A potential traffic consumption user determination method and system based on interaction information

Abstract

The application discloses a potential traffic consumption user determination method and system based on interaction information, and the method comprises the following steps: identifying traffic association data of a user based on interaction information; preprocessing the traffic association data to obtain standard traffic data of the user, and constructing a multidimensional user vector of the user; obtaining package data of a current traffic package to be promoted, and constructing a multidimensional package vector of the current traffic package to be promoted; calculating the vector similarity between the multidimensional user vector and the multidimensional package vector based on a preset similarity algorithm; and determining the user as a potential consumption user of the current traffic package to be promoted when the vector similarity is greater than a preset similarity threshold. Through the technical scheme, the efficiency and accuracy of determining the potential traffic consumption user can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data processing, and particularly relates to a potential traffic consumption user determination method and system based on interaction information. BACKGROUND

[0002] The potential traffic consumption user refers to a user who has a consumption demand or interest in a certain traffic package service but has not yet handled the package service, and has the possibility of becoming a future service handler. In order to improve the sales of the traffic package service and the operator's income, it has become very important to process the consumption data of the traffic consumption user and then mine the potential traffic consumption user.

[0003] The prior art mainly determines whether a user is interested in a current traffic package service to be promoted by sending an advertisement push link of the traffic package to the user to identify whether the user has clicked the current push traffic package advertisement, or sends a traffic consumption survey questionnaire to the user to determine whether the current traffic package service to be promoted meets the user's demand by processing the feedback data of the user, and then determines whether the user is a potential traffic consumption user. However, whether the user clicks the advertisement link of the traffic package is not completely the same as the user's final purchase result, and a large amount of time cost is required for the investigation based on the survey questionnaire and the feedback data processing. Therefore, when the prior art is used to determine the potential traffic consumption user to improve the operator's income, there are problems of low determination efficiency and inaccurate determination result. SUMMARY

[0004] The purpose of the embodiments of the application is to provide a potential traffic consumption user determination method and system based on interaction information, which solves the problems of low determination efficiency and inaccurate determination result when the prior art is used to determine the potential traffic consumption user. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current traffic package to be promoted, the multi-dimensional user vector and the multi-dimensional package vector are processed, the vector similarity is calculated, and it is determined whether the user is a potential consumption user of the current traffic package to be promoted. The purpose of determining the potential traffic consumption user of the current traffic package to be promoted based on the actual interaction of the user and the traffic purchase platform can be achieved, and the efficiency and accuracy of determining the potential traffic consumption user are improved.

[0005] In a first aspect, the embodiments of the application provide a potential traffic consumption user determination method based on interaction information, and the method comprises:

[0006] Obtaining interaction information of a user with a traffic purchase platform within a preset time length, and identifying traffic association data of the user based on the interaction information;

[0007] The traffic correlation data is preprocessed to obtain standard traffic data of the user, and a multi-dimensional user vector of the user is constructed based on the standard traffic data and a preset dimension;

[0008] Package data of the current to-be-promoted traffic package is obtained, and a multi-dimensional package vector of the current to-be-promoted traffic package is constructed based on the package data and the preset dimension;

[0009] The vector similarity between the multi-dimensional user vector of the user 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;

[0010] In a case where the vector similarity is greater than the preset similarity threshold, it is determined that the user is a potential consumer of the current to-be-promoted traffic package.

[0011] Optionally, the vector similarity between the multi-dimensional user vector of the user 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, including:

[0012] The vector angle between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on a multi-dimensional vector dot product algorithm;

[0013] It is identified whether the size of the vector angle is greater than a preset vector angle threshold, so as to determine whether the vector similarity is greater than the preset similarity threshold.

[0014] Optionally, the traffic correlation data includes cross-province traffic demand data and total traffic demand data of the user;

[0015] Before the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on the preset similarity algorithm, the method further includes:

[0016] The proportion of the cross-province traffic demand data in the total traffic demand data is calculated;

[0017] The total traffic data and the cross-province traffic data of the package in the package data are obtained, and the target cross-province traffic data of the user in a case where the current to-be-promoted traffic package is used is predicted based on the proportion and the total traffic data of the package;

[0018] The difference between the target cross-province traffic data and the cross-province traffic data of the package is calculated, and the weight of the cross-province traffic data of the package in the multi-dimensional package vector is determined based on the difference and a corresponding relationship between a preset traffic difference and a traffic weight;

[0019] 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 the preset similarity algorithm.

[0020] Optionally, before the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on the preset similarity algorithm, the method further comprises:

[0021] Obtaining a contract period of the purchased traffic package of the user;

[0022] Identifying whether the contract period is less than a promotion period threshold of the current traffic package to be promoted;

[0023] In the case that 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 consumption user, so as to calculate the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector based on the preset similarity algorithm.

[0024] Optionally, after the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on the preset similarity algorithm, the method further comprises:

[0025] Identifying a historical traffic fee level of the candidate potential consumption user based on the traffic association data;

[0026] Determining a package traffic fee level of the current traffic package to be promoted based on the package data;

[0027] Respectively identifying whether the historical traffic fee level and the package traffic fee level are consistent;

[0028] In the case that the historical traffic fee level and the package traffic fee level are consistent, assigning a first preset weight to the vector similarity of the candidate potential consumption user, and calculating a first weighted value of the vector similarity based on the first preset weight;

[0029] In the case that the historical traffic fee level and the package traffic fee level are inconsistent, assigning a second preset weight to the vector similarity of the candidate potential consumption user, and calculating a second weighted value of the vector similarity based on the second preset weight;

[0030] Identifying whether the vector similarity is greater than a preset similarity threshold based on the first weighted value or the second weighted value.

[0031] Optionally, the traffic association data is preprocessed, including:

[0032] The traffic association data is normalized and data-aligned;

[0033] At least two traffic consumption triplets of the user are constructed based on the aligned traffic association data;

[0034] Based on a preset rule, whether the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets are all reasonable is identified respectively;

[0035] In at least one unreasonable case of the group relationship and the inter-group relationship of the at least two traffic consumption triplets, the traffic association data of the user is deleted to complete the preprocessing of the traffic association data.

[0036] Optionally, after determining that the user is a potential consumption user of the current traffic package to be promoted, the method further comprises:

[0037] Identifying whether the potential consumption user is a new user of the current traffic package to be promoted;

[0038] In a case where the potential consumption user is a new user of the current traffic package to be promoted, promoting the package to the potential consumption user based on a first preset package promotion strategy;

[0039] In a case where the potential consumption user is not a new user of the current traffic package to be promoted, promoting the package to the potential consumption user based on a second preset package promotion strategy.

[0040] In a second aspect, an embodiment of the present application provides a system for determining a potential traffic consumption user based on interaction information, the system comprising:

[0041] A traffic association data identification module, configured to acquire interaction information of a user with a traffic purchase platform within a preset time length, and identify traffic association data of the user based on the interaction information;

[0042] A user vector construction module, configured to preprocess the traffic association data to obtain standard traffic data of the user, and construct a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension;

[0043] A package vector construction module, configured to acquire package data of a 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 dimension;

[0044] A similarity calculation module, configured to calculate a vector similarity between the 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;

[0045] A potential user determination module, configured to determine that the user is a potential consumption user of the current traffic package to be promoted in a case where the vector similarity is greater than the preset similarity threshold.

[0046] In a third aspect, an embodiment of the present application provides an electronic device, which comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and the program or instruction is executed by the processor to implement the steps of the method of the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a readable storage medium, and the readable storage medium stores a program or instructions, and the program or instructions are executed by a processor to implement steps of the method in the first aspect.

[0048] In a fifth aspect, an embodiment of the present application further provides a computer program product, and the computer program product includes a computer program stored in a computer readable storage medium, and at least one processor of a device reads and executes the computer program from the computer readable storage medium, so that the device executes the method in the first aspect.

[0049] In the embodiment of the present application, the interaction information of the user with the traffic purchase platform in a preset time period is acquired, the traffic association data of the user is identified based on the interaction information; the traffic association data is preprocessed to obtain the standard traffic data of the user, and the multi-dimensional user vector of the user is constructed based on the standard traffic data and the preset dimension; the package data of the current to-be-promoted traffic package is acquired, and the multi-dimensional package vector of the current to-be-promoted traffic package is constructed based on the package data and the preset dimension; the vector similarity of the multi-dimensional user vector and the multi-dimensional package vector is calculated based on the preset similarity algorithm, and it is identified whether the vector similarity is greater than a preset similarity threshold; in the case that the vector similarity is greater than the preset similarity threshold, the user is determined as a potential traffic consumption user of the current to-be-promoted traffic package. Through the above-mentioned potential traffic consumption user determination method based on the interaction information, the problems of low determination efficiency and inaccurate determination result in the prior art are solved. By constructing the multi-dimensional user vector and the multi-dimensional package vector of the current to-be-promoted traffic package, the vector similarity of the multi-dimensional user vector and the multi-dimensional package vector is calculated to determine whether the user is a potential consumption user of the current to-be-promoted traffic package, which can achieve the purpose of determining the potential traffic consumption user of the current to-be-promoted traffic package based on the actual interaction of the user with the traffic purchase platform, and improve the efficiency and accuracy of the determination of the potential traffic consumption user. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 is a flowchart of a potential traffic consumption user determination method based on interaction information provided by an embodiment of the present application;

[0051] Figure 2 is a display interface of a traffic purchase platform on a user terminal provided by the present application;

[0052] Figure 3 is a flowchart of another potential traffic consumption user determination method based on interaction information provided by an embodiment of the present application;

[0053] Figure 4 is a flowchart of preprocessing traffic association data provided by an embodiment of the present application;

[0054] Figure 5 is a structural block diagram of a potential traffic consumption user determination system based on interaction information provided by an embodiment of the present application;

[0055] Figure 6 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the objects, technical solutions and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below with reference to the drawings. It can be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application. In addition, it should be noted that, for the convenience of description, only parts related to the present application are shown in the drawings, but not all. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when the operations are completed, but can also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, etc.

[0057] The technical solutions in the embodiments of the present application will be described clearly below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0058] 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 exchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally a category and do not limit the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / ", generally indicates that the front and rear associated objects are in an "or" relationship.

[0059] Firstly, the use scenario of the scheme can be a scenario of mining potential users of a to-be-promoted product, especially a scenario of mining potential traffic consumption users of a to-be-promoted traffic package to increase the sales of the to-be-promoted traffic package. By constructing a multi-dimensional user vector and a multi-dimensional package vector of the current to-be-promoted traffic package, the vector similarity of the multi-dimensional user vector and the multi-dimensional package vector is calculated to determine whether the user is a potential traffic consumption user of the current to-be-promoted traffic package, which can achieve the purpose of determining the potential traffic consumption user of the current to-be-promoted traffic package based on the actual interaction of the user with the traffic purchase platform, and improve the efficiency and accuracy of determining the potential traffic consumption user. Based on the above use scenario, it can be understood that the execution subject of the scheme can be a server.

[0060] The application embodiment provides a potential traffic consumption user determination method and system based on interaction information, which will be described in detail below in combination with the drawings, specific embodiments and application scenarios.

[0061] Figure 1 is a flowchart of a potential traffic consumption user determination method based on interaction information provided by the application embodiment. As shown in Figure 1 , the specific steps include the following steps:

[0062] S101, obtaining interaction information of a user with a traffic purchase platform within a preset time length, and identifying traffic association data of the user based on the interaction information.

[0063] The traffic purchase platform can be a channel for the user to select and purchase a traffic package. The traffic purchase platform collects multiple operators and traffic packages of each operator. The traffic package includes local traffic and / or cross-province traffic, which is used to connect the terminal device of the user to the Internet for data transmission in the business handling province or other provinces of the user.

