Method and system for determining potential flow consumption user based on interaction information

Abstract

The invention discloses a potential traffic consumption user determination method and system based on interaction information. The method comprises the following steps: identifying traffic associated data of a user based on the interaction information; preprocessing the traffic associated data to obtain standard traffic data of the user, and constructing a multi-dimensional user vector of the user; obtaining package data of a current to-be-promoted traffic package, and constructing a multi-dimensional package vector of the current to-be-promoted traffic package; calculating the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector of the user based on a preset similarity algorithm; and when the vector similarity is greater than a preset similarity threshold, determining that the user is a potential consumption user of the current to-be-promoted traffic plan. According to the technical scheme, the efficiency and accuracy of determining the potential traffic consumption users can be improved.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and specifically relates to a method and system for determining potential traffic consumption users based on interactive information. Background Art

[0002] Potential traffic consumption users refer to users who have consumption needs or are interested in a certain traffic package service but have not yet applied for the package service. They have the possibility of becoming future service users. In order to increase the sales of traffic package services and the revenue of operators, it has become very important to process the consumption data of traffic consumption users and then tap into potential traffic consumption users.

[0003] The existing technology mainly sends a traffic package advertisement push link to the user, identifies whether the user has clicked on the currently pushed traffic package advertisement to determine whether the user is interested in the current traffic package service to be promoted, or sends a traffic consumption survey intention form to the user, and processes the user's feedback data to determine whether the current traffic package service to be promoted meets the user's needs, and then determines whether the user is a potential traffic consumption user. However, whether the user clicks on the traffic package advertisement link is not exactly the same as the user's final purchase result. At the same time, it takes a lot of time to conduct surveys based on the survey intention form and process feedback data. Therefore, when using the existing technology to determine potential traffic consumption users to increase operator revenue, there are problems of low determination efficiency and inaccurate determination results. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method and system for determining potential traffic consumption users based on interactive information, which solves the problems of low determination efficiency and inaccurate determination results when determining potential traffic consumption users using the existing technology. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current traffic package to be promoted, data processing is performed on the multi-dimensional user vector and the multi-dimensional package vector, and the vector similarity is calculated to determine whether the user is a potential consumer of the current traffic package to be promoted. This can achieve the purpose of determining the potential traffic consumption users of the current traffic package to be promoted based on the actual interaction between the user and the traffic purchasing platform, thereby improving the efficiency and accuracy of determining the potential traffic consumption users.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a potential traffic consumption user based on interaction information, the method comprising: Obtaining the interaction information between the user and the traffic purchasing platform within a preset time period, and identifying the user's traffic-related data based on the interaction information; Preprocess the traffic-related data to obtain the user's standard traffic data, and construct a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions; Obtain package data of the current traffic package to be promoted, and construct a multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions; Calculate the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identify whether the vector similarity is greater than a preset similarity threshold; When the vector similarity is greater than a preset similarity threshold, the user is determined to be a potential consumer of the current traffic package to be promoted.

[0006] Optionally, calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identifying whether the vector similarity is greater than a preset similarity threshold, includes: Calculate the vector angle between the user's multi-dimensional user vector and the multi-dimensional package vector based on the multi-dimensional vector dot multiplication algorithm; It is determined whether the magnitude of the vector angle is greater than a preset vector angle threshold value, so as to determine whether the vector similarity is greater than a preset similarity threshold value.

[0007] Optionally, the traffic-related data includes the user's inter-provincial traffic demand data and total traffic demand data; Before calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Calculate the proportion of inter-provincial traffic demand data in the total traffic demand data; Obtain the total package traffic data and inter-provincial package traffic data in the package data, and predict the target inter-provincial traffic data of the user when using the current traffic package to be promoted based on the proportion and total package traffic data; Calculate the difference between the target inter-provincial traffic data and the package inter-provincial traffic data, and determine the weight of the package inter-provincial traffic data in the multi-dimensional package vector based on the difference and the corresponding relationship between the preset traffic difference and the traffic weight; The multi-dimensional package vector is updated based on the weight, so as to calculate the vector similarity between the multi-dimensional user vector of the user and the updated multi-dimensional package vector based on a preset similarity algorithm.

[0008] Optionally, before calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Get the contract period of the user's purchased data package; Identify whether the contract period is less than the promotion period threshold of the current traffic package to be promoted; When the contract period is less than the promotion period threshold of the current traffic package to be promoted, the user is determined as a candidate potential consumer user, and the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector is calculated based on a preset similarity algorithm.

[0009] Optionally, after calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Identify the historical traffic cost level of candidate potential consumer users based on traffic correlation data; Determine the package traffic fee level of the current traffic package to be promoted based on the package data; Identify whether the historical traffic fee level is consistent with the package traffic fee level; When the historical traffic cost level is consistent with the package traffic cost level, assigning a first preset weight to the vector similarity of the candidate potential consumer user, and calculating a first weighted value of the vector similarity based on the first preset weight; When the historical traffic fee level is inconsistent with the package traffic fee level, assigning a second preset weight to the vector similarity of the candidate potential consumer user, and calculating a second weighted value of the vector similarity based on the second preset weight; Whether the vector similarity is greater than a preset similarity threshold is identified based on the first weighted value or the second weighted value.

[0010] Optionally, preprocess the traffic correlation data, including: Normalize and align traffic correlation data; Construct at least two traffic consumption triplets of the user based on the aligned traffic association data; Based on preset rules, identify whether the intra-group relationships and inter-group relationships of at least two traffic consumption triplets are all reasonable; When at least one of the intra-group relationship and the inter-group relationship of at least two traffic consumption triples is unreasonable, the traffic association data of the user is deleted to complete the preprocessing of the traffic association data.

[0011] Optionally, after determining that the user is a potential consumer of the current traffic package to be promoted, the method further includes: Identify whether the potential consumer user is a new user of the current traffic package to be promoted; In the case where the potential consumer user is a new user of the current traffic package to be promoted, promoting the package to the potential consumer user based on the first preset package promotion strategy; When the potential consumer user is not a new user of the current traffic package to be promoted, the package is promoted to the potential consumer user based on the second preset package promotion strategy.

[0012] In a second aspect, an embodiment of the present application provides a system for determining potential traffic consumption users based on interaction information, the system comprising: A traffic-related data identification module is used to obtain the interaction information between the user and the traffic purchasing platform within a preset time period, and identify the user's traffic-related data based on the interaction information; A user vector construction module is used to pre-process the traffic-related data to obtain the user's standard traffic data, and to construct a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions; A package vector construction module is used to obtain the package data of the current traffic package to be promoted, and to construct a multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions; A similarity calculation module, used to calculate the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identify whether the vector similarity is greater than a preset similarity threshold; The potential user determination module is used to determine that the user is a potential consumer user of the current traffic package to be promoted when the vector similarity is greater than a preset similarity threshold.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method of the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method of the first aspect are implemented.

[0015] In the fifth aspect, an embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium, and at least one processor of the device reads and executes the computer program from the computer-readable storage medium, so that the device performs the method of the first aspect.

[0016] In an embodiment of the present application, interaction information between a user and a traffic purchasing platform within a preset time period is obtained, and traffic-related data of the user is identified based on the interaction information; the traffic-related data is preprocessed to obtain the user's standard traffic data, and a multi-dimensional user vector of the user is constructed based on the standard traffic data and preset dimensions; package data of the current traffic package to be promoted is obtained, and a multi-dimensional package vector of the current traffic package to be promoted is constructed based on the package data and preset dimensions; the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector is calculated based on a preset similarity algorithm, and it is identified whether the vector similarity is greater than a preset similarity threshold; when the vector similarity is greater than the preset similarity threshold, the user is determined to be a potential consumer user of the current traffic package to be promoted. Through the above-mentioned method for determining potential traffic consumption users based on interactive information, the problems of low determination efficiency and inaccurate determination results existing in determining potential traffic consumption users using the existing technology are solved. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current traffic package to be promoted, the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector is calculated to determine whether the user is a potential consumer user of the current traffic package to be promoted. The purpose of determining the potential traffic consumption users of the current traffic package to be promoted based on the actual interaction between the user and the traffic purchasing platform can be achieved, thereby improving the efficiency and accuracy of determining potential traffic consumption users. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a method for determining potential traffic consumption users based on interaction information provided by an embodiment of the present application; Figure 2 It is the display interface of the traffic purchasing platform provided by this application on the user terminal; Figure 3 is a flowchart of another method for determining potential traffic consumption users based on interaction information provided by an embodiment of the present application; Figure 4 is a flow chart of preprocessing traffic association data provided by an embodiment of the present application; Figure 5 This is a structural block diagram of a system for determining potential traffic consumption users based on interactive information provided by an embodiment of the present application; Figure 6 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only part of the present application is shown in the accompanying drawings, but not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0021] First of all, the usage scenario of this solution can be the scenario of mining potential users of products to be promoted, especially mining potential traffic consumption users of traffic packages to be promoted, in order to increase the sales of traffic packages to be promoted. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current traffic package to be promoted, and calculating the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector to determine whether the user is a potential consumer user of the current traffic package to be promoted, the purpose of determining the potential traffic consumption users of the current traffic package to be promoted based on the actual interaction between the user and the traffic purchasing platform can be achieved, thereby improving the efficiency and accuracy of determining potential traffic consumption users. Based on the above usage scenarios, it can be understood that the executor of this solution can be a server.

[0022] In conjunction with the accompanying drawings, a method and system for determining potential traffic consumption users based on interactive information provided by an embodiment of the present application will be described in detail through specific embodiments and application scenarios.

[0023] Figure 1 1 is a flow chart of a method for determining potential traffic consumption users based on interactive information provided by an embodiment of the present application. Figure 1 As shown, the specific steps include: S101, obtaining interaction information between a user and a traffic purchasing platform within a preset time period, and identifying the user's traffic related data based on the interaction information.

[0024] Among them, the traffic purchase platform can be a channel for users to select and purchase traffic packages. The traffic purchase platform brings together multiple operators and the traffic packages of each operator. The traffic package includes local traffic and / or inter-provincial traffic, which is used to connect the user's terminal device to the Internet for data transmission in the province where the user's business is handled or in other provinces.

[0025] Figure 2 This is the display interface of the traffic purchasing platform provided by this application on the user terminal. Figure 2 As shown, users can interact with the traffic purchasing platform through this interface, select the operator they want to use and the user's location, search and filter packages directly according to traffic consumption needs through the search box, and click to enter the package recommendations displayed on the interface to understand the details of the package and choose whether to purchase it. When users interact with the traffic purchasing platform through this interface, the traffic purchasing platform can record all the user's operations, input data, and the length of time they stay on each page to obtain interaction information between the user and the traffic purchasing platform.

[0026] The interaction information between users and the traffic purchasing platform can be the operation information of users on the platform recorded by the traffic purchasing platform and the feedback information of the platform based on the user's operation. The operation information of users on the traffic purchasing platform includes the operation information of the traffic package search, browsing, purchase and link sharing performed by users through the traffic purchasing platform, and also includes the user identity information when the user logs in to the traffic purchasing platform, such as: user name, age and mobile phone number. Traffic-related data can be the package data of the traffic package purchased by the user and the package data of other traffic packages browsed by the user within the preset time. Package data can be data used to identify the package mode, available traffic and usage rules of the traffic package. For example: traffic operator, total available traffic, inter-provincial available traffic, package fees and network speed limit rules.

[0027] Traffic-related data can reflect the user's traffic demand and the traffic package model that the user is interested in. For example: by comparing the user's purchased traffic package data with the same or frequently appearing package data in other traffic package data that the user browses, the traffic package data that the user is interested in can be determined, including the operator of interest, the total amount of available traffic, the available traffic across provinces, the package fee, and the network speed limit rules, etc.; the user's traffic data demand can also be determined by comparing the user's purchased traffic package data with the different package data in other traffic package data that the user browses, including whether the available cross-provincial traffic in the purchased traffic package is insufficient and whether the package fee in the purchased traffic package is too high.

[0028] In one embodiment, the interaction information between the user and the traffic purchasing platform within a preset time period can be obtained by reading the interaction data records stored in the traffic purchasing platform, and the browsing and purchasing of the traffic packages of the user within the preset time period can be determined based on the user's click-to-view operation and click-to-purchase operation on the traffic package in the interaction information, and the package data in the traffic packages browsed and purchased by the user is used as the traffic associated data of the user. Since different users can use the same traffic purchasing platform to purchase traffic packages, that is, the traffic purchasing platform can store the interaction information of multiple users at the same time, the traffic associated data of multiple users can be obtained at the same time, and the traffic associated data of each user can be distinguished based on the user name and login password in the login information of each user.

[0029] S102, pre-processing the traffic-related data to obtain the user's standard traffic data, and constructing a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions.

[0030] Among them, preprocessing can be the processing of unifying, completing and filtering data in various formats. Standard traffic data can be unified and reasonable traffic data related to the user's traffic package purchase and browsing situation. Preset dimensions can be pre-set items related to the package content in the traffic package. Preset dimensions can include: operator name, traffic usage in the same region, traffic usage across regions, monthly traffic bill, whether speed is limited, etc. Multi-dimensional user vectors can be multi-dimensional data based on preset dimensions that reflect the characteristics of the traffic package that the user is interested in.

[0031] In one embodiment, the traffic-related data can be unified according to the data format and data type of each data in the traffic-related data, and the unified data can be completed based on the average value or median, and the data can be screened based on the correlation relationship between the data to obtain the user's standard traffic data. When identifying the traffic-related data of each user based on the interactive information, since the user names or user identifiers of multiple users may be highly similar, which leads to the problem that the traffic-related data between users affect each other, it is necessary to screen the traffic-related data, filter out unreasonable data and re-identify it to obtain the standard traffic data of each user. For example: if it is identified that the traffic-related data of the same user is simultaneously associated with traffic packages of more than five phone numbers, it means that the traffic-related data for the user is incorrectly identified, and the traffic-related data of the user needs to be deleted and re-acquired.

[0032] The standard traffic data is vectorized according to the preset dimensions to obtain a multi-dimensional user vector of the user. Since a user may correspond to multiple pieces of standard traffic data, and one piece of standard traffic data corresponds to a purchased traffic package or browsing traffic package of the user, the dimension value of each dimension when vectorizing the standard traffic data can be obtained by calculating the average value of the traffic data corresponding to each dimension in the multiple pieces of standard traffic data.

[0033] S103, obtaining package data of the current traffic package to be promoted, and constructing a multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions.

[0034] The current traffic package to be promoted may be a package to be promoted to provide users with mobile data for Internet access. The multi-dimensional package vector may be multi-dimensional data reflecting the package characteristics of the current traffic package to be promoted based on preset dimensions.

[0035] In one embodiment, the package data of the current traffic package to be promoted can be obtained by receiving the operator's product data, preprocessing the package data, and vectorizing the processed package data according to preset dimensions to obtain a multi-dimensional package vector of the current traffic package to be promoted.

[0036] S104, calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identifying whether the vector similarity is greater than a preset similarity threshold.

[0037] Among them, the preset similarity algorithm can be a preset algorithm for calculating the similarity between a multi-dimensional user vector and a multi-dimensional package vector. For example: calculating the Euclidean distance, Manhattan distance and cosine value of the angle between two vectors. Since the multi-dimensional package vector and the multi-dimensional user vector have the same dimension, the degree of consistency between the package characteristics of the traffic package that the user is interested in and the package characteristics of the current traffic package to be promoted can be determined based on the similarity between the vectors. The higher the degree of consistency, the more the current traffic package to be promoted meets the user's needs, and the more likely the user is to be a potential traffic consumer user of the current traffic package to be promoted. Vector similarity can be the degree of consistency between the multi-dimensional user vector and the multi-dimensional package vector. The preset similarity threshold can be the minimum value of the vector similarity between the multi-dimensional user vector of a potential traffic consumer user and the multi-dimensional package vector that is preset.

[0038] In one embodiment, the vector similarities between the multi-dimensional user vectors and the multi-dimensional package vectors of each user interacting with the traffic purchasing platform can be calculated respectively through a preset similarity algorithm, and whether the similarity of each vector is greater than the preset similarity threshold is determined by calculating whether the difference between each vector similarity and the preset similarity threshold is greater than 0.

[0039] In one embodiment, optionally, calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identifying whether the vector similarity is greater than a preset similarity threshold, includes: Calculate the vector angle between the user's multi-dimensional user vector and the multi-dimensional package vector based on the multi-dimensional vector dot multiplication algorithm; It is determined whether the magnitude of the vector angle is greater than a preset vector angle threshold value, so as to determine whether the vector similarity is greater than a preset similarity threshold value.

[0040] Among them, the multidimensional vector dot multiplication algorithm can be expressed by the following formula: The vector angle can be used to indicate the degree of difference between the multi-dimensional user vector and the multi-dimensional package vector. The larger the vector angle, the greater the degree of difference between the multi-dimensional user vector and the multi-dimensional package vector, the lower the vector similarity, and vice versa. The preset vector angle threshold can be the maximum value of the vector angle between the multi-dimensional user vector and the multi-dimensional package vector of a pre-set potential traffic consumption user.

[0041] In one embodiment, the vector angle between the user's multi-dimensional user vector and the multi-dimensional package vector can be calculated based on the multi-dimensional vector dot multiplication algorithm, and the size of the vector angle can be compared to see whether it is greater than a preset vector angle threshold. If it is greater, it means that the difference between the user's multi-dimensional user vector and the multi-dimensional package vector is large, and the vector similarity is less than the preset similarity threshold; if it is less than or equal to, it means that the difference between the user's multi-dimensional user vector and the multi-dimensional package vector is small, and the vector similarity is greater than or equal to the preset similarity threshold.

[0042] This solution calculates the vector angle between the multi-dimensional user vector and the multi-dimensional package vector through a multi-dimensional vector dot multiplication algorithm, and determines whether the vector similarity is greater than a preset similarity threshold based on the size of the vector angle, thereby improving the efficiency of determining potential traffic consumption users.

[0043] In one embodiment, optionally, the traffic-related data includes the user's inter-provincial traffic demand data and total traffic demand data; Before calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Calculate the proportion of inter-provincial traffic demand data in the total traffic demand data; Obtain the total package traffic data and inter-provincial package traffic data in the package data, and predict the target inter-provincial traffic data of the user when using the current traffic package to be promoted based on the proportion and total package traffic data; Calculate the difference between the target inter-provincial traffic data and the package inter-provincial traffic data, and determine the weight of the package inter-provincial traffic data in the multi-dimensional package vector based on the difference and the corresponding relationship between the preset traffic difference and the traffic weight; The multi-dimensional package vector is updated based on the weight, so as to calculate the vector similarity between the multi-dimensional user vector of the user and the updated multi-dimensional package vector based on a preset similarity algorithm.

[0044] Among them, the inter-provincial traffic demand data may be the amount of mobile data required by users when using traffic to access the Internet in provinces other than those where traffic package services are applied for. The total traffic demand data may be the total amount of mobile data required by users when using traffic to access the Internet in all provinces. The total package traffic data may be the total amount of mobile data available in all provinces included in the traffic package to be promoted. The package inter-provincial traffic data may be the amount of mobile data available in provinces other than those where users apply for traffic package services, which are included in the traffic package to be promoted. The target inter-provincial traffic data may be the amount of mobile data in other provinces that users hope to obtain when using the traffic package to be promoted. The traffic weight may be the weight of the inter-provincial traffic data allocated to the traffic package to be promoted. The more the traffic package to be promoted meets the needs of users, the smaller the difference and the larger the corresponding traffic weight.

[0045] In one embodiment, the user's inter-provincial traffic demand data can be determined by calculating the average value of the inter-provincial traffic in the user's purchased traffic package and the browsing traffic package, and the user's total traffic demand data can be determined by calculating the average value of all available traffic in the user's purchased traffic package and the browsing traffic package. The ratio of the inter-provincial traffic demand data to the total traffic demand data is calculated to determine the proportion of the inter-provincial traffic demand data in the total traffic demand data, the total package traffic data and the package inter-provincial traffic data in the package data are identified, and the product of the proportion and the package total traffic data is calculated to predict the user's target inter-provincial traffic data when using the current traffic package to be promoted. The difference between the target inter-provincial traffic data and the package inter-provincial traffic data is calculated, and the weight of the package inter-provincial traffic data in the multi-dimensional package vector is determined according to the difference and the corresponding relationship between the preset traffic difference and the traffic weight, and the weighted value of the package inter-provincial traffic data in the multi-dimensional package vector is calculated to obtain the update result of the multi-dimensional package vector, so as to calculate the vector similarity between the user's multi-dimensional user vector and the updated multi-dimensional package vector based on the preset similarity algorithm.

[0046] This solution calculates the proportion of the user's inter-provincial traffic demand data in the total traffic demand data, predicts the user's target inter-provincial traffic data when using the current traffic package to be promoted, and determines the weight of the package's inter-provincial traffic data in the multi-dimensional package vector. This can achieve the purpose of focusing on mining potential traffic consumption users of the current traffic to be promoted based on inter-provincial traffic, and further improves the accuracy of determining potential traffic consumption users.

[0047] S105: When the vector similarity is greater than a preset similarity threshold, the user is determined to be a potential consumer of the current traffic package to be promoted.

[0048] In one embodiment, when the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector is greater than a preset similarity threshold, it indicates that the package data in the current traffic package to be promoted meets the user's needs, and the user is determined to be a potential consumer user of the current traffic package to be promoted.

[0049] In one embodiment, optionally, after determining that the user is a potential consumer of the current traffic package to be promoted, the method further includes: Identify whether the potential consumer user is a new user of the current traffic package to be promoted; In the case where the potential consumer user is a new user of the current traffic package to be promoted, promoting the package to the potential consumer user based on the first preset package promotion strategy; When the potential consumer user is not a new user of the current traffic package to be promoted, the package is promoted to the potential consumer user based on the second preset package promotion strategy.

[0050] Among them, the new user of the current traffic package to be promoted may be a user who has not purchased the current traffic package to be promoted. The first preset package promotion strategy may be a promotion strategy for new users of the traffic package pre-formulated by the operator. The second preset package promotion strategy may be a promotion strategy for old users of the traffic package pre-formulated by the operator. The first preset package promotion strategy and the second preset package promotion strategy are related to the specific marketing rules of the operator, and the first preset package promotion strategy and the second preset package promotion strategy may be the same or different.

[0051] In one embodiment, it can be determined whether the potential consumer user is a new user of the current traffic package to be promoted based on the traffic package purchase record of the potential consumer user. If the potential consumer user is a new user of the current traffic package to be promoted, a first traffic package promotion link is generated according to a first preset package promotion strategy, and the link is sent to the terminal of the potential consumer user for package promotion; if the potential consumer user is not a new user of the current traffic package to be promoted, a second traffic package promotion link is generated according to a second preset package promotion strategy, and the link is sent to the terminal of the potential consumer user for package promotion.

[0052] This solution, by identifying whether the potential consumer user is a new user of the current traffic package to be promoted, determines the package promotion strategy for the user, and then promotes the package to the user. This can achieve the purpose of promoting the package in different ways according to the characteristics of different users, which is conducive to improving the success rate of potential traffic consumer users in applying for the current traffic package to be promoted.

[0053] The technical solution provided in the embodiment of the present application obtains the interaction information between the user and the traffic purchasing platform within a preset time period, identifies the user's traffic association data based on the interaction information; pre-processes the traffic association data to obtain the user's standard traffic data, and constructs the user's multi-dimensional user vector based on the standard traffic data and preset dimensions; obtains the package data of the current traffic package to be promoted, and constructs the multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions; calculates the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector based on a preset similarity algorithm, and identifies whether the vector similarity is greater than a preset similarity threshold; when the vector similarity is greater than the preset similarity threshold, determines that the user is a potential consumer user of the current traffic package to be promoted. Through the above-mentioned method for determining potential traffic consumption users based on interactive information, the problems of low determination efficiency and inaccurate determination results existing in determining potential traffic consumption users using the existing technology are solved. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current traffic package to be promoted, the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector is calculated to determine whether the user is a potential consumer user of the current traffic package to be promoted. The purpose of determining the potential traffic consumption users of the current traffic package to be promoted based on the actual interaction between the user and the traffic purchasing platform can be achieved, thereby improving the efficiency and accuracy of determining potential traffic consumption users.

[0054] Figure 3 FIG. 1 is a flowchart of another method for determining potential traffic consumption users based on interactive information provided by an embodiment of the present application. Figure 3 As shown, the specific steps include: S301, obtaining interaction information between a user and a traffic purchasing platform within a preset time period, and identifying the user's traffic related data based on the interaction information.

[0055] S302, pre-processing the traffic-related data to obtain the user's standard traffic data, and constructing a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions.

[0056] S303, obtaining package data of the current traffic package to be promoted, and constructing a multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions.

[0057] S304, obtaining the contract period of the user's purchased traffic package.

[0058] The contract period of the purchased data package may be the earliest period at which the user can stop using the purchased data package. For example, if the contract period of a data package is two years, and the user signs up for the data package in December 2022, the contract period of the user is December 2024, that is, the user can stop using the data package after December 2024.

[0059] In one embodiment, the contract duration and package processing time of the user's purchased traffic package can be determined based on the package data of the user's purchased traffic package, and the user's contract period for the traffic package can be calculated based on the contract duration and package processing time.

[0060] S305, identifying whether the contract period is less than the promotion period threshold of the current traffic package to be promoted.

[0061] The promotion period threshold may be the latest promotion period of the current traffic package to be promoted. Since the traffic packages of various operators and the traffic consumption needs of users are constantly adjusted and changed, in order to ensure the effectiveness of the promotion of the current traffic package to be promoted, it is necessary to determine the promotion period threshold for the current traffic package to be promoted according to the promotion needs of the operator.

[0062] In one embodiment, whether the contract period of the user's purchased traffic package is less than the promotion period threshold of the current traffic package to be promoted can be determined by comparing the contract period with the promotion period threshold of the current traffic package to be promoted in order of date.

[0063] S306, when the contract period is less than the promotion period threshold of the current traffic package to be promoted, the user is determined as a candidate potential consumer user, and the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector is calculated based on a preset similarity algorithm.

[0064] Among them, the candidate potential consumer users may be traffic consumer users whose contract period is before the promotion period threshold of the current traffic package to be promoted.

[0065] In one embodiment, when the contract period of the user's purchased traffic package is before the promotion period threshold of the current traffic package to be promoted, the user is determined as a candidate potential consumer user, and the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector is calculated based on a preset similarity algorithm.

[0066] S307, calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identifying whether the vector similarity is greater than a preset similarity threshold.

[0067] In one embodiment, optionally, after calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Identify the historical traffic cost level of candidate potential consumer users based on traffic correlation data; Determine the package traffic fee level of the current traffic package to be promoted based on the package data; Identify whether the historical traffic fee level is consistent with the package traffic fee level; When the historical traffic cost level is consistent with the package traffic cost level, assigning a first preset weight to the vector similarity of the candidate potential consumer user, and calculating a first weighted value of the vector similarity based on the first preset weight; When the historical traffic fee level is inconsistent with the package traffic fee level, assigning a second preset weight to the vector similarity of the candidate potential consumer user, and calculating a second weighted value of the vector similarity based on the second preset weight; Whether the vector similarity is greater than a preset similarity threshold is identified based on the first weighted value or the second weighted value.

[0068] Among them, the historical traffic cost level may be the level corresponding to the package fee of the traffic package that the user has historically applied for. The package traffic cost level may be the level corresponding to the package fee of the current traffic package to be promoted. The historical traffic cost level and the package traffic cost level are determined by the correspondence between the same fee amount and the fee level. The first preset weight may be a parameter for increasing the magnitude of vector similarity. The second preset weight may be a parameter for reducing the magnitude of vector similarity. When the user's historical traffic cost level is consistent with the package traffic cost level, the user is more likely to be a potential traffic consumer. At this time, the vector similarity value can be increased by the first preset weight to determine the user as a potential traffic consumer. Otherwise, the vector similarity value is reduced by the second preset weight to avoid the user being determined as a potential traffic consumer.

