Communication package recommendation method, system and device and storage medium

Abstract

The embodiment of the invention provides a communication package recommendation method, system and device and a storage medium. The method comprises the steps that an activeness value is calculated based on page access duration, page access times and recent access time; when the activeness value is greater than a first preset threshold value, querying whether a package change record exists in the historical package information; under the condition that the package change record does not exist in the historical package information, respectively performing statistical feature calculation on the historical call information and the historical traffic information to obtain a call feature value and a traffic feature value; when the call characteristic value is greater than a first threshold value and the flow characteristic value is greater than a second threshold value, increasing the exposure weight of a communication package corresponding to the comprehensive package type in an exposure weight list; and exposing at least one target communication package of which the exposure weight is greater than a preset weight threshold in the adjusted exposure weight list in a preset network page. According to the scheme, personalized exposure of the communication package can be carried out according to different requirements of users.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of data processing, and in particular to a communication package recommendation method, system, device and storage medium. BACKGROUND

[0002] With the continuous progress and popularization of communication technology, people's demand for communication services is also increasingly diversified. In order to meet the needs of different user groups, operators begin to launch various communication packages, which usually contain different combinations of call duration, number of short messages, data traffic, etc. for users to choose the appropriate package according to their own usage habits and budget. In order to bring a better experience to users, operators usually recommend communication packages based on web pages, and increase the user's attention to communication packages by exposing them in web pages.

[0003] In related technologies, when recommending communication packages, the operator pre-sets multiple communication packages and fixedly sets them in the web page for exposure. This way cannot adapt to different user needs for communication package exposure, the conversion rate of exposed products is low, the exposure efficiency is low, and precise personalized recommendation cannot be achieved, which needs to be improved. SUMMARY

[0004] The present application provides a communication package recommendation method, system, device and storage medium, which solves the problem that in related technologies, multiple communication packages are fixedly set in the web page for exposure, which cannot adapt to different user needs for communication package exposure, the conversion rate of exposed products is low, the exposure efficiency is low, and precise personalized recommendation cannot be achieved. It can effectively adjust the exposure weight of different communication packages in the preset web page, adapt to different user needs for exposure of target communication packages, improve exposure efficiency, facilitate conversion of exposed products, achieve precise personalized recommendation, and improve user experience.

[0005] In a first aspect, the present application provides a communication package recommendation method, which comprises: obtaining a user identifier and a corresponding page access record of a preset web page, determining a page access time, a page access frequency and a recent access time based on the page access record, and calculating an activity value based on the page access time, the page access frequency and the recent access time; if the activity value is greater than a first preset threshold, obtaining historical package information corresponding to the user identifier, and querying whether there is a package change record in the historical package information; in the case that there is no package change record in the historical package information, obtaining historical call information and historical traffic information corresponding to the user identifier, and performing statistical feature calculation on the historical call information and the historical traffic information to obtain call feature values and traffic feature values; in the case that the call feature values are greater than a first threshold value and the traffic feature values are greater than a second threshold value, obtaining an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded in a setting, and increasing the exposure weight of a communication package corresponding to a comprehensive package type in the exposure weight list; exposing at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list in the preset network page.

[0006] In a second aspect, the present application further provides a communication package recommendation system, comprising: an activity determination module configured to obtain a user identifier and page access records of a corresponding preset network page, determine a page access time length, a page access frequency, and a latest access time based on the page access records, and calculate an activity value based on the page access time length, the page access frequency, and the latest access time; a package change determination module configured to, in the case that the activity value is greater than a first preset threshold value, obtain historical package information corresponding to the user identifier, and query whether there is a package change record in the historical package information; a feature value determination module configured to, in the case that there is no package change record in the historical package information, obtain historical call information and historical traffic information corresponding to the user identifier, and perform statistical feature calculation on the historical call information and the historical traffic information to obtain call feature values and traffic feature values; a first exposure weight adjustment module configured to, in the case that the call feature values are greater than a first threshold value and the traffic feature values are greater than a second threshold value, obtain an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded in a setting, and increase the exposure weight of a communication package corresponding to a comprehensive package type in the exposure weight list; a first communication package exposure module configured to expose at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list in the preset network page.

[0007] In a third aspect, the present application further provides a communication package recommendation device, comprising: one or more processors; a storage device configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the communication package recommendation method described in the present application.

[0008] In a fourth aspect, the present application also provides a non-volatile storage medium storing computer executable instructions which, when executed by a computer processor, are configured to perform the communication package recommendation method described in the present application.