[0064] Figure 2 is a display interface of the traffic purchase platform on the user terminal. As shown in Figure 2 , the user can interact with the traffic purchase platform through the interface, select the operator expected to be used and the home of the user, directly search and filter the package according to the traffic consumption demand through the search box, click into the recommended package displayed on the interface to understand the detailed content of the package, and select whether to purchase, etc. When the user interacts with the traffic purchase platform through the interface, the traffic purchase platform can record all operations of the user, input data and the stay time of each page to obtain the interaction information of the user with the traffic purchase platform.

[0065] The interaction information of the user with the traffic purchase platform can be operation information of the user on the platform recorded by the traffic purchase platform and feedback information of the platform based on the operation of the user. The operation information of the user on the traffic purchase platform includes operation information of the user searching, browsing, purchasing, and sharing links of a traffic package through the traffic purchase platform, and also includes user identity information of the user when logging in to the traffic purchase platform, such as a user name, age, and mobile phone number. The traffic association data can be package data of a traffic package purchased by the user and package data of other traffic packages browsed by the user within a preset time period. The package data can be data for identifying characteristics of a traffic package, such as a package mode, available traffic, and usage rules. For example, a traffic operator, a total amount of available traffic, cross-province available traffic, a package fee, and network speed limit rules.

[0066] The traffic association data can reflect the traffic demand of the user and the traffic package mode of interest to the user. For example, by comparing the same or frequently-occurring package data in the traffic package data purchased by the user and the other traffic package data browsed by the user, the traffic package data of interest to the user can be determined, including an operator of interest, a total amount of available traffic, cross-province available traffic, a package fee, and network speed limit rules; and by comparing different package data in the traffic package data purchased by the user and the other traffic package data browsed by the user, the traffic data demand of the user can be determined, including whether the available cross-province traffic in the purchased traffic package is not enough and whether the package fee in the purchased traffic package is high.

[0067] In one embodiment, the interaction information of the user with the traffic purchase platform within a preset time period can be obtained by reading the interaction data records stored in the traffic purchase platform, the browsing and purchasing conditions of the traffic package of the user within the preset time period can be determined according to the traffic package click-to-view operation and the click-to-purchase operation of the user in the interaction information, and the package data in the traffic package browsed and purchased by the user can be taken as the traffic association data of the user. Since different users can use the same traffic purchase platform to purchase traffic packages, that is, the interaction information of multiple users can be stored in the traffic purchase platform at the same time, the traffic association data of multiple users can be obtained at the same time, and the traffic association data of each user can be distinguished based on the user name and login password in the login information of each user.

[0068] S102, preprocessing the traffic association 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 a preset dimension.

[0069] The preprocessing can be data unification, data completion and data screening of data in multiple formats. The standard traffic data can be traffic data related to traffic package purchase and browsing of the user, which is unified and reasonable. The preset dimension can be a preset item related to the content of the traffic package. The preset dimension can include an operator name, a same-region traffic usage, a cross-region traffic usage, a monthly traffic bill, whether speed limiting, etc. The multi-dimensional user vector can be multi-dimensional data reflecting the characteristics of the traffic package of interest to the user based on the preset dimension.

[0070] In an embodiment, the traffic association data can be unified according to the data format and data type of each item of the traffic association data, the unified data can be completed based on the average value or median value, and the data can be screened based on the association between the data to obtain the standard traffic data of the user. When identifying the traffic association data of each user based on the interaction information, since the user names or user identifiers of multiple users can be highly similar, the traffic association data between users can affect each other, so it is necessary to screen the traffic association data, filter out unreasonable data and re-identify to obtain the standard traffic data of each user. For example, if the traffic package of more than five phone numbers is associated with the traffic association data of the same user, it means that the traffic association data of the user is incorrectly identified, and the traffic association data of the user needs to be deleted and re-acquired.

[0071] The standard traffic data is vectorized according to the preset dimension to obtain the multi-dimensional user vector of the user. Since one user can correspond to multiple standard traffic data, one standard traffic data corresponds to one purchased traffic package or browsed traffic package of the user, therefore, when vectorizing the standard traffic data, the dimension value of each dimension can be obtained by calculating the average value of the traffic data corresponding to each dimension in multiple standard traffic data.

[0072] In S103, package data of a 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 the preset dimension.

[0073] The current traffic package to be promoted can be a package that will be promoted to provide mobile data for online use of the user. The multi-dimensional package vector can be multi-dimensional data reflecting the characteristics of the current traffic package to be promoted based on the preset dimension.

[0074] In an embodiment, the package data of the current traffic package to be promoted can be obtained by receiving product data of the operator, the package data can be preprocessed, and the processed package data can be vectorized according to the preset dimension to obtain the multi-dimensional package vector of the current traffic package to be promoted.

[0075] S104, calculate a 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.

[0076] The preset similarity algorithm can be an algorithm preset for calculating the similarity between the multi-dimensional user vector and the multi-dimensional package vector. For example, the Euclidean distance between two vectors, the Manhattan distance, and the cosine value of the angle between vectors, etc. Since the multi-dimensional package vector and the multi-dimensional user vector have the same dimension, the consistency between the package characteristics of the traffic package of interest of the user 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 consistency, the more consistent the current traffic package to be promoted is with the user's demand, and the more likely the user is a potential traffic consumption user of the current traffic package to be promoted. The vector similarity can be the 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 and the multi-dimensional package vector of the potential traffic consumption user.

[0077] In one embodiment, the vector similarity between the multi-dimensional user vector of each user interacting with the traffic purchase platform and the multi-dimensional package vector can be calculated by the preset similarity algorithm, and whether each vector similarity is greater than the preset similarity threshold can be determined by whether the difference between each vector similarity and the preset similarity threshold is greater than 0.

[0078] In one embodiment, the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector can be calculated based on the preset similarity algorithm, and whether the vector similarity is greater than the preset similarity threshold can be identified, including:

[0079] calculating a vector angle between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a multi-dimensional vector dot product algorithm;

[0080] identifying whether the size of the vector angle is greater than a preset vector angle threshold to determine whether the vector similarity is greater than the preset similarity threshold.

