CN109995539B - OCS (online charging System) traffic authorization method, OCS, server and readable storage medium - Google Patents

Abstract

The invention discloses an OCS flow authorization method, an OCS, a server and a readable storage medium, which are used to solve the problem that the OCS in the prior art is not flexible enough to perform dynamic authorization configuration, resulting in low accuracy of user authorization configuration. The technical problem is to improve the flexibility of traffic authorization configuration, so that differentiated traffic authorization can be implemented for different users to meet the actual traffic service requirements of users as much as possible, and enhance the user's traffic service experience. The method includes: creating a traffic authorization model according to the surfing behavior data of the terminal user and the service characteristics of the subscription service; obtaining a traffic service request sent by a terminal device corresponding to the terminal user; inputting the traffic service request into the traffic authorization model to obtain the predicted traffic authorization information for the traffic service request; send the predicted traffic authorization information to the PGW, so as to forward the predicted traffic authorization information to the terminal device through the PGW.

Description

A kind of flow authorization method of OCS, OCS, server and readable storage medium

technical field

The present invention relates to the technical field of wireless communication, in particular to an OCS flow authorization method, an OCS, a server and a readable storage medium.

Background technique

At present, the traffic service has become the main business of major operators. In order to ensure the user experience and enterprise benefits in the communication network environment, each operator has deployed OCS (Online Charging System, online charging system). Various communication services (such as traffic services) are charged in real time, and the relationship between the current OCS and each network element is shown in Figure 1 . The rapid development of services requires the network elements in the communication network to perform message and bill change trigger processing from multiple dimensions. Many factors such as user location, service content, and network type will lead to PGW (Packet Data Network Gateway, packet data network gateway). The amount of messages interacting with the OCS has surged, and the real-time message processing and data storage capabilities of the OCS system are facing greater challenges.

At present, one way is to improve the business level expansion capability and deployment efficiency of OCS through cloud-based architecture technology and container technology to cope with the rapid growth of business volume. It is not conducive to the long-term operation and actual deployment of the system, so the purpose of reducing the pressure of the OCS system is further achieved by reducing the amount of message interaction between the PGW and the OCS. The most direct way to reduce the amount of message interaction is to increase each traffic service request. In this way, the frequency of message interaction will be significantly reduced to achieve the purpose of reducing the pressure of the OCS system.

In the method of reducing the amount of message interaction between the PGW and the OCS, it has also experienced the configuration of the dynamic authorization slice from the initial static ladder authorization slice setting. In the current dynamic authorization slice configuration method, it can be configured according to different time periods or services The authorization slices corresponding to different types are dynamically configured, but the authorization slices configured for all users are the same. Different authorization configuration cannot be implemented according to the difference of each user, which may lead to inaccurate authorization configuration for users, that is to say , the way in which the OCS performs dynamic authorization configuration in the prior art is not flexible enough, and the accuracy of the user authorization configuration is low.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide an OCS traffic authorization method, an OCS, a server, and a readable storage medium, which are used to solve the problem that the way in which the OCS performs dynamic authorization configuration in the prior art is not flexible enough, resulting in low accuracy of user authorization configuration In order to improve the flexibility of traffic authorization configuration, differentiated traffic authorization can be implemented for different users to meet the actual traffic service requirements of users as much as possible, and enhance the user's traffic service experience.

A first aspect provides a traffic authorization method for OCS, the method comprising:

Create a traffic authorization model according to the end user's online behavior data and the service characteristics of the subscription service;

obtaining the traffic service request sent by the terminal device corresponding to the terminal user;

Inputting the traffic service request into the traffic authorization model to obtain predicted traffic authorization information for the traffic service request;

Sending the predicted traffic authorization information to the PGW, so as to forward the predicted traffic authorization information to the terminal device through the PGW.

Optionally, create a traffic authorization model according to the end user's surfing behavior data and the service characteristics of the subscription service, including:

Abstracting the surfing behavior data and the service feature of the subscription service into an surfing feature label class; wherein the surfing feature label class includes at least one surfing feature label;

According to the surfing behavior data, an initial weight is set for each surfing feature label in the surfing feature label class; wherein, the surfing feature label with a larger weight has a greater impact on the user's surfing behavior;

The traffic authorization model is created according to the surfing feature tag class and the corresponding initial weight.

