Traffic feature-based user type determination method, device, and storage medium

Abstract

This application provides a method, device, and storage medium for determining user types based on traffic characteristics, relating to the field of Internet technology. The method includes: collecting traffic information of target users based on a Broadband Access Server (BRAS); sorting the traffic information based on the time information corresponding to the traffic information; performing feature analysis on the sorted traffic information to determine traffic characteristics; and determining the user type of the target user based on the traffic characteristics. The method of this application achieves the technical effect of improving the accuracy of user type identification and the effectiveness of product recommendations.

Description

Technical Field

[0001] This application relates to Internet technology, and in particular to a method, device and storage medium for determining user types based on traffic characteristics. Background Technology

[0002] With the widespread use of the internet, more and more users are using it for entertainment, communication, and work. Every user generates data traffic when using the internet. Extracting traffic characteristics based on this traffic information can help determine user types and has significant research value for targeted product recommendations.

[0003] In existing technologies, network operators provide source-destination transmission services for user traffic, enabling users to access the Internet through a path of optical line terminal or switch - broadband network gateway control equipment - metropolitan area network core network - 169 backbone network.

[0004] Because network operators lack the ability to analyze and distinguish user traffic in a refined manner, they cannot determine user types based on user traffic, which makes it impossible to make targeted product recommendations. Therefore, existing technologies suffer from low accuracy in identifying user types and low effectiveness in product recommendations. Summary of the Invention

[0005] This application provides a method, device, and storage medium for determining user types based on traffic characteristics, in order to solve the technical problems of low accuracy in identifying user types and low effectiveness in product recommendations in the prior art.

[0006] On the one hand, this application provides a method for determining user types based on traffic characteristics, including:

[0007] Traffic information of target users is collected based on the Broadband Access Server (BRAS).

[0008] The traffic information is sorted based on the time information corresponding to the traffic information, and the sorted traffic information is subjected to feature analysis to determine the traffic characteristics.

[0009] Determine the user type of the target user based on traffic characteristics.

[0010] Optionally, traffic information of the target user is collected based on the Broadband Access Server (BRAS), including:

[0011] Based on the Broadband Access Server (BRAS), at least one of the following is collected for the target user: uplink traffic utilization, downlink traffic utilization, overall traffic utilization, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value.

[0012] Optionally, feature analysis is performed on the sorted traffic information to determine traffic characteristics, including at least one of the following:

[0013] Based on traffic information, determine the comprehensive traffic utilization rate, the first ratio of the uplink traffic utilization rate to the downlink traffic utilization rate of the target user for the preset time period, and determine the first traffic characteristic.

[0014] Based on traffic information, a second ratio of downlink network throughput to bit rate is determined, and a second traffic characteristic is determined;

[0015] Based on traffic information, a third ratio of uplink network throughput to bit rate is determined, and a third traffic characteristic is identified.

[0016] Based on traffic protocol information, determine the fourth traffic characteristic of the target user;

[0017] Based on preset port traffic values, the fifth traffic characteristic of the target user is determined.

[0018] Optionally, based on traffic protocol information, a fourth traffic characteristic of the target user is determined, including:

[0019] Based on traffic protocol information, determine the uplink UDP protocol traffic, downlink UDP protocol traffic, uplink TCP protocol traffic, and downlink TCP protocol traffic;

[0020] The fourth ratio is determined based on the uplink UDP protocol traffic and the uplink TCP protocol traffic, and the fifth ratio is determined based on the downlink UDP protocol traffic and the downlink TCP protocol traffic;

[0021] The fourth flow characteristic is determined based on the fourth and fifth ratios.

[0022] Optionally, based on preset port traffic values, a fifth traffic characteristic of the target user is determined, including:

[0023] Determine the upstream and downstream traffic of the preset port based on the preset port traffic value;

[0024] The fifth traffic characteristic is determined based on the uplink traffic and downlink traffic of the preset port.

[0025] Optionally, the user type of the target user can be determined based on traffic characteristics, including:

[0026] Based on the first traffic feature, the second traffic feature, the third traffic feature, the fourth traffic feature and / or the fifth traffic feature, the user type of the target user is determined; among which, the user type includes content provider and network access user.

[0027] Optionally, the user type of the target user can be determined based on traffic characteristics, including:

[0028] When the first ratio of the first traffic characteristic indicator on a single day is greater than the first preset threshold, the user type is determined to be content provider; content provider includes video provider, game provider, and enterprise application provider;

[0029] When the first ratio on a single day is less than or equal to the first preset threshold, the user type is determined to be network access type; network access type includes enterprise leased line type, home broadband type and internet cafe type.

[0030] Optionally, the user type of the target user can be determined based on traffic characteristics, including:

[0031] When the daily traffic utilization rate is greater than the second preset threshold, the user type is determined to be internet cafe type; when the sixth ratio of the traffic utilization rate during working hours to the traffic utilization rate during non-working hours is greater than the third preset threshold, the user type is determined to be enterprise leased line type; when the seventh ratio of the traffic utilization rate during non-working hours to the traffic utilization rate during working hours is greater than the fourth preset threshold, the user type is determined to be home broadband type.

[0032] When the second ratio and / or the third ratio fall within the range of the first preset threshold, the user type is determined to be standard; when the second ratio falls within the range of the second preset threshold, the user type is determined to be video provider.

[0033] When the third ratio falls within the third preset threshold range, the user type is determined to be abnormal; when the third ratio falls within the fourth preset threshold range, the user type is determined to be either enterprise leased line or home broadband.

[0034] When the fourth ratio falls within the fifth preset threshold range, the user type is determined to be either a video provider or a game provider; when the fourth ratio falls within the sixth preset threshold range, the user type is determined to be an enterprise application.

[0035] When the fifth ratio falls within the seventh preset threshold range, the user type is determined to be home broadband; when the fifth ratio falls within the eighth preset threshold range, the user type is determined to be enterprise leased line.

[0036] When the ratio of uplink traffic on the first preset port to uplink traffic on the second preset port is greater than the fifth preset threshold, the user type is determined to be enterprise application type; when the ratio of downlink traffic on the first preset port to downlink traffic on the second preset port is greater than the sixth preset threshold, the user type is determined to be network access type; when the ratio of uplink traffic on the third preset port to uplink traffic on the fourth preset port is greater than the seventh preset threshold, the user type is determined to be video provider type.

[0037] Optionally, after determining the user type of the target user based on traffic characteristics, the process includes:

[0038] User behavior information is obtained based on user type. User behavior information includes online time, behavior name, and behavior object.

[0039] User behavior trajectory maps are drawn based on user behavior information to identify high-frequency user behaviors;

[0040] A product recommendation list is generated based on users' frequent behaviors.

[0041] Secondly, this application provides a user type determination device based on traffic characteristics, comprising:

[0042] The acquisition module is used to collect traffic information of target users based on the Broadband Access Server (BRAS).

[0043] The processing module is used to sort the traffic information based on the time information corresponding to the traffic information, perform feature analysis on the sorted traffic information, and determine the traffic characteristics.

[0044] The determination module is used to determine the user type of a target user based on traffic characteristics.

[0045] Optionally, the acquisition module is used for:

[0046] Based on the Broadband Access Server (BRAS), at least one of the following is collected for the target user: uplink traffic utilization, downlink traffic utilization, overall traffic utilization, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value.

[0047] Optionally, the processing module is used for:

[0048] Based on traffic information, determine the comprehensive traffic utilization rate, the first ratio of the uplink traffic utilization rate to the downlink traffic utilization rate of the target user for the preset time period, and determine the first traffic characteristic.

[0049] Based on traffic information, a second ratio of downlink network throughput to bit rate is determined, and a second traffic characteristic is determined;

[0050] Based on traffic information, a third ratio of uplink network throughput to bit rate is determined, and a third traffic characteristic is identified.

[0051] Based on traffic protocol information, determine the fourth traffic characteristic of the target user;

[0052] Based on preset port traffic values, the fifth traffic characteristic of the target user is determined.

[0053] Optionally, the processing module is also used for:

[0054] Based on traffic protocol information, determine the uplink UDP protocol traffic, downlink UDP protocol traffic, uplink TCP protocol traffic, and downlink TCP protocol traffic;

[0055] The fourth ratio is determined based on the uplink UDP protocol traffic and the uplink TCP protocol traffic, and the fifth ratio is determined based on the downlink UDP protocol traffic and the downlink TCP protocol traffic;

[0056] The fourth flow characteristic is determined based on the fourth and fifth ratios.

[0057] Optionally, the processing module is also used for:

[0058] Determine the upstream and downstream traffic of the preset port based on the preset port traffic value;

[0059] The fifth traffic characteristic is determined based on the uplink traffic and downlink traffic of the preset port.

[0060] Optionally, the determination module is used for:

[0061] Based on the first traffic feature, the second traffic feature, the third traffic feature, the fourth traffic feature and / or the fifth traffic feature, the user type of the target user is determined; among which, the user type includes content provider and network access user.

[0062] Optionally, the determining module is also used for:

[0063] When the first ratio of the first traffic characteristic indicator on a single day is greater than the first preset threshold, the user type is determined to be content provider; content provider includes video provider, game provider, and enterprise application provider;

[0064] When the first ratio on a single day is less than or equal to the first preset threshold, the user type is determined to be network access type; network access type includes enterprise leased line type, home broadband type and internet cafe type.