[0081] The multi-dimensional vector dot product algorithm can be represented by the following formula: The vector angle can be used to represent the difference between the multi-dimensional user vector and the multi-dimensional package vector. The greater the vector angle, the greater the difference between the multi-dimensional user vector and the multi-dimensional package vector, and 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 the potential traffic consumption user.

[0082] In one embodiment, the vector included angle between the multi-dimensional user vector of the user and the multi-dimensional package vector can be calculated based on a multi-dimensional vector dot product algorithm, and whether the vector included angle is greater than a preset vector included angle threshold is compared. If greater, it indicates that the difference between the multi-dimensional user vector of the user and the multi-dimensional package vector is greater, and the vector similarity is less than a preset similarity threshold. If less than or equal to, it indicates that the difference between the multi-dimensional user vector of the user and the multi-dimensional package vector is smaller, and the vector similarity is greater than or equal to the preset similarity threshold.

[0083] The scheme calculates the vector included angle between the multi-dimensional user vector and the multi-dimensional package vector through a multi-dimensional vector dot product algorithm, and determines whether the vector similarity is greater than a preset similarity threshold according to the size of the vector included angle, which can improve the efficiency of determining potential traffic consumption users.

[0084] In one embodiment, optionally, the traffic association data includes cross-province traffic demand data and total traffic demand data of the user.

[0085] 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:

[0086] The proportion of the cross-province traffic demand data in the total traffic demand data is calculated.

[0087] The total traffic data and the cross-province traffic data of the package in the package data are obtained, the target cross-province traffic data of the user in the case of using the current to-be-promoted traffic package is predicted based on the proportion and the total traffic data of the package.

[0088] The difference between the target cross-province traffic data and the cross-province traffic data of the package is calculated, and the weight of the cross-province traffic data of the package in the multi-dimensional package vector is determined based on the difference and a preset traffic difference and traffic weight corresponding relationship.

[0089] 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 the preset similarity algorithm.

[0090] The cross-province traffic demand data can be the mobile data amount required by the user when using traffic to surf the Internet in a province other than the province where the user subscribes to the traffic package service. The total traffic demand data can be the total mobile data amount required by the user when using traffic to surf the Internet in all provinces. The total traffic data of the package can be the total mobile data amount available in all provinces included in the traffic package to be promoted. The cross-province traffic data of the package can be the mobile data amount available in the provinces other than the province where the user subscribes to the traffic package service included in the traffic package to be promoted. The target cross-province traffic data can be the mobile data amount in other provinces that the user hopes to obtain when using the traffic package to be promoted. The traffic weight can be the weight of the cross-province traffic data allocated to the traffic package to be promoted. The smaller the difference is, the more the traffic package to be promoted meets the user's demand, and the greater the corresponding traffic weight is.

[0091] In one embodiment, the cross-province traffic demand data of the user can be determined by calculating the average of the cross-province traffic in the traffic package purchased by the user and the traffic package browsed by the user, and the total traffic demand data of the user can be determined by calculating the average of the total available traffic in the traffic package purchased by the user and the traffic package browsed by the user. The proportion of the cross-province traffic demand data in the total traffic demand data is determined by calculating the ratio of the cross-province traffic demand data to the total traffic demand data. The total traffic data of the package and the cross-province traffic data of the package in the package data are identified, and the target cross-province traffic data of the user when using the current traffic package to be promoted is predicted by calculating the product of the proportion and the total traffic data of the package. The difference between the target cross-province traffic data and the cross-province traffic data of the package is calculated, the weight of the cross-province traffic data of the package in the multi-dimensional package vector is determined according to the difference and the preset correspondence between the traffic difference and the traffic weight, the weighted value of the cross-province traffic data of the package in the multi-dimensional package vector is calculated, and the multi-dimensional package vector update result is obtained. The vector similarity between the multi-dimensional user vector of the user and the updated multi-dimensional package vector is calculated based on the preset similarity algorithm.

[0092] The scheme can predict the target cross-province traffic data of the user when using the current traffic package to be promoted by calculating the proportion of the cross-province traffic demand data of the user in the total traffic demand data, and determine the weight of the cross-province traffic data of the package in the multi-dimensional package vector, so as to achieve the purpose of focusing on mining potential traffic consumption users of the current traffic to be promoted based on cross-province traffic, and further improve the accuracy of determining potential traffic consumption users.

[0093] S105, in the case where the vector similarity is greater than the preset similarity threshold, determining that the user is a potential consumption user of the current traffic package to be promoted.

[0094] 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 is indicated that the package data in the current to-be-promoted traffic package meets the user demand, and the user is determined as a potential consumption user of the current to-be-promoted traffic package.

[0095] In one embodiment, after determining that the user is a potential consumption user of the current to-be-promoted traffic package, the method further includes:

[0096] identifying whether the potential consumption user is a new user of the current to-be-promoted traffic package;

[0097] when the potential consumption user is a new user of the current to-be-promoted traffic package, promoting the package to the potential consumption user based on a first preset package promotion strategy;

[0098] when the potential consumption user is not a new user of the current to-be-promoted traffic package, promoting the package to the potential consumption user based on a second preset package promotion strategy.

[0099] The new user of the current to-be-promoted traffic package can be a user who has not purchased the current to-be-promoted traffic package. The first preset package promotion strategy can be a promotion strategy for new users of a traffic package prepared in advance by an operator. The second preset package promotion strategy can be a promotion strategy for old users of a traffic package prepared in advance by the operator. The first preset package promotion strategy and the second preset package promotion strategy are related to specific marketing rules of the operator, and the first preset package promotion strategy and the second preset package promotion strategy can be the same or different.

[0100] In one embodiment, whether the potential consumption user is a new user of the current to-be-promoted traffic package can be determined according to a traffic package purchase record of the potential consumption user. When the potential consumption user is a new user of the current to-be-promoted traffic package, a first traffic package promotion link is generated according to the first preset package promotion strategy, and the link is sent to a terminal of the potential consumption user for package promotion. When the potential consumption user is not a new user of the current to-be-promoted traffic package, a second traffic package promotion link is generated according to the second preset package promotion strategy, and the link is sent to the terminal of the potential consumption user for package promotion.

[0101] The scheme can achieve the purpose of promoting the package in different ways according to different user characteristics by identifying whether the potential consumption user is a new user of the current to-be-promoted traffic package, determining the package promotion strategy for the user, and then promoting the package to the user, which is beneficial to promoting the success rate of the potential traffic consumption user in handling the current to-be-promoted traffic package.

[0102] The technical scheme provided by the embodiments of the present application obtains the interaction information of a user with a traffic purchase platform within a preset time length, identifies traffic association data of the user based on the interaction information, pre-processes the traffic association data to obtain standard traffic data of the user, and constructs a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension. The package data of a current traffic package to be promoted is obtained, a multi-dimensional package vector of the current traffic package to be promoted is constructed based on the package data and the preset dimension, the vector similarity between the multi-dimensional user vector and the multi-dimensional package vector is calculated based on a preset similarity algorithm, and it is determined whether the vector similarity is greater than a preset similarity threshold. In the case where the vector similarity is greater than the preset similarity threshold, the user is determined to be a potential consumption user of the current traffic package to be promoted. Through the above-mentioned method for determining a potential traffic consumption user based on interaction information, the problems of low determination efficiency and inaccurate determination results in the prior art are solved. By constructing the multi-dimensional user vector and the 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 consumption user of the current traffic package to be promoted, the purpose of determining the potential traffic consumption user of the current traffic package to be promoted based on the actual interaction of the user with the traffic purchase platform is achieved, and the efficiency and accuracy of determining the potential traffic consumption user are improved.

[0103] Figure 3 is a flowchart of another method for determining a potential traffic consumption user based on interaction information provided by the embodiments of the present application. As shown in Figure 3 , the method specifically includes the following steps:

[0104] S301, obtaining the interaction information of a user with a traffic purchase platform within a preset time length, and identifying the traffic association data of the user based on the interaction information.

[0105] S302, pre-processing the traffic association data to obtain the standard traffic data of the user, and constructing a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension.

[0106] S303, obtaining the package data of a 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 the preset dimension.

[0107] S304, obtaining the contract period of a purchased traffic package of the user.

[0108] The contract period of the purchased traffic package can be the earliest possible termination period of the purchased traffic package for the user. For example, the contract duration of a certain package is two years, and the user handles the traffic package in December 2022. The contract period of the user is December 2024, that is, the user can terminate the package after December 2024.

[0109] In one embodiment, the contract duration and the contract handling time of the purchased traffic package of the user can be determined according to the package data of the purchased traffic package of the user, and the contract period of the user for the traffic package can be calculated according to the contract duration and the contract handling time.

[0110] S305, whether the contract period is less than the promotion period threshold of the current to-be-promoted traffic package is identified.

[0111] The promotion period threshold can be the latest promotion period of the current to-be-promoted traffic package. Since the traffic packages of various operators and the traffic consumption demands of users are constantly adjusted and changed, in order to ensure the effectiveness of the promotion of the current to-be-promoted traffic package, it is necessary to determine the promotion period threshold of the current to-be-promoted traffic package according to the promotion demand of the operator.

[0112] In one embodiment, whether the contract period of the user's purchased traffic package is less than the promotion period threshold of the current to-be-promoted traffic package can be determined by comparing the date sequence of the contract period and the promotion period threshold of the current to-be-promoted traffic package.

[0113] S306, in the case that the contract period is less than the promotion period threshold of the current to-be-promoted traffic package, the user is determined as a candidate potential consumption user, and the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on a preset similarity algorithm.

[0114] The candidate potential consumption user can be a traffic consumption user whose contract period is before the promotion period threshold of the current to-be-promoted traffic package.

[0115] In one embodiment, in the case that the contract period of the user's purchased traffic package is before the promotion period threshold of the current to-be-promoted traffic package, the user is determined as a candidate potential consumption user, and the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on a preset similarity algorithm.

[0116] S307, the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on a preset similarity algorithm, and whether the vector similarity is greater than a preset similarity threshold is identified.

[0117] In one embodiment, after the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on a preset similarity algorithm, the method further comprises:

[0118] The historical traffic cost level of the candidate potential consumption user is identified based on the traffic association data;

[0119] The package traffic cost level of the current to-be-promoted traffic package is determined based on the package data;

[0120] respectively identify whether the historical traffic fee level and the package traffic fee level are consistent;

[0121] In the case that the historical traffic fee level and the package traffic fee level are consistent, a first preset weight is assigned to the vector similarity of the candidate potential consumption user, and a first weighted value of the vector similarity is calculated based on the first preset weight;

[0122] In the case that the historical traffic fee level and the package traffic fee level are inconsistent, a second preset weight is assigned to the vector similarity of the candidate potential consumption user, and a second weighted value of the vector similarity is calculated based on the second preset weight;

[0123] The vector similarity is identified based on the first weighted value or the second weighted value whether the vector similarity is greater than a preset similarity threshold.

[0124] The historical traffic fee level can be a level corresponding to a package fee of a traffic package historically handled by the user. The package traffic fee level can be a level corresponding to a package fee of a traffic package to be promoted. The historical traffic fee level and the package traffic fee level are determined by using the same correspondence between a fee amount and a fee level. The first preset weight can be a parameter for increasing the size of the vector similarity. The second preset weight can be a parameter for decreasing the size of the vector similarity. When the historical traffic fee level of the user and the package traffic fee level are consistent, the user is more likely to be a potential traffic consumption user, and at this time, the value of the vector similarity can be increased by the first preset weight, so that the user is determined to be a potential traffic consumption user, and vice versa, the value of the vector similarity is decreased by the second preset weight, so as to avoid the user being determined to be a potential traffic consumption user.

[0125] In one embodiment, the historical traffic fee of the candidate potential consumption user can be determined according to the package fee of the purchased traffic package in the traffic association data, and the historical traffic fee level of the user can be determined according to the correspondence between the preset fee amount and the fee level. The package traffic fee level of the current traffic package to be promoted can be determined according to the package fee in the package data and the correspondence between the preset fee amount and the fee level. Whether the historical traffic fee level and the package traffic fee level are the same level is compared, if yes, a first preset weight is assigned to the vector similarity of the candidate potential consumption user, and a first weighted value of the vector similarity is calculated; if no, a second preset weight is assigned to the vector similarity of the candidate potential consumption user, and a second weighted value of the vector similarity is calculated, and whether the vector similarity is greater than a preset similarity threshold is identified based on the first weighted value or the second weighted value.

[0126] The scheme can determine the weight of the vector similarity according to the historical traffic cost level of the candidate potential consumption user and the package traffic cost level of the current to-be-promoted traffic package, and calculate the weighted value of the vector similarity based on the weight, so as to further determine the potential traffic consumption user based on the user consumption level, and improve the comprehensiveness of the determination factors of the potential traffic consumption user.

[0127] S308, in the case where the vector similarity is greater than the preset similarity threshold, determining that the user is a potential consumption user of the current to-be-promoted traffic package.

[0128] The technical scheme provided by the embodiment of the application can determine the candidate potential consumption user by identifying whether the contract period of the purchased traffic package of the user is less than the promotion period threshold of the current to-be-promoted traffic package, so as to ensure the effectiveness of the current to-be-promoted traffic package for the potential traffic consumption user, and further improve the transaction probability of the potential traffic consumption user for the current to-be-promoted traffic package.

[0129] Figure 4 is a flowchart of preprocessing traffic association data provided by the embodiment of the application. As shown in Figure 4 , the specific steps include the following steps:

[0130] S401, performing normalization processing and data alignment on the traffic association data.

[0131] The normalization processing can be an operation for eliminating the differences between data, so as to convert data of different sources or formats into standard format data. For example, the cost amount in the package data and the cross-province available traffic are different dimensions, and cannot be directly compared by numbers, so normalization processing is needed to convert them into scalar data. The data alignment is an operation of unifying the data length. For example, the missing data is completed.

[0132] In an embodiment, the traffic data can be normalized and aligned according to the format, type and length of the data in the traffic association data.

[0133] S402, constructing at least two traffic consumption triples of the user based on the aligned traffic association data.

[0134] The traffic consumption triple can be a structure representing the relationship between the user and the entity in the traffic package or the relationship between the entities in the traffic package. For example, <username: mobile number: 12345678910>, <username: package amount: 38>.

[0135] In an embodiment, at least two traffic consumption triples of the user can be constructed according to the relationship between each two entities in the aligned traffic association data.

[0136] S403, respectively identify whether the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets are all reasonable based on a preset rule.

[0137] The preset rule can be a rule for identifying whether the entity relationship of the traffic consumption triplet conforms to a regular situation, which is set in advance according to an operator operation rule and traffic consumption experience data.

[0138] In an embodiment, whether the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets are all reasonable can be respectively identified according to the preset rule. For example, the preset rule includes that a user can be associated with at most five mobile phone numbers. When the mobile phone number triplets of the same user exceed five groups, it can be determined that the mobile phone number triplet relationship of the user is unreasonable, or the traffic fee triplets of a user in a certain month are much higher than those in other months, and the traffic fee triplet relationship of the user in the month is unreasonable.

[0139] S404, in a case where the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets exist at least one unreasonable situation, deleting the traffic association data of the user to complete the preprocessing of the traffic association data.

[0140] In an embodiment, when the user name or login information of a user is highly similar, the traffic consumption record is prone to be confused. Therefore, in a case where the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets exist at least one unreasonable situation, the traffic association data of the user needs to be deleted to avoid the interference of the error data on the subsequent potential traffic consumption user identification.

[0141] The technical scheme provided by the embodiment of the application can avoid the problem that the determination result of the potential traffic consumption user is incorrect due to the incorrect traffic association data record, and improve the accuracy of the determination result of the potential traffic consumption user, by constructing at least two traffic consumption triplets of a user, identifying whether the intra-group relationship and the inter-group relationship of each traffic consumption triplet are all reasonable, and deleting the traffic association data of an unreasonable user.

[0142] Figure 5 is a structural block diagram of a potential traffic consumption user determination system based on interaction information provided by the embodiment of the application. As shown in Figure 5 specifically includes the following:

[0143] The traffic association data identification module 501 is configured to acquire interaction information of a user and a traffic purchase platform in a preset time period, and identify traffic association data of the user based on the interaction information.

[0144] The user vector construction module 502 is configured to preprocess the traffic association data, obtain standard traffic data of the user, and construct a multi-dimensional user vector of the user based on the standard traffic data and preset dimensions.

[0145] The package vector construction module 503 is configured to obtain package data of a 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.

[0146] The similarity calculation module 504 is configured to calculate a 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.

[0147] The potential user determination module 505 is configured to determine that the user is a potential consumption user of the current traffic package to be promoted in a case where the vector similarity is greater than the preset similarity threshold.

[0148] Optionally, the similarity calculation module 504 is specifically configured to:

[0149] calculate a vector included angle between the multi-dimensional user vector of the user and the multi-dimensional package vector based on a multi-dimensional vector dot product algorithm;

[0150] identify whether the vector included angle is greater than a preset vector included angle threshold, to determine whether the vector similarity is greater than the preset similarity threshold.

[0151] Optionally, the traffic association data includes cross-province traffic demand data and total traffic demand data of the user.

[0152] The similarity calculation module 504 is further configured to:

[0153] calculate a proportion of the cross-province traffic demand data in the total traffic demand data;

[0154] obtain package total traffic data and package cross-province traffic data in the package data, predict target cross-province traffic data of the user in a case where the current traffic package to be promoted is used based on the proportion and the package total traffic data;

[0155] calculate a difference value between the target cross-province traffic data and the package cross-province traffic data, and determine a weight of the package cross-province traffic data in the multi-dimensional package vector based on the difference value and a preset correspondence relationship between a traffic difference value and a traffic weight;

[0156] update the multi-dimensional package vector based on the weight, to calculate a vector similarity between the multi-dimensional user vector of the user and the updated multi-dimensional package vector based on the preset similarity algorithm.

[0157] Optionally, the system further includes:

[0158] The contract period acquisition module is configured to acquire a contract period of the purchased traffic package of the user.

[0159] The period identification module is configured to identify whether the contract period is less than a promotion period threshold of the current traffic package to be promoted.

[0160] The candidate potential consumption user determination module is configured to determine the user as a candidate potential consumption user in a case where the contract period is less than the promotion period threshold of the current traffic package to be promoted, so as to calculate a vector similarity between the multi-dimensional user vector of the user and a multi-dimensional package vector based on a preset similarity algorithm.

[0161] Optionally, the system further comprises:

[0162] The historical traffic fee level identification module is configured to identify a historical traffic fee level of the candidate potential consumption user based on the traffic association data.

[0163] The package traffic fee level determination module is configured to determine a package traffic fee level of the current traffic package to be promoted based on the package data.

[0164] The level identification module is configured to identify whether the historical traffic fee level and the package traffic fee level are consistent, respectively.

[0165] The similarity first weighting module is configured to assign a first preset weight to the vector similarity of the candidate potential consumption user in a case where the historical traffic fee level and the package traffic fee level are consistent, and calculate a first weighted value of the vector similarity based on the first preset weight.

[0166] The similarity second weighting module is configured to assign a second preset weight to the vector similarity of the candidate potential consumption user in a case where the historical traffic fee level and the package traffic fee level are inconsistent, and calculate a second weighted value of the vector similarity based on the second preset weight.

[0167] The similarity identification module is configured to identify whether the vector similarity is greater than a preset similarity threshold based on the first weighted value or the second weighted value.

[0168] Optionally, the user vector construction module 502 is specifically configured to:

[0169] normalize and align the traffic association data;

[0170] construct at least two traffic consumption triplets of the user based on the aligned traffic association data;

[0171] identify whether all of an intra-group relationship and an inter-group relationship of the at least two traffic consumption triplets are reasonable based on a preset rule, respectively.

[0172] In at least one unreasonable case of the group relationship and the inter-group relationship of the at least two traffic consumption triplets, the traffic association data of the user is deleted to complete the preprocessing of the traffic association data.

[0173] Optionally, the system further comprises:

[0174] The new user identification module is configured to identify whether the potential consumption user is a new user of the current traffic package to be promoted.

[0175] The first promotion module is configured to promote the package to the potential consumption user based on a first preset package promotion strategy in a case where the potential consumption user is a new user of the current traffic package to be promoted.

[0176] The second promotion module is configured to promote the package to the potential consumption user based on a second preset package promotion strategy in a case where the potential consumption user is not a new user of the current traffic package to be promoted.

[0177] The technical scheme provided by the embodiments of the application comprises a traffic association data identification module configured to acquire interaction information of a user with a traffic purchase platform within a preset time length and identify traffic association data of the user based on the interaction information; a user vector construction module configured to preprocess the traffic association data to obtain standard traffic data of the user and construct a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension; a package vector construction module configured to acquire package data of a 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 dimension; a similarity calculation module configured to calculate a vector similarity between the 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; and a potential user determination module configured to determine that the user is a potential consumption user of the current traffic package to be promoted in a case where the vector similarity is greater than the preset similarity threshold. The above-mentioned potential traffic consumption user determination system based on interaction information solves the problems of low determination efficiency and inaccurate determination results in the prior art, determines whether the user is a potential consumption user of the current traffic package 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 a vector similarity between the multi-dimensional user vector and the multi-dimensional package vector, and achieves the purpose of determining the potential traffic consumption user of the current traffic package to be promoted based on actual interaction of the user with the traffic purchase platform, thereby improving the efficiency and accuracy of determining the potential traffic consumption user.

[0178] The potential traffic consumer determination system based on interactive information in this application embodiment can be a component, integrated circuit, or chip configured in a terminal. It can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0179] The potential traffic consumer determination system based on interactive information in this application embodiment can be an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0180] The potential traffic consumer determination system based on interactive information provided in this application embodiment can implement the various processes implemented in the above method embodiments, and will not be repeated here to avoid repetition.

[0181] like Figure 6 As shown, this application embodiment also provides an electronic device 600, including a processor 601, a memory 602, and a program or instructions stored in the memory 602 and executable on the processor 601. When the program or instructions are executed by the processor 601, they implement the various processes of the above-described embodiment of a method for determining potential traffic consumers based on interactive information, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0182] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0183] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described method for determining potential traffic consumers based on interactive information, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0184] The processor is the processor in the electronic device described in the above embodiments. 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.

[0185] The program product includes program codes for causing a computer device to perform the steps in the methods according to various exemplary embodiments of the present application described in the specification when the program product is run on the computer device. For example, the computer device can perform a potential traffic consumption user determination method based on interaction information according to the embodiments of the present application. The program product can be realized by any combination of one or more readable media.

[0186] It should be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles, or systems that include a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles, or systems. Without more limitations, the element defined by the statement "including a" does not exclude the presence 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 methods and systems in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but can also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method can be performed in an order different from the described order, and various steps can also be added, omitted, or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0187] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by software and necessary general hardware platforms, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0188] The embodiments of the present application are described above with reference to the drawings, but the present application is not limited to the specific embodiments described above, and the specific embodiments described above are merely illustrative, but not restrictive, and those of ordinary skill in the art can make many forms without departing from the purpose of the present application and the scope protected by the claims under the inspiration of the present application, which all belong to the protection of the present application.

[0189] The above are only the 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 replacements 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 more other equivalent embodiments can be included 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 potential traffic consumption user determination method based on interaction information, characterized in that, The method comprises: acquiring interaction information of a user with a traffic purchase platform within a preset time length, determining target traffic package data and demand traffic package data of the user by comparing purchased traffic package data and browsed traffic package data of the user in the interaction information, obtaining traffic association data, the demand traffic package data including cross-province traffic demand data and total traffic demand data; preprocessing the traffic association data, including: normalizing and aligning the traffic association data, constructing at least two traffic consumption triplets of the user based on the aligned traffic association data, identifying whether the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets are all reasonable based on a preset rule, and deleting the traffic association data of the user in the case that at least one of the intra-group relationship and the inter-group relationship of the at least two traffic consumption triplets is unreasonable, to complete preprocessing of the traffic association data and obtain standard traffic data of the user, and constructing a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension; acquiring package data of a 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 the preset dimension; calculating the proportion of the cross-province traffic demand data in the total traffic demand data, acquiring total traffic data and cross-province traffic data of the package in the package data, predicting target cross-province traffic data of the user based on the proportion and the total traffic data, calculating the difference between the target cross-province traffic data and the cross-province traffic data of the package, determining the weight of the cross-province traffic data of the package in the multi-dimensional package vector based on the difference and the corresponding relationship between preset traffic difference and traffic weight, and updating the multi-dimensional package vector based on the weight; calculating 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, and identifying whether the vector similarity is greater than a preset similarity threshold; in the case that the vector similarity is greater than the preset similarity threshold, determining that the user is a potential consumption user of the current traffic package to be promoted. 2.The potential traffic consumption user determining method based on interaction information according to claim 1, characterized in that, The method comprises: calculating 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 product algorithm; identifying whether the size of the vector angle is greater than a preset vector angle threshold, to determine whether the vector similarity is greater than a preset similarity threshold. 3.The potential traffic consumption user determining method based on interaction 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 comprises: acquiring the contract period of the purchased traffic package of the user; identifying whether the contract period is less than the promotion period threshold of the current traffic package to be promoted; In a case where 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 consumption user, and a vector similarity between a multi-dimensional user vector of the user and a multi-dimensional package vector is calculated based on a preset similarity algorithm. 4.The method of claim 3, wherein, After the vector similarity between the multi-dimensional user vector of the user and the multi-dimensional package vector is calculated based on the preset similarity algorithm, the method further includes: identifying a historical traffic fee level of the candidate potential consumption user based on the traffic association data; determining a package traffic fee level of the current traffic package to be promoted based on the package data; respectively identifying whether the historical traffic fee level and the package traffic fee level are consistent; in a case where the historical traffic fee level and the package traffic fee level are consistent, assigning a first preset weight to the vector similarity of the candidate potential consumption user, and calculating a first weighted value of the vector similarity based on the first preset weight; in a case where the historical traffic fee level and the package traffic fee level are inconsistent, assigning a second preset weight to the vector similarity of the candidate potential consumption user, and calculating a second weighted value of the vector similarity based on the second preset weight; identifying whether the vector similarity is greater than a preset similarity threshold based on the first weighted value or the second weighted value. 5.The potential traffic consumption user determining method based on interaction information according to claim 1, characterized in that, After determining that the user is a potential consumption user of the current traffic package to be promoted, the method further includes: identifying whether the potential consumption user is a new user of the current traffic package to be promoted; in a case where the potential consumption user is a new user of the current traffic package to be promoted, promoting the package to the potential consumption user based on a first preset package promotion strategy; in a case where the potential consumption user is not a new user of the current traffic package to be promoted, promoting the package to the potential consumption user based on a second preset package promotion strategy.

6. An interactive information based potential traffic consuming user determination system, characterized by, The system includes: a traffic association data identification module, configured to obtain interaction information of a user with a traffic purchase platform within a preset time length, determine target traffic package data and demand traffic package data of the user by comparing purchased traffic package data and browsed traffic package data of the user in the interaction information, and obtain traffic association data, wherein the demand traffic package data includes cross-province traffic demand data and total traffic demand data; a user vector construction module, configured to preprocess the traffic association data, including: performing normalization processing and data alignment on the traffic association data, constructing at least two traffic consumption triplets of the user based on the aligned traffic association data, respectively identifying whether all of intra-group relationships and inter-group relationships of the at least two traffic consumption triplets are reasonable based on a preset rule, deleting traffic association data of the user in a case where at least one of the intra-group relationships and the inter-group relationships is unreasonable, to complete preprocessing of the traffic association data, obtaining standard traffic data of the user, and constructing a multi-dimensional user vector of the user based on the standard traffic data and a preset dimension. The package vector construction module is configured to acquire package data of a 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. The similarity calculation module is configured to calculate a proportion of the cross-province traffic demand data in the total traffic demand data, acquire total traffic data and cross-province traffic data in the package data, predict target cross-province traffic data of the user based on the proportion and the total traffic data, calculate a difference between the target cross-province traffic data and the cross-province traffic data, determine a weight of the cross-province traffic data in the multi-dimensional package vector based on the difference and a preset correspondence between a traffic difference and a traffic weight, update the multi-dimensional package vector based on the weight, calculate a vector similarity between a multi-dimensional user vector of the user and the updated 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 configured to determine that the user is a potential consumption user of the current traffic package to be promoted if the vector similarity is greater than the preset similarity threshold.

7. An electronic device, comprising: The computer readable storage medium stores a program or instructions, and the program or instructions are executed by the processor to implement the steps of the potential traffic consumption user determination method based on interaction information according to any one of claims 1-5.

8. A readable storage medium, characterized by, The computer readable storage medium stores a program or instructions, and the program or instructions are executed by the processor to implement the steps of the potential traffic consumption user determination method based on interaction information according to any one of claims 1-5.

Images