CN110019382A - User's cohesion index determines method, apparatus, storage medium and electronic equipment - Google Patents
User's cohesion index determines method, apparatus, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110019382A CN110019382A CN201710601355.XA CN201710601355A CN110019382A CN 110019382 A CN110019382 A CN 110019382A CN 201710601355 A CN201710601355 A CN 201710601355A CN 110019382 A CN110019382 A CN 110019382A
- Authority
- CN
- China
- Prior art keywords
- user
- network
- record information
- historical communication
- communication record
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004891 communication Methods 0.000 claims description 164
- 239000013598 vector Substances 0.000 claims description 63
- 230000014509 gene expression Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 10
- 238000012549 training Methods 0.000 description 9
- 230000006855 networking Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Telephonic Communication Services (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This disclosure relates to which a kind of user's cohesion index determines method, apparatus, storage medium and electronic equipment, this method comprises: obtaining the history log information of this network users, wherein, the history log information of this network users include: network entry time be no more than preset time period the first user history log information and/or network entry time be more than preset time period second user history log information；The cohesion exponential model of this network users Yu rete mirabile user is obtained according to the history log information of this network users；The cohesion index between target rete mirabile user and this network users is calculated using cohesion exponential model, the method increase the efficiency for determining relevance between user.
Description
Technical Field
The present disclosure relates to the field of data mining technologies, and in particular, to a method and an apparatus for determining a user intimacy degree index, a storage medium, and an electronic device.
Background
With the popularization of mobile communication, in order to expand the user amount and provide services for more users, the operators need to try to maintain the original customers on one hand, and also start to target the competitor users, i.e. the users of different networks, especially the high-end users on the other hand.
At present, the main means for marketing the users in the different networks is to determine the marketability of the users in the different networks based on the relevance between the users in the different networks and the users in the local networks. The association between the users needs to be acquired by analyzing a large amount of data of the users of the two parties, finding out data capable of reflecting the association between the users, and then determining the association between the users based on the data. Obviously, this operation mode needs more data to be processed, and the operation is more complicated, resulting in lower efficiency. Therefore, how to efficiently determine the relevance between users is an urgent problem to be solved.
Disclosure of Invention
The disclosure aims to provide a user intimacy index obtaining method, a user intimacy index obtaining device, a storage medium and electronic equipment, which are used for solving the problem that the efficiency of a mode for determining the relevance between users in the related art is low.
The present disclosure provides a method for determining a user intimacy index, including: acquiring historical communication record information of a home network user, wherein the historical communication record information of the home network user comprises: historical communication record information of a first user of which the network access time does not exceed a preset time period and/or historical communication record information of a second user of which the network access time exceeds the preset time period; obtaining an intimacy index model of the home network user and the different network users according to the historical communication record information of the home network user; and calculating the intimacy index between the target different-network user and the local-network user by using the intimacy index model.
Optionally, the acquiring historical communication record information of the home network user includes: for the first user, determining a different network user identifier used by the first user before network access according to the historical communication record information of the first user; acquiring historical communication record information of the first user and the home network user before the first user accesses the network according to the different network user identification; acquiring historical communication record information of the first user after the first user accesses the network according to the user identification of the first user after the first user accesses the network; and for the second user, acquiring the historical communication record information of the second user according to the home network user identification of the second user.
Optionally, the determining, according to the historical communication record information of the first user, the identifier of the different-network user used by the first user before the first user accesses the network includes: acquiring a third user of which the communication frequency with the first user reaches a preset frequency within the preset time period after the first user accesses the network; determining a fourth user which communicates with each user in the third users within the preset time period before the first user accesses the network; respectively calculating the total communication time length of each user in the fourth users and each user in the third users; and determining the user identifier of the target user in the fourth users corresponding to the calculated longest total communication time length as the corresponding different-network user identifier before the first user accesses the network.
Optionally, the obtaining an affinity index model of the home network user and the heterogeneous network user according to the historical communication record information of the home network user includes: extracting historical communication record information of the first user in the preset time period before the first user accesses the network and historical communication record information of the first user in the preset time period after the first user accesses the network to obtain a first vector representing the historical communication characteristics of the first user before the first user accesses the network and a second vector representing the historical communication characteristics of the first user after the first user accesses the network; respectively establishing relational expressions containing unknown coefficient vectors according to the relationship between the first vector and the affinity index and the relationship between the second vector and the affinity index to obtain an equation set; solving the equation set according to the relation that the corresponding affinity indexes of the first user in the preset time period before the first user accesses the network and in the preset time period after the first user accesses the network are the same, and calculating the unknown coefficient vector; and expressing the relationship between the historical communication characteristics of the user and the intimacy index by using the calculated unknown coefficient vector to obtain the intimacy index model.
Optionally, the method further comprises: collecting the information of the preset type service customized by the user of the home network; and recommending the preset type service customized by the user of the local network to the user of the different network, wherein the affinity index of the user of the local network exceeds a preset value.
Optionally, the historical communication record information of the target different-network user and the historical communication record information of the local network user both include one or more of the following information: the number of calls, the duration of the calls, the number of people in the calls, the number of times of messages, and the number of people in the messages.
The present disclosure also provides a device for determining a user intimacy index, including: the acquisition module is used for acquiring the historical communication record information of the home network user, and the historical communication record information of the home network user comprises: historical communication record information of a first user of which the network access time does not exceed a preset time period and/or historical communication record information of a second user of which the network access time exceeds the preset time period; the modeling module is used for obtaining an intimacy index model of the home network user and the different network users according to the historical communication record information of the home network user; and the calculating module is used for calculating the intimacy index between the target different-network user and the local-network user by using the intimacy index model.
Optionally, the obtaining module includes: a determining unit, configured to determine, for the first user, a different-network user identifier used by the first user before network access according to historical communication record information of the first user; a first obtaining unit, configured to obtain, according to the different-network user identifier, historical communication record information between the first user and the home network user before accessing the network; a second obtaining unit, configured to obtain, according to a home network user identifier after the first user accesses a network, historical communication record information of the first user after accessing the network; and the third obtaining unit is used for obtaining the historical communication record information of the second user according to the home network user identifier of the second user.
Optionally, the determining unit is configured to: acquiring a third user of which the communication frequency with the first user reaches a preset frequency within the preset time period after the first user accesses the network; determining a fourth user which communicates with each user in the third users within the preset time period before the first user accesses the network; respectively calculating the total communication time length of each user in the fourth users and each user in the third users; and determining the user identifier of the target user in the fourth users corresponding to the calculated longest total communication time length as the corresponding different-network user identifier before the first user accesses the network.
Optionally, the modeling module includes: the extracting unit is used for extracting historical communication record information of the first user in the preset time period before the first user accesses the network and historical communication record information of the first user in the preset time period after the first user accesses the network to obtain a first vector representing the historical communication characteristics of the first user before the first user accesses the network and a second vector representing the historical communication characteristics of the first user after the first user accesses the network; the establishing unit is used for respectively establishing a relational expression containing an unknown coefficient vector according to the relationship between the first vector and the intimacy index and the relationship between the second vector and the intimacy index to obtain an equation set; the calculation unit is used for solving the equation set according to the relation that the corresponding affinity indexes of the first user in the preset time period before the first user accesses the network and in the preset time period after the first user accesses the network are the same, and calculating the unknown coefficient vector; and the relational expression unit is used for expressing the relation between the historical communication characteristics of the user and the intimacy index by using the calculated unknown coefficient vector to obtain the intimacy index model.
Optionally, the apparatus further comprises: the acquisition module is used for acquiring the information of the preset type of service customized by the user of the home network; and the recommending module is used for recommending the preset type service customized by the user of the local network to the user of the different network, the affinity index of which with the user of the local network exceeds a preset value.
Optionally, the historical communication record information of the target foreign network user and the historical communication record information of the home network user include one or more of the following information: the number of calls, the duration of the calls, the number of people in the calls, the number of times of messages, and the number of people in the messages.
The present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the methods described above.
The present disclosure also provides an electronic device, including: the computer-readable storage medium described above; and one or more processors for executing the program in the computer-readable storage medium.
According to the scheme provided by the embodiment of the disclosure, in consideration of the existence of users switched from the different network to the local network in the local network users, the intimacy relationship between the different network users and the local network users is reflected in the historical communication record information of the local network users to establish an intimacy index model for solving the intimacy index between the users. When the association between the different network users and the home network users needs to be obtained, the communication record data of the different network users and the home network users are used as input data, and the intimacy index between the different network users and the home network users can be conveniently and quickly obtained by using the model, so that the efficiency of determining the association between the users is improved by the scheme.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a flow chart of an exemplary user affinity index determination method of the present disclosure.
Fig. 2 is a schematic diagram of an exemplary user affinity index determination process according to the present disclosure.
Fig. 3 is a block diagram illustrating an exemplary user affinity index determination apparatus according to the present disclosure.
Fig. 4 is a block diagram of an exemplary electronic device of the present disclosure.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
In order to solve the above problems, the present disclosure provides a method for determining a user intimacy index, where the intimacy index is used to characterize the degree of association between users, provide a quantitative measure based on historical communication record information for users, and obtain the association between users by calculating the user intimacy index. The method for determining the user intimacy degree index provided by the present disclosure is shown in fig. 1, and comprises the following steps:
s101: acquiring historical communication record information of a home network user;
the historical communication record information of the user of the local network can comprise: the historical communication record information of the first user whose network access time does not exceed the preset time period and/or the historical communication record information of the second user whose network access time exceeds the preset time period, for example, the preset time period may be three months. The historical communication record information can be obtained from a historical call ticket and/or a short message ticket, and can comprise one or more items of a calling party, a called party, call time, call duration and short message time.
S102: obtaining an intimacy index model of the home network user and the different network users according to the historical communication record information of the home network user;
after the historical communication record information of the user of the local network is obtained, data for representing the historical communication characteristics of the user, such as the number of calls, the call duration, the number of people in the call, the number of times of messages, the number of people in the messages and the like, can be extracted from the historical communication record information, training is carried out based on the extracted data, and an affinity index model can be obtained.
The intimacy index model can be obtained by:
extracting historical communication record information of a user who changes from a different network to a home network before accessing the network and historical communication record information of the user after accessing the network to obtain two historical communication characteristics representing the user before accessing the network and after accessing the network; establishing an equation set containing unknown coefficient vectors according to the relationship between the two historical communication record characteristics and the intimacy index; solving the equation set according to the relation that corresponding affinity indexes of the user before and after the user accesses the network are the same, and obtaining a coefficient vector; and expressing the relation between the historical communication characteristics of the user and the intimacy index by using the obtained coefficient vector to obtain an intimacy index model.
S103: and calculating the affinity index between the target different-network user and the local-network user by using an affinity index model.
The historical communication record information of the target different-network user and the historical communication record information of the local network user may include one or more of the following information:
the number of calls, the duration of the calls, the number of people in the calls, the number of times of messages, and the number of people in the messages.
And (4) bringing the historical communication record information of the home network user and the target different network user into the intimacy index model to obtain the intimacy index between the home network user and the target different network user.
According to the method for determining the user affinity index, an affinity index model for calculating the affinity index between users is established according to historical communication record information of users of the home network, the communication record information of the users of the home network and the target different-network users is used as input data, and the affinity index between the users of the home network and the target different-network users can be directly calculated by using the model, so that the relevance between the users of the home network and the different networks can be conveniently and quickly obtained, and the efficiency for determining the relevance between the users is improved.
For a new user whose network access exceeds or does not exceed a preset time period, because the user may use a different network for communication before network access, that is, the new network-accessing user is a network-switching user, the historical communication record information of the new network-accessing user in the preset time period before network access cannot be directly obtained according to the home network user identifier (such as a customer identification number) of the new network-accessing user, therefore, in the present disclosure, the different network user identifier used by the user before network switching is determined according to the user affinity relationship embodied in the communication record information of the user and other users in the preset time period after network access of the new network-accessing user, and the communication record of the different network user identifier and the home network user in the preset time period before network switching is taken as the communication record information of the user in the preset time period before network access. The historical communication record information of the user after the user accesses the network can be directly obtained according to the user identification of the local network after the network is switched. The historical communication record information of the user of the local network who accesses the network and exceeds the preset time period can also be directly obtained through the user identification.
Based on the above analysis, the present disclosure provides an embodiment, in which obtaining the historical communication record information of the user in the home network may include the following processing procedures:
for a first user whose network access time does not exceed a preset time period, determining a different network user identifier used by the first user before network access according to historical communication record information of the first user; acquiring historical communication record information of a first user and a home network user before the first user accesses the network according to the different network user identification; acquiring historical communication record information of a first user after the first user accesses the network according to the user identification of the first user after the first user accesses the network; and for a second user with the network access time exceeding the preset time period, acquiring the historical communication record information of the second user according to the home network user identifier of the second user.
The determining, according to the historical communication record information of the first user, the identifier of the different-network user used by the first user before accessing the network may include: acquiring a second user of which the communication frequency with a first user reaches a preset frequency within a preset time period after the first user accesses the network; determining a third user which communicates with each user in the second users in a preset time period before the first user accesses the network; respectively calculating the total communication time length of each user in the third users and each user in the second users; and determining the user identifier of the target user in the third users corresponding to the calculated longest total communication time length as the corresponding different network user identifier before the first user accesses the network.
In order to facilitate understanding of the process of acquiring the historical communication record information of the user of the home network, the following further describes the process of acquiring the historical communication record information of the user of the home network from the viewpoint of a mathematical set.
Setting a user set with a network access time not exceeding a preset time period as P, and setting a user set with a network access time exceeding the preset time period as Q; for user P in PiFinding out the sum P in a preset time period before network accessiN users whose communication reaches a predetermined number of times are recorded as fijWherein j ∈ [1, n ]](ii) a Searching for the sum f in a preset time period before network accessijThe users who have communicated among the users form a user set Tij(ii) a Determining TijNeutralization ofijA user set R in which all users have communicated; for each user in R, find and fijCommunication time length g of each usereijAnd calculating each user in R and fijThe total duration V of communication of each userij(ii) a Will VijDetermining the corresponding user identifier as P under the condition of maximum valueiUser identification before network access; acquiring communication record information of a user corresponding to the user identification in a preset time period before the user enters the network according to the user identification; and acquiring the communication record information of the user in the preset time period before the current time in the Q.
In another embodiment, the training process of the user intimacy degree index model may include the following processes:
extracting historical communication record information of a first user in a preset time period before the first user accesses the network and historical communication record information of the first user in a preset time period after the first user accesses the network to obtain a first vector representing historical communication characteristics of the first user before the first user accesses the network and a second vector representing historical communication characteristics of the first user after the first user accesses the network; taking the first vector and the second vector as known quantities and substituting the known quantities into the following formula (1) for calculating the intimacy index to obtain an intimacy index equation;
wherein,is a first vector or a second vector, yiThe expression of the index of the intimacy degree,is a vector of the first coefficients and is,is a second coefficient vector; respectively establishing relational expressions containing unknown coefficient vectors according to the first vector and the relationship between the second vector and the intimacy index to obtain an equation set; solving an equation set according to the relation that the corresponding affinity indexes of the first user in a preset time period before the first user accesses the network and in a preset time period after the first user accesses the network are the same, and calculating an unknown coefficient vector; and expressing the relationship between the historical communication characteristics of the user and the intimacy index by using the calculated unknown coefficient vector to obtain an intimacy index model.
The present disclosure also provides another embodiment, which is different from the foregoing embodiment in that the process of establishing the intimacy degree index model is different, and the establishing the intimacy degree index model in this embodiment includes the following processes:
the method comprises the steps of taking the acquired historical communication record information of a home network user as training data of a training intimacy index model, sorting the training data, wherein the sorted data consists of two-dimensional tables, each two-dimensional table comprises six rows, the information in the six rows respectively comprises the number of calls, the call duration, the number of people in calls, the number of short messages, the number of people in short messages and the intimacy index, and the quantities are vector quantity in the following formula (1)To indicate. The first two-dimensional table comprises the current home network users which are not more than the preset time periodHistorical call record information in a previous preset time period, and the second two-dimensional table comprises the historical call record information in the current previous preset time period. The first five columns in the six lists are all original data, and the sixth column of data is obtained through calculation. All the vectors yiWritten together, further written as a matrix, is represented by the following equation (2):
since the intimacy indexes between users are consistent, the first to fifth columns and unknown index vector are applied to the first two-dimensional table Vector obtained by operationAnd the sum vector of the first to fifth columns of the second two-dimensional table Vector obtained by operationAre equal, and from this equality relationship, a system of consistency equations can be established.
In the resulting system of consistency equations, where there are five unknowns in the n equations, and n is much greater than 5, the system is an overdetermined system of equations, and to obtain solutions to the overdetermined system of equations, the following optimization criteria may be established:
the above optimization criteria are represented in aiAnd biAll belong to the R set, make Δ yiTaking the minimum value, wherein aiIs thatElement (b) ofiIs thatElement of (5), Δ yiRepresenting the first to fifth columns of said first two-dimensional table and said vector The vector obtained by the operation, the first to fifth columns of the second two-dimensional table and the vector And calculating the difference of the vectors, wherein R is a set of users which have communicated with each user in the users who have accessed the network for more than the preset time period, namely the set of the third users, in the preset time period before the users accessing the network for more than the preset time period.
Obtaining a vector by solving the over-determined equation set based on the optimization criterionAnd
using calculated vectors And representing the relation between the historical communication characteristics of the user and the intimacy index to obtain the intimacy index model.
In addition, in the process of establishing the intimacy degree index model, according to the principle that the accuracy of the model and the sufficiency of information have positive correlation, the latest acquired call record data can be firstly put into a buffer area, when the buffer area reaches a certain threshold value, the model is retrained in a batch processing mode, and then the original model is updated by the new model obtained through training.
The present disclosure further provides another embodiment, and based on the foregoing embodiment, the method provided in this embodiment may guide recommendation of some communication services through an affinity index between a home network user and a foreign network user. Based on this, on the basis of the foregoing S101 to S103, the method for determining the user affinity index in this embodiment may further include: collecting the information of preset kinds of services customized by a user of the network; and recommending preset types of services customized by the users of the local network to the users of the different networks, wherein the affinity indexes among the users of the local network exceed the preset values. Specifically, when the information of the preset type of service customized by the home network user is collected, the identifier of the preset type of service can be obtained, so that when service recommendation is performed, the identifier of the preset type of service can be directly recommended to the target different network user. The predetermined kind of traffic may include, for example, virtual or affinity networks, or some other kind of interactive traffic. For example, the home network user a customizes the affinity network service, and the affinity index between the foreign network user B and the home network user a calculated by the user affinity index determining method of this embodiment reaches a preset value, which indicates that the affinity index between the home network user a and the foreign network user B is higher, indicating that the foreign network user B is likely to intentionally handle the affinity network service customized by the home network user a, so that the networking ID of the affinity network customized by the home network user a can be recommended to the foreign network user B when the affinity index between the foreign network user B and the home network user a is calculated to reach the preset value.
The present embodiment provides another embodiment, in which a method for determining a user affinity index is described with reference to fig. 2. As shown in fig. 2, the method includes the following processes:
acquiring historical communication record information of a user by collecting a historical ticket; and extracting the target user according to the acquired historical communication record information. Because the characteristics of the user capable of switching the network can be mined based on the historical communication record information of the user switching the different network to the home network, the user switching the different network to the home network can be taken as a target user for extraction. And training a user intimacy index model according to the extracted historical communication record information of the target user to obtain the user intimacy index model.
And acquiring communication record information of the local network user and the different network user through real-time ticket acquisition. And calculating by using a user intimacy index model based on the acquired historical communication record information of the home network user and the different network users to obtain intimacy indexes of the home network user and the different network users. The calculation of the user intimacy degree index can be realized by adopting a real-time flow calculation engine Storm.
Based on the calculated affinity index between the home network user and the different network user, the method can be applied to service recommendation for the different network user, and CRM (Customer Relationship Management) information needs to be acquired when service recommendation is performed; the information of the customized service of the user can be obtained according to the acquired CRM information, for example, networking information of the customized virtual network/affinity network of the user. And then recommending the association degree of the different network users and the local network users according to the user networking information and the obtained affinity indexes of the different network users and the local network users. For example, the virtual network/affinity network customized by the user of the local network can be recommended to the user of the different network whose affinity index with the user of the local network reaches a preset value. In addition, the method for determining the user affinity index of the embodiment is applied to the service system, so that the service system can recommend various services based on the affinity index between users.
Actual application result data of the recommended users can be obtained by collecting CRM information, the actual application result data of the recommended users are fed back to the training process of the intimacy index model, and online optimization training can be performed on the intimacy index model according to the actual application result data of the recommended users.
The method for determining the user intimacy index, which is disclosed by the embodiment of the disclosure, can be used for deeply mining historical communication record information such as conversation among users and short messages and providing quantitative measurement derived from the historical communication record information for the relevance among the users. In practical application, the intimacy index between users can be obtained only by substituting the recorded data of the conversation and short message conditions of a certain user into the intimacy index model, and the efficiency of determining the relevance between users is improved.
Based on the above method for determining the user intimacy degree index, the present disclosure also provides a device for determining the user intimacy degree index, as shown in fig. 3, where the device 30 includes the following components:
an obtaining module 31, configured to obtain historical communication record information of a home network user, where the historical communication record information of the home network user includes: the historical communication record information of the first user of which the network access time does not exceed the preset time period and/or the historical communication record information of the second user of which the network access time exceeds the preset time period. The historical communication record information may include calling party, called party, call time, call duration, short message time and the like.
The modeling module 32 is used for obtaining an intimacy index model of the home network user and the different network users according to the historical communication record information of the home network user;
and the calculating module 33 is configured to calculate an affinity index between the target different-network user and the home-network user by using an affinity index model.
The historical communication record information of the target different-network user and the historical communication record information of the local network user comprise the following information: the number of calls, the duration of the calls, the number of people in the calls, the number of times of messages, and the number of people in the messages.
The obtaining module 31 may further include: the determining unit is used for determining the different network user identifier used by the first user before the first user accesses the network according to the historical communication record information of the first user; the first obtaining unit is used for obtaining the historical communication record information of the first user and the user of the local network before the first user accesses the network according to the user identification of the different network; the second obtaining unit is used for obtaining the historical communication record information of the first user after the first user accesses the network according to the user identification of the first user after the first user accesses the network; and the third acquisition unit is used for acquiring the historical communication record information of the second user according to the home network user identifier of the second user. Wherein the determining unit may be further configured to: acquiring a second user of which the communication frequency with a first user reaches a preset frequency within a preset time period after the first user accesses the network; determining a third user which communicates with each user in the second users in a preset time period before the first user accesses the network; respectively calculating the total communication time length of each user in the third users and each user in the second users; and determining the user identifier of the target user in the third users corresponding to the calculated longest total communication time length as the corresponding different network user identifier before the first user accesses the network.
The modeling module 32 may include: the extraction unit is used for extracting historical communication record information of a first user in a preset time period before the first user accesses the network and historical communication record information of the first user in a preset time period after the first user accesses the network to obtain a first vector representing the historical communication characteristics of the first user before the first user accesses the network and a second vector representing the historical communication characteristics of the first user after the first user accesses the network; the establishing unit is used for respectively establishing a relational expression containing an unknown coefficient vector according to the first vector and the relationship between the second vector and the intimacy index to obtain an equation set; the calculation unit is used for solving an equation set according to the relation that the corresponding affinity indexes of the first user in the preset time period before the first user accesses the network and in the preset time period after the first user accesses the network are the same, and calculating an unknown coefficient vector; and the relational expression unit is used for expressing the relation between the historical communication characteristics of the user and the intimacy index by using the calculated unknown coefficient vector to obtain an intimacy index model. The historical communication characteristics can include user call list characteristics such as the number of calls between users, the total call duration, the number of people in the calls, the number of short messages, the number of people in the short messages and the like.
The intimacy index between the home network user and the different network user calculated by the user intimacy index determining device provided by the disclosure can be used for guiding the recommendation of some communication services. Based on this, the above apparatus may further include: the acquisition module is used for acquiring the information of the preset type of service customized by the user of the local network; and the recommending module is used for recommending the preset type service customized by the user in the local network to the user in the different network, wherein the affinity index between the user in the local network and the user in the local network exceeds the preset value. For example, for the home network user, whether the foreign network users in the circle of interaction have the possibility of the familiarity network/virtual network networking is judged according to the intimacy index between the home network user and the foreign network users, and if networking is possible, the virtual network/familiarity network networking ID is recommended.
Fig. 4 is a block diagram illustrating an electronic device 400 according to an example embodiment. As shown in fig. 4, the electronic device 400 may include: a processor 401, a memory 402, a multimedia component 403, an input/output (I/O) interface 404, and a communication component 405.
The processor 401 is configured to control the overall operation of the electronic device 400, so as to complete all or part of the steps of the user affinity index determination method. The memory 402 is used to store various types of data to support operation at the electronic device 400, such as instructions for any application or method operating on the electronic device 400 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The Memory 402 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 403 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 402 or transmitted through the communication component 405. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 404 provides an interface between the processor 401 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 405 may include: Wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the electronic Device 400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the user affinity index determination methods described above.
In another exemplary embodiment, a computer readable storage medium comprising program instructions, such as the memory 402 comprising program instructions, executable by the processor 401 of the electronic device 400 to perform the method of determining a user affinity index described above is also provided.
In another exemplary embodiment, a computer readable storage medium, such as a memory, including program instructions executable by a processor of an electronic device to perform the above-described method of determining a user affinity index is also provided.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
According to the technical scheme provided by the embodiment of the disclosure, the intimacy index model between the users can be obtained according to the historical communication record information of the users of the local network, and the intimacy indexes of the users of the local network and the users of the different network are obtained based on the intimacy index model, so that the relevance between the users of the different network and the users of the local network can be more efficiently and accurately obtained; based on the calculated intimacy index between the users of the local network and the users of the different network, the users of the different network which can carry out marketing can be mined out in real time, and then the related business which is customized by the users of the local network and has the intimacy reaching a certain degree is recommended to the users, so that the problem of low success rate of business marketing is solved, and meanwhile, the communication cost of the users of the different network can be reduced under the condition of successful business marketing.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure. For example.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, various possible combinations will not be separately described in this disclosure.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. A method for determining a user affinity index, comprising:
acquiring historical communication record information of a home network user, wherein the historical communication record information of the home network user comprises: historical communication record information of a first user of which the network access time does not exceed a preset time period and/or historical communication record information of a second user of which the network access time exceeds the preset time period;
obtaining an intimacy index model of the home network user and the different network users according to the historical communication record information of the home network user;
and calculating the intimacy index between the target different-network user and the local-network user by using the intimacy index model.
2. The method of claim 1, wherein the obtaining historical communication record information of the home network user comprises:
for the first user, determining a different network user identifier used by the first user before network access according to the historical communication record information of the first user;
acquiring historical communication record information of the first user and the home network user before the first user accesses the network according to the different network user identification;
acquiring historical communication record information of the first user after the first user accesses the network according to the user identification of the first user after the first user accesses the network;
and for the second user, acquiring the historical communication record information of the second user according to the home network user identification of the second user.
3. The method of claim 2, wherein the determining the identifier of the first user before the first user accesses the network according to the historical address information of the first user comprises:
acquiring a third user of which the communication frequency with the first user reaches a preset frequency within the preset time period after the first user accesses the network;
determining a fourth user which communicates with each user in the third users within the preset time period before the first user accesses the network;
respectively calculating the total communication time length of each user in the fourth users and each user in the third users;
and determining the user identifier of the target user in the fourth users corresponding to the calculated longest total communication time length as the corresponding different-network user identifier before the first user accesses the network.
4. The method according to claim 1, wherein the obtaining an affinity index model of the home network user and the heterogeneous network user according to the historical communication record information of the home network user comprises:
extracting historical communication record information of the first user in the preset time period before the first user accesses the network and historical communication record information of the first user in the preset time period after the first user accesses the network to obtain a first vector representing the historical communication characteristics of the first user before the first user accesses the network and a second vector representing the historical communication characteristics of the first user after the first user accesses the network;
respectively establishing relational expressions containing unknown coefficient vectors according to the relationship between the first vector and the affinity index and the relationship between the second vector and the affinity index to obtain an equation set;
solving the equation set according to the relation that the corresponding affinity indexes of the first user in the preset time period before the first user accesses the network and in the preset time period after the first user accesses the network are the same, and calculating the unknown coefficient vector;
and expressing the relationship between the historical communication characteristics of the user and the intimacy index by using the calculated unknown coefficient vector to obtain the intimacy index model.
5. The method of claim 1, further comprising:
collecting the information of the preset type service customized by the user of the home network;
and recommending the preset type service customized by the user of the local network to the user of the different network, wherein the affinity index of the user of the local network exceeds a preset value.
6. The method according to any one of claims 1 to 5, wherein the historical communication record information of the target heterogeneous network user and the historical communication record information of the home network user comprise one or more of the following information:
the number of calls, the duration of the calls, the number of people in the calls, the number of times of messages, and the number of people in the messages.
7. A user affinity index determination apparatus, comprising:
the acquisition module is used for acquiring the historical communication record information of the home network user, and the historical communication record information of the home network user comprises: historical communication record information of a first user of which the network access time does not exceed a preset time period and/or historical communication record information of a second user of which the network access time exceeds the preset time period;
the modeling module is used for obtaining an intimacy index model of the home network user and the different network users according to the historical communication record information of the home network user;
and the calculating module is used for calculating the intimacy index between the target different-network user and the local-network user by using the intimacy index model.
8. The apparatus of claim 7, wherein the modeling module comprises:
the extracting unit is used for extracting historical communication record information of the first user in the preset time period before the first user accesses the network and historical communication record information of the first user in the preset time period after the first user accesses the network to obtain a first vector representing the historical communication characteristics of the first user before the first user accesses the network and a second vector representing the historical communication characteristics of the first user after the first user accesses the network;
the establishing unit is used for respectively establishing a relational expression containing an unknown coefficient vector according to the relationship between the first vector and the intimacy index and the relationship between the second vector and the intimacy index to obtain an equation set;
the calculation unit is used for solving the equation set according to the relation that the corresponding affinity indexes of the first user in the preset time period before the first user accesses the network and in the preset time period after the first user accesses the network are the same, and calculating the unknown coefficient vector;
and the relational expression unit is used for expressing the relation between the historical communication characteristics of the user and the intimacy index by using the calculated unknown coefficient vector to obtain the intimacy index model.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
10. An electronic device, comprising:
the computer-readable storage medium recited in claim 9; and one or more processors for executing the program in the computer-readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710601355.XA CN110019382B (en) | 2017-07-21 | 2017-07-21 | User intimacy index determination method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710601355.XA CN110019382B (en) | 2017-07-21 | 2017-07-21 | User intimacy index determination method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110019382A true CN110019382A (en) | 2019-07-16 |
| CN110019382B CN110019382B (en) | 2021-09-24 |
Family
ID=67185822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710601355.XA Active CN110019382B (en) | 2017-07-21 | 2017-07-21 | User intimacy index determination method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110019382B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112751749A (en) * | 2020-12-30 | 2021-05-04 | 上海掌门科技有限公司 | Method and equipment for presenting information in audio and video calling process |
| CN114143770A (en) * | 2020-09-04 | 2022-03-04 | 中国电信股份有限公司 | Service recommendation method and device based on different-network mobile phone numbers |
| CN114173006A (en) * | 2020-09-11 | 2022-03-11 | 中国联合网络通信集团有限公司 | Communication user off-network early warning method and server |
| CN114364020A (en) * | 2021-12-29 | 2022-04-15 | 中国电信股份有限公司 | Method, device, equipment and medium for positioning users in different networks |
| CN114900553A (en) * | 2022-04-28 | 2022-08-12 | 中国联合网络通信集团有限公司 | Information pushing method, device, equipment and storage medium |
| CN115396329A (en) * | 2022-08-10 | 2022-11-25 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining target different network number and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070111714A1 (en) * | 2005-11-14 | 2007-05-17 | Bellsouth Intellectual Property Corporation | Methods and apparatus for recognizing home network provider of incoming wireless calls |
| CN101170734A (en) * | 2007-11-28 | 2008-04-30 | 华为技术有限公司 | Method and device for service intercommunication between different networks |
| CN101588540A (en) * | 2008-05-23 | 2009-11-25 | 马天驰 | Communication method for realizing information interaction of cellphone 2.5G and 3G through Internet |
| CN102737118A (en) * | 2012-05-30 | 2012-10-17 | 安科智慧城市技术（中国）有限公司 | Method, device and mobile terminal for handling relationship among people according to call records |
| CN104636439A (en) * | 2015-01-04 | 2015-05-20 | 中国联合网络通信集团有限公司 | Method and device for analyzing user social relation |
| CN105160547A (en) * | 2015-08-07 | 2015-12-16 | 北京思特奇信息技术股份有限公司 | Cross-network identification method and system based on stable contact index |
| US20170039656A1 (en) * | 2013-06-25 | 2017-02-09 | Arthur Paul Drennan, III | System and method for evaluating text to support multiple insurance applications |
| CN106686198A (en) * | 2015-11-06 | 2017-05-17 | 中国移动通信集团公司 | Address book management method, intimacy information management method, address book management device, and intimacy information management device |
| CN106791227A (en) * | 2016-11-23 | 2017-05-31 | 杭州东信北邮信息技术有限公司 | It is a kind of based on communicating data come the method and system of identifying user frequent contact |
| CN106791221A (en) * | 2016-12-06 | 2017-05-31 | 北京邮电大学 | A kind of kith and kin based on call enclose relation recognition method |
-
2017
- 2017-07-21 CN CN201710601355.XA patent/CN110019382B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070111714A1 (en) * | 2005-11-14 | 2007-05-17 | Bellsouth Intellectual Property Corporation | Methods and apparatus for recognizing home network provider of incoming wireless calls |
| CN101170734A (en) * | 2007-11-28 | 2008-04-30 | 华为技术有限公司 | Method and device for service intercommunication between different networks |
| CN101588540A (en) * | 2008-05-23 | 2009-11-25 | 马天驰 | Communication method for realizing information interaction of cellphone 2.5G and 3G through Internet |
| CN102737118A (en) * | 2012-05-30 | 2012-10-17 | 安科智慧城市技术（中国）有限公司 | Method, device and mobile terminal for handling relationship among people according to call records |
| US20170039656A1 (en) * | 2013-06-25 | 2017-02-09 | Arthur Paul Drennan, III | System and method for evaluating text to support multiple insurance applications |
| CN104636439A (en) * | 2015-01-04 | 2015-05-20 | 中国联合网络通信集团有限公司 | Method and device for analyzing user social relation |
| CN105160547A (en) * | 2015-08-07 | 2015-12-16 | 北京思特奇信息技术股份有限公司 | Cross-network identification method and system based on stable contact index |
| CN106686198A (en) * | 2015-11-06 | 2017-05-17 | 中国移动通信集团公司 | Address book management method, intimacy information management method, address book management device, and intimacy information management device |
| CN106791227A (en) * | 2016-11-23 | 2017-05-31 | 杭州东信北邮信息技术有限公司 | It is a kind of based on communicating data come the method and system of identifying user frequent contact |
| CN106791221A (en) * | 2016-12-06 | 2017-05-31 | 北京邮电大学 | A kind of kith and kin based on call enclose relation recognition method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114143770A (en) * | 2020-09-04 | 2022-03-04 | 中国电信股份有限公司 | Service recommendation method and device based on different-network mobile phone numbers |
| CN114173006A (en) * | 2020-09-11 | 2022-03-11 | 中国联合网络通信集团有限公司 | Communication user off-network early warning method and server |
| CN112751749A (en) * | 2020-12-30 | 2021-05-04 | 上海掌门科技有限公司 | Method and equipment for presenting information in audio and video calling process |
| CN114364020A (en) * | 2021-12-29 | 2022-04-15 | 中国电信股份有限公司 | Method, device, equipment and medium for positioning users in different networks |
| CN114364020B (en) * | 2021-12-29 | 2024-06-07 | 中国电信股份有限公司 | Different network user positioning method, device, equipment and medium |
| CN114900553A (en) * | 2022-04-28 | 2022-08-12 | 中国联合网络通信集团有限公司 | Information pushing method, device, equipment and storage medium |
| CN114900553B (en) * | 2022-04-28 | 2023-04-25 | 中国联合网络通信集团有限公司 | Information pushing method, device, equipment and storage medium |
| CN115396329A (en) * | 2022-08-10 | 2022-11-25 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining target different network number and storage medium |
| CN115396329B (en) * | 2022-08-10 | 2023-12-08 | 中国联合网络通信集团有限公司 | Method, device, equipment and storage medium for determining target different network number |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110019382B (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110019382B (en) | User intimacy index determination method and device, storage medium and electronic equipment | |
| CN107679211B (en) | Method and device for pushing information | |
| KR102064203B1 (en) | Emoji recommendation method and device | |
| CN107305611B (en) | Method and device for establishing model corresponding to malicious account and method and device for identifying malicious account | |
| WO2020134608A1 (en) | Method, apparatus and device for pushing login mode, and method, apparatus and device for displaying login mode | |
| CN106446054B (en) | A kind of information recommendation method, device and electronic equipment | |
| TW201732656A (en) | Providing application program and user recommendation information | |
| US9866454B2 (en) | Generating anonymous data from web data | |
| CN107330019A (en) | Searching method and device | |
| CN108875993B (en) | Invitation behavior prediction method and device | |
| CN111859020A (en) | Recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN111159587A (en) | User access information processing method and device and terminal equipment | |
| CN113826089A (en) | Contextual feedback with expiration indicators for natural understanding systems in chat robots | |
| CN110688576B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN110598109A (en) | Information recommendation method, device, equipment and storage medium | |
| US11470032B2 (en) | Method for recommending groups and related electronic device | |
| CN108805332B (en) | Feature evaluation method and device | |
| CN111523035A (en) | Recommendation method, device, server and medium for APP browsing content | |
| CN111339438A (en) | Friend relation data processing method, server, terminal device and storage medium | |
| US10977285B2 (en) | Using observations of a person to determine if data corresponds to the person | |
| KR101811751B1 (en) | Advertisement providing server using chatbot | |
| CN112783779A (en) | Test case generation method and device, electronic equipment and storage medium | |
| CN112131466A (en) | Group display method, device, system and storage medium | |
| CN114245185B (en) | Video recommendation method, model training method, device, electronic equipment and medium | |
| CN105141664A (en) | Method and equipment for recommending friends to network reading user |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |