CN117319475A - Communication resource recommendation method, device, computer equipment and storage medium - Google Patents
Communication resource recommendation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117319475A CN117319475A CN202311125621.8A CN202311125621A CN117319475A CN 117319475 A CN117319475 A CN 117319475A CN 202311125621 A CN202311125621 A CN 202311125621A CN 117319475 A CN117319475 A CN 117319475A
- Authority
- CN
- China
- Prior art keywords
- communication resource
- resource
- current
- communication
- predicted
- 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
- 230000006854 communication Effects 0.000 title claims abstract description 513
- 238000004891 communication Methods 0.000 title claims abstract description 512
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004590 computer program Methods 0.000 claims abstract description 26
- 230000006399 behavior Effects 0.000 claims description 148
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000013500 data storage Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Abstract
The application relates to a communication resource recommendation method, a communication resource recommendation device, a communication resource recommendation computer device, a communication resource recommendation storage medium and a communication resource recommendation computer program product. The method comprises the following steps: and using the behavior characteristics and the communication resource characteristics of the candidate communication resources according to the communication resources of the user to be recommended. And calculating the association degree between the using behavior characteristics of each communication resource and the communication resource characteristics, and obtaining the sub-prediction resource acquisition rate according to the relative importance degree. And determining the predicted resource acquisition rate of the user to be recommended on each candidate communication resource according to the sub-predicted resource acquisition rate. And recommending the target communication resource to the user to be recommended according to the predicted resource acquisition rate. By adopting the method, the communication resource recommendation with high accuracy and strong real-time performance can be realized.
Description
Technical Field
The present invention relates to the technical field of IT and software development, and in particular, to a communication resource recommendation method, apparatus, computer device, storage medium and computer program product.
Background
Along with the great popularization of mobile equipment such as mobile phones and the like, telecommunication service development is rapid, and a zoom attention technology appears, and the technology can judge the importance of each element in the collection and judge the importance of each element according to the numerical value of an attention weight matrix. Elements of greater attention weight are considered relatively important, while elements of lesser attention weight are considered relatively unimportant. Thus the current conventional communication resource recommendation method is mainly based on the zoom attention technique.
In the traditional technology, a method for improving the service quality, the service quality and the resource quality is sought by largely researching the dimensions of satisfaction, loss rate and the like.
However, the conventional communication resource recommendation method at present has the problem that the use preference of the user for the communication product may change in a short time, so that the recommendation accuracy is not high and the real-time performance is not strong.
Disclosure of Invention
Based on this, it is necessary to provide a communication resource recommendation method, apparatus, computer device, storage medium and computer program product capable of improving the accuracy of resource prediction and enhancing the real-time performance, aiming at the technical problems that the above-mentioned user's usage preference of communication products may change in a short time and thus the recommendation accuracy is not high and the real-time performance is not strong.
In a first aspect, the present application provides a communication resource recommendation method. The method comprises the following steps:
acquiring a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
acquiring the association degree between each communication resource use behavior feature and each communication resource feature, and acquiring the sub-prediction resource acquisition rate of each communication resource use behavior feature for each communication resource feature according to the association degree and the relative importance degree of each communication resource feature;
Based on the predicted resource acquisition rate of each sub-, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource;
and determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the users to be recommended.
In one embodiment, obtaining the degree of association between each of the communication resource usage behavior characteristics and each of the communication resource characteristics includes:
obtaining the similarity between the current communication resource characteristics in the current candidate communication resources and the use behavior characteristics of each communication resource; the current candidate communication resource is any one of the candidate communication resources; the current communication resource characteristic is any one of a plurality of communication resource characteristics contained in the current candidate communication resource;
and obtaining the association degree between the using behavior characteristics of each communication resource and the current communication resource characteristics according to each similarity degree.
In one embodiment, the obtaining, according to each of the similarities, a degree of association between each of the communication resource usage behavior characteristics and the current communication resource characteristics includes:
acquiring the current similarity between the current communication resource use behavior characteristic and the current resource attribute characteristic; the current communication resource use behavior characteristic is any one of communication resource use behavior characteristics;
And summing the similarity degrees, and taking the ratio between the current similarity degree and the summation result as the association degree between the current communication resource use behavior characteristic and the current resource attribute characteristic.
In one embodiment, the obtaining the sub-predicted resource acquisition rate of each of the communication resource usage behavior features for each of the communication resource features according to the association degree and the relative importance degree of each of the communication resource features includes:
acquiring the relative importance degree of the current communication resource characteristics;
obtaining a current attention weight of the current communication resource use behavior feature aiming at the current communication resource feature according to the association degree between the current communication resource use behavior feature and the current resource attribute feature and the relative importance degree of the current communication resource feature;
and obtaining the sub-predicted resource acquisition rate of the current communication resource use behavior characteristic aiming at the current communication resource characteristic according to the current attention weight.
In one embodiment, the obtaining, according to the current attention weight, a sub-predicted resource acquisition rate of the current communication resource usage behavior feature for the current communication resource feature includes:
Acquiring attention weights of current communication resource use behavior characteristics aiming at all communication resource characteristics;
and carrying out normalization processing on the current attention weight by utilizing each attention weight to obtain the sub-predicted resource acquisition rate of the current communication resource utilization behavior characteristic aiming at the current communication resource characteristic.
In one embodiment, the obtaining the relative importance of the current communication resource feature includes:
acquiring a random weight matrix corresponding to the current communication resource characteristics;
based on the random weight matrix, the relative importance degree of the current communication resource characteristic is obtained.
In one embodiment, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource based on each sub-predicted resource acquisition rate includes:
acquiring a target sub-predicted resource acquisition rate associated with the target communication resource characteristic from the sub-predicted resource acquisition rates;
and summing the sub-predicted resource acquisition rates to obtain the predicted resource acquisition rate of the target candidate communication resource of the user to be recommended.
In one embodiment, obtaining a plurality of communication resource usage behavior characteristics of a user to be recommended, and a plurality of communication resource characteristics included in each candidate communication resource includes:
Acquiring communication resource use behavior information of a user to be recommended and communication resource information of each candidate communication resource;
and obtaining a plurality of communication resource use behavior characteristics of the user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource according to the communication resource use behavior information and the communication resource information.
In a second aspect, the present application further provides a communication resource recommendation apparatus. The device comprises:
the acquisition module is used for acquiring a plurality of communication resource use behavior characteristics of the user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
the computing module is used for acquiring the association degree between the communication resource use behavior characteristics and the communication resource characteristics, and obtaining the sub-prediction resource acquisition rate of the communication resource use behavior characteristics aiming at the communication resource characteristics according to the association degree and the relative importance degree of the communication resource characteristics;
the summation module is used for obtaining the predicted resource acquisition rate of the user to be recommended aiming at each candidate communication resource based on each sub predicted resource acquisition rate;
and the recommending module is used for determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates and recommending the target communication resources to the users to be recommended.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
acquiring the association degree between each communication resource use behavior feature and each communication resource feature, and acquiring the sub-prediction resource acquisition rate of each communication resource use behavior feature for each communication resource feature according to the association degree and the relative importance degree of each communication resource feature;
based on the predicted resource acquisition rate of each sub-, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource;
and determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the users to be recommended.
In a fourth aspect, the present application also provides a computer-readable storage medium. A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
Acquiring the association degree between each communication resource use behavior feature and each communication resource feature, and acquiring the sub-prediction resource acquisition rate of each communication resource use behavior feature for each communication resource feature according to the association degree and the relative importance degree of each communication resource feature;
based on the predicted resource acquisition rate of each sub-, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource;
and determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the users to be recommended.
In a fifth aspect, the present application also provides a computer program product. Computer program product comprising a computer program which, when executed by a processor, realizes the steps of:
acquiring a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
acquiring the association degree between each communication resource use behavior feature and each communication resource feature, and acquiring the sub-prediction resource acquisition rate of each communication resource use behavior feature for each communication resource feature according to the association degree and the relative importance degree of each communication resource feature;
Based on the predicted resource acquisition rate of each sub-, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource;
and determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the users to be recommended.
The communication resource recommendation method, the device, the computer equipment, the storage medium and the computer program product acquire a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource by acquiring the communication resource use behavior characteristics; acquiring the association degree between each communication resource use behavior feature and each communication resource feature, and acquiring the sub-prediction resource acquisition rate of each communication resource use behavior feature for each communication resource feature according to the association degree and the relative importance degree of each communication resource feature; based on the predicted resource acquisition rate of each sub-, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource; and determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the users to be recommended. The relative importance degree among the associated communication resource use behavior characteristics, the communication resource characteristics and the communication resource attribute characteristics can achieve higher recommendation accuracy, and the real-time performance is higher by timely acquiring the communication resource use behavior information of the user to be recommended and the communication resource information of the candidate communication resources.
Drawings
FIG. 1 is an application environment diagram of a communication resource recommendation method in one embodiment;
FIG. 2 is a flow chart of a communication resource recommendation method in one embodiment;
FIG. 3 is a flow diagram of constructing a communication resource usage behavior feature in one embodiment;
FIG. 4 is a flow chart of constructing a communication resource attribute feature in another embodiment;
FIG. 5 is a flow diagram of computing an operator predicted resource acquisition rate in one embodiment;
FIG. 6 is a schematic diagram of an application of a communication resource recommendation method in a detailed embodiment;
FIG. 7 is a detailed flowchart of another embodiment of a communication resource recommendation method;
FIG. 8 is a block diagram of a communication resource recommendation device in one embodiment;
fig. 9 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The communication resource recommendation method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 acquires communication resource information of the user to be recommended through interaction with the terminal 102, acquires candidate communication resource information from a communication network, constructs corresponding features based on the acquired information, calculates sub-predicted resource acquisition rate and predicted resource acquisition rate based on the association degree of the acquired features and the relative importance degree of each communication resource attribute feature, determines target communication resources according to the predicted resource acquisition rate, and recommends the target communication resources to the user to be recommended. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a communication resource recommendation method is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:
step S201, a plurality of communication resource usage behavior characteristics of the user to be recommended and a plurality of communication resource characteristics included in each candidate communication resource are obtained.
The process of acquiring and constructing the communication resource usage behavior feature and the communication resource attribute feature in step S201 is shown in fig. 3 and fig. 4, respectively.
Such as the communication resource usage behavior feature r= { R 1 ,r 2 ,...,r n Communication resource attribute feature v= { V } 1 ,v 2 ,...,v k }。
R represents a user to be recommended, R 1 ,r 2 ,...,r n Representing the behaviour of the use of a communication resource, V representing a single communication resource, V 1 ,v 2 ,...,v k A communication resource attribute characteristic representing the communication resource, wherein the values of the subscripts n and k may not be equal.
The communication resource usage behavior features can be understood as short message usage, call usage, directional traffic packet usage, general traffic packet usage, optional packet usage and other tariff conditions, and the other tariff conditions include international call and third party consumption. Correspondingly, the attribute features of the communication resource can be understood as short message service capacity, call service capacity, directional flow packet service capacity, general flow packet service capacity, optional packet content and other tariff content, wherein the other tariff content comprises international call and third party consumption content. The communication resource usage behavior feature is also referred to herein as a user vector, and the communication resource attribute feature is also referred to herein as a package vector.
For example, the server 104 obtains a plurality of communication resource usage behavior characteristics of the user to be recommended and a plurality of communication resource characteristics included in each candidate communication resource through information interaction with the terminal 102.
Step S202, the association degree between the communication resource usage behavior features and the communication resource features is obtained, and the sub-prediction resource acquisition rate of the communication resource usage behavior features for the communication resource features is obtained according to the association degree and the relative importance degree of the communication resource features.
Wherein the method comprises the steps ofWith q ij Representing end user vector r i And attention weight gamma ij Normalized inner product, q ij I.e. representing the sub-predicted resource acquisition rate, softmax represents the calculation formula of the normalized inner product.
Wherein, the association degree can be understood as the association degree between the using behavior characteristic and the communication resource characteristic; the relative importance degree can be understood as that the mutual comparison of the internal elements is not influenced by external factors, and the sub-prediction resource acquisition rate can be understood as a probability value for measuring the recommended degree of the communication resource.
Optionally, the server 104 obtains the association degree between the usage behavior feature of each communication resource and the relative importance degree between the attribute features of each communication resource, and based on the two obtained data, obtains the sub-predicted resource obtaining rate of the user to be recommended for each candidate communication resource after processing.
Step S203, based on the predicted resource acquisition rate of each sub, the predicted resource acquisition rate of each candidate communication resource of the user to be recommended is obtained.
Wherein,Q x the final probability value representing the communication resource usage characteristics versus the communication resource X, i=1 to n, represents that all the communication resource usage behavior characteristics are considered, i.e. all the sub-predicted resource acquisition rates of the users to be recommended are summed up.
For example, the server 104 performs corresponding addition calculation according to the sub-predicted resource acquisition rate, to obtain the predicted resource acquisition rate of the final determined target communication resource.
Step S204, determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the user to be recommended.
Wherein for n communication resources X 1 ,X 2 ,...,X n The same calculation method is used to obtain the corresponding Q 1 ,Q 2 ,...Q n . Maximum Q k The communication resource of the corresponding K subscript is the optimal recommendation, where the subscript n is equal to the previous r= { R 1 ,r 2 ,...,r n The subscript n that appears is not a value.
Optionally, the server determines the target communication resource from the communication resources with the largest predicted resource acquisition rate selected from the plurality of candidate communication resources according to the predicted resource acquisition rate obtained by adding the obtained sub-predicted resource acquisition rates of the users to be recommended, and pushes the target communication resource to the users to be recommended through the terminal 102.
In the communication resource recommendation method, the communication resource use behavior information of the user to be recommended and the communication resource information of each candidate communication resource are obtained; obtaining a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource according to the communication resource use behavior information and the communication resource information; acquiring the association degree between each communication resource use behavior feature and each communication resource feature, and acquiring the sub-prediction resource acquisition rate of each communication resource use behavior feature for each communication resource feature according to the association degree and the relative importance degree of each communication resource feature; based on the predicted resource acquisition rate of each sub-, obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource; and determining target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommending the target communication resources to the users to be recommended. The method has the advantages that the relative importance degree among the associated communication resource use behavior characteristics, the communication resource characteristics and the communication resource attribute characteristics can reach higher recommendation accuracy, and meanwhile, the real-time performance of the method is strong by timely acquiring the communication resource use behavior information of the user to be recommended and the communication resource information of the candidate communication resources.
In one embodiment, the obtaining the association degree between each communication resource usage behavior feature and each communication resource feature includes:
obtaining the similarity between the current communication resource characteristics in the current candidate communication resources and the use behavior characteristics of each communication resource; the current candidate communication resource is any one of the candidate communication resources; the current communication resource characteristic is any one of a plurality of communication resource characteristics contained in the current candidate communication resource;
and obtaining the association degree between the using behavior characteristics of each communication resource and the current communication resource characteristics according to each similarity degree.
Wherein ω is ij ＝f(r i ,v j ),r i ∈R,v j ∈V，ω ij Representing the degree of association between the usage behavior feature and the communication resource feature, f (x, y) represents an inner product function, i and j represent subscripts, which may be the same or different.
In this embodiment, the similarity is calculated by calculating the similarity between the attribute features of the current candidate communication resource and the usage behavior features of the respective communication resources and comparing the values between them. Through the process, the association degree between the attribute characteristics of the candidate communication resources and the use behaviors of the communication resources can be obtained, so that more accurate communication resource recommendation is provided for users. The accuracy of communication resource recommendation can be improved. The relevancy analysis may better understand the user's preferences and needs to provide the user with a recommendation of communication resources that better meets their needs.
In one embodiment, the obtaining the association degree between the usage behavior feature of each communication resource and the current communication resource feature according to each similarity degree includes:
acquiring the current similarity degree between the current communication resource use behavior characteristic and the current resource attribute characteristic; the current communication resource use behavior characteristic is any one of the communication resource use behavior characteristics;
and carrying out summation processing on the similarity degrees, and taking the ratio between the current similarity degree and the summation result as the association degree between the current communication resource use behavior characteristic and the current resource attribute characteristic.
Wherein,β ij representing communication resource usage behavior characteristics r i For communication resource attribute characteristics v j Is a weight of (2).
In this example, based on the obtained current similarity between the communication resource usage behavior feature and the current resource attribute feature, the similarity is summed, and the current similarity is used to compare the summation result to be used as the association degree between the current communication resource usage behavior feature and the current resource attribute feature. The larger the ratio is, the more similar the current communication resource usage behavior characteristic is to the current resource attribute characteristic is, the larger the numerical value is when the probability is calculated later, and the communication resource which is most suitable for the user can be searched more effectively.
In one embodiment, as shown in fig. 5, according to the association degree and the relative importance degree of each communication resource feature, obtaining the sub-predicted resource acquisition rate of each communication resource usage behavior feature for each communication resource feature includes:
step S501, obtaining the relative importance degree of the current communication resource characteristics;
step S502, obtaining the current attention weight of the current communication resource using behavior feature aiming at the current communication resource feature according to the association degree between the current communication resource using behavior feature and the current resource attribute feature and the relative importance degree of the current communication resource feature;
step S503, obtaining the sub-predicted resource acquisition rate of the current communication resource using behavior characteristic aiming at the current communication resource characteristic according to the current attention weight.
Wherein,wherein->Is a random weight matrix, and T represents the meaning of an inversion matrix; ρ j To measure the element V within a single communication resource V j Relative importance of itself gamma ij ＝f(β ij ,ρ j )，γ ij Representing the attention weight.
Attention weight is understood to be a specific value that measures the relative importance of a current communication resource characteristic.
In this embodiment, the server 104 obtains the relative importance degree of each communication resource feature currently stored in the data storage system, obtains a weight value according to the current relative importance degree and the previous association degree, and calculates a sub-predicted resource acquisition rate of the current communication resource usage behavior feature for the current communication resource feature according to the given weight. The relative importance degree of the associated user behavior characteristics and the self resource characteristics is beneficial to improving the accuracy of resource recommendation, and the utilization rate of communication resources can be improved by matching with the selection of users.
In one embodiment, the obtaining, according to the current attention weight, a sub-predicted resource acquisition rate of the current communication resource usage behavior feature for the current communication resource feature includes:
acquiring attention weights of current communication resource use behavior characteristics aiming at all communication resource characteristics;
and carrying out normalization processing on the current attention weight by utilizing each attention weight to obtain the sub-predicted resource acquisition rate of the current communication resource utilization behavior characteristic aiming at the current communication resource characteristic.
In this embodiment, the current attention weight is normalized to obtain the sub-predicted resource acquisition rate of the current communication resource usage behavior feature for the current communication resource feature, and the originally scattered values are integrated after normalization, so that the subsequent calculation is more facilitated, the workload of the subsequent summation is reduced, and meanwhile, the values between 0 and 1 can also more intuitively represent what communication resource feature is more suitable for the user.
In one embodiment, obtaining the relative importance of the current communication resource characteristic comprises:
acquiring a random weight matrix corresponding to the current communication resource characteristics;
based on the random weight matrix, the relative importance degree of the current communication resource characteristic is obtained.
In this embodiment, the server 104 decimates a random weight matrix corresponding to the current communication resource feature from the data storage system, and based on the random weight matrix, can calculate the relative importance degree of the current communication resource feature. By calculating the relative importance of the communication resource characteristics, the more important communication resource characteristics can be better decided, and the target communication resources can be recommended more effectively.
In another embodiment, the obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource based on each sub-predicted resource acquisition rate includes:
acquiring communication resource use behavior information of a user to be recommended and communication resource information of each candidate communication resource;
acquiring a target sub-predicted resource acquisition rate associated with the target communication resource characteristic from the sub-predicted resource acquisition rates;
and summing the sub-predicted resource acquisition rates to obtain the predicted resource acquisition rate of the target candidate communication resource of the user to be recommended.
In this embodiment, the server 104 obtains a target sub-predicted resource obtaining rate associated with the target communication resource feature from the plurality of sub-resource obtaining rates, and performs summation processing on the extracted target sub-predicted resource obtaining rates, so as to obtain a predicted resource obtaining rate of the target candidate communication resource for the user to be recommended. The technology can more accurately predict the acquisition rate of the user to the target communication resource and provide more targeted recommendation results. By carrying out summation processing on the predicted resource acquisition rate, the influence of the behavior characteristics of a plurality of users is comprehensively considered, the accuracy and reliability of recommendation are improved, the satisfaction degree and experience of the users are improved, and meanwhile, the use effect of communication resources is also improved.
In one embodiment, obtaining a plurality of communication resource usage behavior characteristics of a user to be recommended, and a plurality of communication resource characteristics included in each candidate communication resource includes:
acquiring communication resource use behavior information of a user to be recommended and communication resource information of each candidate communication resource;
and obtaining a plurality of communication resource use behavior characteristics of the user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource according to the communication resource use behavior information and the communication resource information.
The communication resource usage behavior information may be understood as data for recording specific behaviors of the user in the communication process, such as call records, short message records, and the like; the communication resource information may be understood as information about resources available to the user, such as communication resource capacity and communication resource type.
Optionally, the server 104 acquires the communication resource usage behavior information of the user to be recommended through interaction with the terminal 102, and acquires the communication resource information from its own data storage system, and constructs the corresponding communication resource usage feature and the communication resource feature based on the above two information, respectively. Constructing communication resource usage characteristics and communication resource characteristics based on the acquired communication resource usage behavior information and communication resource information can realize personalized recommendation, resource optimization, decision making and user insight.
The application environment of the most detailed embodiment is shown in fig. 6, comprising:
the constructed communication resource set formed by the user behavior utilization characteristics and the communication resource characteristics performs the detailed embodiment operation based on the multi-cross attention network mechanism, and finally an optimal target communication resource is obtained and recommended to the user to be recommended.
A detailed embodiment of a method of communication resource recommendation, as shown in fig. 7, includes:
step S701, obtaining the communication resource usage behavior information of the user to be recommended and the communication resource information of each candidate communication resource.
Step S702, according to the communication resource usage behavior information and the communication resource information, a plurality of communication resource usage behavior characteristics of the user to be recommended and a plurality of communication resource characteristics included in each candidate communication resource are obtained.
Step S703, obtaining the similarity between the current communication resource characteristics in the current candidate communication resources and the use behavior characteristics of each communication resource; the current candidate communication resource is any one of the candidate communication resources; the current communication resource characteristic is any one of a plurality of communication resource characteristics included in the current candidate communication resource.
Step S704, summing the similarity degrees, and using the ratio between the current similarity degree and the sum result as the association degree between the current communication resource usage behavior feature and the current resource attribute feature.
Step S705, obtaining a random weight matrix corresponding to the current communication resource characteristics.
Step S706, based on the random weight matrix, the relative importance degree of the current communication resource characteristic is obtained.
Step S707 obtains the current attention weight of the current communication resource usage behavior feature for the current communication resource feature according to the association degree between the current communication resource usage behavior feature and the current resource attribute feature and the relative importance degree of the current communication resource feature.
Step S708, the current attention weight is normalized by using the attention weights, so as to obtain the sub-predicted resource acquisition rate of the current communication resource usage behavior feature aiming at the current communication resource feature.
Step S709, a target sub-predicted resource acquisition rate associated with the target communication resource feature is acquired from the sub-predicted resource acquisition rates.
And step S710, summing the sub-predicted resource acquisition rates to obtain the predicted resource acquisition rate of the target candidate communication resource of the user to be recommended.
In step S711, a target communication resource is determined from the candidate communication resources according to the predicted resource acquisition rates, and the target communication resource is recommended to the user to be recommended.
The embodiments disclosed above have the following advantages over the prior art:
1. supporting the behavior analysis of real-time data of a target client;
2. the method comprises the steps of providing a communication resource use behavior characteristic and a communication resource characteristic, considering the self-relevance in the communication resource characteristic, and analyzing the relevance of the characteristic by utilizing a multi-cross network;
3. based on the current development situation of operators, a commodity prediction method based on a multi-cross attention network is provided, the requirements of matched customers can be analyzed according to the real-time use habit of the users, the current commodity situation is coupled, and proper communication resource pushing is predicted, so that the requirements of the customers are better met, and the self competitiveness of the operators is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a communication resource recommendation device for realizing the above related communication resource recommendation method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation in the embodiments of the one or more communication resource recommendation apparatuses provided below may be referred to the limitation of the communication resource recommendation method hereinabove, and will not be described herein.
In one embodiment, as shown in fig. 8, there is provided a communication resource recommendation apparatus, including: an acquisition module 801, a calculation module 802, a summation module 803 and a recommendation module 804, wherein:
the obtaining module 801 obtains a plurality of communication resource usage behavior characteristics of the user to be recommended, and a plurality of communication resource characteristics included in each candidate communication resource.
The calculation module 802 is configured to obtain a degree of association between each communication resource usage behavior feature and each communication resource feature, and obtain a sub-predicted resource obtaining rate of each communication resource usage behavior feature for each communication resource feature according to the degree of association and a relative importance degree of each communication resource feature.
And the summation module 803 is used for obtaining the predicted resource acquisition rate of the user to be recommended aiming at each candidate communication resource based on each sub-predicted resource acquisition rate.
And a recommending 804 module, which determines target communication resources from the candidate communication resources according to the predicted resource acquisition rates, and recommends the target communication resources to the users to be recommended.
The calculating module 802 is specifically configured to obtain a similarity degree between the current communication resource characteristic in the current candidate communication resources and the usage behavior characteristic of each communication resource; the current candidate communication resource is any one of the candidate communication resources; the current communication resource characteristic is any one of a plurality of communication resource characteristics contained in the current candidate communication resource;
and obtaining the association degree between the using behavior characteristics of each communication resource and the current communication resource characteristics according to each similarity degree.
Acquiring the current similarity degree between the current communication resource use behavior characteristic and the current resource attribute characteristic; the current communication resource use behavior characteristic is any one of the communication resource use behavior characteristics;
and carrying out summation processing on the similarity degrees, and taking the ratio between the current similarity degree and the summation result as the association degree between the current communication resource use behavior characteristic and the current resource attribute characteristic.
The calculation module 802 is further configured to obtain a random weight matrix corresponding to the current communication resource feature, and obtain a relative importance degree of the current communication resource feature based on the random weight matrix.
Obtaining a current attention weight of the current communication resource use behavior feature aiming at the current communication resource feature according to the association degree between the current communication resource use behavior feature and the current resource attribute feature and the relative importance degree of the current communication resource feature;
acquiring attention weights of current communication resource use behavior characteristics aiming at all communication resource characteristics;
and carrying out normalization processing on the current attention weight by utilizing each attention weight to obtain the sub-predicted resource acquisition rate of the current communication resource utilization behavior characteristic aiming at the current communication resource characteristic.
The summation module 803 is specifically configured to obtain a target sub-predicted resource acquisition rate associated with the target communication resource feature from the sub-predicted resource acquisition rates;
and summing the sub-predicted resource acquisition rates to obtain the predicted resource acquisition rate of the target candidate communication resource of the user to be recommended.
The obtaining module 801 is specifically configured to obtain communication resource usage behavior information of a user to be recommended and communication resource information of each candidate communication resource; and obtaining a plurality of communication resource use behavior characteristics of the user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource according to the communication resource use behavior information and the communication resource information.
The respective modules in the above-described communication resource recommendation apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing the communication resource use behavior information of the user to be recommended and the communication resource information of each candidate communication resource, and the communication resource use behavior characteristics of the user to be recommended and the plurality of communication resource attribute characteristics contained in each candidate communication resource after being processed. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a communication resource recommendation method.
It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided, including a memory and a processor, where the memory stores a computer program, and the processor implements the communication resource recommendation method in the above embodiments when executing the computer program.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the communication resource recommendation method in the above embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the communication resource recommendation method in the above embodiments.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (12)
1. A method for recommending communication resources, the method comprising:
acquiring a plurality of communication resource use behavior characteristics of a user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
acquiring the association degree between the communication resource usage behavior features and the communication resource features, and acquiring the sub-prediction resource acquisition rate of the communication resource usage behavior features for the communication resource features according to the association degree and the relative importance degree of the communication resource features;
Based on the sub-predicted resource acquisition rate, obtaining a predicted resource acquisition rate of the user to be recommended for each candidate communication resource;
and determining a target communication resource from the candidate communication resources according to the predicted resource acquisition rate, and recommending the target communication resource to the user to be recommended.
2. The method of claim 1, wherein said obtaining a degree of association between each of said communication resource usage behavior characteristics and each of said communication resource characteristics comprises:
obtaining the similarity between the current communication resource characteristics in the current candidate communication resources and the use behavior characteristics of each communication resource; the current candidate communication resource is any one of the candidate communication resources; the current communication resource characteristic is any one of a plurality of communication resource characteristics contained in the current candidate communication resource;
and obtaining the association degree between the using behavior characteristics of each communication resource and the current communication resource characteristics according to the similarity degree.
3. The method according to claim 2, wherein said obtaining a degree of association between each of the communication resource usage behavior characteristics and the current communication resource characteristics based on each of the degrees of similarity comprises:
Acquiring the current similarity between the current communication resource use behavior characteristic and the current resource attribute characteristic; the current communication resource use behavior characteristic is any one of communication resource use behavior characteristics;
and summing the similarity degrees, and taking the ratio between the current similarity degree and the summation result as the association degree between the current communication resource use behavior characteristic and the current resource attribute characteristic.
4. The method of claim 1, wherein said deriving a sub-predicted resource acquisition rate for each of said communication resource characteristics from said degree of association, and a relative importance of each of said communication resource characteristics, comprises:
acquiring the relative importance degree of the current communication resource characteristics;
obtaining a current attention weight of the current communication resource use behavior feature aiming at the current communication resource feature according to the association degree between the current communication resource use behavior feature and the current resource attribute feature and the relative importance degree of the current communication resource feature;
and obtaining the sub-predicted resource acquisition rate of the current communication resource use behavior characteristic aiming at the current communication resource characteristic according to the current attention weight.
5. The method of claim 4, wherein said deriving a sub-predicted resource acquisition rate for the current communication resource usage behavior feature for the current communication resource feature based on the current attention weight comprises:
acquiring attention weights of current communication resource use behavior characteristics aiming at all the communication resource characteristics;
and carrying out normalization processing on the current attention weight by utilizing each attention weight to obtain a sub-predicted resource acquisition rate of the current communication resource utilization behavior characteristic aiming at the current communication resource characteristic.
6. The method of claim 4, wherein said obtaining the relative importance of the current communication resource characteristics comprises:
acquiring a random weight matrix corresponding to the current communication resource characteristics;
and based on the random weight matrix, obtaining the relative importance degree of the current communication resource characteristics.
7. The method of claim 1, wherein the obtaining, based on each of the sub-predicted resource acquisition rates, a predicted resource acquisition rate for each candidate communication resource for the user to be recommended includes:
acquiring a target sub-predicted resource acquisition rate associated with the target communication resource characteristic from the sub-predicted resource acquisition rates;
And summing the sub-predicted resource acquisition rates to obtain the predicted resource acquisition rate of the target candidate communication resource of the user to be recommended.
8. The method of claim 1, wherein the obtaining the plurality of communication resource usage behavior characteristics of the user to be recommended and the plurality of communication resource characteristics included in each candidate communication resource comprises:
acquiring communication resource use behavior information of the user to be recommended and communication resource information of each candidate communication resource;
and obtaining a plurality of communication resource use behavior characteristics of the user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource according to the communication resource use behavior information and the communication resource information.
9. A communication resource recommendation device, the device comprising:
the acquisition module is used for acquiring a plurality of communication resource use behavior characteristics of the user to be recommended and a plurality of communication resource characteristics contained in each candidate communication resource;
the computing module is used for acquiring the association degree between the communication resource use behavior characteristics and the communication resource characteristics, and obtaining the sub-prediction resource acquisition rate of the communication resource use behavior characteristics for the communication resource characteristics according to the association degree and the relative importance degree of the communication resource characteristics;
The summation module is used for obtaining the predicted resource acquisition rate of the user to be recommended for each candidate communication resource based on each sub-predicted resource acquisition rate;
and the recommending module is used for determining target communication resources from the candidate communication resources according to the predicted resource acquisition rate and recommending the target communication resources to the user to be recommended.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.
11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 8.
12. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311125621.8A CN117319475A (en) | 2023-09-01 | 2023-09-01 | Communication resource recommendation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311125621.8A CN117319475A (en) | 2023-09-01 | 2023-09-01 | Communication resource recommendation method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117319475A true CN117319475A (en) | 2023-12-29 |
Family
ID=89287441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311125621.8A Pending CN117319475A (en) | 2023-09-01 | 2023-09-01 | Communication resource recommendation method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117319475A (en) |
-
2023
- 2023-09-01 CN CN202311125621.8A patent/CN117319475A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110321422B (en) | Method for training model on line, pushing method, device and equipment | |
| US20170293865A1 (en) | Real-time updates to item recommendation models based on matrix factorization | |
| JP6484730B2 (en) | Collaborative filtering method, apparatus, server, and storage medium for fusing time factors | |
| US20210056458A1 (en) | Predicting a persona class based on overlap-agnostic machine learning models for distributing persona-based digital content | |
| WO2020253357A1 (en) | Data product recommendation method and apparatus, computer device and storage medium | |
| CN111783810A (en) | Method and apparatus for determining attribute information of user | |
| CN115795000A (en) | Joint similarity algorithm comparison-based enclosure identification method and device | |
| CN116737373A (en) | Load balancing method, device, computer equipment and storage medium | |
| CN115758271A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN115619261A (en) | Job label portrait data processing method and device and computer equipment | |
| CN117319475A (en) | Communication resource recommendation method, device, computer equipment and storage medium | |
| CN116882408B (en) | Construction method and device of transformer graph model, computer equipment and storage medium | |
| CN116881543A (en) | Financial resource object recommendation method, device, equipment, storage medium and product | |
| CN116881297A (en) | Cache content ordering method, device, computer equipment and storage medium | |
| CN117407746A (en) | User classification method, apparatus, computer device and storage medium | |
| CN117435130A (en) | Financial data storage method, apparatus, computer device and storage medium | |
| CN115409576A (en) | Product recommendation method and device, computer equipment and storage medium thereof | |
| CN117667999A (en) | Data pushing method, device, computer equipment and computer readable storage medium | |
| CN117829951A (en) | Three-dimensional model recommendation method, device, computer equipment and storage medium | |
| CN117033451A (en) | Searching method, searching device, computer equipment and storage medium | |
| CN117132335A (en) | Method and device for determining resource transaction value in resource contract and computer equipment | |
| CN117312892A (en) | User clustering method, device, computer equipment and storage medium | |
| CN117440041A (en) | Silence service information pushing method, device, computer equipment and storage medium | |
| CN115660786A (en) | Service recommendation method, device, computer equipment, storage medium and program product | |
| CN115757971A (en) | Business object recommendation method and device, computer 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 |