Optionally, inputting the traffic service request into the traffic authorization model to obtain predicted traffic authorization information for the traffic service request, including:

Parsing the traffic service request to determine multiple surfing feature tags corresponding to the traffic service request;

adding up the weight values corresponding to the plurality of surfing feature tags respectively to obtain a total weight value corresponding to the traffic service request;

The predicted traffic authorization information is determined according to the total weight value.

Optionally, determining the predicted traffic authorization information according to the total weight value includes:

After obtaining the total weight value, determine whether the traffic service request matches the predetermined traffic packet service included in the subscription service;

If the traffic service request matches the predetermined traffic packet service, adding a predetermined weight on the basis of the total weight value to obtain a target total weight value;

The predicted traffic authorization information is determined according to the target total weight value.

Optionally, sending the predicted traffic authorization information to the PGW includes:

Judging whether the predicted traffic authorization information is wrong according to a predetermined judgment rule;

If the predicted traffic authorization information is correct, sending the predicted traffic authorization information to the PGW;

If the predicted traffic authorization information is wrong, send the pre-configured authorization information to the PGW

Optionally, after sending the predicted traffic authorization information to the PGW, the method further includes:

Obtaining the actual traffic usage information of the traffic service performed by the terminal user based on the predicted traffic authorization information;

The predicted traffic authorization information and the traffic actual usage information are input into the traffic authorization model to train the traffic authorization model to obtain a trained traffic authorization model.

In a second aspect, an OCS is provided, the OCS comprising;

The model creation module is used to create a traffic authorization model according to the end user's online behavior data and the service characteristics of the subscription service;

a first obtaining module, configured to obtain a traffic service request sent by a terminal device corresponding to the terminal user;

an authorization module, configured to input the traffic service request into the traffic authorization model to obtain predicted traffic authorization information for the traffic service request;

A sending module, configured to send the predicted traffic authorization information to the PGW, so as to forward the predicted traffic authorization information to the terminal device through the PGW.

Optionally, the model creation module is used for:

Abstracting the surfing behavior data and the service feature of the subscription service into an surfing feature label class; wherein the surfing feature label class includes at least one surfing feature label;

According to the surfing behavior data, an initial weight is set for each surfing feature label in the surfing feature label class; wherein, the surfing feature label with a larger weight has a greater impact on the user's surfing behavior;

The traffic authorization model is created according to the surfing feature tag class and the corresponding initial weight.

Optionally, the authorization module is used for:

Parsing the traffic service request to determine multiple surfing feature tags corresponding to the traffic service request;

adding up the weight values corresponding to the plurality of surfing feature tags respectively to obtain a total weight value corresponding to the traffic service request;

The predicted traffic authorization information is determined according to the total weight value.

Optionally, the authorization module is used for:

After obtaining the total weight value, determine whether the traffic service request matches the predetermined traffic packet service included in the subscription service;

If the traffic service request matches the predetermined traffic packet service, adding a predetermined weight on the basis of the total weight value to obtain a target total weight value;

The predicted traffic authorization information is determined according to the target total weight value.

Optionally, the sending module is used for:

Judging whether the predicted traffic authorization information is wrong according to a predetermined judgment rule;

If the predicted traffic authorization information is correct, sending the predicted traffic authorization information to the PGW;

If the predicted traffic authorization information is wrong, the pre-configured authorization information is sent to the PGW.

Optionally, the OCS further includes:

a second obtaining module, configured to obtain, after the sending module sends the predicted flow authorization information to the PGW, the actual flow usage information of the terminal user performing the flow service based on the predicted flow authorization information;

A model training module, configured to input the predicted traffic authorization information and the traffic actual usage information into the traffic authorization model to train the traffic authorization model to obtain a trained traffic authorization model.

In a third aspect, a server is provided, the server comprising:

at least one processor;

a communication interface connected to the at least one processor for sending and receiving information;

a memory connected to the at least one processor;

The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the OCS traffic authorization method according to any one of the first aspects by executing the instructions stored in the memory A step of.

In a fourth aspect, a readable storage medium is provided, wherein the readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes any one of the first aspect. The steps of the OCS traffic authorization method.

In this embodiment of the present invention, a traffic authorization model can be created according to the end user's Internet behavior data and the service characteristics of the subscription service, and then when the traffic service request reported by the end user is obtained, the traffic service request can be input into the created traffic authorization model to Obtain the predicted traffic authorization information for the traffic service request, and finally send the obtained predicted traffic authorization information to the terminal device to realize automatic authorization of the user's traffic service request. Since the traffic authorization model is created based on the end user's surfing behavior data combined with the service characteristics of the subscription service, the user's traffic service request is highly targeted when it is estimated, and can meet the actual use requirements of the end user as much as possible. This improves the accuracy of the traffic authorization configuration, and can perform differentiated traffic authorization for different end users, making the traffic authorization method more flexible, so as to meet the actual traffic service requirements of users as much as possible, and enhance the user's traffic service experience.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without any creative effort.

1 is a schematic diagram of the relationship between the OCS and each network element in the prior art;

2 is a flowchart of a flow authorization method for OCS in an embodiment of the present invention;

3 is a structural block diagram of an OCS in an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a server in an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. The embodiments of the present invention and the features of the embodiments may be arbitrarily combined with each other without conflict. Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.

The terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive protections. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally also includes For other steps or units inherent to these processes, methods, products or devices.

In addition, the term "and/or" in this article is only an association relationship to describe the associated objects, indicating that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, There are three cases of B alone. In addition, the character "/" in this text, unless otherwise specified, generally indicates that the related objects before and after are an "or" relationship.

Embodiments of the present invention provide an OCS traffic authorization method, an OCS, a server, and a readable storage medium, which are used to solve the problem that the way in which the OCS performs dynamic authorization configuration in the prior art is not flexible enough, resulting in low accuracy of user authorization configuration In order to improve the flexibility of traffic authorization configuration, differentiated traffic authorization can be implemented for different users to meet the actual traffic service requirements of users as much as possible, and enhance the user's traffic service experience.

To better understand the OCS traffic authorization method, OCS, server, and readable storage medium provided by the embodiments of the present invention, the foregoing technical solutions will be described in detail below with reference to the accompanying drawings and specific implementations.

First, the application scenarios of the embodiments of the present invention are introduced.

The construction of OCS marks the beginning of BSS (Business Support System, business support system) participating in the user's business use process control. Since then, the relationship between BSS and network elements has become more intimate, and the functional boundary of BSS has also expanded rapidly. In the process of business development and maturity, OCS has been making breakthroughs in improving the processing capacity of the system itself and reducing the system load, and has achieved remarkable results. Looking back at the construction process of OCS, technical means such as automatic business identification and control, peak reduction and pressure reduction, and cloudification of architecture have solved the phased problems in the system development process, but we have only focused on the improvement of the OCS system itself or the All end users adopt the same traffic authorization configuration, but do not take into account the differences between users themselves and services. This makes the current method of traffic authorization for end users inflexible, which leads to the inaccuracy of traffic authorization for end users. It cannot meet the actual business needs of different users, and the embodiment of the present invention provides a dynamic traffic authorization scheme for different users, improves the flexibility of traffic authorization configuration, and enables differentiated traffic for different users. Authorization can meet the actual traffic service requirements of users as much as possible and enhance the user's traffic service experience.

Referring to FIG. 2, FIG. 2 is a flowchart of an OCS traffic authorization method provided by an embodiment of the present invention. The OCS traffic authorization method provided by the embodiment of the present invention may be applied to, for example, the OCS shown in FIG. 1 . The flow of this method is described below.

Step 21: Create a traffic authorization model according to the end user's surfing behavior data and the service characteristics of the subscription service.

The terminal user refers to a user who uses a terminal device, and the terminal device can be a device that can use the traffic service provided by the operator, such as a mobile phone, PAD (tablet computer), PDA (Personal Digital Assistant, personal digital assistant), wearable type devices (such as smart watches), laptop computers and other different types of terminal devices.

The Internet behavior of end users refers to the operation behavior of using the traffic service provided by the operator to surf the Internet, and the Internet behavior data is the usage information generated in the process of using the traffic service to surf the Internet, such as how much traffic is consumed in a certain period of time, Or, for example, how much traffic is consumed by a certain APP (Application) in a certain period of time, or for example, the average network speed in a certain period of time, and so on.

Operators can provide users with a variety of tariff packages or other value-added services, and users can purchase appropriate tariff packages and selectively purchase some value-added services according to their own usage needs. The business is called a subscription business. Depending on the subscription business, the corresponding business characteristics will also be different, and the business characteristics of the business may include account balance, free traffic in the package, total and remaining directional traffic (such as provincial traffic and domestic traffic), and timed traffic (such as From 23:00 to 5:00 am the next day, the total amount and remaining amount of free-time traffic), excess traffic outside the package, free call minutes (including local and roaming), etc. Since the traffic service is one of the communication services, then Naturally, traffic business characteristics can also be obtained, such as the free traffic in the aforementioned package, the total and remaining amount of directional traffic (such as provincial traffic and domestic traffic), and timed traffic (such as idle time from 23:00 to 5:00 am the next day). The total amount and the remaining amount of traffic (time traffic) belong to the traffic service characteristics, and the actual configuration authority and the already used situation of the corresponding subscription service can be known through the service characteristics.

The end user's surfing behavior data and the service characteristics of the subscription service can indicate the end user's usage habits, preferences and special service needs in the actual use of the service, because the service subscribed by the user generally does not change greatly in a short period of time. On this premise, the user's historical surfing behavior data and the service characteristics of the subscription service can roughly reflect the terminal user's usage habits and actual service needs, that is, the user's historical surfing behavior data and the service characteristics of the subscription service can be used. Future traffic service requests are pre-judged, so in this embodiment of the present invention, a traffic authorization model corresponding to the terminal user is created according to the terminal user's surfing behavior data and the service characteristics of the subscription service. Estimate and judge future traffic service requests. Since the traffic authorization model is created based on the end user's historical online behavior data combined with the service characteristics of the subscription service, the subsequent estimation of the user's traffic service request is more targeted and can meet the end user's requirements as much as possible. In addition, OCS can build differentiated models for different end users, making the authorization method for traffic more flexible.

In the specific implementation process, the surfing behavior data and the service features of the subscription service can be abstracted into multiple surfing feature tags. Set a corresponding initial weight. The Internet feature tag with a larger weight value indicates a greater force affecting the user's Internet behavior. It can be understood that the Internet access event corresponding to the Internet feature tag with a larger weight value is frequently performed by the user. The larger the value, the higher the frequency of the corresponding Internet access events, or the initial weight can be set for each Internet access feature tag according to the system preset method. weight to create a traffic authorization model for the end user, and there is no limitation on the specific model creation algorithm used in this embodiment of the present invention. Algorithms to create traffic authorization models.

That is to say, a labelled user portrait model can be created according to the end user's online behavior data and the service characteristics of the subscription service, which can indicate the end user's consumption behavior, online behavior and basic attributes and other data. The screen can roughly reflect the regular business usage of end users, which facilitates the differentiation and precise configuration of traffic authorization, and enhances the user experience.

Please refer to Table 1. For example, 18 surfing feature tags as shown in Table 1 are abstracted according to the surfing behavior data of the terminal user and the service features of the subscription service. In the embodiment of the present invention, the 18 surfing feature tags may be called The Internet feature label class of the end user.

Table 1

serial number Internet feature label initial weight 1 User Internet traffic from 22:00 to 6:00 am the next day 0.79 2 6:00 to 12:00 User Internet Traffic 0.79 3 User Internet traffic from 12:00 to 22:00 0.85 4 User's Internet traffic on weekdays 0.66 5 User Internet traffic during holidays 0.85 6 Free data in the tariff plan subscribed by the user 0.43 7 Users use the business category as video 0.43 8 Users use business categories as web pages 0.59 9 The main business category of users is music 0.43 10 The main business category of users is games 0.43 11 User Occupation for Students 0.09 12 User occupation is entertainment star 0.09 13 User occupation is entrepreneur 0.09 14 User occupation is ordinary white-collar workers 0.09 15 User occupation is farmer 0.09 16 User age is youth 0.02 17 User age is middle age 0.02 18 User age is old 0.02

As shown in Table 1, each surfing feature tag corresponds to an initial weight. For example, for the 3 surfing feature tags with serial numbers 1-3, the "22:00 to 6:00 am the next day" The weight value of "Internet traffic" and "User Internet traffic from 6:00 to 12:00" is 0.79, while "User Internet traffic from 12:00 to 22:00" is a higher value of 0.85, which can indicate the user's Internet habits There is a lot of Internet access during the period from 12:00 to 22:00. For example, for the four Internet feature tags with serial numbers 7-10, the weight value of "users use business categories is web pages" is greater than other 3, it can indicate that the user spends most of the time browsing the web during Internet access, and so on.

The above describes a method for creating a traffic authorization model. It should be noted that, in addition to the method described above, other methods can be used to create the model, as long as the end user's online behavior data and the service characteristics of the subscription service are used. The creation of the final traffic authorization model can be completed as input data, and the embodiments of the present invention will not give examples one by one.

Step 22: Obtain the traffic service request sent by the terminal device corresponding to the terminal user.

After the traffic authorization model for end users is created, in actual use, when the user needs to access the Internet through the terminal device, the corresponding traffic service request will be sent to the OCS system first, specifically through the terminal device corresponding to the end user. Report traffic service requests to the OCS system.

Step 23: Input the traffic service request into the traffic authorization model to obtain the predicted traffic authorization information for the traffic service request.

Further, in order to authorize the traffic service request of the terminal user, after the OCS system obtains the traffic service request reported by the terminal device, the traffic service request can be input into the previously created traffic authorization model as an input condition for calculation, and then The predicted traffic authorization information for the traffic service request can be dynamically obtained, that is to say, the OCS system performs authorization configuration according to the traffic service request reported by the user in real time, and the authorization information predicted by different users is different. Differentiated traffic authorization configuration for different users is realized, and the authorization information predicted by different traffic service requests is also different, so that not only different users can be configured differently, but also different service requests of the same user. Therefore, each authorization configuration for the user can match the current specific traffic service request as much as possible, so as to achieve the purpose of satisfying the current actual use demand of the user as much as possible.

Combining the above-mentioned method of creating a traffic authorization model with the Internet feature tag class and the corresponding initial weight, after the OCS system obtains the traffic service request reported by the terminal device, it can first parse the traffic service request to determine whether it is related to the traffic service request. Multiple Internet access feature tags corresponding to the traffic service request, and then add the weight values corresponding to the multiple Internet access feature tags respectively to obtain the total weight value corresponding to the traffic service request, and then determine the corresponding weight value according to the obtained total weight value. The predicted traffic authorization information corresponding to the traffic service request.

By decomposing the traffic service requests reported by users in real time into multiple corresponding Internet feature tags, and configuring traffic authorization according to the corresponding weight values of these Internet feature tags, because a large amount of Internet usage data can roughly reflect the user's usual services Therefore, the method in this embodiment of the present invention may be to make targeted and accurate prediction on the current traffic authorization by associating the current traffic service request of the user with the historical usage habit of the user.

In addition, in practice, the services subscribed by users may include special traffic services. For example, on the basis of the existing tariff package, they additionally subscribe to scheduled traffic package services such as idle-time traffic package services or video-specific traffic package services. These also include the case of predetermined traffic package services, and additional weights can be supplemented when the weight values are used for traffic authorization prediction. For example, if the user subscribes to the video-specific traffic package service, after obtaining the total weight value of all Internet feature tags according to the aforementioned method, if the traffic service request reported by the user indicates that the requested traffic is for watching videos, then it indicates that The traffic service request matches the predetermined traffic package service. At this time, the predetermined weight can be corrected on the basis of the total weight value to obtain the final target total weight value, and finally the traffic authorization is performed according to the target total weight value. forecast configuration.

Because the predetermined traffic package service is subscribed by the user on the basis of the tariff package, it indicates that the user's actual demand for the predetermined traffic package service is relatively strong. That is, its influence on the user's online behavior is generally large, so by adding additional weights to special traffic services, the user's traffic service requests can be authorized to the greatest extent, so as to meet the user's requirements as much as possible. actual use requirements.

For example, a campus user subscribes to a Tencent video data package and a provincial 10G data package. The user's data account has a reminder threshold of 15G for the Tencent video data package, and the provincial data package reminder threshold is 6G. :30 to initiate a Tencent video service request, combined with Table 1, when calculating the total weight value, the “user’s Internet traffic from 22:00 to 6:00 am the next day”, “users use the business category is video”, The initial weights corresponding to the 4 online feature labels "user occupation is student" and "user age is youth" are added together to obtain the total weight value of 0.79+0.43+0.09+0.01=1.32. Further, since the current request is the Tencent video service request, which matches the Tencent Video traffic package ordered by the user, additional weights can also be added, such as adding a weight of 0.8, so the final use The target total weight value for traffic authorization configuration is the sum of the total weight value of 1.32 obtained at the beginning and the supplementary weight value of 0.8, that is, 2.12, so the current Tencent video service request initiated by the user can obtain 2.12 times the regular authorization amount. Due to the increase in the amount of authorization for a single time, the amount of message interaction between users and OCS can be reduced by about 50% when using this service, which can reduce the system pressure of OCS and minimize the use of the service. It can also improve the user's experience to a certain extent by interacting with the OCS message locally.

Step 24: Send the predicted traffic authorization information to the PGW, so as to forward the predicted traffic authorization information to the terminal device through the PGW.

After obtaining the predicted authorization information for the traffic service request in the manner described above, the OCS can return it to the PGW, and then return the predicted authorization information to the terminal device through the PGW to complete the automatic configuration of the terminal user's traffic authorization.

In practice, the configuration of the predictive authorization information may fail or be wrong due to some abnormal reasons. To ensure that the predictive authorization information fed back to the terminal device is accurate and does not affect the user's service, before sending the predictive authorization information to the PGW, you can First judge whether the predicted traffic authorization information is wrong according to the predetermined judgment rules. For example, the predicted traffic authorization information is obviously wrong, such as 0 or 10T. At this time, in order not to affect the user's service use, the pre-configured authorization information can be sent to the PGW and then the PGW Forwarded to the terminal device, and the pre-configured authorization information is the authorization information that can at least ensure that the user can perform services normally. Of course, if it is determined that there is no obvious error in the predicted traffic authorization information, the estimated predicted traffic authorization information will be sent to the PGW and then forwarded by the PGW. to the terminal device.

After the user's traffic service request is predicted and authorized according to the created traffic authorization model, in order to optimize the traffic authorization model so that the user's other traffic service requests can be more accurately authorized subsequently, in the present invention In the embodiment, after a predicted traffic authorization is performed on the terminal user, the actual traffic usage information generated by the terminal user performing the traffic service based on the predicted traffic authorization information configured by the OCS can also be obtained, and then the actual traffic usage information and the previous traffic usage information can be obtained. The predicted traffic authorization information is used as training conditions to input the previously created traffic authorization model for model training, and then the trained traffic authorization model is obtained. Use the information to continue to train the traffic authorization model, and gradually optimize and adjust the traffic authorization model through self-learning. It is close to the actual usage requirements of users, so that the traffic authorization for users can be more and more accurate, and the accuracy of traffic authorization is improved.

In the specific implementation process, the traffic authorization model can be continuously trained according to a certain period. For example, the model training can be performed at a predetermined time interval (for example, 2 days), or the model training can be performed after a predetermined number of traffic service requests. , or when it is determined that the tariff package subscribed by the user changes, model training can be performed in time to meet the user's traffic usage requirements under the new tariff package as much as possible.

In this embodiment of the present invention, a traffic authorization model can be created according to the end user's surfing behavior data and the service characteristics of the subscription service, and then when the traffic service request reported by the end user is obtained, the traffic service request can be input into the created traffic authorization model to Obtain the predicted traffic authorization information for the traffic service request, and finally send the obtained predicted traffic authorization information to the terminal device to realize automatic authorization of the user's traffic service request. Since the traffic authorization model is created based on the end user's surfing behavior data combined with the service characteristics of the subscription service, the user's traffic service request is highly targeted when it is estimated, and can meet the actual use requirements of the end user as much as possible. This further improves the accuracy of the traffic authorization configuration, and can perform differentiated traffic authorization for different end users, making the traffic authorization method more flexible, so as to meet the user's actual traffic service requirements as much as possible and enhance the user's traffic service experience.

Based on the same inventive concept, referring to FIG. 3 , an embodiment of the present invention provides an OCS, and the OCS may be the OCS mentioned in the introduction in the foregoing embodiments. The OCS includes a model creation module 31, a first acquisition module 32, an authorization module 33, and a transmission module 34, and the model creation module 31, the first acquisition module 32, the authorization module 33, and the transmission module 34 in the embodiment of the present invention can be implemented by hardware The processor implements the relevant functional units. in:

The model creation module 31 is used for creating a traffic authorization model according to the surfing behavior data of the end user and the service characteristics of the subscription service;

The first obtaining module 32 is configured to obtain the traffic service request sent by the terminal device corresponding to the end user;

The authorization module 33 is used to input the traffic service request into the traffic authorization model to obtain the predicted traffic authorization information for the traffic service request;

The sending module 34 is configured to send the predicted traffic authorization information to the PGW, so as to forward the predicted traffic authorization information to the terminal device through the PGW.

In a possible implementation, the model creation module 31 is used to:

Abstract the surfing behavior data and the business features of the subscription service into surfing feature label classes; wherein, the surfing feature label classes include at least one surfing feature label;

According to the surfing behavior data, an initial weight is set for each surfing feature label in the surfing feature label class; wherein, the surfing feature label with a larger weight has a greater impact on the user's surfing behavior;

Create a traffic authorization model according to the Internet feature label class and the corresponding initial weight.

In a possible implementation, the authorization module 33 is used to:

Parsing the traffic service request to determine multiple Internet feature tags corresponding to the traffic service request;

The weight values corresponding to the plurality of Internet access feature tags are added together to obtain a total weight value corresponding to the traffic service request;

The predicted traffic authorization information is determined according to the total weight value.

In a possible implementation, the authorization module 33 is used to:

After obtaining the total weight value, determine whether the traffic service request matches the predetermined traffic package service included in the subscription service;

If the traffic service request matches the predetermined traffic package service, the predetermined weight is added on the basis of the total weight value to obtain the target total weight value;

The predicted traffic authorization information is determined according to the target total weight value.

In a possible implementation, the sending module 34 is used for:

Judging whether the predicted traffic authorization information is wrong according to the predetermined judgment rule;

If the predicted traffic authorization information is correct, send the predicted traffic authorization information to the PGW;

If the predicted traffic authorization information is wrong, the pre-configured authorization information is sent to the PGW.

In a possible implementation, the OCS further includes:

The second obtaining module is used to obtain the actual flow usage information of the terminal user performing the flow service based on the predicted flow authorization information after the sending module 34 sends the predicted flow authorization information to the PGW;

The model training module is used to input the predicted traffic authorization information and the actual traffic usage information into the traffic authorization model to train the traffic authorization model to obtain the trained traffic authorization model.

Since the OCS provided in the embodiment of the present invention can be used to execute the steps included in the foregoing OCS traffic authorization method, for the functions that can be implemented by each functional module included in the OCS in the embodiment of the present invention and some implementation processes, refer to the foregoing. The description of the embodiment part of the traffic authorization method of the OCS will not be repeated here.

Based on the same inventive concept, referring to FIG. 4, an embodiment of the present invention provides a server, the server includes at least one processor 41 (in FIG. 4, one processor 41 is used for illustration), and the at least one processor The communication interface 42 connected with the processor 41 is used for sending and receiving information, and the memory 43 is connected with the at least one processor 41 . The memory 43 stores instructions that can be executed by at least one processor 41, and the at least one processor 41 can execute the steps of the aforementioned data storage method by executing the instructions stored in the memory.

Specifically, the processor 41 may be a general-purpose CPU (central processing unit), or may be an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), or may be one or more integrated circuits for controlling program execution, or may be a baseband chip ,and many more.

The number of the memory 43 may be one or more, and the memory 43 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, RAM (Random Access Memory, random access memory), SRAM ( Static Random Access Memory), PROM (Programmable Read Only Memory, Programmable Read Only Memory), ROM (Read Only Memory, Read Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory, erasable with electricity) programmable read-only memory), magnetic memory, magnetic disk, optical disk, etc.

By designing and programming the processor 41, the code corresponding to the aforementioned data storage method can be solidified into the chip, so that the chip can execute the steps of the aforementioned OCS traffic authorization method during operation. How to design and program the processor 41 It is a technique known to those skilled in the art and will not be repeated here.

Based on the same inventive concept, an embodiment of the present invention further provides a readable storage medium, where the readable storage medium stores computer instructions, when the computer instructions are executed on the computer, the computer executes the aforementioned OCS traffic The steps of the authorization method.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, optical storage, and the like.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims (7)

1. A method for authorizing traffic of an OCS (online charging system), the method comprising:

abstracting the internet behavior data of the terminal user and the service characteristics of the ordering service into internet characteristic label classes; the internet access feature tag class comprises at least one internet access feature tag, the internet access behavior data is use information generated by the terminal user in the process of using a flow service to perform internet access behavior, and the internet access behavior is an operation behavior of using the flow service to perform internet access;

setting an initial weight for each internet surfing feature tag in the internet surfing feature tag class according to the internet surfing behavior data; the internet surfing feature tags with larger weights have larger influence on the internet surfing behavior of the user, and the internet surfing feature tags with larger weights indicate that the frequency of the corresponding internet surfing events of the user is higher;

creating a flow authorization model according to the Internet characteristic label class and the corresponding initial weight;

acquiring a flow service request sent by terminal equipment corresponding to the terminal user;

inputting the traffic service request into the traffic authorization model to obtain predicted traffic authorization information for the traffic service request, including: analyzing the flow service request to determine a plurality of internet access characteristic labels corresponding to the flow service request; adding the weight values respectively corresponding to the plurality of internet access feature tags to obtain a total weight value corresponding to the traffic service request; determining the predicted flow authorization information according to the total weight value;

and sending the predicted traffic authorization information to a packet data network gateway (PGW) so as to forward the predicted traffic authorization information to the terminal equipment through the PGW.

2. The method of claim 1, wherein determining the predicted traffic authorization information based on the total weight value comprises:

after obtaining the total weight value, judging whether the flow service request is matched with a preset flow packet service included in the subscription service;

if the flow service request is matched with the preset flow packet service, adding a preset weight on the basis of the total weight to obtain a target total weight;

and determining the predicted flow authorization information according to the target total weight value.

3. The method of claim 1, wherein sending the predicted traffic authorization information to a PGW comprises:

judging whether the predicted flow authorization information has errors according to a preset judgment rule;

if the predicted traffic authorization information is not in error, sending the predicted traffic authorization information to the PGW;

and if the predicted flow authorization information is wrong, sending preset authorization information to the PGW.

4. The method of any of claims 1-3, wherein after sending the predicted traffic authorization information to the PGW, further comprising:

acquiring actual traffic use information of traffic service performed by the terminal user based on the predicted traffic authorization information;

and inputting the predicted traffic authorization information and the actual traffic use information into the traffic authorization model to train the traffic authorization model so as to obtain the trained traffic authorization model.

5. An OCS (online charging System), wherein the OCS comprises:

the model creating module is used for abstracting the internet behavior data of the terminal user and the service characteristics of the ordering service into internet characteristic label classes; the internet access feature tag class comprises at least one internet access feature tag, the internet access behavior data is use information generated by the terminal user in the process of using a flow service to perform internet access behavior, and the internet access behavior is an operation behavior of using the flow service to perform internet access; setting an initial weight for each internet surfing feature tag in the internet surfing feature tag class according to the internet surfing behavior data; the internet surfing feature tags with larger weights have larger influence on the internet surfing behavior of the user, and the internet surfing feature tags with larger weights indicate that the frequency of the corresponding internet surfing events of the user is higher; creating a flow authorization model according to the Internet characteristic label class and the corresponding initial weight;

an obtaining module, configured to obtain a traffic service request sent by a terminal device corresponding to the terminal user;

the authorization module is used for analyzing the flow service request by using the flow authorization model to determine a plurality of internet access feature tags corresponding to the flow service request, adding weight values corresponding to the internet access feature tags respectively to obtain a total weight value corresponding to the flow service request, and determining predicted flow authorization information aiming at the flow service request according to the total weight value;

a sending module, configured to send the predicted traffic authorization information to a packet data network gateway PGW, so as to forward the predicted traffic authorization information to the terminal device through the PGW.

6. A server, characterized in that the server comprises:

at least one processor;

a communication interface coupled to the at least one processor for transceiving information;

a memory coupled to the at least one processor;

wherein the memory stores instructions executable by the at least one processor, the at least one processor performing the steps of the method of any one of claims 1-4 by executing the instructions stored by the memory.

7. A readable storage medium storing computer instructions which, when executed on a computer, cause the computer to perform the steps of the method according to any one of claims 1-4.

Images