[0065] Optionally, the determining module is also used for:

[0066] When the daily traffic utilization rate is greater than the second preset threshold, the user type is determined to be internet cafe type; when the sixth ratio of the traffic utilization rate during working hours to the traffic utilization rate during non-working hours is greater than the third preset threshold, the user type is determined to be enterprise leased line type; when the seventh ratio of the traffic utilization rate during non-working hours to the traffic utilization rate during working hours is greater than the fourth preset threshold, the user type is determined to be home broadband type.

[0067] When the second ratio and / or the third ratio fall within the range of the first preset threshold, the user type is determined to be standard; when the second ratio falls within the range of the second preset threshold, the user type is determined to be video provider.

[0068] When the third ratio falls within the third preset threshold range, the user type is determined to be abnormal; when the third ratio falls within the fourth preset threshold range, the user type is determined to be either enterprise leased line or home broadband.

[0069] When the fourth ratio falls within the fifth preset threshold range, the user type is determined to be either a video provider or a game provider; when the fourth ratio falls within the sixth preset threshold range, the user type is determined to be an enterprise application.

[0070] When the fifth ratio falls within the seventh preset threshold range, the user type is determined to be home broadband; when the fifth ratio falls within the eighth preset threshold range, the user type is determined to be enterprise leased line.

[0071] When the ratio of uplink traffic on the first preset port to uplink traffic on the second preset port is greater than the fifth preset threshold, the user type is determined to be enterprise application type; when the ratio of downlink traffic on the first preset port to downlink traffic on the second preset port is greater than the sixth preset threshold, the user type is determined to be network access type; when the ratio of uplink traffic on the third preset port to uplink traffic on the fourth preset port is greater than the seventh preset threshold, the user type is determined to be video provider type.

[0072] Optionally, the device is also used for:

[0073] User behavior information is obtained based on user type. User behavior information includes online time, behavior name, and behavior object.

[0074] User behavior trajectory maps are drawn based on user behavior information to identify high-frequency user behaviors;

[0075] A product recommendation list is generated based on users' frequent behaviors.

[0076] A third aspect of this application provides a user type determination device based on traffic characteristics, comprising:

[0077] Processor and memory;

[0078] The memory stores instructions that the computer executes;

[0079] The processor executes computer execution instructions stored in memory, causing the user type determination device based on traffic characteristics to execute the user type determination method based on traffic characteristics of any one of the first aspects.

[0080] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement a user type determination method based on traffic characteristics as described in any of the first aspects.

[0081] The user type determination method, device, and storage medium based on traffic characteristics provided in this application collect traffic information of the target user based on a Broadband Access Server (BRAS) when the target user accesses the Internet and generates corresponding traffic. The traffic information includes at least one of the following: uplink utilization rate, downlink utilization rate, overall traffic utilization rate, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value. The traffic information is sorted based on the time information corresponding to it to obtain sorted traffic information. By performing relevant calculations on the traffic information, feature analysis of the traffic information is achieved to determine the traffic characteristics. Based on the traffic characteristics, the accurate user type of the target user is obtained. Then, the user's behavior information and preference level are determined through the user type, and products are screened to complete targeted product recommendations. This achieves the technical effect of improving the accuracy of user type identification and the effectiveness of product recommendations. Attached Figure Description

[0082] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0083] Figure 1 A diagram illustrating application scenarios where operators provide services for user traffic in existing technologies;

[0084] Figure 2 The user type determination method based on traffic characteristics provided in the embodiments of this application is as follows: Figure 1 ;

[0085] Figure 3 A scenario diagram illustrating the user type determination method based on traffic characteristics provided in this application embodiment;

[0086] Figure 4 The user type determination method based on traffic characteristics provided in the embodiments of this application is as follows: Figure 2 ;

[0087] Figure 5 A schematic diagram of the structure of a user type determination device based on traffic characteristics provided in an embodiment of this application;

[0088] Figure 6 The hardware structure diagram of the user type determination device based on traffic characteristics provided in the embodiments of this application is shown.

[0089] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0090] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0091] In the existing technology, Figure 1 This diagram illustrates application scenarios where operators provide services for user traffic in existing technologies, such as... Figure 1 As shown, network operators provide source-destination transmission services for user traffic. Users access the Internet through the path of Optical Line Terminal (OLT) or Switch (SW) - Broadband Network Gateway Control Device (BNG) - Metropolitan Area Network Core Network (CR) - 169 backbone network. However, network operators lack the ability to analyze and distinguish user traffic in a refined manner, and cannot determine user type based on user traffic. This results in the inability to make targeted product recommendations. Therefore, the existing technology has technical problems of low accuracy in identifying user type and low effectiveness in product recommendations.

[0092] The user type determination method, device, and storage medium based on traffic characteristics provided in this application collect traffic information of the target user based on a Broadband Access Server (BRAS) when the target user accesses the Internet and generates corresponding traffic. The traffic information includes at least one of the following: uplink utilization rate, downlink utilization rate, overall traffic utilization rate, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value. The traffic information is sorted based on the time information corresponding to it to obtain sorted traffic information. By performing relevant calculations on the traffic information, feature analysis of the traffic information is achieved to determine the traffic characteristics. Based on the traffic characteristics, the accurate user type of the target user is obtained. Then, the user's behavior information and preference level are determined through the user type, and products are screened to complete targeted product recommendations. This achieves the technical effect of improving the accuracy of user type identification and the effectiveness of product recommendations.

[0093] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0094] Figure 2 The user type determination method based on traffic characteristics provided in the embodiments of this application is as follows: Figure 1 .like Figure 2 As shown in the figure, this embodiment provides a user type determination method based on traffic characteristics, including:

[0095] S201. Collect traffic information of target users based on Broadband Access Server (BRAS);

[0096] In this embodiment, traffic information of the target user is collected based on the Broadband Access Server (BRAS). The traffic information includes at least one of the following: uplink traffic utilization, downlink traffic utilization, overall traffic utilization, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value.

[0097] In the first example, Figure 3 A scenario diagram for the user type determination method based on traffic characteristics provided in the embodiments of this application, such as... Figure 3 As shown, the system acquires the traffic received by the optical line terminal (OLT) of the target user, sends the received traffic to the Layer 2 aggregation switch connected to the OLT, processes the received traffic through the Layer 2 aggregation switch to obtain the corresponding traffic information, collects and processes the traffic information based on the broadband access server (BRAS), and sends the processing result to the 169 backbone network through the metropolitan area network core network (CR).

[0098] S202. Sort the traffic information based on the time information corresponding to the traffic information, perform feature analysis on the sorted traffic information, and determine the traffic characteristics.

[0099] In this embodiment, determining traffic characteristics based on traffic information includes at least one of the following: calculating the overall traffic utilization rate and the ratio of the uplink traffic utilization rate to the downlink traffic utilization rate of the target user within a preset time period based on traffic information, thereby determining the corresponding traffic characteristics; calculating the ratio of downlink network throughput to bit rate, or the ratio of uplink network throughput to bit rate in the traffic information, thereby determining the corresponding traffic characteristics; determining uplink and downlink UDP protocol traffic and uplink and downlink TCP protocol traffic based on traffic protocol information, and calculating the ratio of uplink UDP protocol traffic to uplink TCP protocol traffic, or the ratio of downlink UDP protocol traffic to downlink TCP protocol traffic, thereby determining the corresponding traffic characteristics; determining the uplink traffic and downlink traffic of a preset port based on preset port traffic values, thereby determining the corresponding traffic characteristics.

[0100] S203. Determine the user type of the target user based on traffic characteristics.

[0101] In this embodiment, the ratio calculated in S202 is compared with a preset threshold, or the preset threshold range in which the ratio falls is determined, to obtain the corresponding result. Based on the obtained result, the corresponding user type is determined. The user type includes content provider and network access type. Content provider includes video provider, game provider, and enterprise application type. Network access type includes enterprise leased line type, home broadband type, and internet cafe type.

[0102] In the second example, when the ratio of the target user's daily uplink utilization to downlink utilization is greater than 2, the user type is determined to be content provider; when the ratio of the target user's daily downlink utilization to uplink utilization is greater than 2, the user type is determined to be network access user. The specific methods for determining the user type are shown in the table below:

[0103]

[0104] In addition, when the ratio of the overall traffic utilization rate during working hours to that during non-working hours is greater than 3, the user type is determined to be a corporate leased line; when the ratio of the overall traffic utilization rate during non-working hours to that during working hours is greater than 3, the user type is determined to be a home broadband.

[0105] In this embodiment, user behavior information is obtained based on the obtained user type, and high-frequency user behaviors are determined through the user behavior information, thereby generating a product recommendation list. The user behavior information includes online time, behavior name, and behavior object.

[0106] The user type determination method based on traffic characteristics provided in this application collects traffic information of the target user based on a Broadband Access Server (BRAS) when the target user accesses the Internet and generates corresponding traffic. The traffic information includes at least one of the following: uplink utilization rate, downlink utilization rate, overall traffic utilization rate, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value. The traffic information is sorted based on the time information corresponding to it to obtain sorted traffic information. Based on the overall traffic utilization rate, uplink and downlink utilization rate, uplink and downlink network throughput and bit rate, traffic protocol information including uplink and downlink UDP protocol traffic and uplink and downlink TCP protocol traffic, and preset port traffic value including preset port uplink and downlink traffic, feature analysis is performed on the sorted traffic information to determine the corresponding traffic characteristics. Based on the different traffic characteristics obtained, the accurate user type of the target user is determined. Then, the user's behavior information and preference level are determined through the user type, and products are screened to complete targeted product recommendations. This achieves the technical effect of improving the accuracy of user type identification and the effectiveness of product recommendations.

