CN110545568B - Heterogeneous network switching method, switching device, control equipment and storage medium - Google Patents
Heterogeneous network switching method, switching device, control equipment and storage medium Download PDFInfo
- Publication number
- CN110545568B CN110545568B CN201910978161.0A CN201910978161A CN110545568B CN 110545568 B CN110545568 B CN 110545568B CN 201910978161 A CN201910978161 A CN 201910978161A CN 110545568 B CN110545568 B CN 110545568B
- Authority
- CN
- China
- Prior art keywords
- network
- terminal
- switched
- switching
- service
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003062 neural network model Methods 0.000 claims abstract description 36
- 230000006870 function Effects 0.000 claims description 96
- 238000012545 processing Methods 0.000 claims description 30
- 230000006978 adaptation Effects 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000001174 ascending effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/0005—Control or signalling for completing the hand-off
- H04W36/0011—Control or signalling for completing the hand-off for data sessions of end-to-end connection
- H04W36/0016—Hand-off preparation specially adapted for end-to-end data sessions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
- H04W36/0005—Control or signalling for completing the hand-off
- H04W36/0083—Determination of parameters used for hand-off, e.g. generation or modification of neighbour cell lists
- H04W36/0085—Hand-off measurements
- H04W36/0094—Definition of hand-off measurement parameters
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
According to the heterogeneous network switching method, the switching device, the control equipment and the storage medium, the neural network model is trained by acquiring the complaint data and the non-complaint data of the user, and key indexes and corresponding weights which influence network switching are acquired; according to historical switching data, key index values and corresponding weights of the current service of the terminal, constructing a user satisfaction function of the network to be switched; based on a user satisfaction function, constructing a utility function of the current service access of the terminal to the network to be switched; selecting a network to be switched with the largest utility function value as a target network, and sending a switching instruction to a terminal so that the terminal is switched to the target network according to the switching instruction; the method and the device train the neural network model by adopting the user complaint data and the non-complaint data, determine each key index and corresponding weight which influence the switching of the heterogeneous network, and further select the better heterogeneous network as a switching target.
Description
Technical Field
The present invention relates to network handover technologies, and in particular, to a heterogeneous network handover method, a handover apparatus, a control device, and a storage medium.
Background
Heterogeneous networks (Heterogeneous networks) are a type of Network that is made up of computers, Network devices and systems produced by different manufacturers, most often operating on different protocols to support different functions or applications.
In the prior art, forced handover is usually performed for handover of a heterogeneous network or handover is performed only according to the strength of wireless signal quality, but in an actual scene, there are many factors affecting heterogeneous network handover, so that the effect of the finally handed heterogeneous network may be poor by using the existing network handover method.
Therefore, a new heterogeneous network handover method is needed to implement handover by selecting a better heterogeneous network.
Disclosure of Invention
In view of the foregoing problems, the present invention provides a heterogeneous network handover method, a handover apparatus, a control device, and a storage medium.
In a first aspect, the present invention provides a method for switching a heterogeneous network, including:
obtaining user complaint data and non-complaint data to train a neural network model, and obtaining key indexes and corresponding weights which influence network switching;
according to historical switching data, key index values and corresponding weights of current services of the terminal, constructing a user satisfaction function of a network to be switched, wherein the network to be switched is a network which can be accessed at the position of the terminal;
based on a user satisfaction function, constructing a utility function of the current service access of the terminal to the network to be switched;
and selecting the network to be switched with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
In other optional embodiments, the obtaining of the user complaint data and the non-complaint data trains the neural network model to obtain key indexes and corresponding weights that affect network switching, including:
acquiring attribute types and attribute values of user complaint data and non-complaint data, wherein the attribute types comprise terminal moving speed, terminal residence time in a cell, service adaptation grade, signal strength, network load, cell load and service bandwidth;
normalizing each attribute value;
and taking each attribute after the normalization processing as a training sample to train the neural network model, and obtaining key indexes and corresponding weights which influence network switching, wherein the types of the key indexes comprise at least one attribute type.
In other optional embodiments, the constructing a user satisfaction function of a network to be switched according to historical switching data, a key index value, and a corresponding weight of a current service of a terminal, where the network to be switched is a network that can be accessed at a location where the terminal is located includes:
extracting key index values of the current service of the terminal, inputting the key index values into the trained neural network model, and obtaining the switching failure probability of each network to be switched;
sequencing all networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks;
constructing a user satisfaction function of a candidate network according to historical switching data, key indexes and corresponding weights of the current service of the terminal;
based on a user satisfaction function, constructing a utility function of the terminal current service access candidate network;
and selecting the candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
In other alternative embodiments, a user satisfaction function for a candidate network is constructed according to equation (1), where
Wherein S represents the service type of the current service of the terminal, X represents a candidate network, i represents a key index, US (S, X) represents a user satisfaction function of the current service S of the terminal to the candidate network X, SNCL (S, X) represents the service adaptation grade of the current service S of the terminal to the candidate network X obtained according to the historical switching data of the terminal,representing a key index value of the current service S of the terminal; wS,iRepresenting the corresponding weight of the key index i.
In other alternative embodiments, a utility function of the terminal's current service accessing candidate network is constructed according to formula (2), wherein,
wherein N isXIndicating the number of other services, S, present in the candidate network XlIndicating the type of service corresponding to other services in the candidate network X, XjIndicating other networks to be switched which can be accessed at the location of the terminal, NetIndicating the number of other networks to be switched,indicating the number of services, S, present in the other network to be switchedkAnd the service type corresponding to each service in other networks to be switched is shown.
In a second aspect, the present invention provides a heterogeneous network switching apparatus, including:
the training module is used for acquiring the complaint data and the non-complaint data of the user to train the neural network model and acquiring key indexes and corresponding weights which influence network switching;
the first processing module is used for constructing a user satisfaction function of a network to be switched according to historical switching data, key index values and corresponding weights of the current service of the terminal, wherein the network to be switched is a network which can be accessed at the position of the terminal;
the second processing module is used for constructing a utility function of the current service access to the network to be switched of the terminal based on the user satisfaction function;
and the third processing module selects the network to be switched with the maximum utility function value as a target network and sends a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
In other optional embodiments, the training module is specifically configured to:
acquiring attribute types and attribute values of user complaint data and non-complaint data, wherein the attribute types comprise terminal moving speed, terminal residence time in a cell, service adaptation grade, signal strength, network load, cell load and service bandwidth;
normalizing each attribute value;
and taking each attribute after the normalization processing as a training sample to train the neural network model, and obtaining key indexes and corresponding weights which influence network switching, wherein the types of the key indexes comprise at least one attribute type.
In other optional embodiments, the first processing module is specifically configured to:
extracting key index values of the current service of the terminal, inputting the key index values into the trained neural network model, and obtaining the switching failure probability of each network to be switched;
sequencing all networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks;
constructing a user satisfaction function of a candidate network according to historical switching data, key indexes and corresponding weights of the current service of the terminal;
the second processing module is specifically configured to:
based on a user satisfaction function, constructing a utility function of the terminal current service access candidate network;
the third processing module is specifically configured to:
and selecting the candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
In a third aspect, the present invention provides a heterogeneous network handover control device, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the memory stored computer-executable instructions causes the at least one processor to perform a heterogeneous network handover method as in any one of the preceding claims.
In a fourth aspect, the present invention provides a readable storage medium, which is characterized in that the readable storage medium stores computer-executable instructions, and when a processor executes the computer-executable instructions, the method for heterogeneous network handover is implemented as in any one of the foregoing methods.
According to the heterogeneous network switching method, the switching device, the control equipment and the storage medium, the neural network model is trained by acquiring the complaint data and the non-complaint data of the user, and key indexes and corresponding weights which influence network switching are acquired; according to historical switching data, key index values and corresponding weights of current services of the terminal, constructing a user satisfaction function of a network to be switched, wherein the network to be switched is a network which can be accessed at the position of the terminal; based on a user satisfaction function, constructing a utility function of the current service access of the terminal to the network to be switched; selecting a network to be switched with the largest utility function value as a target network, and sending a switching instruction to a terminal so that the terminal is switched to the target network according to the switching instruction; the method and the device train the neural network model by adopting the user complaint data and the non-complaint data, determine each key index and corresponding weight which influence the switching of the heterogeneous network, and further select the better heterogeneous network as a switching target.
Drawings
Fig. 1 is a schematic diagram of a heterogeneous network architecture on which the present invention is based;
fig. 2 is a schematic flowchart of a heterogeneous network handover method according to the present invention;
fig. 3 is a flowchart illustrating another heterogeneous network handover method according to the present invention;
fig. 4 is a schematic structural diagram of a heterogeneous network switching apparatus according to the present invention;
fig. 5 is a schematic diagram of a hardware structure of a control device according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the examples of the present invention will be clearly and completely described below with reference to the accompanying drawings in the examples of the present invention.
Heterogeneous networks (Heterogeneous networks) are a type of Network that is made up of computers, Network devices and systems produced by different manufacturers, most often operating on different protocols to support different functions or applications.