[0009] In the above, by obtaining the user identifier and the corresponding preset network page access record, the page access duration, the page access frequency and the latest access time are determined based on the page access record, and the activity value is calculated based on the page access duration, the page access frequency and the latest access time. In the case where the activity value is greater than the first preset threshold, the historical package information corresponding to the user identifier is obtained, and it is queried whether there is a package change record in the historical package information. In the case where there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are obtained, and the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information respectively. In the case where the call feature value is greater than the first threshold and the traffic feature value is greater than the second threshold, the exposure weight list of the exposure weight corresponding to the multiple communication packages recorded and set is obtained, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased. At least one target communication package in the exposure weight list after adjustment, whose exposure weight is greater than a preset weight threshold, is exposed in the preset network page. In the above scheme, the activity value is calculated based on the page access duration, the page access frequency and the latest access time, which can effectively judge the activity degree of the user accessing the preset network page, so as to determine whether the exposure weight list of the communication package needs to be adjusted subsequently. In the case where the activity value is greater than the first preset threshold, it can be considered that the user has a high activity degree, and it can be further queried whether there is a package change record in the historical package information, so as to judge whether the user has the behavior of actively adjusting the communication package. In the case where there is no package change record in the historical package information, the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information respectively, which can provide a judgment basis for evaluating whether the user focuses on using call or focuses on using traffic. In the case where the call feature value is greater than the first threshold and the traffic feature value is greater than the second threshold, it can be considered that the user has a high demand for both call and traffic, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list set can be correspondingly increased, so as to adapt to the different needs of the user to expose the target communication package, improve the exposure efficiency, be conducive to the conversion of exposed products, realize accurate personalized recommendation, and improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1A flow chart of a communication package recommendation method provided by an embodiment of the present application; Figure 2 A flow chart of a communication package recommendation method provided by an embodiment of the present application, which comprises a process of calculating an activity value; Figure 3 A flow chart of a communication package recommendation method provided by an embodiment of the present application, which comprises a process of calculating an activity value; Figure 4 A flow chart of a communication package recommendation method provided by an embodiment of the present application, which comprises a process of calculating a call feature value and a traffic feature value; Figure 5 A flow chart of a communication package recommendation method provided by an embodiment of the present application, which comprises a process of adjusting exposure weight based on package change records; Figure 6 A flow chart of a communication package recommendation method provided by an embodiment of the present application, which comprises a process of adjusting exposure weight according to different call feature values and traffic feature values; Figure 7 A structural block diagram of a communication package recommendation system provided by an embodiment of the present application; Figure 8 A structural schematic diagram of a communication package recommendation device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0011] The embodiments of the present application will be further described below in conjunction with the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the embodiments of the present application, but not to limit the embodiments of the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the embodiments of the present application are shown in the drawings, not all the structures.

[0012] The terms "first", "second", and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be exchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually a class, not limited to the number of objects, for example, the first object can be one or more. In addition, the specification and claims "and / or" means at least one of the connected objects, the character " / ", generally indicates that the front and rear associated objects are in a "or" relationship.

[0013] The execution subject of each step of the communication package recommendation method provided in the embodiments of the present application can be a computer device, which refers to any electronic device with data calculation, processing and storage capabilities, such as a mobile phone, a PC (Personal Computer), a tablet computer and the like, or a server or the like, and the embodiments of the present application do not limit this.

[0014] Figure 1 A flowchart of a communication package recommendation method provided in the embodiments of the present application is shown in FIG. 1. Figure 1 The communication package recommendation method specifically includes the following steps: In step S101, a user identifier and corresponding page access records of a preset network page are obtained, the page access duration, the page access frequency and the latest access time are determined based on the page access records, and the activity value is calculated based on the page access duration, the page access frequency and the latest access time.

[0015] The preset network page can be a self-service page provided by an operator, and the user can handle package change, package subscription, fee inquiry, bill inquiry and the like on the preset network page, and can also learn about the latest preferential activities and product information. The operator can recommend a communication package based on the network page to increase the user's attention to the communication package and improve the product conversion rate. The page access records can include a plurality of access information items corresponding to the user identifier within a preset time range, and each access information item can include a starting time node, an ending time node and page operation information of the user accessing the preset network page this time, and the like. Thus, the page access duration, the page access frequency and the latest access time required for calculating the activity value can be determined based on the page access records. The page access duration can be the total duration of the user accessing the preset network page within the preset time range, the page access frequency can be the total number of times of the user accessing the preset network page within the preset time range, and the latest access time can be the specific time node of the user's latest access to the preset network page within the preset time range. Since the page access duration, the page access frequency and the latest access time reflect the user's active procedures for accessing the preset network page from different dimensions, the three can be comprehensively calculated for the activity value. In an embodiment, the weight coefficients corresponding to the page access duration, the page access frequency and the latest access time can be obtained in advance, and the activity value can be obtained by linearly weighting and summing the page access duration, the page access frequency, the latest access time and the respective weight coefficients. The weight coefficients can be adaptively set by the developer according to the relevant experience data of the user accessing the page in the actual application scenario, which is not limited herein. In an embodiment, the page access duration, the page access frequency and the latest access time can be respectively converted into corresponding activity scores, and the activity value can be obtained by summing the plurality of activity scores.

[0016] In a case where the activity value is greater than the first preset threshold, historical package information corresponding to the user identifier is acquired, and it is queried whether there is a package change record in the historical package information.

[0017] The first preset threshold can be used to determine whether the user accesses the preset network page is active enough, and the specific value can be adaptively set by the developer according to the relevant experience data of the user accessing the page in the actual application scenario, which is not limited herein. If the activity value is greater than the first preset threshold, it can be considered that the user has a high frequency of accessing the preset network page, a relatively long stay time or a recent access time, and the activity degree is high. The exposure weight list can be adjusted in combination with the historical package information, the historical call information and the historical traffic information, so as to adapt to the specific needs of the user for package exposure recommendation. If the activity value is less than or equal to the first preset threshold, it can be considered that the user has a low frequency of accessing the preset network page, a relatively short stay time or a distant access time, and the activity degree is low. The exposure weight list can not be adjusted, and the package exposure recommendation can be performed according to the original exposure weight list. In a case where the activity value is greater than the first preset threshold, the historical package information corresponding to the user identifier can be acquired first. The historical package information records the package usage of the user in a preset time range. By querying the historical package information, it can be determined whether there is a package change record corresponding to the user identifier, so as to determine whether the user has the behavior of actively adjusting the communication package. If there is a package change record in the historical package information, it can be considered that the user actively changes the package according to the change of the demand, and the exposure weight list can be adjusted based thereon to improve the exposure weight of the corresponding changed package type in the plurality of communication packages, so as to adapt to the user demand for package exposure recommendation. If there is no package change record in the historical package information, the user preference can be determined in combination with the actual communication service usage of the user, such as the call condition and the traffic usage of the user, and the exposure weight list can be adjusted based thereon to adapt to the actual needs of the user for package exposure recommendation.

[0018] In a case where there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are acquired, and the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information, respectively.

[0019] If the package change record does not exist in the historical package information, historical call information corresponding to the user identifier and historical traffic information are obtained, the historical call information can record information such as call time, call duration, call type, and the like, and the historical traffic information can record information such as usage time, traffic usage, traffic type, and the like. The statistical feature calculation can be a mean value, a median, or a growth rate reflecting a change trend, and the like, which is not limited herein. The call feature value can be a quantitative index indicating the user call usage degree, which can be obtained by fusing and calculating one or more of the call duration mean value, the median, or the growth rate calculated based on the historical call information, and the like. The greater the call feature value, the higher the actual call usage degree of the user, and the higher the call demand. The smaller the call feature value, the lower the actual call usage degree of the user, and the lower the call demand. The traffic feature value can be a quantitative index indicating the user traffic usage degree, which can be obtained by fusing and calculating one or more of the traffic usage mean value, the median, or the growth rate calculated based on the historical traffic information, and the like. The greater the traffic feature value, the higher the actual traffic usage degree of the user, and the higher the traffic demand. The smaller the traffic feature value, the lower the actual traffic usage degree of the user, and the lower the traffic demand.

[0020] In step S104, if the call feature value is greater than the first threshold value, and the traffic feature value is greater than the second threshold value, an exposure weight list recording exposure weights corresponding to a plurality of communication packages is obtained, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased.

[0021] The first threshold value can be used to judge the call demand of the user, and the second threshold value can be used to judge the traffic demand of the user. The specific values can be adaptively set by the developer according to the experience data of the actual call and traffic usage of the user in the actual application scenario, which is not limited herein. If the call feature value is greater than the first threshold value, and the traffic feature value is greater than the second threshold value, it can be considered that the call demand and the traffic demand of the user are both high, and therefore the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list can be increased. The comprehensive package type can be a communication package that simultaneously focuses on call duration and traffic. The exposure weight list can record exposure weights corresponding to a plurality of communication packages. The exposure weight can represent the exposure priority of the communication package. The higher the exposure weight of the communication package, the higher the exposure ranking of the communication package, and the longer the corresponding exposure time. Specifically, the exposure weight of the communication package corresponding to the comprehensive package type can be multiplied by a preset increase factor, or the exposure weight of the communication package corresponding to the comprehensive package type can be added by a preset increase step, which is not limited herein.

[0022] In step S105, at least one target communication package whose exposure weight is greater than the preset weight threshold in the adjusted exposure weight list is exposed in the preset network page.

[0023] The preset network page can be provided with a fixed package exposure area, which can alternatively expose different communication packages in sequence or simultaneously expose different communication packages, which is not limited herein. The exposure weight of the corresponding communication package of the comprehensive package type in the adjusted exposure weight list becomes more forward, and the possibility of the at least one target communication package covering the corresponding communication package of the comprehensive package type becomes greater. Thus, the target communication package more suitable for the actual needs of the user is screened from the multiple communication packages preset by the operator and exposed. Optionally, the exposure time of the communication package with a higher exposure weight can be set longer.

[0024] Optionally, in the case where the activity value is less than or equal to the first preset threshold, at least one target communication package whose exposure weight is greater than the preset weight threshold in the original exposure weight list is exposed in the preset network page.

[0025] The above, by acquiring the user identifier and the corresponding preset network page access record, the page access time length, the page access times and the latest access time are determined based on the page access record, and the activity value is calculated based on the page access time length, the page access times and the latest access time; in the case where the activity value is greater than the first preset threshold, the historical package information corresponding to the user identifier is acquired, and it is queried whether there is a package change record in the historical package information; in the case where there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are acquired, and the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information respectively; in the case where the call feature value is greater than the first threshold, and the traffic feature value is greater than the second threshold, the exposure weight list of the exposure weight corresponding to the plurality of communication packages recorded and set is acquired, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased; at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in the preset network page. In the above scheme, the activity value is calculated based on the page access time length, the page access times and the latest access time, which can effectively judge the activity degree of the user accessing the preset network page to determine whether the exposure weight list of the communication package needs to be adjusted subsequently. In the case where the activity value is greater than the first preset threshold, it can be considered that the user has a high activity degree, and it can be further queried whether there is a package change record in the historical package information to judge whether the user has the behavior of actively adjusting the communication package, and in the case where there is no package change record in the historical package information, the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information respectively, which can provide a judgment basis for evaluating whether the user focuses on using call or focuses on using traffic, and in the case where the call feature value is greater than the first threshold, and the traffic feature value is greater than the second threshold, it can be considered that the user has a high demand for both call and traffic, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list set can be correspondingly increased, so as to adapt to the different needs of the user to expose the target communication package, improve the exposure efficiency, be beneficial to the exposure product conversion, realize the accurate personalized recommendation, and improve the user experience.

[0026] Figure 2 A flow chart of a communication package recommendation method including a process of calculating an activity value is provided for the embodiments of the present application. As shown in Figure 2 the communication package recommendation method specifically includes the following steps: Step S201, acquiring a user identifier and a page access record of a corresponding preset network page, determining a page access time length, a page access times and a latest access time based on the page access record.

[0027] In step S202, the average access time length is calculated according to the page access time length and the time length of the corresponding preset time range, the average access frequency is calculated according to the page access frequency and the time length, the time decay factor is calculated according to the latest access time and a preset decay function, and the activity value is obtained by multiplying the average access time length, the average access frequency and the time decay factor.

[0028] The average access time length can be obtained by dividing the page access time length by the time length of the corresponding preset time range, for example, how long is the average daily access time, how long is the average weekly access time, etc. The average access frequency can be obtained by dividing the page access frequency by the time length, for example, how many times is the average daily access, how many times is the average weekly access, etc. The preset decay function can be a linear decay function, an exponential decay function, a logarithmic decay function, etc. The specific calculation of the time decay factor can be that the time interval of the latest access time relative to the current system time is calculated, and then the time interval is substituted into the preset decay function. It can be understood that the greater the average access time length, the longer the user stays when accessing the preset network page, and the higher the relative activity level. The greater the average access frequency, the higher the frequency of the user accessing the preset network page, and the higher the relative activity level. The closer the latest access time, the smaller the calculated time interval, the greater the time decay factor calculated based on the preset decay function, and the greater the possibility of recent user activity. Therefore, the activity value can be obtained by multiplying the average access time length, the average access frequency and the time decay factor, which can reflect the activity level of the user accessing the preset network page. In step S203, if the activity value is greater than a first preset threshold, the historical package information corresponding to the user identifier is obtained, and it is queried whether there is a package change record in the historical package information.

[0029] In step S204, if there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are obtained, and the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information, respectively.

[0030] In step S205, if the call feature value is greater than a first threshold and the traffic feature value is greater than a second threshold, an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded in the setting is obtained, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased.

[0031] In step S206, at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in the preset network page.

[0032] The above, by multiplying the calculated average access duration, average access times and time decay factor to obtain the activity value, can comprehensively evaluate the user activity degree of access data in different dimensions, and improve the reference value of the activity value.

[0033] Figure 3 Another flowchart of the communication package recommendation method provided by the embodiment of the application is provided. As shown in the figure, Figure 3 The communication package recommendation method specifically includes the following steps: Step S301, obtaining a user identifier and a page access record of a corresponding preset network page, determining a page access duration, a page access times and a recent access time based on the page access record.

[0034] Step S302, comparing the page access duration with a plurality of preset duration gears to determine a first activity score, comparing the page access times with a plurality of preset times gears to determine a second activity score, comparing the recent access time with a plurality of preset time gears to determine a third activity score, and weighting the first activity score, the second activity score and the third activity score to obtain an activity value.

[0035] Each preset duration gear can record a pre-set time threshold range and a corresponding set activity score. The larger the range value corresponding to the time threshold range, the higher the corresponding set activity score. By comparing the page access duration with the plurality of preset duration gears, it can be determined that the page access duration is in which time threshold range, and the first activity score is matched accordingly. Each preset times gear can record a pre-set times threshold range and a corresponding set activity score. The larger the range value corresponding to the times threshold range, the higher the corresponding set activity score. By comparing the page access times with the plurality of preset times gears, it can be determined that the page access times is in which times threshold range, and the second activity score is matched accordingly. Each preset time gear can record a pre-set time stamp range and a corresponding set activity score. The larger the time value corresponding to the time stamp range, the higher the corresponding set activity score. By comparing the recent access time with the plurality of preset time gears, it can be determined that the recent access time is in which time stamp range, and the third activity score is matched accordingly. The division granularity and activity score of the specific preset duration gear, preset times gear and preset time gear can be adaptively set by the developer according to the relevant experience data of the user accessing the page in the actual application scenario, which is not limited herein. Thus, the first activity score, the second activity score and the third activity score can be weighted to obtain the activity value, which can reflect the activity degree of the user accessing the preset network page. Step S303, in the case where the activity value is greater than the first preset threshold, historical package information corresponding to the user identifier is obtained, and it is queried whether there is a package change record in the historical package information.

[0036] Step S304, in the case where there is no package change record in the historical package information, historical call information and historical traffic information corresponding to the user identifier are obtained, and call feature values and traffic feature values are obtained by performing statistical feature calculation on the historical call information and the historical traffic information respectively.

[0037] Step S305, in the case where the call feature value is greater than the first threshold and the traffic feature value is greater than the second threshold, an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded and set is obtained, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased.

[0038] Step S306, at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in a preset network page.

[0039] The above, by comparing the page access time, the page access times and the recent access time respectively, the corresponding active score can be quickly determined, by weighting the first active score, the second active score and the third active score to obtain the activity value, the user activity degree can be reasonably evaluated in combination with multi-dimensional information, and the reliability of the activity value is guaranteed.

[0040] Figure 4 A flowchart of a communication package recommendation method provided by the embodiment of the application includes a process of calculating call feature values and traffic feature values. As shown in Figure 4 The communication package recommendation method specifically includes the following steps: Step S401, obtain the page access record of the user identifier and the corresponding preset network page, determine the page access time, the page access times and the recent access time based on the page access record, and calculate the activity value based on the page access time, the page access times and the recent access time.

[0041] Step S402, in the case where the activity value is greater than the first preset threshold, historical package information corresponding to the user identifier is obtained, and it is queried whether there is a package change record in the historical package information.

[0042] In step S403, if there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are obtained, the call duration average and the call duration growth rate are calculated based on the historical call information, the call duration average and the call duration growth rate are multiplied to obtain a call feature value, the traffic usage average and the traffic usage growth rate are calculated based on the historical traffic information, and the traffic usage average and the traffic usage growth rate are multiplied to obtain a traffic feature value.

[0043] The call duration average can be obtained by dividing the cumulative call duration in a preset time range by the time length corresponding to the preset time range, which can be, for example, minutes per day or minutes per week, and the like, which are not limited in the present application. The call duration growth rate can be calculated by dividing the preset time range into two time periods in advance, calculating the first call total duration and the second call total duration accumulated in the two time periods respectively, and calculating the call duration growth rate based on the first call total duration and the second call total duration. Alternatively, after dividing the preset time range into two time periods, the extreme values of the call duration in the two time periods can be filtered out first, then the first call total duration and the second call total duration accumulated in the two time periods are calculated, and finally the call duration growth rate is calculated based on the first call total duration and the second call total duration. Specifically, the call duration growth rate can be obtained by dividing the difference between the second call total duration and the first call total duration by the first call total duration. It can be understood that the greater the call duration average, the higher the user's call demand, or the greater the call duration growth rate, the higher the user's call demand gradually. Therefore, the call duration average and the call duration growth rate can be multiplied to obtain a call feature value, which can represent the degree of user's call demand. The traffic usage average can be obtained by dividing the cumulative usage traffic in a preset time range by the time length corresponding to the preset time range, which can be, for example, megabytes per day or megabytes per week, and the like, which are not limited in the present application. The traffic usage growth rate can be calculated by dividing the preset time range into two time periods in advance, calculating the first traffic sum and the second traffic sum accumulated in the two time periods respectively, and calculating the traffic usage growth rate based on the first traffic sum and the second traffic sum. Alternatively, after dividing the preset time range into two time periods, the short-term extreme values of the traffic usage in the two time periods can be filtered out first, then the first traffic sum and the second traffic sum accumulated in the two time periods are calculated, and finally the traffic usage growth rate is calculated based on the first traffic sum and the second traffic sum. Specifically, the traffic usage growth rate can be obtained by dividing the difference between the second traffic sum and the first traffic sum by the first traffic sum. It can be understood that the greater the traffic usage average, the higher the user's traffic demand, or the greater the traffic usage growth rate, the higher the user's traffic demand gradually. Therefore, the traffic usage average and the traffic usage growth rate can be multiplied to obtain a traffic feature value, which can represent the degree of user's traffic demand.

[0044] Step S404, in the case that the call feature value is greater than the first threshold value and the traffic feature value is greater than the second threshold value, an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded in the setting is obtained, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased.

[0045] Step S405, at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in a preset network page.

[0046] The call feature value is obtained by multiplying the call duration mean value and the call duration growth rate, and the traffic feature value is obtained by multiplying the traffic usage mean value and the traffic usage growth rate, which can accurately evaluate the call demand and the traffic demand of the user, and provide reliable reference information for adjusting the exposure weight list.

[0047] Figure 5 A flowchart of a communication package recommendation method provided by an embodiment of the present application is shown in FIG. 5. As shown in the figure, the communication package recommendation method specifically includes the following steps: Figure 5 Step S501, a user identifier and a page access record of a corresponding preset network page are obtained, the page access duration, the page access times and the latest access time are determined based on the page access record, and the activity value is calculated based on the page access duration, the page access times and the latest access time.

[0048] Step S502, in the case that the activity value is greater than a first preset threshold value, historical package information corresponding to the user identifier is obtained, and it is queried whether there is a package change record in the historical package information.

[0049] Step S503, in the case that there is a package change record in the historical package information, the first package type before the last package change and the second package type after the change are determined by querying the package change record, the exposure weight of the communication package corresponding to the first package type in the exposure weight list is reduced, and the exposure weight of the communication package corresponding to the second package type in the exposure weight list is increased.

[0050] ​If there is a package change record in the historical package information, it can be considered that the user has the behavior of actively changing the package according to his own needs. Therefore, the first package type before the last package change and the second package type after the change can be determined by querying the package change record, the user's package type change situation is judged, and the exposure weight is adjusted as a reference. The exposure weight of the communication package corresponding to the first package type before the change can be adaptively reduced, specifically, the exposure weight can be multiplied by a preset downshift coefficient, or the exposure weight can be subtracted by a preset amplitude step. The exposure weight of the communication package corresponding to the second package type after the change can be adaptively increased, specifically, the exposure weight can be multiplied by a preset upshift coefficient, or the exposure weight can be added by a preset amplitude step.

[0051] In step S504, if there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are obtained, and the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information, respectively.

[0052] In step S505, if the call feature value is greater than the first threshold value and the traffic feature value is greater than the second threshold value, the exposure weight list of the exposure weights of the plurality of communication packages recorded and set is obtained, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased.

[0053] In step S506, at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in a preset network page.

[0054] The above, by adjusting the exposure weight of the communication package corresponding to the different package types before and after the change based on the package change record, the behavior of the user actively changing the package type can be effectively captured, the exposure weight adjustment is made according to the actual demand change, and the personalized recommendation can be more accurate.

[0055] Figure 6 A flowchart of a communication package recommendation method provided by an embodiment of the present application includes a process of adjusting the exposure weight according to different call feature values and traffic feature values. As shown in Figure 6 The communication package recommendation method specifically includes the following steps: In step S601, the user identifier and the page access record of the corresponding preset network page are obtained, the page access time, the page access times and the latest access time are determined based on the page access record, and the activity value is calculated based on the page access time, the page access times and the latest access time.

[0056] Step S602, in the case that the activity value is greater than the first preset threshold, historical package information corresponding to the user identifier is acquired, and it is queried whether there is a package change record in the historical package information.

[0057] Step S603, in the case that there is no package change record in the historical package information, historical call information and historical traffic information corresponding to the user identifier are acquired, and call feature values and traffic feature values are obtained by performing statistical feature calculation on the historical call information and the historical traffic information, respectively.

[0058] Step S604, in the case that the call feature value is greater than the first threshold and the traffic feature value is greater than the second threshold, an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded and set is acquired, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased.

[0059] Step S605, in the case that the call feature value is greater than the first threshold and the traffic feature value is less than or equal to the second threshold, the exposure weight of the communication package corresponding to the call package type in the exposure weight list is increased, and the exposure weight of the communication package corresponding to the traffic package type in the exposure weight list is decreased.

[0060] Among them, if the call feature value is greater than the first threshold and the traffic feature value is less than or equal to the second threshold, it can be considered that the user's call demand is high and the traffic demand is low, and the exposure weight of the communication package corresponding to the call package type can be increased, and the exposure weight of the communication package corresponding to the traffic package type can be decreased.

[0061] Step S606, in the case that the call feature value is less than or equal to the first threshold and the traffic feature value is greater than the second threshold, the exposure weight of the communication package corresponding to the traffic package type in the exposure weight list is increased, and the exposure weight of the communication package corresponding to the call package type in the exposure weight list is decreased.

[0062] Among them, if the call feature value is less than or equal to the first threshold and the traffic feature value is greater than the second threshold, it can be considered that the user's call demand is low and the traffic demand is high, and the exposure weight of the communication package corresponding to the call package type can be decreased, and the exposure weight of the communication package corresponding to the traffic package type can be increased.

[0063] Step S607, at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in a preset network page.

[0064] The above, by adapting to different call feature values and traffic feature values to adjust the exposure weight of the communication package corresponding to different package types, the package exposure adjustment can be adapted to different user demands to more accurately hit user preferences and improve exposure efficiency.

[0065] Figure 7 A structural block diagram of a communication package recommendation system provided by an embodiment of the present application is provided, the system is configured to execute the communication package recommendation method provided by the above-mentioned embodiment, and has the corresponding function modules and beneficial effects of the execution method. As shown in the figure, the system specifically includes: Figure 7 The activity determination module 101 is configured to obtain a user identifier and a corresponding preset network page access record, determine a page access time length, a page access frequency and a recent access time based on the page access record, and calculate an activity value based on the page access time length, the page access frequency and the recent access time; The package change determination module 102 is configured to, in a case where the activity value is greater than a first preset threshold, obtain historical package information corresponding to the user identifier, and query whether there is a package change record in the historical package information; The feature value determination module 103 is configured to, in a case where there is no package change record in the historical package information, obtain historical call information and historical traffic information corresponding to the user identifier, and calculate a call feature value and a traffic feature value by performing statistical feature calculation on the historical call information and the historical traffic information, respectively; The first exposure weight adjustment module 104 is configured to, in a case where the call feature value is greater than a first threshold and the traffic feature value is greater than a second threshold, obtain an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded in the setting, and increase the exposure weight of a communication package corresponding to a comprehensive package type in the exposure weight list; The communication package exposure module 105 is configured to expose at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list in a preset network page.

[0066] ​According to the above, by acquiring the user identifier and the page access record of the corresponding preset network page, the page access duration, the page access times and the latest access time are determined based on the page access record, and the activity value is calculated based on the page access duration, the page access times and the latest access time. In the case where the activity value is greater than the first preset threshold, the historical package information corresponding to the user identifier is acquired, and it is queried whether there is a package change record in the historical package information. In the case where there is no package change record in the historical package information, the historical call information and the historical traffic information corresponding to the user identifier are acquired, and the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information respectively. In the case where the call feature value is greater than the first threshold and the traffic feature value is greater than the second threshold, the exposure weight list of the exposure weight corresponding to the plurality of communication packages recorded and set is acquired, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased. At least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list is exposed in the preset network page. In the above scheme, the activity value is calculated based on the page access duration, the page access times and the latest access time, which can effectively determine the activity degree of the user accessing the preset network page to determine whether the exposure weight list of the communication package needs to be adjusted subsequently. In the case where the activity value is greater than the first preset threshold, it can be considered that the user has a high activity degree, and it can be further queried whether there is a package change record in the historical package information to determine whether the user has the behavior of actively adjusting the communication package. In the case where there is no package change record in the historical package information, the call feature value and the traffic feature value are calculated by performing statistical feature calculation on the historical call information and the historical traffic information respectively, which can provide a judgment basis for evaluating whether the user focuses on using call or focuses on using traffic. In the case where the call feature value is greater than the first threshold and the traffic feature value is greater than the second threshold, it can be considered that the user has a high demand for both call and traffic, and the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list set can be increased accordingly, so as to adapt to the different needs of the user to expose the target communication package, improve the exposure efficiency, facilitate the conversion of exposed products, realize accurate personalized recommendation, and improve the user experience.

[0067] In one possible embodiment, the activity determination module 101 is further configured to: calculate an average access duration according to the page access duration and the time length of the corresponding preset time range, and calculate an average access times according to the page access times and the time length; calculate a time decay factor according to the latest access time and a preset decay function; multiply the average access duration, the average access times and the time decay factor to obtain the activity value.

[0068] In a possible embodiment, the activity determination module 101 is further configured to: determine the first activity score by comparing the page access duration with a plurality of preset duration levels; determine the second activity score by comparing the page access frequency with a plurality of preset frequency levels; determine the third activity score by comparing the recent access time with a plurality of preset time levels; respectively weight the first activity score, the second activity score and the third activity score to obtain the activity value.

[0069] In a possible embodiment, the feature value determination module 103 is further configured to: calculate the call duration mean value and the call duration growth rate based on the historical call information, and multiply the call duration mean value and the call duration growth rate to obtain the call feature value; calculate the traffic usage mean value and the traffic usage growth rate based on the historical traffic information, and multiply the traffic usage mean value and the traffic usage growth rate to obtain the traffic feature value.

[0070] In a possible embodiment, the method further includes a second exposure weight adjustment module configured to: in a case where the historical package information includes a package change record, query the package change record to determine a first package type before a most recent package change and a second package type after the most recent package change; decrease the exposure weight of the communication package corresponding to the first package type in the exposure weight list, and increase the exposure weight of the communication package corresponding to the second package type in the exposure weight list.

[0071] In a possible embodiment, the method further includes a third exposure weight adjustment module configured to: in a case where the call feature value is greater than a first threshold value and the traffic feature value is less than or equal to a second threshold value, increase the exposure weight of the communication package corresponding to the call package type in the exposure weight list, and decrease the exposure weight of the communication package corresponding to the traffic package type in the exposure weight list.

[0072] In a possible embodiment, the method further includes a fourth exposure weight adjustment module configured to: in a case where the call feature value is less than or equal to the first threshold value and the traffic feature value is greater than the second threshold value, increase the exposure weight of the communication package corresponding to the traffic package type in the exposure weight list, and decrease the exposure weight of the communication package corresponding to the call package type in the exposure weight list.

[0073] In a possible embodiment, the method further includes a second communication package exposure module configured to: If the activity value is less than or equal to the first preset threshold, at least one target communication package with an exposure weight greater than the preset weight threshold in the original exposure weight list will be exposed on the preset network page.

[0074] Figure 8 This is a schematic diagram of the structure of a communication package recommendation device provided in an embodiment of this application, as shown below. Figure 8 As shown, the device includes a processor 201, a memory 202, an input device 203, and an output device 204; the number of processors 201 in the device can be one or more. Figure 8 Taking a processor 201 as an example; the processor 201, memory 202, input device 203, and output device 204 in the device can be connected via a bus or other means. Figure 8 Taking a bus connection as an example, the memory 202, as a computer-readable storage medium, can be configured to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the communication package recommendation method in this embodiment. The processor 201 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 202, thereby implementing the aforementioned communication package recommendation method. The input device 203 can be configured to receive input digital or character information and generate key signal inputs related to user settings and function control of the device. The output device 204 may include a display device such as a screen.

[0075] The communication package recommendation device provided above can be used to execute the communication package recommendation method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0076] The embodiment of the present application further provides a nonvolatile storage medium containing computer executable instructions, which are configured to perform the communication package recommendation method described in the above embodiment when executed by a computer processor, and the method comprises the following steps: obtaining a user identifier and a corresponding preset webpage access record, determining a webpage access duration, a webpage access frequency and a latest access time based on the webpage access record, and calculating an activity value based on the webpage access duration, the webpage access frequency and the latest access time; in the case that the activity value is greater than a first preset threshold, obtaining historical package information corresponding to the user identifier, and querying whether there is a package change record in the historical package information; in the case that there is no package change record in the historical package information, obtaining historical call information and historical traffic information corresponding to the user identifier, and calculating a call feature value and a traffic feature value by performing statistical feature calculation on the historical call information and the historical traffic information respectively; in the case that the call feature value is greater than a first threshold and the traffic feature value is greater than a second threshold, obtaining an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded and set, and increasing the exposure weight of a communication package corresponding to a comprehensive package type in the exposure weight list; and exposing at least one target communication package with an exposure weight greater than a preset weight threshold in the preset network page in the exposure weight list after adjustment.

[0077] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include an installation medium, e.g., a CD-ROM, floppy disks, or tape device; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; or a non-volatile memory such as a magnetic medium, e.g., a hard drive; optical storage, e.g., a CD; flash memory devices; registers, other similar types of storage, etc. The term "storage medium" can also include a non- transitory storage medium, e.g., a non-volatile memory, a magnetic medium, e.g., a hard drive, an optical storage etc. The term "storage medium" should be taken to include a single medium or multiple media that store the same or different versions of a program for use by a personal or server computer system. A single storage medium can store individual or groups of instructions for implementing the application. The term "storage medium" should be taken to include a single medium or multiple media that store the same or different versions of a program for use by a personal or server computer system. A single storage medium can store individual or groups of instructions for implementing the application. The term "storage medium" should be taken to include individual or collective contributions of multiple storage media that store instructions for implementing the application.

[0078] Of course, the storage medium containing computer executable instructions provided by the embodiment of the present application is not limited to the communication package recommendation method as above, and can also perform the related operations in the communication package recommendation method provided by any embodiment of the present application.

[0079] It should be noted that the numbering of the steps in the present scheme is only used to describe the overall design framework of the present scheme, and does not indicate the inevitable sequence between the steps. As long as the overall implementation process conforms to the overall design framework of the present scheme, it belongs to the protection scope of the present scheme, and the sequence in the description is not an exclusive limitation on the specific implementation process of the present scheme. Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory can include non-persistent memory in a computer readable medium, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer readable medium.

[0080] It should also be noted that the terms "comprising", "including", or any other variation thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles, or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0081] Note that the above is only the preferred embodiment of the present application and the technical principles applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and those skilled in the art can make various obvious changes, readjustments and substitutions without departing from the scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A communication package recommendation method characterized by comprising: The method comprises the following steps: obtaining a user identifier and a corresponding preset network page access record, determining a page access duration, a page access frequency and a recent access time based on the page access record, and calculating an activity value based on the page access duration, the page access frequency and the recent access time; in a case where the activity value is greater than a first preset threshold, obtaining historical package information corresponding to the user identifier, and querying whether there is a package change record in the historical package information; in a case where there is no package change record in the historical package information, obtaining historical call information and historical traffic information corresponding to the user identifier, and calculating a call feature value and a traffic feature value by performing statistical feature calculation on the historical call information and the historical traffic information, respectively; in a case where the call feature value is greater than a first threshold and the traffic feature value is greater than a second threshold, obtaining an exposure weight list of exposure weights corresponding to a plurality of communication packages recorded and set, and increasing the exposure weight of a communication package corresponding to a comprehensive package type in the exposure weight list; exposing at least one target communication package with an exposure weight greater than a preset weight threshold in the preset network page in the adjusted exposure weight list. 2.The communication package recommendation method of claim 1, wherein, The method comprises the following steps: calculating an average access duration according to the page access duration and the time length of a corresponding preset time range, and calculating an average access frequency according to the page access frequency and the time length; calculating a time decay factor according to the recent access time and a preset decay function; multiplying the average access duration, the average access frequency and the time decay factor to obtain an activity value. 3.The communication package recommendation method of claim 1, wherein, The method comprises the following steps: comparing the page access duration with a plurality of preset duration positions set to determine a first activity score; comparing the page access frequency with a plurality of preset frequency positions set to determine a second activity score; comparing the recent access time with a plurality of preset time positions set to determine a third activity score; respectively weighting and calculating the first activity score, the second activity score and the third activity score to obtain an activity value. 4.The method of claim 1, wherein, The method comprises the following steps: calculating a call duration mean and a call duration growth rate based on the historical call information, and multiplying the call duration mean and the call duration growth rate to obtain a call feature value; calculating a traffic usage mean and a traffic usage growth rate based on the historical traffic information, and multiplying the traffic usage mean and the traffic usage growth rate to obtain a traffic feature value. 5.The communication package recommendation method of claim 1, wherein, After the step of querying whether there is a package change record in the historical package information, the method further comprises the following steps: In a case where there is a package change record in the historical package information, the package change record is queried to determine a first package type before a latest package change and a second package type after the change; The exposure weight of the communication package corresponding to the first package type in the exposure weight list is reduced, and the exposure weight of the communication package corresponding to the second package type in the exposure weight list is increased. 6.The communication package recommendation method of claim 1, wherein, After the call feature value and the traffic feature value are obtained by respectively performing statistical feature calculation on the historical call information and the historical traffic information, the method further includes: In a case where the call feature value is greater than a first threshold value and the traffic feature value is less than or equal to a second threshold value, the exposure weight of the communication package corresponding to the call package type in the exposure weight list is increased, and the exposure weight of the communication package corresponding to the traffic package type in the exposure weight list is reduced. 7.The communication package recommendation method of claim 1, wherein, After the call feature value and the traffic feature value are obtained by respectively performing statistical feature calculation on the historical call information and the historical traffic information, the method further includes: In a case where the call feature value is less than or equal to a first threshold value and the traffic feature value is greater than a second threshold value, the exposure weight of the communication package corresponding to the traffic package type in the exposure weight list is increased, and the exposure weight of the communication package corresponding to the call package type in the exposure weight list is reduced. 8.The method of claim 1, wherein, After the activity value is calculated based on the page access duration, the page access frequency and the latest access time, the method further includes: In a case where the activity value is less than or equal to the first preset threshold value, at least one target communication package with an exposure weight greater than a preset weight threshold value in an original exposure weight list is exposed in the preset network page. 9.A communication package recommendation system, characterized by, The method includes: an activity determination module configured to obtain a user identifier and page access records of a corresponding preset network page, determine a page access duration, a page access frequency and a latest access time based on the page access records, and calculate an activity value based on the page access duration, the page access frequency and the latest access time; a package change determination module configured to, in a case where the activity value is greater than a first preset threshold value, obtain historical package information corresponding to the user identifier, and query whether there is a package change record in the historical package information; a feature value determination module configured to, in a case where there is no package change record in the historical package information, obtain historical call information and historical traffic information corresponding to the user identifier, and respectively perform statistical feature calculation on the historical call information and the historical traffic information to obtain a call feature value and a traffic feature value; a first exposure weight adjustment module configured to, in a case where the call feature value is greater than a first threshold value and the traffic feature value is greater than a second threshold value, obtain an exposure weight list recording exposure weights of a plurality of communication packages set, and increase the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list. The first communication package exposure module is configured to expose at least one target communication package with an exposure weight greater than a preset weight threshold in the adjusted exposure weight list in the preset network page.

10. A communication package recommendation device, the device comprising: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the communication package recommendation method in any one of claims 1-8.

11. A non-volatile storage medium storing computer executable instructions, which when executed by a computer processor are configured to perform the communication package recommendation method in any one of claims 1-8.

Images