CN114282933A - User to be off-network user identification method and device based on user preservation - Google Patents
User to be off-network user identification method and device based on user preservation Download PDFInfo
- Publication number
- CN114282933A CN114282933A CN202011044552.4A CN202011044552A CN114282933A CN 114282933 A CN114282933 A CN 114282933A CN 202011044552 A CN202011044552 A CN 202011044552A CN 114282933 A CN114282933 A CN 114282933A
- Authority
- CN
- China
- Prior art keywords
- operator
- foreground
- value
- user
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a method and a device for identifying a user to be off-network based on user retention. The method comprises the following steps: acquiring attribute values corresponding to a current operator and a target operator; and determining a reference point for the service attribute; calculating a foreground value function and a foreground weight function of a current operator and a target operator; further calculating the foreground values of the current operator and the target operator; and finally, comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result. The scheme can accurately identify the user to be off-grid with the off-grid tendency, thereby facilitating the off-grid pre-warning; moreover, key push objects with the policies kept by the user can be screened out, and waste of push resources is avoided; in addition, the scheme can avoid the influence of marketing tendency users and further avoid the waste of pushing resources. In a word, the scheme can greatly improve the success rate of the user retention strategy and reduce the user off-network rate.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method and a device for identifying a user to be off-network based on user retention.
Background
With the continuous development of science and technology and society, the telecommunication industry has also gained rapid development, and the degree of freedom for people to select operators is greatly increased, so that users of the operators are kept as an important and very challenging task. In order to timely save potential off-network users, users with a tendency to be off-network (i.e., users to be off-network) are generally identified first, and then a corresponding policy is applied to the users to avoid the users performing the off-network operation.
The currently adopted method for identifying the user to be off-network is generally an identification method based on traffic, namely, traffic information of the user is obtained, and when the traffic of the user has a decreasing trend, the user is determined to be the user to be off-network.
However, the inventor finds that the following defects exist in the prior art in the implementation process: the user identified by the method for identifying the user to be off-network in the prior art is in an off-network transition period (namely a transition period of a new operator and an old operator), so that the off-network behavior of the user cannot be avoided in time through a corresponding user holding strategy; in addition, the identification method in the prior art is low in identification precision, the identified to-be-off-network users usually include marketing tendency users (that is, when a certain operator launches a corresponding marketing activity, the operator products are used), and when corresponding user hold information is pushed to the users, waste of push messages is usually caused.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a method and apparatus for identifying a user to be off-network based on user retention that overcomes or at least partially solves the above-mentioned problems.
According to one aspect of the invention, a method for identifying a user to be off-network based on user retention is provided, and comprises the following steps:
determining a current operator and a target operator corresponding to a user, and acquiring an attribute value of at least one service attribute corresponding to the current operator and the target operator;
for any service attribute, determining a reference point of the service attribute;
respectively calculating a foreground value function corresponding to the current operator and a foreground value function of the target operator according to the reference point and the attribute value;
respectively calculating foreground weight functions of the current operator and the target operator;
calculating a foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result.
Optionally, the obtaining an attribute value of at least one service attribute corresponding to the current operator and the target operator further includes:
acquiring an initial attribute value of at least one service attribute corresponding to a current operator and a target operator;
and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
Optionally, the obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator further includes:
and obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator by adopting an evaluation quantification method.
Optionally, the service attribute includes at least one of the following attributes:
economic factors, signal quality, charging accuracy, and quality of service.
Optionally, the determining the reference point of the service attribute further includes:
identifying a maximum attribute value and a minimum attribute value corresponding to the service attribute from the attribute values of the service attribute of the target operator;
and determining the reference point of the service attribute according to the maximum attribute value and the minimum attribute value.
Optionally, the respectively calculating the foreground weighting functions of the current operator and the target operator further includes:
calculating a foreground weight function of the current operator according to the foreground value function and the basic weight function corresponding to the current operator; and
and calculating the foreground weight function of the target operator according to the foreground value function and the basic weight function corresponding to the target operator.
Optionally, the determining whether the user is off-network according to the comparison result further includes:
and if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, determining that the user can have an off-network behavior.