[0069] In one embodiment, the historical traffic cost of the user can be determined based on the package cost of the purchased traffic package of the candidate potential consumer user in the traffic association data, and the historical traffic cost level of the user can be determined based on the correspondence between the preset cost amount and the cost level. The package traffic cost level of the current traffic package to be promoted is determined based on the correspondence between the package cost and the preset cost amount and the cost level in the package data. Compare whether the historical traffic cost level and the package traffic cost level are at the same level. If so, assign a first preset weight to the vector similarity of the candidate potential consumer user, and calculate the first weighted value of the vector similarity; if not, assign a second preset weight to the vector similarity of the candidate potential consumer user, and calculate the second weighted value of the vector similarity, and identify whether the vector similarity is greater than the preset similarity threshold based on the first weighted value or the second weighted value.

[0070] This scheme, by determining the weight of vector similarity according to the historical traffic cost level of candidate potential consumer users and the package traffic cost level of the current traffic package to be promoted, and calculating the weighted value of vector similarity based on the weight, can achieve the purpose of further determining potential traffic consumer users based on user consumption levels, and improves the comprehensiveness of factors for determining potential traffic consumer users.

[0071] S308: When the vector similarity is greater than a preset similarity threshold, the user is determined to be a potential consumer of the current traffic package to be promoted.

[0072] The technical solution provided in the embodiment of the present application determines candidate potential consumer users by identifying whether the contract period of the user's purchased traffic package is less than the promotion period threshold of the current traffic package to be promoted, thereby ensuring the effectiveness of the current traffic package to be promoted for potential traffic consumer users, and thus helping to increase the probability of potential traffic consumer users completing a transaction for the current traffic package to be promoted.

[0073] Figure 4 Flowchart of preprocessing traffic correlation data provided by the embodiment of the present application. Figure 4 As shown, the specific steps include: S401, normalizing and aligning the traffic-related data.

[0074] Among them, normalization can be an operation used to eliminate differences between data and convert data from different sources or formats into standard format data. For example, the fee amount in the package data and the available traffic across provinces are of different dimensions and cannot be directly compared by numbers. In this case, these data need to be normalized and converted into scalar data. Data alignment is an operation to unify the length of data. For example, to complete missing data, etc.

[0075] In one embodiment, the traffic data may be normalized and aligned according to the format, type, and length of the data in the traffic association data.

[0076] S402: construct at least two traffic consumption triplets of the user based on the aligned traffic association data.

[0077] The traffic consumption triplet may be a structure representing the relationship between a user and an entity in a traffic package or between entities in a traffic package, for example: <user name: mobile phone number: 12345678910>, <user name: package amount: 38>.

[0078] In one embodiment, at least two traffic consumption triplets of a user may be constructed according to the relationship between every two entities in the aligned traffic association data.

[0079] S403: Identify, based on preset rules, whether the intra-group relationships and inter-group relationships of at least two traffic consumption triples are all reasonable.

[0080] Among them, the preset rules can be rules pre-set according to the operator's operating rules and traffic consumption experience data for identifying whether the entity relationship of the traffic consumption triplet conforms to normal circumstances.

[0081] In one embodiment, it is possible to identify whether the intra-group relationship and inter-group relationship of at least two traffic consumption triplets are all reasonable according to preset rules. For example, if the preset rules include that a user can only be associated with five mobile phone numbers at most, then when the mobile phone number triplets of the same user exceed five groups, it can be determined that the mobile phone number triplets of the user are unreasonable, or if the amount of traffic expenses of a user in a triplet in a certain month is far more than that in other months, then the traffic expense triplets of the user in that month are unreasonable.

[0082] S404: When at least one of the intra-group relationship and the inter-group relationship of at least two traffic consumption triples is unreasonable, the traffic association data of the user is deleted to complete the preprocessing of the traffic association data.

[0083] In one embodiment, when the user names or login information of users are highly similar, confusion in traffic consumption records is likely to occur. Therefore, when it is identified that there is at least one unreasonable intra-group relationship and inter-group relationship of at least two traffic consumption triplets, the user's traffic-related data needs to be deleted to avoid interference of erroneous data in the subsequent identification of potential traffic consumption users.

[0084] The technical solution provided in the embodiment of the present application constructs at least two traffic consumption triplets of the user, identifies whether the intra-group relationships and inter-group relationships of each traffic consumption triplet are all reasonable, and deletes the traffic-related data of unreasonable users. This can avoid the problem of incorrect determination results of potential traffic consumption users due to incorrect records of traffic-related data, thereby improving the accuracy of determination results of potential traffic consumption users.

[0085] Figure 5 is a structural block diagram of a system for determining potential traffic consumption users based on interactive information provided by an embodiment of the present application. Figure 5 As shown, specifically including the following: The traffic correlation data identification module 501 is used to obtain the interaction information between the user and the traffic purchasing platform within a preset time period, and identify the user's traffic correlation data based on the interaction information; A user vector construction module 502 is used to pre-process the traffic-related data to obtain the user's standard traffic data, and to construct a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions; A package vector construction module 503 is used to obtain package data of the current traffic package to be promoted, and to construct a multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions; A similarity calculation module 504 is used to calculate the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identify whether the vector similarity is greater than a preset similarity threshold; The potential user determination module 505 is used to determine that the user is a potential consumer user of the current traffic package to be promoted when the vector similarity is greater than a preset similarity threshold.