Fig. 1 is a schematic diagram of a heterogeneous network architecture on which the present invention is based. As shown in fig. 1, the heterogeneous Network includes a Public mobile communication Network (such as 2G, 3G, 4G, etc.), a Public Switched Telephone Network (PSTN), a wide area Network, and various types of networks, where the various types of networks are connected to a core Network through a gateway and finally connected to the Internet (Internet), so as to implement convergence of the heterogeneous networks, and a user terminal can select a suitable Network for access according to its service type or terminal mobility, that is, the terminal implements switching of the heterogeneous networks.
In the prior art, forced handover is usually performed for handover of a heterogeneous network or handover is performed only according to the strength of wireless signal quality, but in an actual scenario, there are many factors that affect handover of the heterogeneous network, such as a mobile state of a terminal, network signal strength, coverage, network load, service bandwidth, and the like.
Aiming at the problem, the invention provides a heterogeneous network switching method, a switching device, control equipment and a storage medium, which realize the switching by selecting a better heterogeneous network and improve the user experience.
In a first aspect, an example of the present invention provides a heterogeneous network handover method, and fig. 2 is a schematic flow chart of the heterogeneous network handover method provided in the present invention, and it should be noted that an execution subject of the method may be a server on a system side.
As shown in fig. 2, the heterogeneous network handover method includes:
Specifically, a user may complain to a telecommunication operator, i.e. a system side, for various problems such as network handover failure, dropped call, noise, etc., and then a server on the system side locates a cause of the complaint problem according to received user complaint data. The present example is considered from the complaint problem of network handover failure, and the reasons affecting network handover generally include user reasons and wireless reasons, where the user reasons include terminal moving speed, terminal residence time in a cell, adaptation level of the terminal current service to the network, and the like, and the wireless reasons include signal strength, network load, cell load, traffic bandwidth, and the like. The non-complaint data refers to the terminal moving speed, the terminal residence time in the cell, the adaptation level of the current service of the terminal to the network, the signal strength, the network load, the cell load, the service bandwidth and the like recorded by the system side when the terminal successfully switches the heterogeneous network. In this example, the switching success (non-complaint data) and the switching failure (complaint data) are used as training samples to train the neural network model, so as to obtain key indexes and corresponding weights that affect the network switching success or failure.
In addition, when the obtained user complaint data and non-complaint data are used as training samples to train the neural network model, it is necessary to locate attribute types and attribute values of the user complaint data and the non-complaint data, and perform normalization processing on the attribute values, because the magnitude difference of the attribute values corresponding to the attribute types affecting heterogeneous network handover is very large, for example, the terminal moving speed may be several seconds per meter, the terminal residence time in a cell may be tens of seconds, the signal intensity is a negative value, the service bandwidth may be several hundred megabytes, and the like, before training the neural network model by using the data, it is necessary to perform normalization processing on the attribute values of different magnitudes, that is, all the attribute values are uniformly quantized between 0 and 1.
That is, one way in which step 101 can be implemented is as follows: acquiring attribute types and attribute values of user complaint data and non-complaint data, wherein the attribute types comprise terminal moving speed, terminal residence time in a cell, service adaptation grade, signal strength, network load, cell load and service bandwidth;
normalizing each attribute value;
and taking each attribute after the normalization processing as a training sample to train the neural network model, and obtaining key indexes and corresponding weights which influence network switching, wherein the types of the key indexes comprise at least one attribute type.
Specifically, the terminal may perform different types of services, such as a voice call service, a hand trip, and the like; the service adaptation level refers to an adaptation level of the terminal to each network when executing different types of services, for example, a voice call service generally stays in the 3G network, in other words, the adaptation level of the voice call service to the 3G network is higher; for example, for high-traffic services, the adaptation level of the 4G network is higher than that of the 3G network; for example, for very high traffic, such as hand-surfing, a 5G network may be required for support. Optionally, the service adaptation level may be embodied by scoring, for example, the adaptation level of the voice service to the 3G network may be set to 10 points, the adaptation level to the 2G network is lower and may be set to 6 points, and the adaptation to the 4G network is general and may be set to 8 points, and the like.
And 102, constructing a user satisfaction function of the network to be switched according to the historical switching data, the key index value and the corresponding weight of the current service of the terminal.
The network to be switched is a network which can be accessed at the position of the terminal.
In this step, the adaptation level of the user terminal to each network when executing the current service is obtained by collecting the historical switching data of the terminal when executing the current service. Theoretically, the most suitable network system corresponds to different service types, for example, the most suitable network for the hand-trip service is a 5G network, but some users may prefer to use a 4G network for the hand-trip service, and for the situation, the step determines the user preference when the user executes the current service by collecting historical switching data of the user so as to determine the adaptation level of the current service of the user terminal to the network; and calculating a user satisfaction function of each network to be switched according to each key index value and the corresponding weight when the terminal is in the current service, wherein the user satisfaction constructed in the step improves the user experience by considering the historical data of the network switching of the user.
And 103, constructing a utility function of the current service access to the network to be switched of the terminal based on the user satisfaction function.
And 104, selecting the network to be switched with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
Specifically, in order to comprehensively consider the utility of the network to be switched, the utility function of the example of the present invention considers not only the satisfaction of the user terminal on the network when executing the current service, but also the satisfaction of other user related services accessed by the network, and the satisfaction of other networks accessible to the periphery of the user terminal except the network when executing the related services, and finally selects the network to be switched with the largest value of the utility function as the target network finally accessed by the user terminal.
According to the heterogeneous network switching method, the neural network model is trained by acquiring the complaint data and the non-complaint data of the user, so that key indexes and corresponding weights which influence network switching are acquired; according to historical switching data, key index values and corresponding weights of current services of the terminal, constructing a user satisfaction function of a network to be switched, wherein the network to be switched is a network which can be accessed at the position of the terminal; based on a user satisfaction function, constructing a utility function of the current service access of the terminal to the network to be switched; selecting a network to be switched with the largest utility function value as a target network, and sending a switching instruction to a terminal so that the terminal is switched to the target network according to the switching instruction; according to the method and the device, the neural network model is trained by adopting the complaint data and the non-complaint data of the user, so that each key index and corresponding weight influencing heterogeneous network switching are determined, and a better heterogeneous network is selected as a switching target.
With reference to the foregoing implementation manners, fig. 3 is a schematic flowchart of another heterogeneous network handover method provided by the present invention, and as shown in fig. 3, the heterogeneous network handover method includes:
And 203, sequencing the networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks.
And step 204, constructing a user satisfaction function of the candidate network according to the historical switching data, the key indexes and the corresponding weights of the current service of the terminal.
And step 205, constructing a utility function of the current service access candidate network of the terminal based on the user satisfaction function.
And step 206, selecting the candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
Different from the foregoing embodiment, in order to improve the efficiency of determining a better heterogeneous network, in the present embodiment, a better heterogeneous network is determined by calculating only the satisfaction function and the utility function of a plurality of candidate networks with lower handover failure probability.
Specifically, extracting each key index value of the current service of the user terminal, for example, when the user terminal is performing a voice call service, extracting values of the terminal moving speed, the terminal residence time in a cell, the service adaptation level, the signal strength, the network load, the cell load, the service bandwidth and the like, inputting each key index value into a trained neural network model, calculating the switching failure probability of each to-be-switched network, then sorting the to-be-switched networks according to the switching failure probability, selecting a plurality of to-be-switched networks with lower switching failure probability as candidate networks, then calculating the utility function of each candidate network, selecting the candidate network with the largest utility function value as a target network, and sending a switching instruction to the terminal by the system side so that the terminal is switched to the target network according to the switching instruction. When the networks to be switched are sorted according to the switching failure probability, the networks to be switched can be sorted according to the ascending order of the switching failure probability, and then a plurality of networks with top ranks (for example, the network with the top five ranks) are selected as candidate networks. In summary, the present invention improves the efficiency of determining a better network configuration by calculating only the user satisfaction function and utility function of the candidate network with a lower probability of handover failure.
Alternatively, a user satisfaction function for the candidate network may be constructed according to equation (1), where
Wherein S represents the service type of the current service of the terminal, X represents a candidate network, i represents a key index, US (S, X) represents a user satisfaction function of the current service S of the terminal to the candidate network X, SNCL (S, X) represents the service adaptation grade of the current service S of the terminal to the candidate network X obtained according to the historical switching data of the terminal,representing a key index value of the current service S of the terminal; wS,iRepresenting the corresponding weight of the key index i.
It should be noted that, for networks of different systems, the types of the key index i may be different; in addition, W in the formula (1)S,iThe weight value is obtained after the neural network model is trained, and is a relative weight value, so the weight value needs to be normalized before being substituted into the formula (1).
Correspondingly, according to the formula (2), a utility function of the terminal current service access candidate network is constructed, wherein,
wherein, N isXIndicating the number of other services, S, present in the candidate network XlIndicating the type of service corresponding to other services in the candidate network X, XjIndicating other networks to be switched which can be accessed at the location of the terminal, NetIndicating the number of other networks to be switched,to indicate othersNumber of services present in the network to be switched, SkAnd the service type corresponding to each service in other networks to be switched is shown. That is, the first item of the utility function represents the user satisfaction of the current service of the user terminal to the candidate network X, the second item represents the user satisfaction of the related service of other users accessing the candidate network X, and the third item represents the user satisfaction of other services accessing other networks to be switched in the area where the user terminal is located.
For example, assuming that a user executes a voice call service, and there are A, B, C, D, E, F six networks to be switched in an accessible area, first extracting key index values of the user executing the current voice call service, and inputting the key index values into a trained neural network model; then respectively calculating failure probabilities of switching to A, B, C, D, E, F six networks to be switched, sequencing the networks in an ascending order according to the failure probabilities, and selecting the network with the top three as a candidate network; assuming that the top three candidate networks are A, B, C respectively, calculating user satisfaction degrees corresponding to A, B, C networks when the terminal performs the voice call service according to formula (1), wherein when determining the first item SNCL (S, X) of formula (1), the service adaptation level of the user when performing the voice call service can be determined according to historical switching data, for example, the user prefers to use the B network, the adaptation level score of the B network is relatively high, and the adaptation level scores of the a and C networks are relatively low; after the user satisfaction functions corresponding to A, B, C are respectively calculated, utility functions corresponding to A, B, C are respectively calculated according to a formula (2), taking the calculation of the utility function of the network a as an example, the utility function of the network a is the sum of the user satisfaction of the current voice call service of the terminal accessing the network a, the user satisfaction of the related service of other users accessing the network a, and the satisfaction of the related service of other users accessing the B, C, D, E, F network; and finally, selecting the network with the maximum utility function value as a target network to which the terminal is finally accessed.
The heterogeneous network switching method provided by the invention obtains the switching failure probability of each network to be switched by extracting the key index value of the current service of the terminal and inputting the key index value into the trained neural network model; sequencing all networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks; constructing a user satisfaction function of a candidate network according to historical switching data, key indexes and corresponding weights of the current service of the terminal; based on a user satisfaction function, constructing a utility function of the terminal current service access candidate network; selecting a candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction; namely, the utility function of a plurality of candidate networks with lower switching failure probability is only calculated, so that the efficiency of determining the superior network is improved.
In a second aspect, an example of the present invention provides a heterogeneous network switching apparatus, fig. 4 is a schematic structural diagram of the heterogeneous network switching apparatus provided in the present invention, and as shown in fig. 4, the switching apparatus includes:
the training module 101 is configured to acquire user complaint data and non-complaint data to train a neural network model, and acquire key indexes and corresponding weights that affect network switching;
the first processing module 102 is configured to construct a user satisfaction function of a to-be-switched network according to historical switching data, a key index value and a corresponding weight of a current service of a terminal, where the to-be-switched network is a network that can be accessed at a position where the terminal is located;
the second processing module 103 is configured to construct a utility function of the terminal, where the current service accesses the network to be switched, based on the user satisfaction function;
and the third processing module 104 selects the network to be switched with the largest utility function value as a target network, and sends a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
In other optional embodiments, the training module 101 is specifically configured to:
acquiring attribute types and attribute values of user complaint data and non-complaint data, wherein the attribute types comprise terminal moving speed, terminal residence time in a cell, service adaptation grade, signal strength, network load, cell load and service bandwidth;
normalizing each attribute value;
and taking each attribute after the normalization processing as a training sample to train the neural network model, and obtaining key indexes and corresponding weights which influence network switching, wherein the types of the key indexes comprise at least one attribute type.
In other optional embodiments, the first processing module 102 is specifically configured to:
extracting key index values of the current service of the terminal, inputting the key index values into the trained neural network model, and obtaining the switching failure probability of each network to be switched;
sequencing all networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks;
constructing a user satisfaction function of a candidate network according to historical switching data, key indexes and corresponding weights of the current service of the terminal;
the second processing module 103 is specifically configured to:
based on a user satisfaction function, constructing a utility function of the terminal current service access candidate network;
the third processing module 104 is specifically configured to:
selecting a candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction:
in other alternative embodiments, a user satisfaction function for a candidate network is constructed according to equation (1), where
Wherein S represents the service type of the current service of the terminal, X represents a candidate network, i represents a key index, US (S, X) represents a user satisfaction function of the current service S of the terminal to the candidate network X, and SNCL(S, X) represents the service adaptation grade of the current service S of the terminal to the candidate network X obtained according to the historical switching data of the terminal,representing a key index value of the current service S of the terminal; wS,iRepresenting the corresponding weight of the key index i.
In other alternative embodiments, a utility function of the terminal's current service accessing candidate network is constructed according to formula (2), wherein,
wherein N isXIndicating the number of other services, S, present in the candidate network XlIndicating the type of service corresponding to other services in the candidate network X, XjIndicating other networks to be switched which can be accessed at the location of the terminal, NetIndicating the number of other networks to be switched,indicating the number of services, S, present in the other network to be switchedkAnd the service type corresponding to each service in other networks to be switched is shown.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and corresponding beneficial effects of the control device described above may refer to the corresponding process in the foregoing method example, and are not described herein again.
According to the heterogeneous network switching device, the training module is used for acquiring the complaint data and the non-complaint data of the user to train the neural network model, and key indexes and corresponding weights which influence network switching are acquired; the first processing module is used for constructing a user satisfaction function of a network to be switched according to historical switching data, key index values and corresponding weights of the current service of the terminal, wherein the network to be switched is a network which can be accessed at the position of the terminal; the second processing module is used for constructing a utility function of the current service access to the network to be switched of the terminal based on the user satisfaction function; the third processing module selects a network to be switched with the largest utility function value as a target network and sends a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction; the method and the device train the neural network model by adopting the user complaint data and the non-complaint data, determine each key index and corresponding weight which influence the switching of the heterogeneous network, and further select the better heterogeneous network as a switching target.
In a third aspect, an example of the present invention provides a control device, and fig. 5 is a schematic diagram of a hardware structure of the control device provided in the present invention, as shown in fig. 5, the control device includes:
at least one processor 501 and memory 502.
In a specific implementation process, at least one processor 501 executes computer-executable instructions stored in the memory 502, so that the at least one processor 501 executes the heterogeneous network handover method, where the processor 501 and the memory 502 are connected through a bus 503.
For a specific implementation process of the processor 501, reference may be made to the above method embodiments, which implement the similar principle and technical effect, and this embodiment is not described herein again.
In the embodiment shown in fig. 5, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
In a fourth aspect, the present invention further provides a readable storage medium, where a computer executable instruction is stored, and when a processor executes the computer executable instruction, the heterogeneous network handover method as above is implemented.
The readable storage medium described above 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 or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A heterogeneous network handover method, comprising:
obtaining user complaint data and non-complaint data to train a neural network model, and obtaining key indexes and corresponding weights which influence network switching;
according to historical switching data, key index values and corresponding weights of current services of the terminal, constructing a user satisfaction function of a network to be switched, wherein the network to be switched is a network which can be accessed at the position of the terminal;
based on a user satisfaction function, constructing a utility function of the current service access of the terminal to the network to be switched;
selecting a network to be switched with the largest utility function value as a target network, and sending a switching instruction to a terminal so that the terminal is switched to the target network according to the switching instruction;
the heterogeneous network switching method is characterized in that a user satisfaction function of a network to be switched is established according to historical switching data, key index values and corresponding weights of current services of a terminal, the network to be switched is a network which can be accessed at the position of the terminal, and the method comprises the following steps:
extracting key index values of the current service of the terminal, inputting the key index values into the trained neural network model, and obtaining the switching failure probability of each network to be switched;
sequencing all networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks;
constructing a user satisfaction function of a candidate network according to historical switching data, key indexes and corresponding weights of the current service of the terminal;
based on a user satisfaction function, constructing a utility function of the terminal current service access candidate network;
and selecting the candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
2. The method of claim 1, wherein the obtaining of the user complaint data and the non-complaint data trains a neural network model to obtain key indicators and corresponding weights that affect network handover, comprises:
acquiring attribute types and attribute values of user complaint data and non-complaint data, wherein the attribute types comprise terminal moving speed, terminal residence time in a cell, service adaptation grade, signal strength, network load, cell load and service bandwidth;
normalizing each attribute value;
and taking each attribute after the normalization processing as a training sample to train the neural network model, and obtaining key indexes and corresponding weights which influence network switching, wherein the types of the key indexes comprise at least one attribute type.
3. The heterogeneous network handover method of claim 1, wherein a user satisfaction function of the candidate network is constructed according to formula (1), wherein
Wherein S represents the service type of the current service of the terminal, X represents a candidate network, i represents a key index, US (S, X) represents a user satisfaction function of the current service S of the terminal to the candidate network X, and SNCL (S, X) represents the current service of the terminal obtained according to the historical switching data of the terminalThe service S adapts to the level of service of the candidate network X,representing a key index value of the current service S of the terminal; wS,iRepresenting the corresponding weight of the key index i.
4. The heterogeneous network handover method of claim 3, wherein a utility function of the terminal's current service access candidate network is constructed according to formula (2), wherein,
wherein N isXIndicating the number of other services, S, present in the candidate network XlIndicating the type of service corresponding to other services in the candidate network X, XjIndicating other networks to be switched which can be accessed at the location of the terminal, NetIndicating the number of other networks to be switched,indicating the number of services, S, present in the other network to be switchedkAnd the service type corresponding to each service in other networks to be switched is shown.
5. A heterogeneous network handover apparatus, comprising:
the training module is used for acquiring the complaint data and the non-complaint data of the user to train the neural network model and acquiring key indexes and corresponding weights which influence network switching;
the first processing module is used for constructing a user satisfaction function of a network to be switched according to historical switching data, key index values and corresponding weights of the current service of the terminal, wherein the network to be switched is a network which can be accessed at the position of the terminal;
the second processing module is used for constructing a utility function of the current service access to the network to be switched of the terminal based on the user satisfaction function;
the third processing module selects a network to be switched with the largest utility function value as a target network and sends a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction;
the first processing module is specifically configured to:
extracting key index values of the current service of the terminal, inputting the key index values into the trained neural network model, and obtaining the switching failure probability of each network to be switched;
sequencing all networks to be switched according to the switching failure probability, and selecting a plurality of networks to be switched with low switching failure probability as candidate networks;
constructing a user satisfaction function of a candidate network according to historical switching data, key indexes and corresponding weights of the current service of the terminal;
the second processing module is specifically configured to:
based on a user satisfaction function, constructing a utility function of the terminal current service access candidate network;
the third processing module is specifically configured to:
and selecting the candidate network with the maximum utility function value as a target network, and sending a switching instruction to the terminal so that the terminal is switched to the target network according to the switching instruction.
6. The device for switching between heterogeneous networks according to claim 5, wherein the training module is specifically configured to:
acquiring attribute types and attribute values of user complaint data and non-complaint data, wherein the attribute types comprise terminal moving speed, terminal residence time in a cell, service adaptation grade, signal strength, network load, cell load and service bandwidth;
normalizing each attribute value;
and taking each attribute after the normalization processing as a training sample to train the neural network model, and obtaining key indexes and corresponding weights which influence network switching, wherein the types of the key indexes comprise at least one attribute type.
7. A heterogeneous network handover control device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the memory-stored computer-executable instructions cause the at least one processor to perform the heterogeneous network handover method of any of claims 1 to 4.
8. A readable storage medium, wherein the readable storage medium stores computer executable instructions, and when a processor executes the computer executable instructions, the method for heterogeneous network handover according to any one of claims 1 to 4 is implemented.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910978161.0A CN110545568B (en) | 2019-10-15 | 2019-10-15 | Heterogeneous network switching method, switching device, control equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910978161.0A CN110545568B (en) | 2019-10-15 | 2019-10-15 | Heterogeneous network switching method, switching device, control equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110545568A CN110545568A (en) | 2019-12-06 |
CN110545568B true CN110545568B (en) | 2021-09-14 |
Family
ID=68715920
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910978161.0A Active CN110545568B (en) | 2019-10-15 | 2019-10-15 | Heterogeneous network switching method, switching device, control equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110545568B (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113496338B (en) * | 2020-04-08 | 2023-08-22 | ***通信集团广东有限公司 | Analysis method, system and device for network quality difference reasons |
CN111586809B (en) * | 2020-04-08 | 2022-05-10 | 西安邮电大学 | Heterogeneous wireless network access selection method and system based on SDN |
CN111885543B (en) * | 2020-06-28 | 2021-08-27 | 北京交通大学 | Internet of vehicles switching method and device based on ultra-dense networking |
CN112153679B (en) * | 2020-09-10 | 2023-10-31 | 中国联合网络通信集团有限公司 | Network switching method and device |
CN112243280B (en) * | 2020-10-20 | 2023-05-09 | Oppo广东移动通信有限公司 | Service initiation method, device, terminal and storage medium |
CN112469093A (en) * | 2020-11-16 | 2021-03-09 | 上海擎昆信息科技有限公司 | Method and apparatus for handover in hybrid network |
CN115190496A (en) * | 2021-04-02 | 2022-10-14 | 华为技术有限公司 | Intelligent network selection method and related device |
CN115442833B (en) * | 2021-06-03 | 2024-06-18 | ***通信集团四川有限公司 | Complaint root cause analysis method and device and electronic equipment |
CN113490248B (en) * | 2021-07-27 | 2022-03-11 | 重庆邮电大学 | Multi-mode terminal switching method and device |
CN113938920B (en) * | 2021-09-06 | 2023-08-22 | 中国联合网络通信集团有限公司 | Method and device for predicting heavy tillage influence |
CN114125962B (en) * | 2021-11-10 | 2024-06-11 | 国网江苏省电力有限公司电力科学研究院 | Self-adaptive network switching method, system and storage medium |
CN114513825B (en) * | 2022-04-18 | 2022-07-29 | 北京邮电大学 | Heterogeneous network switching method and device and electronic equipment |
CN114828124B (en) * | 2022-05-13 | 2023-07-14 | 中国联合网络通信集团有限公司 | Method and device for determining target base station |
CN114980234B (en) * | 2022-06-24 | 2024-02-06 | 中国联合网络通信集团有限公司 | Different frequency switching method, device and storage medium |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101511111B (en) * | 2009-03-18 | 2010-12-29 | 东南大学 | Vertical switching method of isomerization network fusion system based on fuzzy neural network |
CN103313333B (en) * | 2012-03-13 | 2016-03-30 | ***通信集团广东有限公司 | The method, communication terminal, server and the network that switch is carried out between mobile network |
CN104113452B (en) * | 2014-07-29 | 2018-02-23 | 中国联合网络通信集团有限公司 | Network quality Forecasting Methodology and device |
CN104703235B (en) * | 2015-03-19 | 2018-06-19 | 北京邮电大学 | A kind of terminal switching method under high-speed mobile |
CN104869594B (en) * | 2015-05-08 | 2018-12-07 | 西安交通大学 | The network selecting method of service quality and network load is considered in a kind of heterogeneous network |
CN105517070B (en) * | 2015-12-25 | 2019-03-22 | 上海交通大学 | Heterogeneous network switch method based on user's use habit |
CN105744592B (en) * | 2016-04-11 | 2019-09-06 | 北京邮电大学 | A kind of business access method based on heterogeneous wireless network, apparatus and system |
CN105792233B (en) * | 2016-05-13 | 2019-03-19 | 华中科技大学 | A method of mobile terminal being accessed based on efficiency theory in isomery cellular network |
CN106131920A (en) * | 2016-06-21 | 2016-11-16 | 南京邮电大学 | A kind of heterogeneous network system of selection based on many attributes Yu queuing theory |
CN106413015B (en) * | 2016-11-28 | 2020-02-11 | 中国联合网络通信集团有限公司 | Network access switching method and device |
CN108419274B (en) * | 2018-02-28 | 2020-07-28 | 华南理工大学 | Heterogeneous wireless network selection method based on utility function |
CN108881067B (en) * | 2018-06-15 | 2020-11-06 | 北京邮电大学 | Bandwidth allocation method and system for ensuring business fairness based on application awareness |
CN109219071B (en) * | 2018-11-05 | 2021-09-10 | 重庆邮电大学 | Vertical switching method based on service classification in heterogeneous wireless network |
CN110225535B (en) * | 2019-06-04 | 2021-07-20 | 吉林大学 | Heterogeneous wireless network vertical switching method based on depth certainty strategy gradient |
-
2019
- 2019-10-15 CN CN201910978161.0A patent/CN110545568B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN110545568A (en) | 2019-12-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110545568B (en) | Heterogeneous network switching method, switching device, control equipment and storage medium | |
CN112417439B (en) | Account detection method, device, server and storage medium | |
US8238525B2 (en) | Voice recognition server, telephone equipment, voice recognition system, and voice recognition method | |
CN110910901A (en) | Emotion recognition method and device, electronic equipment and readable storage medium | |
CN111294819B (en) | Network optimization method and device | |
CN108764951B (en) | User similarity obtaining method and device, equipment and storage medium | |
CN112966865B (en) | Number-carrying network-switching prediction method, device and equipment | |
CN106651580B (en) | Method and device for judging whether financial account is malicious or not and computing device | |
CN115665665A (en) | Moving path recognition method, recognition device, electronic equipment and readable storage medium | |
CN111277662B (en) | Processing method of proxy server, electronic device and storage medium | |
CN110348471B (en) | Abnormal object identification method, device, medium and electronic equipment | |
WO2022121164A1 (en) | Suspension-causing sensitive word prediction method and apparatus, and computer device and storage medium | |
CN111368858B (en) | User satisfaction evaluation method and device | |
CN114173006A (en) | Communication user off-network early warning method and server | |
CN112699099A (en) | Method, device and storage medium for expanding user complaint database | |
CN110337118B (en) | Method and device for quickly processing user complaints | |
CN116208513A (en) | Gateway health degree prediction method and device | |
CN112291421B (en) | Single-pass detection method and device based on voice communication, storage medium and electronic equipment | |
CN114065187A (en) | Abnormal login detection method and device, computing equipment and storage medium | |
CN113962712A (en) | Method for predicting fraud gangs and related equipment | |
CN114970495A (en) | Name disambiguation method and device, electronic equipment and storage medium | |
CN114363082A (en) | Network attack detection method, device, equipment and computer readable storage medium | |
CN113457142A (en) | Method and device for determining cloud equipment server in cloud game and business server | |
CN115175166B (en) | Wireless roaming access point determining method, device, electronic equipment and storage medium | |
CN111859078B (en) | Information identification method and device and electronic equipment |
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 |