According to another aspect of the present invention, there is provided a device for identifying a user to be off-network based on user retention, including:
the operator determining module is suitable for determining a current operator and a target operator corresponding to the user;
the attribute value acquisition module is suitable for acquiring the attribute value of at least one service attribute corresponding to the current operator and the target operator;
a reference point determining module, adapted to determine, for any service attribute, a reference point of the service attribute;
the value function calculation module is suitable for calculating a foreground value function corresponding to the current operator and a foreground value function of the target operator according to the reference point and the attribute value;
the weight function calculation module is suitable for calculating foreground weight functions of the current operator and the target operator respectively;
the foreground value calculation module is suitable for calculating the foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and the judging module is suitable for comparing the foreground value of the current operator with the foreground value of the target operator and judging whether the user is the user to be off-network according to the comparison result.
Optionally, the attribute value obtaining module is further adapted to: acquiring an initial attribute value of at least one service attribute corresponding to a current operator and a target operator;
and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
Optionally, the attribute value obtaining module is further adapted to: and obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator by adopting an evaluation quantification method.
Optionally, the service attribute includes at least one of the following attributes:
economic factors, signal quality, charging accuracy, and quality of service.
Optionally, the reference point determining module is further adapted to: identifying a maximum attribute value and a minimum attribute value corresponding to the service attribute from the attribute values of the service attribute of the target operator;
and determining the reference point of the service attribute according to the maximum attribute value and the minimum attribute value.
Optionally, the weight function calculation module is further adapted to: calculating a foreground weight function of the current operator according to the foreground value function and the basic weight function corresponding to the current operator; and
and calculating the foreground weight function of the target operator according to the foreground value function and the basic weight function corresponding to the target operator.
Optionally, the determining module is further adapted to: and if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, determining that the user can have an off-network behavior.
According to yet another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the user identification method to be off-network based on user preservation.
According to still another aspect of the present invention, a computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform an operation corresponding to the user-owned method for identifying a user to be off-network.
According to the method and the device for identifying the user to be off-network based on the user reservation, provided by the invention, attribute values corresponding to a current operator and a target operator are obtained; and determining a reference point for the service attribute; calculating a foreground value function and a foreground weight function of a current operator and a target operator; further calculating the foreground values of the current operator and the target operator; and finally, comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result. The scheme can accurately identify the user to be off-grid with the off-grid tendency, thereby facilitating the off-grid pre-warning; moreover, key push objects with the policies kept by the user can be screened out, and waste of push resources is avoided; in addition, the scheme can avoid the influence of marketing tendency users and further avoid the waste of pushing resources. In a word, the scheme can greatly improve the success rate of the user retention strategy and reduce the user off-network rate.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flowchart illustrating a user-owned to-be-off-network user identification method according to an embodiment of the present invention;
fig. 2 is a schematic flowchart illustrating an attribute value obtaining method according to an embodiment of the present invention;
fig. 3 is a schematic functional structure diagram of a user-owned device for identifying a user to be off-network according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computing device according to a fourth embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Example one
Fig. 1 is a schematic flowchart illustrating a to-be-off-network subscriber identification method based on a subscriber identity module according to an embodiment of the present invention, where the identification method provided in this embodiment can be applied to the subscriber identities of various operators, and a specific implementation device of the method is not limited in this embodiment.
As shown in fig. 1, the method includes:
step S110: determining a current operator and a target operator corresponding to the user, and acquiring an attribute value of at least one service attribute corresponding to the current operator and the target operator.
The embodiment can identify whether the user is the user to be off-network or not for any user. In a specific identification process, a current operator corresponding to a user is determined according to a user identifier (such as a telephone number) of the user, and then a target operator is determined according to other current candidate operators, wherein the target operator is other operators which may be selected if the user leaves the network.
After the current operator and the target operator are determined, at least one service attribute corresponding to the current operator and the target operator is determined. The service attribute is a relevant service characteristic which can influence the user off-network decision in each attribute of the operator. In this embodiment, the service attribute may include at least one of the following attributes: economic factors, signal quality, charging accuracy, and quality of service, among others.
Further, an attribute value of at least one service attribute corresponding to the current operator and the target operator is obtained. The attribute value is specifically a specific quantized value of the service attribute of the operator, and for example, an evaluation quantization method may be used to obtain the corresponding attribute value.