[0086] Optionally, the similarity calculation module 504 is specifically used for: Calculate the vector angle between the user's multi-dimensional user vector and the multi-dimensional package vector based on the multi-dimensional vector dot multiplication algorithm; It is determined whether the magnitude of the vector angle is greater than a preset vector angle threshold value, so as to determine whether the vector similarity is greater than a preset similarity threshold value.

[0087] Optionally, the traffic-related data includes the user's inter-provincial traffic demand data and total traffic demand data; The similarity calculation module 504 is further used for: Calculate the proportion of inter-provincial traffic demand data in the total traffic demand data; Obtain the total package traffic data and inter-provincial package traffic data in the package data, and predict the target inter-provincial traffic data of the user when using the current traffic package to be promoted based on the proportion and total package traffic data; Calculate the difference between the target inter-provincial traffic data and the package inter-provincial traffic data, and determine the weight of the package inter-provincial traffic data in the multi-dimensional package vector based on the difference and the corresponding relationship between the preset traffic difference and the traffic weight; The multi-dimensional package vector is updated based on the weight, so as to calculate the vector similarity between the multi-dimensional user vector of the user and the updated multi-dimensional package vector based on a preset similarity algorithm.

[0088] Optionally, the system further includes: The contract period acquisition module is used to obtain the contract period of the user's purchased traffic package; A term identification module is used to identify whether the contract term is less than the promotion term threshold of the current traffic package to be promoted; The candidate potential consumer user determination module is used to determine the user as a candidate potential consumer user when the contract period is less than the promotion period threshold of the current traffic package to be promoted, so as to calculate the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector based on a preset similarity algorithm.

[0089] Optionally, the system further includes: A historical traffic cost level identification module is used to identify the historical traffic cost level of candidate potential consumer users based on traffic correlation data; A package traffic fee level determination module is used to determine the package traffic fee level of the current traffic package to be promoted based on the package data; A level identification module is used to identify whether the historical traffic fee level is consistent with the package traffic fee level; A similarity first weighting module, used for assigning a first preset weight to the vector similarity of the candidate potential consumer user when the historical traffic cost level is consistent with the package traffic cost level, and calculating a first weighted value of the vector similarity based on the first preset weight; A similarity second weighting module, used for assigning a second preset weight to the vector similarity of the candidate potential consumer user when the historical traffic cost level is inconsistent with the package traffic cost level, and calculating a second weighted value of the vector similarity based on the second preset weight; The similarity identification module is used to identify whether the vector similarity is greater than a preset similarity threshold based on the first weighted value or the second weighted value.

[0090] Optionally, the user vector construction module 502 is specifically used for: Normalize and align traffic correlation data; Construct at least two traffic consumption triplets of the user based on the aligned traffic association data; Based on preset rules, identify whether the intra-group relationships and inter-group relationships of at least two traffic consumption triplets are all reasonable; When at least one of the intra-group relationship and the inter-group relationship of at least two traffic consumption triples is unreasonable, the traffic association data of the user is deleted to complete the preprocessing of the traffic association data.

[0091] Optionally, the system further includes: A new user identification module is used to identify whether a potential consumer user is a new user of the current traffic package to be promoted; A first promotion module, configured to promote a package to a potential consumer user based on a first preset package promotion strategy when the potential consumer user is a new user of the current traffic package to be promoted; The second promotion module is used to promote packages to potential consumer users based on a second preset package promotion strategy when the potential consumer users are not new users of the current traffic package to be promoted.

[0092] The technical solution provided in the embodiment of the present application includes a traffic association data identification module, which is used to obtain the interaction information between the user and the traffic purchasing platform within a preset time period, and identify the user's traffic association data based on the interaction information; a user vector construction module, which is used to pre-process the traffic association data to obtain the user's standard traffic data, and construct the user's multi-dimensional user vector based on the standard traffic data and preset dimensions; a package vector construction module, which is used to obtain the package data of the current traffic package to be promoted, and construct the multi-dimensional package vector of the current traffic package to be promoted based on the package data and preset dimensions; a similarity calculation module, which is used to calculate the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector based on a preset similarity algorithm, and identify whether the vector similarity is greater than a preset similarity threshold; a potential user determination module, which is used to determine that the user is a potential consumer user of the current traffic package to be promoted when the vector similarity is greater than the preset similarity threshold. The above-mentioned system for determining potential traffic consumption users based on interactive information solves the problems of low efficiency and inaccurate results in determining potential traffic consumption users using the prior art. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current traffic package to be promoted, and calculating the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector, it is determined whether the user is a potential consumer of the current traffic package to be promoted. The purpose of determining the potential traffic consumption users of the current traffic package to be promoted based on the actual interaction between the user and the traffic purchasing platform can be achieved, thereby improving the efficiency and accuracy of determining the potential traffic consumption users.

[0093] A potential traffic consumption user determination system based on interactive information in an embodiment of the present application can be configured in a component, integrated circuit, or chip in a terminal. It can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0094] In the embodiment of the present application, a system for determining potential traffic consumption users based on interactive information may be an operating system, which may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0095] The system for determining potential traffic consumption users based on interactive information provided in the embodiments of the present application can implement the various processes implemented in the above-mentioned method embodiments. To avoid repetition, they will not be described again here.

[0096] like Figure 6 As shown, an embodiment of the present application also provides an electronic device 600, including a processor 601, a memory 602, and a program or instruction stored in the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, each process of an embodiment of a method for determining a potential traffic consumption user based on interactive information is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0097] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0098] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned embodiment of a method for determining potential traffic consumption users based on interactive information is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0099] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0100] The embodiment of the present application further provides a program product, which includes a program code. When the program product is run on a computer device, the program code is used to enable the computer device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification. For example, the computer device can execute a method for determining a potential traffic consumption user based on interactive information recorded in the embodiment of the present application. The program product can be implemented in any combination of one or more readable media.

[0101] It should be noted that, in this article, the term "comprises", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or system including the element. In addition, it should be pointed out that the scope of the method and system in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0103] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0104] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for determining potential traffic consumption users based on interactive information, characterized in that: The method comprises: Acquire interaction information between the user and the traffic purchasing platform within a preset time period, and identify traffic-related data of the user based on the interaction information; Preprocessing the traffic-related data to obtain standard traffic data of the user, and constructing a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions; Acquire package data of the current traffic package to be promoted, and construct a multi-dimensional package vector of the current traffic package to be promoted based on the package data and the preset dimensions; Calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identifying whether the vector similarity is greater than a preset similarity threshold; When the vector similarity is greater than the preset similarity threshold, it is determined that the user is a potential consumer user of the current traffic package to be promoted.

2. The method for determining potential traffic consumption users based on interactive information according to claim 1, characterized in that: The calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identifying whether the vector similarity is greater than a preset similarity threshold, includes: Calculate the vector angle between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a multi-dimensional vector dot multiplication algorithm; It is identified whether the magnitude of the vector angle is greater than a preset vector angle threshold, so as to determine whether the vector similarity is greater than a preset similarity threshold.

3. The method for determining potential traffic consumption users based on interactive information according to claim 1, characterized in that: The traffic-related data includes the user's inter-provincial traffic demand data and total traffic demand data; Before calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Calculate the proportion of the inter-provincial traffic demand data in the total traffic demand data; Obtaining total package traffic data and inter-provincial package traffic data from the package data, and predicting target inter-provincial traffic data of the user when using the current traffic package to be promoted based on the proportion and the total package traffic data; Calculate the difference between the target inter-provincial traffic data and the inter-provincial traffic data of the package, and determine the weight of the inter-provincial traffic data of the package in the multi-dimensional package vector based on the difference and the corresponding relationship between the preset traffic difference and the traffic weight; The multi-dimensional package vector is updated based on the weight, so as to calculate the vector similarity between the multi-dimensional user vector of the user and the updated multi-dimensional package vector based on a preset similarity algorithm.

4. The method for determining potential traffic consumption users based on interactive information according to claim 1, characterized in that: Before calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Obtain the contract period of the purchased traffic package of the user; Identify whether the contract period is less than the promotion period threshold of the current traffic package to be promoted; When the contract period is less than the promotion period threshold of the current traffic package to be promoted, the user is determined as a candidate potential consumer user, and the vector similarity between the user's multi-dimensional user vector and the multi-dimensional package vector is calculated based on a preset similarity algorithm.

5. The method for determining potential traffic consumption users based on interactive information according to claim 4, characterized in that: After calculating the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, the method further includes: Identify the historical traffic cost level of the candidate potential consumer user based on the traffic association data; Determine the package traffic fee level of the current traffic package to be promoted based on the package data; Respectively identify whether the historical traffic fee level is consistent with the package traffic fee level; In the case where the historical traffic cost level is consistent with the package traffic cost level, assigning a first preset weight to the vector similarity of the candidate potential consumer user, and calculating a first weighted value of the vector similarity based on the first preset weight; In the case where the historical traffic cost level is inconsistent with the package traffic cost level, assigning a second preset weight to the vector similarity of the candidate potential consumer user, and calculating a second weighted value of the vector similarity based on the second preset weight; It is identified whether the vector similarity is greater than a preset similarity threshold based on the first weighted value or the second weighted value.

6. The method for determining potential traffic consumption users based on interactive information according to claim 1, characterized in that: The preprocessing of the traffic-related data includes: Performing normalization and data alignment on the traffic-related data; Constructing at least two traffic consumption triplets of the user based on the aligned traffic association data; Based on preset rules, respectively identify whether the intra-group relationship and the inter-group relationship of the at least two traffic consumption triples are all reasonable; When at least one of the intra-group relationship and the inter-group relationship of the at least two traffic consumption triples is unreasonable, the traffic association data of the user is deleted to complete the preprocessing of the traffic association data.

7. The method for determining potential traffic consumption users based on interactive information according to claim 1, characterized in that: After determining that the user is a potential consumer of the current traffic package to be promoted, the method further includes: Identify whether the potential consumer user is a new user of the current traffic package to be promoted; In the case where the potential consumer user is a new user of the current traffic package to be promoted, promoting the package to the potential consumer user based on a first preset package promotion strategy; In a case where the potential consumer user is not a new user of the current traffic package to be promoted, a package promotion is performed to the potential consumer user based on a second preset package promotion strategy.

8. A system for determining potential traffic consumption users based on interactive information, characterized in that: The system comprises: A traffic-related data identification module, used to obtain interaction information between a user and a traffic purchasing platform within a preset time period, and identify the user's traffic-related data based on the interaction information; A user vector construction module, configured to pre-process the traffic-related data to obtain standard traffic data of the user, and to construct a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension; A package vector construction module, used to obtain package data of the current traffic package to be promoted, and to construct a multi-dimensional package vector of the current traffic package to be promoted based on the package data and the preset dimensions; A similarity calculation module, used to calculate the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a preset similarity algorithm, and identify whether the vector similarity is greater than a preset similarity threshold; The potential user determination module is used to determine that the user is a potential consumer user of the current traffic package to be promoted when the vector similarity is greater than the preset similarity threshold.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of a method for determining potential traffic consumption users based on interactive information as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of a method for determining potential traffic consumption users based on interactive information as described in any one of claims 1-7 are implemented.

Images