[0107] Figure 4 The user type determination method based on traffic characteristics provided in the embodiments of this application is as follows: Figure 2 This embodiment provides a user type determination method based on traffic characteristics, including:

[0108] S401. Collect traffic information of target users based on the Broadband Access Server (BRAS). The traffic information includes at least one of the following: uplink traffic utilization rate, downlink traffic utilization rate, overall traffic utilization rate, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value.

[0109] S402. Sort the traffic information based on the time information corresponding to the traffic information, and perform feature analysis on the sorted traffic information to determine traffic characteristics, including at least one of the following: Based on the traffic information, determine the comprehensive utilization rate of traffic for a preset time period, the first ratio of the uplink utilization rate to the downlink utilization rate of the target user, and determine the first traffic characteristic; Based on the traffic information, determine the second ratio of the uplink network throughput to the bit rate, and determine the second traffic characteristic; Based on the traffic information, determine the third ratio of the downlink network throughput to the bit rate, and determine the third traffic characteristic; Based on the traffic protocol information, determine the uplink UDP protocol traffic, downlink UDP protocol traffic, uplink TCP protocol traffic, and downlink TCP protocol traffic; Based on the uplink UDP protocol traffic and uplink TCP protocol traffic, determine the fourth ratio; Based on the downlink UDP protocol traffic and downlink TCP protocol traffic, determine the fifth ratio; Based on the fourth and fifth ratios, determine the fourth traffic characteristic; Based on the preset port traffic value, determine the preset port uplink traffic and preset port downlink traffic; Based on the preset port uplink traffic and preset port downlink traffic, determine the fifth traffic characteristic.

[0110] S403. Based on the first traffic feature, the second traffic feature, the third traffic feature, the fourth traffic feature, and / or the fifth traffic feature, determine the user type of the target user; wherein, the user type includes content provider and network access user;

[0111] S404. When the first ratio of the first traffic characteristic indicator on a single day is greater than the first preset threshold, the user type is determined to be content provider; content provider includes video provider, game provider, and enterprise application provider; when the first ratio on a single day is less than or equal to the first preset threshold, the user type is determined to be network access provider; network access provider includes enterprise leased line, home broadband, and internet cafe.

[0112] S405. When the daily traffic utilization rate is greater than the second preset threshold, the user type is determined to be internet cafe type; when the sixth ratio of the traffic utilization rate during working hours to the traffic utilization rate during non-working hours is greater than the third preset threshold, the user type is determined to be enterprise leased line type; when the seventh ratio of the traffic utilization rate during non-working hours to the traffic utilization rate during working hours is greater than the fourth preset threshold, the user type is determined to be home broadband type.

[0113] S406. When the second ratio and / or the third ratio fall within the range of the first preset threshold, the user type is determined to be standard type; when the second ratio falls within the range of the second preset threshold, the user type is determined to be video provider type; when the third ratio falls within the range of the third preset threshold, the user type is determined to be abnormal type; when the third ratio falls within the range of the fourth preset threshold, the user type is determined to be enterprise leased line type or home broadband type.

[0114] S407. When the fourth ratio falls within the fifth preset threshold range, the user type is determined to be either video provider or game provider; when the fourth ratio falls within the sixth preset threshold range, the user type is determined to be enterprise application; when the fifth ratio falls within the seventh preset threshold range, the user type is determined to be home broadband; when the fifth ratio falls within the eighth preset threshold range, the user type is determined to be enterprise leased line.

[0115] S408. When the ratio of uplink traffic on the first preset port to uplink traffic on the second preset port is greater than the fifth preset threshold, the user type is determined to be enterprise application type; when the ratio of downlink traffic on the first preset port to downlink traffic on the second preset port is greater than the sixth preset threshold, the user type is determined to be network access type; when the ratio of uplink traffic on the third preset port to uplink traffic on the fourth preset port is greater than the seventh preset threshold, the user type is determined to be video provider type.

[0116] S409. Obtain user behavior information based on user type, including online time, behavior name, and behavior object; draw a user behavior trajectory map based on user behavior information to determine high-frequency user behaviors; generate a product recommendation list based on high-frequency user behaviors.

[0117] By executing steps S401 to S409, when a target user accesses the Internet and generates corresponding traffic, the Broadband Access Server (BRAS) collects the target user's traffic information. This traffic information includes at least one of the following: uplink utilization rate, downlink utilization rate, overall traffic utilization rate, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic values. The traffic information is sorted based on the corresponding time information to obtain sorted traffic information. Based on the overall traffic utilization rate, uplink and downlink utilization rate, uplink and downlink network throughput and bit rate within a preset time period, the traffic protocol information (including uplink and downlink UDP and TCP protocol traffic), and the preset port traffic values ​​(including preset port uplink and downlink traffic), corresponding ratios are calculated. Based on these ratios, different traffic characteristics are obtained. Based on these traffic characteristics, the precise user type of the target user is determined. Furthermore, the user's behavioral information and preference levels are determined through the user type, and products are screened to complete targeted product recommendations. This achieves the technical effect of improving the accuracy of user type identification and the effectiveness of product recommendations.

[0118] Figure 5 This is a schematic diagram of the user type determination device based on traffic characteristics provided in an embodiment of this application. Figure 5 As shown, this embodiment provides a user type determination device 500 based on traffic characteristics, including: a data acquisition module 501, a processing module 502, and a determination module 503.

[0119] The acquisition module 501 is used to collect traffic information of target users based on the Broadband Access Server (BRAS).

[0120] Processing module 502 is used to sort the traffic information based on the time information corresponding to the traffic information, perform feature analysis on the sorted traffic information, and determine the traffic characteristics.

[0121] The determination module 503 is used to determine the user type of the target user based on traffic characteristics.

[0122] In one possible implementation, the acquisition module 501 is used for:

[0123] Based on the Broadband Access Server (BRAS), at least one of the following is collected for the target user: uplink traffic utilization, downlink traffic utilization, overall traffic utilization, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value.

[0124] In one possible implementation, the processing module 502 is used for:

[0125] Based on traffic information, determine the comprehensive traffic utilization rate, the first ratio of the uplink traffic utilization rate to the downlink traffic utilization rate of the target user for the preset time period, and determine the first traffic characteristic.

[0126] Based on traffic information, a second ratio of downlink network throughput to bit rate is determined, and a second traffic characteristic is determined;

[0127] Based on traffic information, a third ratio of uplink network throughput to bit rate is determined, and a third traffic characteristic is identified.

[0128] Based on traffic protocol information, determine the fourth traffic characteristic of the target user;

[0129] Based on preset port traffic values, the fifth traffic characteristic of the target user is determined.

[0130] In one possible implementation, the processing module 502 is further used for:

[0131] Based on traffic protocol information, determine the uplink UDP protocol traffic, downlink UDP protocol traffic, uplink TCP protocol traffic, and downlink TCP protocol traffic;

[0132] The fourth ratio is determined based on the uplink UDP protocol traffic and the uplink TCP protocol traffic, and the fifth ratio is determined based on the downlink UDP protocol traffic and the downlink TCP protocol traffic;

[0133] The fourth flow characteristic is determined based on the fourth and fifth ratios.

[0134] In one possible implementation, the processing module 502 is further used for:

[0135] Determine the upstream and downstream traffic of the preset port based on the preset port traffic value;

[0136] The fifth traffic characteristic is determined based on the uplink traffic and downlink traffic of the preset port.

[0137] In one possible implementation, the determining module 503 is used for:

[0138] Based on the first traffic feature, the second traffic feature, the third traffic feature, the fourth traffic feature and / or the fifth traffic feature, the user type of the target user is determined; among which, the user type includes content provider and network access user.

[0139] In one possible implementation, the determining module 503 is further used for:

[0140] When the first ratio of the first traffic characteristic indicator on a single day is greater than the first preset threshold, the user type is determined to be content provider; content provider includes video provider, game provider, and enterprise application provider;

[0141] When the first ratio on a single day is less than or equal to the first preset threshold, the user type is determined to be network access type; network access type includes enterprise leased line type, home broadband type and internet cafe type.

[0142] In one possible implementation, the determining module 503 is further used for:

[0143] When the daily traffic utilization rate is greater than the second preset threshold, the user type is determined to be internet cafe type; when the sixth ratio of the traffic utilization rate during working hours to the traffic utilization rate during non-working hours is greater than the third preset threshold, the user type is determined to be enterprise leased line type; when the seventh ratio of the traffic utilization rate during non-working hours to the traffic utilization rate during working hours is greater than the fourth preset threshold, the user type is determined to be home broadband type.

[0144] When the second ratio and / or the third ratio fall within the range of the first preset threshold, the user type is determined to be standard; when the second ratio falls within the range of the second preset threshold, the user type is determined to be video provider.

[0145] When the third ratio falls within the third preset threshold range, the user type is determined to be abnormal; when the third ratio falls within the fourth preset threshold range, the user type is determined to be either enterprise leased line or home broadband.

[0146] When the fourth ratio falls within the fifth preset threshold range, the user type is determined to be either a video provider or a game provider; when the fourth ratio falls within the sixth preset threshold range, the user type is determined to be an enterprise application.

[0147] When the fifth ratio falls within the seventh preset threshold range, the user type is determined to be home broadband; when the fifth ratio falls within the eighth preset threshold range, the user type is determined to be enterprise leased line.

[0148] When the ratio of uplink traffic on the first preset port to uplink traffic on the second preset port is greater than the fifth preset threshold, the user type is determined to be enterprise application type; when the ratio of downlink traffic on the first preset port to downlink traffic on the second preset port is greater than the sixth preset threshold, the user type is determined to be network access type; when the ratio of uplink traffic on the third preset port to uplink traffic on the fourth preset port is greater than the seventh preset threshold, the user type is determined to be video provider type.

[0149] In one possible implementation, device 500 is also used for:

[0150] User behavior information is obtained based on user type. User behavior information includes online time, behavior name, and behavior object.

[0151] User behavior trajectory maps are drawn based on user behavior information to identify high-frequency user behaviors;

[0152] A product recommendation list is generated based on users' frequent behaviors.

[0153] The user type determination device based on traffic characteristics provided in this application includes a collection module, a processing module, and a determination module. When a target user accesses the Internet and generates corresponding traffic, the collection module collects the target user's traffic information based on a Broadband Access Server (BRAS). The traffic information includes at least one of the following: uplink utilization rate, downlink utilization rate, overall traffic utilization rate, uplink network throughput, downlink network throughput, bit rate, traffic protocol information, and preset port traffic value. The processing module sorts the traffic information based on the time information corresponding to it, obtaining sorted traffic information. Based on the overall traffic utilization rate, uplink and downlink utilization rate, uplink and downlink network throughput and bit rate within a preset time period, the traffic protocol information including uplink and downlink UDP protocol traffic and uplink and downlink TCP protocol traffic, and the preset port traffic value including preset port uplink and downlink traffic, the corresponding ratios are calculated to obtain different traffic characteristics. The determination module determines the accurate user type of the target user based on the obtained different traffic characteristics. Then, based on the user type, the user's behavioral information and preference level are determined, and products are screened to complete targeted product recommendations. This achieves the technical effect of improving the accuracy of user type identification and the effectiveness of product recommendations.

[0154] Figure 6 The hardware structure diagram of the user type determination device based on traffic characteristics provided in the embodiments of this application is shown below. Figure 6 As shown, the user type determination device 600 based on traffic characteristics includes:

[0155] Processor 601 and memory 602;

[0156] The memory stores instructions that the computer executes;

[0157] The processor executes computer execution instructions stored in memory 602, causing the user type determination device based on traffic characteristics to perform the user type determination method based on traffic characteristics as described above.

[0158] It should be understood that the processor 601 described above can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The memory 602 may include high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk, or optical disc, etc.

[0159] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the user type determination method based on traffic characteristics as described above.

[0160] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0161] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A traffic feature based user type determination method, characterized by, The method comprises: acquiring traffic information of a target user based on a broadband remote access server (BRAS); sorting time information corresponding to the traffic information; determining a first traffic feature based on the traffic information, including a traffic comprehensive utilization rate corresponding to a preset time period, a first ratio of traffic uplink utilization rate to traffic downlink utilization rate of the target user, and a second ratio of downlink network throughput rate to bit rate; determining a second traffic feature based on the traffic information, including a third ratio of traffic uplink network throughput rate to bit rate; determining a third traffic feature based on the traffic information, including a fourth ratio of uplink UDP protocol traffic to uplink TCP protocol traffic, and a fifth ratio of downlink UDP protocol traffic to downlink TCP protocol traffic; determining a fourth traffic feature based on the fourth ratio and the fifth ratio; determining preset port uplink traffic and preset port downlink traffic based on a preset port traffic value; determining a fifth traffic feature based on the preset port uplink traffic and the preset port downlink traffic; determining a user type of the target user based on the first traffic feature, the second traffic feature, the third traffic feature, the fourth traffic feature, and / or the fifth traffic feature, and a corresponding preset threshold or preset threshold range, wherein the user type includes a content providing type and a network accessing type, and the content providing type includes a video providing type, a game providing type, and an enterprise application type, and the network accessing type includes an enterprise private line type, a home broadband type, and a cybercafe type. The method of acquiring traffic information of a target user based on a broadband remote access server (BRAS) comprises: acquiring at least one of the following corresponding to the target user based on the broadband remote access server (BRAS): traffic uplink utilization rate, traffic downlink utilization rate, traffic comprehensive utilization rate, uplink network throughput rate, downlink network throughput rate, bit rate, traffic protocol information, and preset port traffic value.

2. The method of claim 1, wherein, The method of determining a user type of the target user based on the traffic feature comprises: when the first ratio of a single day indicated by the first traffic feature is greater than a first preset threshold, determining that the user type is the content providing type, and the content providing type includes a video providing type, a game providing type, and an enterprise application type; 3. The method of claim 1, wherein, when the first ratio of a single day is less than or equal to the first preset threshold, determining that the user type is the network accessing type, and the network accessing type includes an enterprise private line type, a home broadband type, and a cybercafe type. The method of determining a user type of the target user based on the traffic feature comprises: ​ 4. The method of claim 3, wherein, ​ when a comprehensive utilization rate of traffic corresponding to a single day is greater than a second preset threshold, determining that the user type is the cybercafe type; when a sixth ratio of a comprehensive utilization rate of traffic corresponding to a work period to a comprehensive utilization rate of traffic corresponding to a non-work period is greater than a third preset threshold, determining that the user type is the enterprise private line type; when a seventh ratio of the comprehensive utilization rate of traffic corresponding to the non-work period to the comprehensive utilization rate of traffic corresponding to the work period is greater than a fourth preset threshold, determining that the user type is the home broadband type; when the second ratio and / or the third ratio falls within a first preset threshold range, determining that the user type is a standard type; when the second ratio falls within a second preset threshold range, determining that the user type is the video providing type; when the third ratio falls within a third preset threshold range, determining that the user type is an abnormal type; when the third ratio falls within a fourth preset threshold range, determining that the user type is the enterprise private line type or the home broadband type; when the fourth ratio falls within a fifth preset threshold range, determining that the user type is the video providing type or the game providing type; when the fourth ratio falls within a sixth preset threshold range, determining that the user type is the enterprise application type; when the fifth ratio falls within a seventh preset threshold range, determining that the user type is the home broadband type; when the fifth ratio falls within an eighth preset threshold range, determining that the user type is the enterprise private line type; when a ratio of first preset port uplink traffic to second preset port uplink traffic is greater than a fifth preset threshold, determining that the user type is the enterprise application type; when a ratio of first preset port downlink traffic to second preset port downlink traffic is greater than a sixth preset threshold, determining that the user type is the network access type; when a ratio of third preset port uplink traffic to fourth preset port uplink traffic is greater than a seventh preset threshold, determining that the user type is the video providing type.

5. The method of claim 1, wherein, after determining the user type of the target user based on the traffic features, comprising: obtaining user behavior information based on the user type, the user behavior information including online time, behavior name, and behavior object; drawing a user behavior trajectory graph based on the user behavior information, and determining a user high-frequency behavior; generating a product recommendation list based on the user high-frequency behavior.

6. A traffic feature based user type determination device, characterized by, comprising: a collection module configured to collect traffic information of a target user based on a broadband remote access server (BRAS); a processing module configured to sort time information corresponding to the traffic information; based on the traffic information, determining a comprehensive utilization rate of traffic corresponding to a preset time period, a first ratio of traffic uplink utilization rate to traffic downlink utilization rate of the target user, and determining a first traffic feature; based on the traffic information, determining a second ratio of downlink network throughput rate to bit rate, and determining a second traffic feature; based on the traffic information, determining a third ratio of traffic uplink network throughput rate to bit rate, and determining a third traffic feature; determine, based on the traffic protocol information, uplink UDP protocol traffic, downlink UDP protocol traffic, uplink TCP protocol traffic, and downlink TCP protocol traffic; determine a fourth ratio based on the uplink UDP protocol traffic and the uplink TCP protocol traffic, and determine a fifth ratio based on the downlink UDP protocol traffic and the downlink TCP protocol traffic; determine a fourth traffic feature based on the fourth ratio and the fifth ratio; determine preset port uplink traffic and preset port downlink traffic based on a preset port traffic value; determine a fifth traffic feature based on the preset port uplink traffic and the preset port downlink traffic; determine, based on the first traffic feature, the second traffic feature, the third traffic feature, the fourth traffic feature, and / or the fifth traffic feature and a corresponding preset threshold value or preset threshold value range, the user type of the target user, the user type including a content providing type and a network accessing type; wherein the content providing type includes a video providing type, a game providing type, and an enterprise application type; and the network accessing type includes an enterprise private line type, a home broadband type, and a cybercafe type.

7. A traffic feature-based user type determination device, comprising: comprise: a processor, and a memory connected to the processor in communication; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the user type determination method based on traffic features according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by the processor to implement the user type determination method based on traffic features according to any one of claims 1 to 5.

Images