Optionally, to facilitate processing of subsequent data and improve the overall execution efficiency of the method, as shown in fig. 2, the attribute value of at least one service attribute corresponding to the current operator and the target operator may be obtained in step S112 through the following step S111:
step S111: and acquiring an initial attribute value of at least one service attribute corresponding to the current operator and the target operator.
Specifically, an evaluation quantification method may be adopted to obtain an initial attribute value of at least one service attribute corresponding to the current operator and the target operator. In the actual implementation process, in order to improve the efficiency of obtaining the attribute values, a corresponding table of the evaluation information of different service attributes and corresponding quantized values may be established in advance. If the service attribute is signal quality, the evaluation information is "excellent", and the quantization value corresponding to the "excellent" is "9", the initial attribute value of the signal quality is determined to be "9".
Step S112: and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
In the normalization process, the maximum initial attribute value and the minimum initial attribute value of any service attribute can be obtained, and then each initial attribute value corresponding to the service attribute is normalized according to the maximum initial attribute value and the minimum initial attribute value.
Specifically, the normalization processing can be performed by the following formula (1-1):
wherein, XijIs the attribute value of the jth service attribute of the ith current operator, YijAttribute value of j service attribute of i target operator; cijIs an initial attribute value of the jth service attribute of the ith current operator, DijAn initial attribute value of a jth service attribute of an ith target operator;
for the minimum initial attribute value corresponding to the jth service attribute in all current operators and the target operator,
the maximum initial attribute value corresponding to the jth service attribute in all the current operators and the target operator; n is the total number of service attributes, m is the total number of the current operator, and p is the total number of the target operator.
Step S120: for any service attribute, a reference point for that service attribute is determined.
In an alternative embodiment, the reference point for each service attribute may be set based on historical data. For example, a machine learning method can be adopted, model training is performed by taking historical reference point values and corresponding prediction precision data of the user to be off-grid as sample data, and a better reference point is obtained through the model training.
In another optional implementation manner, for any service attribute, a maximum attribute value and a minimum attribute value corresponding to the service attribute are identified from the attribute values of the service attribute of the target operator, and then a reference point of the service attribute is determined according to the maximum attribute value and the minimum attribute value.
Specifically, the maximum attribute value may be obtained by the following formula (1-2), and the minimum attribute value may be obtained by the formula (1-3).
ej＝max{Yij1,2, …, p }; j-1, 2, …, n formula (1-2)
fj＝min{Yij1,2, …, p }; j-1, 2, …, n formula (1-3)
Wherein e isjMaximum attribute value, f, for jth service attribute of target operatorjMinimum attribute value of jth service attribute of target operator; n is the total number of service attributes and p is the total number of target operators.
The reference point for the service attribute may further be determined using the following equations (1-4).
Sj＝f(ej,fj) (ii) a j-1, 2, …, n formula (1-4)
Wherein S isjReference point for jth service attribute, ejMaximum attribute value, f, for jth service attribute of target operatorjMinimum attribute value of jth service attribute of target operator; n is the total number of service attributes. Wherein, f (e)j,fj) May be as to ejAnd fjBinary linear functions, etc., and those skilled in the art can select corresponding functions according to actual services.
Step S130: and respectively calculating the foreground value function corresponding to the current operator and the foreground value function of the target operator according to the reference point and the attribute value.
In a specific implementation process, for any current operator, a foreground value function of the current operator can be generated according to a reference point of each service attribute of the operator and a difference value of corresponding attribute values; correspondingly, for any target operator, a foreground value function of the target operator is generated according to the reference point of each service attribute of the target operator and the difference value of the corresponding attribute value.
Specifically, the foreground cost function corresponding to the current operator can be calculated by the following formula (1-5):
wherein, V (X)ij) A foreground value function corresponding to the ith current operator; xijIs the attribute value of the jth service attribute of the ith current operator, SjA reference point for the jth service attribute; lambda [ alpha ]iTaking a value of a lambda parameter corresponding to the ith current operator; lambda is a fixed parameter, alpha is a fixed parameter, and beta is a fixed parameter; n is the total number of service attributes, and m is the total number of the current operator.
Accordingly, the corresponding prospect merit function of the current operator can be calculated by the following formulas (1-6):
wherein, V (Y)ij) A foreground value function corresponding to the ith target operator; y isijIs the attribute value of the jth service attribute of the ith target operator, SjA reference point for the jth service attribute; lambda [ alpha ]iTaking a value of a lambda parameter corresponding to the ith target operator; λ is a constant, α is a constant, β is a constant; n is the total number of service attributes and p is the total number of the current operator.
Step S140: and respectively calculating foreground weight functions of the current operator and the target operator.
In a specific implementation process, in order to improve the accuracy of the generated foreground weight function, the foreground weight function of the current operator can be calculated according to the foreground value function and the basic weight function corresponding to the current operator.
Specifically, in the basic weight function, each service attribute corresponds to a corresponding weight coefficient, and the magnitude of the weight coefficient is positively related to the influence degree of the service attribute on the user off-network decision. The basis weight function is shown in equations (1-7).
Wherein W is a basic weight function, WjAnd the jth service attribute corresponds to a weight coefficient, and n is the total number of the service attributes.
Further, the foreground weight function pi of the current operatorαIncluded
And
wherein the content of the first and second substances,
the representative of the benefit is that,
loss is represented;
can be obtained by the following formulae (1-8);
can be obtained by the following formulae (1-9).
Wherein, V (X)ij) A foreground value function corresponding to the ith current operator; wjCorresponding to a weight coefficient for the jth service attribute, wherein epsilon and delta are constant coefficients; n is the total number of service attributes, and m is the total number of the current operator.
Correspondingly, the foreground weight function of the target operator is calculated according to the foreground value function and the basic weight function corresponding to the target operator. Wherein the content of the first and second substances,
foreground weight function pi of current operatorsIncluded
And
wherein the content of the first and second substances,
the representative of the benefit is that,
loss is represented;
can be obtained by the following formulae (1-10);
can be obtained by the following formulae (1-11).
Wherein, V (Y)ij) A foreground value function corresponding to the ith target operator; y isijIs the attribute value of the jth service attribute of the ith target operator, SjA reference point for the jth service attribute; epsilon and delta are constant coefficients; n is the total number of service attributes and p is the total number of target operators.
Step S150: calculating the foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; and calculating the foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator.
In a specific implementation, the foreground value of the current operator can be calculated according to the following formula (1-12):
wherein, VaiIs the foreground value of the ith current operator; v (X)ij) A foreground value function corresponding to the ith current operator;
and
as a foreground weight function of the current operator; and m is the total number of the current operators.
Accordingly, the foreground value of the target operator may be calculated according to the following equations (1-13):
wherein, VsiIs the foreground value of the ith target operator; v (Y)ij) A foreground value function corresponding to the ith target operator;
and
is a foreground weight function of the target operator; p is the total number of current operators.
Step S160: comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result.
Specifically, if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, it is determined that the user may have an off-network behavior. That is, when the perception of the network loss of the user is greater than or equal to the off-network loss evaluation, the user has an off-network tendency, and thus the user is determined to be the user to be off-network.
Therefore, the method and the device can accurately identify the user to be off-grid with the off-grid tendency, so that the off-grid pre-warning is facilitated; moreover, the identified user to be off-network is a user capable of carrying out on-network saving on the client through the corresponding user holding strategy, so that a key push object with the user holding strategy can be screened out, and waste of push resources is avoided; moreover, the identification method provided by the embodiment can avoid the influence of marketing tendency users, and further avoid the waste of push resources. In a word, by adopting the scheme, the success rate of the user retention strategy can be greatly improved, and the user off-network rate is reduced.
Example two
Fig. 3 is a schematic functional structure diagram of a device for identifying a user to be off-network based on user retention according to a second embodiment of the present invention.
As shown in fig. 3, the apparatus includes: the system comprises an operator determining module 31, an attribute value acquiring module 32, a reference point determining module 33, a value function calculating module 34, a weight function calculating module 35, a foreground value calculating module 36 and a judging module 37.
An operator determining module 31, adapted to determine a current operator and a target operator corresponding to the user;
an attribute value obtaining module 32, adapted to obtain an attribute value of at least one service attribute corresponding to a current operator and a target operator;
a reference point determining module 33 adapted to determine, for any service attribute, a reference point of the service attribute;
a cost function calculation module 34, adapted to calculate a foreground cost function corresponding to the current operator and a foreground cost function of the target operator according to the reference point and the attribute value;
a weighting function calculation module 35 adapted to calculate foreground weighting functions of the current operator and the target operator, respectively;
a foreground value calculation module 36, adapted to calculate a foreground value of the current operator according to a foreground cost function and a foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and the judging module 37 is adapted to compare the foreground value of the current operator with the foreground value of the target operator, and judge whether the user is a user to be off-network according to the comparison result.
Optionally, the attribute value obtaining module is further adapted to: acquiring an initial attribute value of at least one service attribute corresponding to a current operator and a target operator;
and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
Optionally, the attribute value obtaining module is further adapted to: and obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator by adopting an evaluation quantification method.
Optionally, the service attribute includes at least one of the following attributes:
economic factors, signal quality, charging accuracy, and quality of service.
Optionally, the reference point determining module is further adapted to: identifying a maximum attribute value and a minimum attribute value corresponding to the service attribute from the attribute values of the service attribute of the target operator;
and determining the reference point of the service attribute according to the maximum attribute value and the minimum attribute value.
Optionally, the weight function calculation module is further adapted to: calculating a foreground weight function of the current operator according to the foreground value function and the basic weight function corresponding to the current operator; and
and calculating the foreground weight function of the target operator according to the foreground value function and the basic weight function corresponding to the target operator.
Optionally, the determining module is further adapted to: and if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, determining that the user can have an off-network behavior.
The specific implementation process of each module in this embodiment may refer to the description of the corresponding part in the foregoing method embodiment, which is not described herein again.
Therefore, the method and the device can accurately identify the user to be off-grid with the off-grid tendency, so that the off-grid pre-warning is facilitated; moreover, the identified user to be off-network is a user capable of carrying out on-network saving on the client through the corresponding user holding strategy, so that a key push object with the user holding strategy can be screened out, and waste of push resources is avoided; moreover, the identification method provided by the embodiment can avoid the influence of marketing tendency users, and further avoid the waste of push resources. In a word, by adopting the scheme, the success rate of the user retention strategy can be greatly improved, and the user off-network rate is reduced.
EXAMPLE III
According to a third embodiment of the present invention, a non-volatile computer storage medium is provided, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction may execute the method in any of the above-mentioned method embodiments.
The executable instructions may be specifically configured to cause the processor to:
determining a current operator and a target operator corresponding to a user, and acquiring an attribute value of at least one service attribute corresponding to the current operator and the target operator;
for any service attribute, determining a reference point of the service attribute;
respectively calculating a foreground value function corresponding to the current operator and a foreground value function of the target operator according to the reference point and the attribute value;
respectively calculating foreground weight functions of the current operator and the target operator;
calculating a foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result.
In an alternative embodiment, the executable instructions may be specifically configured to cause the processor to:
acquiring an initial attribute value of at least one service attribute corresponding to a current operator and a target operator;
and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
In an alternative embodiment, the executable instructions may be specifically configured to cause the processor to:
and obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator by adopting an evaluation quantification method.
In an alternative embodiment, the service attributes include at least one of the following attributes:
economic factors, signal quality, charging accuracy, and quality of service.
In an alternative embodiment, the executable instructions may be specifically configured to cause the processor to:
identifying a maximum attribute value and a minimum attribute value corresponding to the service attribute from the attribute values of the service attribute of the target operator;
and determining the reference point of the service attribute according to the maximum attribute value and the minimum attribute value.
In an alternative embodiment, the executable instructions may be specifically configured to cause the processor to:
calculating a foreground weight function of the current operator according to the foreground value function and the basic weight function corresponding to the current operator; and
and calculating the foreground weight function of the target operator according to the foreground value function and the basic weight function corresponding to the target operator.
In an alternative embodiment, the executable instructions may be specifically configured to cause the processor to:
and if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, determining that the user can have an off-network behavior.
