potential demand and consumption habit information.

[0014] Optionally, in a third implementation method of the second aspect of the present invention, the tracking and judgment module includes: a tracking unit, used to track the courier's first location information and the user's second location information in real time; a calculation unit, used to calculate the real-time distance between the first location information and the second location information by using the Haversine formula; a calculation and setting unit, used to calculate the real-time coverage range of the courier based on the first location information, and set the virtual boundary of the real-time coverage range by using geo-fence technology; and a judgment unit, used to judge whether the second location information is within the virtual boundary based on the real-time distance.

[0015] Optionally, in a fourth implementation method of the second aspect of the present invention, the generation and sending module includes: a generation unit, used to generate personalized discount information according to the push strategy, and the personalized discount information includes express service type and exclusive discounts; an acquisition and filling unit, used to obtain a personalized push template, fill the personalized discount information into the graphic position corresponding to the personalized push template, and obtain a personalized discount table; a sending unit, used to send the personalized discount table to the client corresponding to the user, so that the client generates and displays a discount page based on the personalized discount table.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the receiving optimization module includes: a receiving unit, used to receive response information of the client to the sent content, the response information including click-through rate information, conversion rate information and user direct feedback information; a feedback adjustment unit, used to feed back the response information to the user behavior prediction model, and use online learning technology to adjust the parameters of the user behavior prediction model to obtain an iterated user behavior prediction model; and a deployment unit, used to deploy the iterated user behavior prediction model.

[0017] Optionally, in a sixth implementation manner of the second aspect of the present invention, it also includes: a generation and acquisition module, used to generate an instant discount push record, and obtain a timestamp from a timestamp service platform; a judgment module, used to judge whether the time interval between two consecutive instant discount push records corresponding to the user is greater than a preset threshold; a generation encryption module, used to generate a frequent push record if so, and use the public key in a preset key pair to encrypt the frequent push record to obtain a frequent push encrypted record; an upload and sending module, used to upload the frequent push encrypted record to the blockchain, and send the private key in the key pair to the management end, so that the management end uses the private key to decrypt the frequent push encrypted record.

[0018] A third aspect of the present invention provides a device for pushing instant discounts based on user behavior, the device comprising: a memory and at least one processor, the memory storing instructions; at least one processor calling the instructions in the memory to enable the device for pushing instant discounts based on user behavior to execute each step of any one of the above-mentioned methods for pushing instant discounts based on user behavior.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, and when the instructions are executed by a processor, the steps of any of the above-mentioned methods for pushing instant discounts based on user behavior are implemented.

[0020] In the technical solution of the present invention, by collecting historical behavior data of users, the historical behavior data is analyzed using a preset user behavior prediction model, potential needs and consumption habit information in the analysis results are identified, and the corresponding push strategy is matched according to the potential needs and consumption habit information. The first location information of the courier and the second location information of the user are tracked in real time. When the second location information is within the coverage of the first location information, personalized preferential information is generated according to the push strategy, and the personalized preferential information is sent to the client corresponding to the user. The user's needs can be accurately predicted, personalized recommendations can be achieved, and the marketing effect and the effective conversion rate of advertising can be improved. The immediate needs of consumers can be responded to in a timely manner, and customer satisfaction can be improved. The response information of the client to the sent content is received, and the user behavior prediction model is optimized according to the response information to improve the accuracy of user demand prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A first flow chart of a method for pushing instant discounts based on user behavior provided by an embodiment of the present invention;

[0022] Figure 2 A second flow chart of the method for pushing instant discounts based on user behavior provided by an embodiment of the present invention;

[0023] Figure 3 A third flow chart of the method for pushing instant discounts based on user behavior provided by an embodiment of the present invention;

[0024] Figure 4 A fourth flow chart of a method for pushing instant discounts based on user behavior provided by an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of a structure of a device for pushing instant discounts based on user behavior provided by an embodiment of the present invention;

[0026] Figure 6 Another structural diagram of the device for pushing instant discounts based on user behavior provided by an embodiment of the present invention;

[0027] Figure 7 A schematic diagram of the structure of a device for pushing instant discounts based on user behavior provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention provides a method, device, equipment and storage medium for pushing instant discounts based on user behavior, which can accurately predict user needs, realize personalized recommendations, improve marketing effects and the effective conversion rate of advertisements, and can promptly respond to consumers' immediate needs and improve customer satisfaction.

[0029] 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.

[0030] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the method for pushing instant discounts based on user behavior in an embodiment of the present invention includes:

[0031] 101. Collect historical behavior data of users, analyze the historical behavior data using a preset user behavior prediction model, and obtain analysis results;

[0032] In this embodiment, the user's historical behavior data is collected from channels such as website browsing records, APP usage, purchase history, search history, etc., and features are extracted and converted for the historical behavior data so that the user behavior prediction model can understand and learn. Through the output results of the user behavior prediction model, the user's behavior patterns and trends can be identified, such as the user's purchase cycle, preferred product categories, time patterns for visiting websites, etc. Based on the analysis results, users can be divided into different groups or segments for subsequent personalized recommendations and marketing strategies.

[0033] 102. Identify potential needs and consumption habit information in the analysis results, and match corresponding push strategies according to the potential needs and consumption habit information;

[0034] In this embodiment, a personalized recommendation system is established based on the user's consumption habits and demand information. The personalized recommendation system identifies potential needs and consumption habit information in the analysis results, and matches corresponding push strategies according to the potential needs and consumption habit information.

[0035] 103. Track the first location information of the courier and the second location information of the user in real time, and determine whether the second location information is within the coverage of the first location information;

[0036] In this embodiment, the global positioning system (GPS) or other positioning technology is used to obtain the real-time location information of the courier and the user, ensuring that the location information of the courier and the user is stored and processed in a unified format, and the longitude and latitude coordinates can be used to spatially match the courier's first location information and the user's second location information to calculate the distance between the two points or to determine whether they are within a predetermined coverage range. Specifically, a geospatial analysis algorithm is used to calculate the distance between the courier's first location and the user's second location, determine a suitable coverage range or radius, and determine whether the user's second location is within the coverage range of the courier's first location. This can be achieved by comparing the location information with a preset radius.

[0037] 104. If yes, generate personalized discount information according to the push strategy, and send the personalized discount information to the client corresponding to the user;

[0038] In this embodiment, if the user's second location is within the coverage area of ​​the courier's first location, preferential information that meets personalized needs is generated according to the formulated push strategy. For example, related products are recommended according to the user's preferences, discounts for supplementary purchases are provided based on purchase history, promotional information of local merchants is provided based on geographic location, etc., and the personalized preferential information is pushed to the user's corresponding client.

[0039] 105. Receive response information of the client to the sent content, and optimize the user behavior prediction model according to the response information;

[0040] In this embodiment, the system is ensured to be able to record and store user response data to pushed content, such as click-through rate, browsing depth, purchase conversion rate, etc., and use data analysis tools and techniques (such as statistical analysis, machine learning algorithms) to conduct in-depth analysis of the response data. The goal is to discover user behavior patterns and trends, such as the impact of specific types of discount information or push time on response rate, determine the key factors that affect user response, including discount type, push time, personalized content, etc., find out the variables that are significantly correlated with response rate or conversion rate through statistical methods or machine learning models, and adjust the existing user behavior prediction model based on the analysis results of the response data.

[0041] In an embodiment of the present invention, by collecting historical behavior data of users, analyzing the historical behavior data using a preset user behavior prediction model, identifying potential needs and consumption habit information in the analysis results, matching corresponding push strategies according to the potential needs and consumption habit information, and tracking the first location information of the courier and the second location information of the user in real time, when the second location information is within the coverage of the first location information, generating personalized preferential information according to the push strategy, and sending the personalized preferential information to the client corresponding to the user, the user's needs can be accurately predicted, personalized recommendations can be achieved, the marketing effect and the effective conversion rate of advertising can be improved, the immediate needs of consumers can be responded to in a timely manner, and customer satisfaction can be improved. The response information of the client to the sent content is received, and the user behavior prediction model is optimized according to the response information to improve the accuracy of user demand prediction.

[0042] See also Figure 2 The second embodiment of the method for pushing instant discounts based on user behavior in the embodiment of the present invention includes:

[0043] 201. Collecting historical behavior data of users on the express service provider platform, including historical purchase records, browsing behavior records, evaluation content records, and GPS location trajectory records reflecting daily activity range and travel habits;

[0044] In this embodiment, historical behavior data of users on the express service provider platform is collected. The historical behavior data includes historical purchase records, browsing behavior records, evaluation content records, and GPS positioning trajectory records reflecting the scope of daily activities and travel habits. Historical purchase records include order number, purchase time, type of purchased product or service (such as express type, service level, etc.), payment amount and other information. Browsing behavior records include visited pages, browsing time, specific product or service pages browsed, etc. Evaluation content records include text comments, ratings and other information. GPS positioning trajectory records record the user's travel habits and scope of activities. The data from all of the above aspects are integrated for cross-analysis and correlation analysis. For example, the relationship between purchasing behavior and browsing behavior, or the correlation between evaluation content and geographic location can be explored.

[0045] 202. Clean the historical behavior data to obtain cleaned data;

[0046] In this embodiment, the historical behavior data is cleaned, duplicate records in the historical behavior data are identified and deleted to ensure that each record is unique, and erroneous values ​​or abnormal values ​​in the historical behavior data are detected and corrected, such as values ​​outside a reasonable range or inconsistent data formats, and missing data is filled or deleted. The filling methods include using the average, median, or through data interpolation and other techniques to ensure the integrity and accuracy of the data.

[0047] 203. Convert the cleaned data into a target format to obtain standard format data;

[0048] In this embodiment, it is confirmed that the arrangement order of the cleaned data fields is consistent with the target format, ensuring that the data type of each field (such as integer, floating point number, date) meets the requirements of the target format, unifying the formats of the date and time fields, and once the requirements of the target format are clear, converting the cleaned data fields to the data types required by the target format, for example, converting text fields to numeric or date data, ensuring that the formats of all date fields are unified and meet the requirements, converting the units of the data to the standard units required by the target format, obtaining standard format data, and verifying whether the format of the standard format data meets the requirements of the target format.

[0049] 204. Analyze the standard format data using a preset user behavior prediction model to obtain analysis results;

[0050] In this embodiment, the basic statistical characteristics of the data, such as the number of fields, the number of records, the data type, etc., are checked to ensure data integrity and consistency, a pre-trained user behavior prediction model is loaded, a data set in a standard format is imported into the user behavior prediction model, and the user behavior prediction model outputs the predicted analysis results.

[0051] 205. Build user portraits based on analysis results;

[0052] In this embodiment, a user portrait is constructed based on the analysis results. The user portrait includes basic information, behavioral characteristics, interests and hobbies, and lifestyle. The basic information includes the user's age, gender, geographical location, etc. The behavioral characteristics describe the user's typical behavior patterns, such as purchasing preferences, browsing habits, click behaviors, etc. The interests and hobbies are preference information such as the user's favorite product categories and content types. The lifestyle is other lifestyle characteristics related to the user's behavior, such as consumption habits, interests and hobbies, etc.

[0053] 206. Based on user portraits, collaborative filtering algorithm is used to identify the similarities between users in the interaction matrix between users and express delivery services;

[0054] In this embodiment, based on the user portrait, a suitable similarity measurement method is selected to measure the similarity between users, and the cosine value of the angle between two vectors is calculated, which can be used to compare the feature vectors in the user portrait and measure the linear correlation between two variables. It can be used to compare whether the behavioral trends of users on certain attributes are consistent, and similar users are discovered by comparing the interaction behaviors between users, and express services similar to similar users are recommended. Similar express services are discovered by comparing the user evaluations or usage of express services, and then recommended to users. According to the selected similarity measurement method, the similarity scores between users are calculated, and based on the similarity of users, express services that similar users like are recommended to each user.

[0055] 207. Determine potential needs and consumption habits based on similarities between users;

[0056] In this embodiment, common characteristics and behavior patterns among similar user groups are found. For example, one group of users may prefer cheap but fast express delivery services, while another group of users may be more concerned about service quality and reliability. Based on the personalized characteristics of the users, their possible needs are inferred. For example, some users may be high-frequency users and need subscription services, while other users may prefer on-demand use.

[0057] 208. Calling a preset strategy library, and matching a push strategy having a mapping relationship with potential demand and consumption habit information in the strategy library;

[0058] In this embodiment, a policy library is established and maintained in advance, which includes storing different types of push policies, which are usually designed based on different user needs or consumption habits, such as: promotional activity push for price-sensitive users, new product recommendations for users who like to try new things, service upgrade notifications for users who value service quality and user experience, regular subscription reminders for users who frequently use services, and analyzing various push policies in the policy library, matching and mapping them with established user profiles. This step is implemented using a similarity metric or matching algorithm, for example: using cosine similarity to calculate the similarity between the user portrait vector and each policy, and determining the policy that best matches each user, that is, the push policy that best matches their potential needs and consumption habit information.

[0059] In the embodiment of the present invention, multiple data sources are integrated, and the consistency and accuracy of the data are ensured through cleaning and conversion, providing a reliable basis for subsequent analysis and decision-making. Through predictive models and user portraits, decisions are made based on data, which improves the personalization of services and the quality of user experience. Collaborative filtering algorithms are used to identify user similarities, customize accurate recommendations and services, and enhance user participation and satisfaction with the platform. By identifying potential needs and consumption habit information, market trends and changes in user needs are predicted in advance, product and service strategies are optimized, and market competitiveness is enhanced. A preset strategy library is integrated for push strategy matching, which improves the pertinence and effect of push content and optimizes service interaction and efficiency.

[0060] See also Figure 3 A third embodiment of the method for pushing instant discounts based on user behavior in the embodiment of the present invention includes:

[0061] 301. Real-time tracking of the courier’s first location information and the user’s second location information;

[0062] In this embodiment, a data collection system is established for obtaining the location information of couriers and users in real time. The global positioning system (GPS) or similar technology is installed on the courier's means of transportation (such as a vehicle) or equipment to obtain their location information in real time. The courier's location data is transmitted to a data center or server via a mobile network (such as 4G / 5G), satellite communication, or a dedicated communication network. Users can actively provide their location information through a mobile application or web interface, which requires the user's explicit consent and is usually obtained through a positioning service. User location data can also be obtained through GPS or location speculation based on the IP address. The courier and user location information needs to be processed in real time by a data stream processing system. These systems are capable of processing large amounts of location data instantly and performing specific calculations and logic as needed. The processed location data can be stored in a cloud database or a dedicated location database.

[0063] 302. Calculate the real-time distance between the first position information and the second position information by using the Haversine formula;

[0064] In this embodiment, the longitude and latitude of the first position information and the second position information are obtained. The Haversine formula uses radians to represent the angle, so the longitude and latitude need to be converted from degrees to radians, and the Haversine formula is used to calculate the real-time distance between the two points.

[0065] 303. Calculate the real-time coverage of the courier according to the first location information, and set a virtual boundary of the real-time coverage using geo-fencing technology;

[0066] In this embodiment, a coverage radius or polygonal area is defined to indicate the maximum range that the courier can cover. This range can be set according to actual conditions, such as a polygonal boundary within 10 kilometers or a specific area. An appropriate geo-fence technology is selected to set the virtual boundary, including a circular fence: using the courier's current location as the center and the defined coverage radius as the radius to create a circular area; a polygonal fence: using multiple longitude and latitude points to define a polygonal area. These points can be manually specified or calculated according to actual needs. According to the selected geo-fence technology, the following steps are implemented: a circular fence: calculating the distance from the courier's current location to the surrounding points to confirm whether it is within the set coverage range; a polygonal fence: using a polygonal boundary algorithm (such as the ray method) to check whether the courier's location is within the polygon, regularly updating the courier's location and recalculating the coverage range after each update.

[0067] 304. Determine whether the second position information is within the virtual boundary according to the real-time distance;

[0068] In this embodiment, whether the second position is within the virtual boundary is determined based on the relationship between the calculated real-time distance and the virtual boundary. If the distance is less than or equal to the boundary radius (for a circular boundary) or within the polygon (for a polygonal boundary), the second position is determined to be within the virtual boundary; otherwise, the second position is determined to be outside the virtual boundary.

[0069] 305. If yes, generate personalized preferential information according to the push strategy, the personalized preferential information including the express service type and the exclusive discount;

[0070] In this embodiment, if the second location is determined to be within the virtual boundary, personalized preferential information is generated according to the push strategy, and the personalized preferential information includes the express service type and the exclusive discount.

[0071] 306. Obtain a personalized push template, fill the personalized discount information into the image and text position corresponding to the personalized push template, and obtain a personalized discount table;

[0072] In this embodiment, a personalized push template for push is obtained. The personalized push template includes a designed graphic structure, which is the format displayed in push notifications, emails or social media platforms. The design of the personalized push template takes into account user interface friendliness and visual appeal. The personalized push template has a reserved position for placing text descriptions, discount pictures or purchase buttons. The text information (such as discount descriptions, discount codes, promotional details, etc.) is filled in according to the text area of ​​the template, ensuring that the format and length of the text conform to the design of the template, and also ensuring that the information is clear and understandable. Select appropriate pictures or graphic elements to fill in the picture or visual content area. These images are used to highlight the discount content or product features. After completing the filling operation, a personalized discount table is obtained.

[0073] 307. Send the personalized discount list to the client corresponding to the user, so that the client generates and displays a discount page based on the personalized discount list;

[0074] In this embodiment, a personalized discount list is sent to the client corresponding to the user. After receiving the personalized discount list, the client needs to parse it to extract the information therein, including the description of the discount, discount code, validity period, information of related products or services, etc. The client needs to generate the structure and layout of the discount page based on the data in the discount list, which includes the layout and design of elements such as the page title, discount details, picture display area, and purchase button. According to the specific content provided in the discount list, the text description, discount picture or other visual content is filled in the corresponding page position to ensure the accuracy and clarity of the content so that the user can clearly understand the content and conditions of the discount. Necessary interactive elements are added to the page, such as the purchase button, view details link, etc. The functions of these elements should be consistent with the relevant information provided in the discount list to ensure that the user can perform the corresponding operations conveniently.

[0075] In the embodiment of the present invention, the location information of the courier and the user can be tracked in real time, and the real-time distance can be quickly calculated through the Haversine formula, thereby ensuring the accuracy of the data and the timeliness of the processing. The virtual boundary is set by using the geographic fence technology to effectively manage the real-time coverage of the courier, thereby improving the accuracy of the service and the user's sense of security. According to the user's location and the judgment within the virtual boundary, personalized preferential information is generated and embedded in a personalized push template, which is sent to the user through the client, thereby enhancing the user experience and sense of participation. By automatically generating and sending personalized preferential information, the efficiency of the push strategy is optimized, and at the same time, the resource utilization efficiency and operating cost control are improved. Based on the feedback of the real-time distance and location information, the push strategy can be adjusted and optimized in real time, thereby improving the personalization and response speed of the service.

[0076] See also Figure 4The fourth embodiment of the method for pushing instant discounts based on user behavior in the embodiment of the present invention includes:

[0077] 401. Receive response information from the client to the sent content, the response information including click rate information, conversion rate information and user direct feedback information;

[0078] In this embodiment, click rate information returned by the client is collected, that is, the number of times users click on links or buttons in the sent content. This data can be obtained through event tracking or log records sent by the client. Click behaviors in different contents or different time periods are analyzed. For example, which type of discount or which push time period has a higher click rate is helpful to optimize future sending strategies and content selection. The conversion rate information returned by the client is obtained, that is, the proportion of users completing the expected operation after clicking. The conversion can be purchasing a product, registering for a service, filling out a survey form, etc. By analyzing the conversion rate, the actual effect of the sent content and the degree of user response to the content can be understood, and then the marketing strategy can be adjusted and the content design can be optimized. The direct user feedback information returned by the client is sorted out, which includes user comments, ratings, suggestions or complaints. These feedbacks are usually collected through feedback forms, questionnaires or direct user replies. Sentiment analysis technology and keyword extraction methods are used to understand the emotional tendencies and main concerns of user feedback.

[0079] 402. Feedback the response information to the user behavior prediction model, and use online learning technology to adjust the parameters of the user behavior prediction model to obtain an iterated user behavior prediction model;

[0080] In this embodiment, response information from user operations is received and processed in real time, and the feature engineering part of the model is updated according to the newly received response information. It is necessary to add new features, adjust feature weights, or transform features so that the model can better capture the latest user behavior patterns. Online learning technology is used to update the parameters of the model in real time according to the new response information, and the parameter update strategy is determined, such as the selection of learning rate, the setting of parameter update frequency, etc. By periodically updating the model parameters and feature engineering parts, the accuracy and adaptability of user behavior prediction are gradually improved.

[0081] 403. Deploy the iterated user behavior prediction model;

[0082] In this embodiment, the iterated user behavior prediction model is deployed in a production environment to ensure that the model can process and predict user behavior in real time and provide support for business decisions.

[0083] 404. Generate an instant discount push record and obtain a timestamp from the timestamp service platform;

[0084] In this embodiment, an instant discount push record is generated, a request is sent to a timestamp service platform through a network protocol, a current timestamp is requested, a response from the timestamp service platform is received, and the acquired timestamp data is processed, and the acquired timestamp is applied to the generated push record.

[0085] 405. Determine whether the time interval between two consecutive instant discount push records corresponding to the user is greater than a preset threshold;

[0086] In this embodiment, the push record data of the user is obtained from the push service or database, and the push records are grouped according to the user identifier to facilitate subsequent analysis of the push interval of each user. The push records of each user are sorted in chronological order to ensure that the calculated time interval is determined according to the order of push. For the sorted push records of each user, the time interval between two consecutive push records is calculated, a preset time interval threshold is set, and the time interval of each pair of consecutive push records is compared with the set threshold to determine whether the time interval between two consecutive instant discount push records corresponding to the user is greater than the preset threshold.

[0087] 406. If yes, generate a push-frequent record, and encrypt the push-frequent record using a public key in a preset key pair to obtain a push-frequent encrypted record;

[0088] In this embodiment, if the time interval between two consecutive instant discount push records corresponding to the user is greater than a preset threshold, a frequent push record is generated, and the frequent push record is encrypted using the public key in the preset key pair to obtain a frequent push encrypted record.

[0089] 407. Upload the frequently pushed encrypted record to the blockchain, and send the private key in the key pair to the management end, so that the management end uses the private key to decrypt the frequently pushed encrypted record;

[0090] In this embodiment, a suitable blockchain platform is selected, such as Ethereum, Hyperledger Fabric, etc., and a smart contract is written to handle the storage and access control of encrypted records. A transaction is created, and the encrypted data is submitted to the blockchain as the input data of the transaction. The private key is encrypted in a secure manner to ensure that only the management end has the right to decrypt. The encrypted private key is transmitted through a secure communication channel, such as using an encrypted communication protocol (such as SSL / TLS) or a secure file transfer method to ensure that only the authorized management end can access the private key. The access control list (ACL) or identity authentication mechanism can be considered to limit access. After the management end receives the encrypted data and the decryption private key, it can obtain the stored encrypted data from the blockchain and use the private key held by the management end to decrypt the encrypted data.

[0091] In the embodiment of the present invention, the response information of the client can be received in time and fed back to the user behavior prediction model. By adjusting the model parameters by online learning technology, the user behavior prediction model can be optimized immediately, and the reaction speed and effect of the system can be improved. By iteratively updating the user behavior prediction model and deploying the optimized model to the system, the accuracy and effect of the push strategy can be continuously improved, while maintaining the stability and reliability of the system, generating instant discount push records and obtaining timestamps, ensuring that the records of push behavior are complete and cannot be tampered with, and improving the credibility and security of the data. By judging the push frequency and encrypting the records and uploading them to the blockchain, it is ensured that users will not be disturbed by excessively frequent pushes. At the same time, encryption technology is used to protect the security of sensitive data, enhancing the user experience and data privacy protection, and uploading the frequently pushed encrypted records to the blockchain. The decentralized and tamper-proof characteristics of the blockchain are used to ensure the authenticity and transparency of the data, while improving the efficiency and security of data management.

[0092] The above describes the instant preferential push method based on user behavior in the embodiment of the present invention. The following describes the instant preferential push device based on user behavior in the embodiment of the present invention. Figure 5 In one embodiment of the present invention, an instant preferential push device based on user behavior includes:

[0093] The collection and analysis module 501 is used to collect historical behavior data of users, analyze the historical behavior data using a preset user behavior prediction model, and obtain analysis results;

[0094] Identification and matching module 502, used to identify potential needs and consumption habit information in the analysis results, and match corresponding push strategies according to the potential needs and consumption habit information;

[0095] A tracking and judging module 503 is used to track the first location information of the courier and the second location information of the user in real time, and judge whether the second location information is within the coverage of the first location information;

[0096] A generating and sending module 504 is used to generate personalized preferential information according to the push strategy and send the personalized preferential information to the client corresponding to the user;

[0097] The receiving optimization module 505 is used to receive the response information of the client to the sent content, and optimize the user behavior prediction model according to the response information.

[0098] In this embodiment, by collecting the user's historical behavior data, the historical behavior data is analyzed using a preset user behavior prediction model, potential demand and consumption habit information in the analysis results are identified, and the corresponding push strategy is matched according to the potential demand and consumption habit information. The courier's first location information and the user's second location information are tracked in real time. When the second location information is within the coverage of the first location information, personalized preferential information is generated according to the push strategy, and the personalized preferential information is sent to the user's corresponding client. The user's needs can be accurately predicted, personalized recommendations can be achieved, and the marketing effect and the effective conversion rate of advertising can be improved. The immediate needs of consumers can be responded to in a timely manner, and customer satisfaction can be improved. The client's response information to the sent content is received, and the user behavior prediction model is optimized according to the response information to improve the accuracy of user demand prediction.

[0099] See also Figure 6 Another embodiment of the device for pushing instant discounts based on user behavior in the embodiment of the present invention includes:

[0100] The collection and analysis module 501 is used to collect historical behavior data of users, analyze the historical behavior data using a preset user behavior prediction model, and obtain analysis results;

[0101] Identification and matching module 502, used to identify potential needs and consumption habit information in the analysis results, and match corresponding push strategies according to the potential needs and consumption habit information;

[0102] A tracking and judging module 503 is used to track the first location information of the courier and the second location information of the user in real time, and judge whether the second location information is within the coverage of the first location information;

[0103] A generating and sending module 504 is used to generate personalized preferential information according to the push strategy and send the personalized preferential information to the client corresponding to the user;

[0104] The receiving optimization module 505 is used to receive the response information of the client to the sent content, and optimize the user behavior prediction model according to the response information;

[0105] In this embodiment, the collection and analysis module 501 includes: a collection unit 5011, which is used to collect historical behavior data of users on the express service provider platform, and the historical behavior data includes historical purchase records, browsing behavior records, evaluation content records, and GPS positioning trajectory records reflecting daily activity range and travel habits; a cleaning unit 5012, which is used to clean the historical behavior data to obtain cleaned data; a conversion unit 5013, which is used to convert the cleaned data into a target format to obtain standard format data; an analysis unit 5014, which is used to analyze the standard format data using a preset user behavior prediction model to obtain analysis results.

[0106] In this embodiment, the identification and matching module 502 includes: a construction unit 5021, which is used to construct a user portrait based on the analysis results; an identification unit 5022, which is used to identify the similarities between users in the user and express service interaction matrix based on the user portrait using a collaborative filtering algorithm; a determination unit 5023, which is used to determine potential demand and consumption habit information based on the similarities between users; and a call matching unit 5024, which is used to call a preset strategy library and match the push strategy that has a mapping relationship with the potential demand and consumption habit information in the strategy library.

[0107] In this embodiment, the tracking and judgment module 503 includes: a tracking unit 5031, which is used to track the first location information of the courier and the second location information of the user in real time; a calculation unit 5032, which is used to calculate the real-time distance between the first location information and the second location information by using the Haversine formula; a calculation and setting unit 5033, which is used to calculate the real-time coverage range of the courier according to the first location information, and set the virtual boundary of the real-time coverage range by using the geo-fence technology; and a judgment unit 5034, which is used to judge whether the second location information is within the virtual boundary according to the real-time distance.

[0108] In this embodiment, the generation and sending module 504 includes: a generation unit 5041, which is used to generate personalized discount information according to the push strategy, and the personalized discount information includes the express service type and exclusive discount; an acquisition and filling unit 5042, which is used to obtain a personalized push template, fill the personalized discount information into the image and text position corresponding to the personalized push template, and obtain a personalized discount table; a sending unit 5043, which is used to send the personalized discount table to the client corresponding to the user, so that the client generates and displays the discount page based on the personalized discount table.

[0109] In this embodiment, the receiving optimization module 505 includes: a receiving unit 5051, which is used to receive the response information of the client to the sent content, and the response information includes click-through rate information, conversion rate information and user direct feedback information; a feedback adjustment unit 5052, which is used to feed back the response information to the user behavior prediction model, and use online learning technology to adjust the parameters of the user behavior prediction model to obtain the iterated user behavior prediction model; a deployment unit 5053, which is used to deploy the iterated user behavior prediction model.

[0110] In this embodiment, it also includes: a generation and acquisition module 506, which is used to generate an instant discount push record and obtain a timestamp from a timestamp service platform; a judgment module 507, which is used to judge whether the time interval between two consecutive instant discount push records corresponding to the user is greater than a preset threshold; a generation encryption module 508, which is used to generate a frequent push record if so, and use the public key in a preset key pair to encrypt the frequent push record to obtain a frequent push encrypted record; an upload and sending module 509, which is used to upload the frequent push encrypted record to the blockchain, and send the private key in the key pair to the management end, so that the management end uses the private key to decrypt the frequent push encrypted record.

[0111] above Figure 5 and Figure 6 The device for pushing instant discounts based on user behavior in an embodiment of the present invention is described in detail from the perspective of modular functional entities. The device for pushing instant discounts based on user behavior in an embodiment of the present invention is described in detail from the perspective of hardware processing.

[0112] Figure 7 6 is a schematic diagram of a device for pushing instant discounts based on user behavior provided by an embodiment of the present invention. The device 600 for pushing instant discounts based on user behavior may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (for example, one or more processors) and a memory 620, and one or more storage media 630 (for example, one or more massive storage devices) for storing application programs 633 or data 632. Among them, the memory 620 and the storage medium 630 may be short-term storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the device 600 for pushing instant discounts based on user behavior. Furthermore, the processor 610 may be configured to communicate with the storage medium 630, and execute a series of instruction operations in the storage medium 630 on the device 600 for pushing instant discounts based on user behavior, so as to implement the steps of the method for pushing instant discounts based on user behavior provided by the above-mentioned various method embodiments.

[0113] The instant discount push device 600 based on user behavior may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input and output interfaces 660, and / or one or more operating systems 631, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 7The illustrated structure of the device for pushing instant discounts based on user behavior does not constitute a limitation on the device for pushing instant discounts based on user behavior, and may include more or fewer components than illustrated, or a combination of certain components, or a different arrangement of components.

[0114] 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 a method for pushing instant discounts based on user behavior.

[0115] 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.

[0116] 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.

[0117] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for pushing instant discounts based on user behavior. It is characterized in that include: Collecting historical behavior data of users, and analyzing the historical behavior data using a preset user behavior prediction model to obtain analysis results; Identify potential needs and consumption habit information in the analysis results, and match corresponding push strategies according to the potential needs and consumption habit information; Tracking the first location information of the courier and the second location information of the user in real time, and determining whether the second location information is within the coverage of the first location information; If yes, generate personalized preferential information according to the push strategy, and send the personalized preferential information to the client corresponding to the user; Receive response information from the client to the sent content, and optimize the user behavior prediction model according to the response information.

2. The method for pushing instant discounts based on user behavior according to claim 1, It is characterized in that The collecting of historical behavior data of the user and analyzing the historical behavior data using a preset user behavior prediction model to obtain analysis results include: Collecting historical behavior data of users on the express service provider platform, including historical purchase records, browsing behavior records, evaluation content records, and GPS location trajectory records reflecting daily activity range and travel habits; Cleaning the historical behavior data to obtain cleaned data; Converting the cleaned data into a target format to obtain standard format data; The standard format data is analyzed using a preset user behavior prediction model to obtain an analysis result.

3. The method for pushing instant discounts based on user behavior according to claim 1, It is characterized in that The identifying potential needs and consumption habit information in the analysis results, and matching corresponding push strategies according to the potential needs and consumption habit information, includes: Build a user profile based on the analysis results; Based on the user portraits, a collaborative filtering algorithm is used to identify similarities between users in the user-courier service interaction matrix; Determine potential demand and consumption habit information based on the similarities between the users; A preset strategy library is called, and a push strategy having a mapping relationship with the potential demand and consumption habit information is matched in the strategy library.

4. The method for pushing instant discounts based on user behavior according to claim 1, It is characterized in that The real-time tracking of the first location information of the courier and the second location information of the user, and determining whether the second location information is within the coverage of the first location information, includes: Tracking the first location information of the courier and the second location information of the user in real time; Calculate the real-time distance between the first position information and the second position information by using the Haversine formula; Calculating the real-time coverage of the courier according to the first location information, and setting a virtual boundary of the real-time coverage using geo-fencing technology; It is determined whether the second position information is within the virtual boundary according to the real-time distance.

5. The method for pushing instant discounts based on user behavior according to claim 1, It is characterized in that If so, generating personalized preferential information according to the push strategy, and sending the personalized preferential information to the client corresponding to the user, including: If yes, then generate personalized preferential information according to the push strategy, the personalized preferential information including the express service type and exclusive discount; Obtain a personalized push template, fill the personalized discount information into the image and text position corresponding to the personalized push template, and obtain a personalized discount table; The personalized discount list is sent to a client corresponding to the user, so that the client generates and displays a discount page based on the personalized discount list.

6. The method for pushing instant discounts based on user behavior according to claim 1, It is characterized in that The receiving the response information of the client to the sent content, and optimizing the user behavior prediction model according to the response information, comprises: Receiving response information of the client to the sent content, the response information including click rate information, conversion rate information and user direct feedback information; Feeding the response information back to the user behavior prediction model, and adjusting the parameters of the user behavior prediction model using online learning technology to obtain an iterated user behavior prediction model; The iterated user behavior prediction model is deployed.

7. The method for pushing instant discounts based on user behavior according to claim 1, It is characterized in that After receiving the response information of the client to the sent content and optimizing the user behavior prediction model according to the response information, the method further includes: Generate instant discount push records and obtain timestamps from the timestamp service platform; Determine whether the time interval between two consecutive instant discount push records corresponding to the user is greater than a preset threshold; If yes, a push-frequent record is generated, and the push-frequent record is encrypted using the public key in the preset key pair to obtain a push-frequent encrypted record; The frequently pushed encrypted record is uploaded to the blockchain, and the private key in the key pair is sent to the management end, so that the management end uses the private key to decrypt the frequently pushed encrypted record.

8. A device for pushing instant discounts based on user behavior, It is characterized in that include: A collection and analysis module is used to collect historical behavior data of users, analyze the historical behavior data using a preset user behavior prediction model, and obtain analysis results; An identification and matching module, used to identify potential needs and consumption habit information in the analysis results, and match corresponding push strategies according to the potential needs and consumption habit information; A tracking and judging module, used for tracking the first location information of the courier and the second location information of the user in real time, and judging whether the second location information is within the coverage of the first location information; A generating and sending module is used for generating personalized preferential information according to the push strategy if yes, and sending the personalized preferential information to the client corresponding to the user; The receiving optimization module is used to receive the response information of the client to the sent content, and optimize the user behavior prediction model according to the response information.

9. A device that pushes instant discounts based on user behavior. It is characterized in that The instant discount push device based on user behavior includes: a memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable the device for pushing instant discounts based on user behavior to execute each step of the method for pushing instant discounts based on user behavior as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, It is characterized in that When the instructions are executed by the processor, the steps of the method for pushing instant discounts based on user behavior as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Personalized highway operation safety propaganda and education information pushing method based on artificial intelligence

    CN119884488A

  • Customer life cycle-based management method and system

    CN120258865A

  • Cabinet configuration method and system of delivery cabinet

    CN120260183A

  • Intelligent decision-making system and method based on big data analysis

    CN120804529A