Therefore, the method and the device can accurately identify the user to be off-grid with the off-grid tendency, so that the off-grid pre-warning is facilitated; moreover, the identified user to be off-network is a user capable of carrying out on-network saving on the client through the corresponding user holding strategy, so that a key push object with the user holding strategy can be screened out, and waste of push resources is avoided; moreover, the identification method provided by the embodiment can avoid the influence of marketing tendency users, and further avoid the waste of push resources. In a word, by adopting the scheme, the success rate of the user retention strategy can be greatly improved, and the user off-network rate is reduced.
Example four
Fig. 4 is a schematic structural diagram of a computing device according to a fourth embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically perform the relevant steps in the above method embodiments.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may specifically be configured to cause the processor 402 to perform the following operations:
determining a current operator and a target operator corresponding to a user, and acquiring an attribute value of at least one service attribute corresponding to the current operator and the target operator;
for any service attribute, determining a reference point of the service attribute;
respectively calculating a foreground value function corresponding to the current operator and a foreground value function of the target operator according to the reference point and the attribute value;
respectively calculating foreground weight functions of the current operator and the target operator;
calculating a foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result.
In an alternative embodiment, the program 410 may be specifically configured to cause the processor 402 to perform the following operations:
acquiring an initial attribute value of at least one service attribute corresponding to a current operator and a target operator;
and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
In an alternative embodiment, the program 410 may be specifically configured to cause the processor 402 to perform the following operations:
and obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator by adopting an evaluation quantification method.
In an alternative embodiment, the service attributes include at least one of the following attributes:
economic factors, signal quality, charging accuracy, and quality of service.
In an alternative embodiment, the program 410 may be specifically configured to cause the processor 402 to perform the following operations:
identifying a maximum attribute value and a minimum attribute value corresponding to the service attribute from the attribute values of the service attribute of the target operator;
and determining the reference point of the service attribute according to the maximum attribute value and the minimum attribute value.
In an alternative embodiment, the program 410 may be specifically configured to cause the processor 402 to perform the following operations:
calculating a foreground weight function of the current operator according to the foreground value function and the basic weight function corresponding to the current operator; and
and calculating the foreground weight function of the target operator according to the foreground value function and the basic weight function corresponding to the target operator.
In an alternative embodiment, the program 410 may be specifically configured to cause the processor 402 to perform the following operations:
and if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, determining that the user can have an off-network behavior.
Therefore, the method and the device can accurately identify the user to be off-grid with the off-grid tendency, so that the off-grid pre-warning is facilitated; moreover, the identified user to be off-network is a user capable of carrying out on-network saving on the client through the corresponding user holding strategy, so that a key push object with the user holding strategy can be screened out, and waste of push resources is avoided; moreover, the identification method provided by the embodiment can avoid the influence of marketing tendency users, and further avoid the waste of push resources. In a word, by adopting the scheme, the success rate of the user retention strategy can be greatly improved, and the user off-network rate is reduced.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A user to be off-network identification method based on user preservation is characterized by comprising the following steps:
determining a current operator and a target operator corresponding to a user, and acquiring an attribute value of at least one service attribute corresponding to the current operator and the target operator;
for any service attribute, determining a reference point of the service attribute;
respectively calculating a foreground value function corresponding to the current operator and a foreground value function of the target operator according to the reference point and the attribute value;
respectively calculating foreground weight functions of the current operator and the target operator;
calculating a foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and comparing the foreground value of the current operator with the foreground value of the target operator, and judging whether the user is the user to be off-network according to the comparison result.
2. The method of claim 1, wherein obtaining the attribute value of the at least one service attribute corresponding to the current operator and the target operator further comprises:
acquiring an initial attribute value of at least one service attribute corresponding to a current operator and a target operator;
and normalizing the initial attribute value to obtain the attribute value of at least one service attribute corresponding to the current operator and the target operator.
3. The method of claim 2, wherein obtaining the initial attribute value of the at least one service attribute corresponding to the current operator and the target operator further comprises:
and obtaining an initial attribute value of at least one service attribute corresponding to the current operator and the target operator by adopting an evaluation quantification method.
4. The method according to any of claims 1-3, wherein the service attributes comprise at least one of the following attributes:
economic factors, signal quality, charging accuracy, and quality of service.
5. The method of claim 1, wherein determining the reference point for the service attribute further comprises:
identifying a maximum attribute value and a minimum attribute value corresponding to the service attribute from the attribute values of the service attribute of the target operator;
and determining the reference point of the service attribute according to the maximum attribute value and the minimum attribute value.
6. The method of claim 1, wherein the calculating foreground weighting functions for the current operator and the target operator, respectively, further comprises:
calculating a foreground weight function of the current operator according to the foreground value function and the basic weight function corresponding to the current operator; and
and calculating the foreground weight function of the target operator according to the foreground value function and the basic weight function corresponding to the target operator.
7. The method according to any one of claims 1-3, wherein the determining whether the user will be off-line based on the comparison further comprises:
and if the foreground value of the target operator is greater than or equal to the foreground value of the current operator, determining that the user can have an off-network behavior.
8. An apparatus for identifying a user to be off-line based on user retention, comprising:
the operator determining module is suitable for determining a current operator and a target operator corresponding to the user;
the attribute value acquisition module is suitable for acquiring the attribute value of at least one service attribute corresponding to the current operator and the target operator;
a reference point determining module, adapted to determine, for any service attribute, a reference point of the service attribute;
the value function calculation module is suitable for calculating a foreground value function corresponding to the current operator and a foreground value function of the target operator according to the reference point and the attribute value;
the weight function calculation module is suitable for calculating foreground weight functions of the current operator and the target operator respectively;
the foreground value calculation module is suitable for calculating the foreground value of the current operator according to the foreground value function and the foreground weight function of the current operator; calculating a foreground value of the target operator according to the foreground value function and the foreground weight function of the target operator;
and the judging module is suitable for comparing the foreground value of the current operator with the foreground value of the target operator and judging whether the user is the user to be off-network according to the comparison result.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the user-owned off-line user identification method according to any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method for identifying a user to be off-line as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044552.4A CN114282933A (en) | 2020-09-28 | 2020-09-28 | User to be off-network user identification method and device based on user preservation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044552.4A CN114282933A (en) | 2020-09-28 | 2020-09-28 | User to be off-network user identification method and device based on user preservation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114282933A true CN114282933A (en) | 2022-04-05 |
Family
ID=80868262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011044552.4A Pending CN114282933A (en) | 2020-09-28 | 2020-09-28 | User to be off-network user identification method and device based on user preservation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114282933A (en) |
-
2020
- 2020-09-28 CN CN202011044552.4A patent/CN114282933A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103902646B (en) | Distributed task managing system and method | |
| CN110264274B (en) | Guest group dividing method, model generating method, device, equipment and storage medium | |
| CN111970400B (en) | Crank call identification method and device | |
| CN109062769B (en) | Method, device and equipment for predicting IT system performance risk trend | |
| CN116596095B (en) | Training method and device of carbon emission prediction model based on machine learning | |
| CN110992124A (en) | House resource recommendation method and system | |
| CN113543117B (en) | Prediction method and device for number portability user and computing equipment | |
| CN116070019A (en) | Intelligent recruitment recommendation method and system based on big data and readable storage medium | |
| CN111401642A (en) | Method, device and equipment for automatically adjusting predicted value and storage medium | |
| CN114647790A (en) | Big data mining method and cloud AI (Artificial Intelligence) service system applied to behavior intention analysis | |
| CN112637223B (en) | Application protocol identification method and device, computer equipment and storage medium | |
| CN111581226B (en) | Data sharing method and device based on big data platform and administrative enterprise cloud platform | |
| CN114282933A (en) | User to be off-network user identification method and device based on user preservation | |
| CN110070392B (en) | User loss early warning method and device | |
| CN111224890A (en) | Traffic classification method and system of cloud platform and related equipment | |
| CN113037728B (en) | Risk judgment method, device, equipment and medium for realizing zero trust | |
| CN115168509A (en) | Processing method and device of wind control data, storage medium and computer equipment | |
| CN110175182B (en) | Data checking method and device | |
| CN110691362B (en) | Station address determination method and device | |
| CN110191460B (en) | New network access user monitoring method and platform | |
| CN110020728B (en) | Service model reinforcement learning method and device | |
| CN115858911A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN110569475A (en) | Evaluation method, device, equipment and storage medium for netizen influence | |
| CN116595428B (en) | User classification method and system based on CNN (CNN) log spectrum analysis | |
| CN114297341B (en) | Public opinion popularity determination method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |