CN113722531A - Data storage method, device, system, equipment and storage medium - Google Patents
Data storage method, device, system, equipment and storage medium Download PDFInfo
- Publication number
- CN113722531A CN113722531A CN202111050189.1A CN202111050189A CN113722531A CN 113722531 A CN113722531 A CN 113722531A CN 202111050189 A CN202111050189 A CN 202111050189A CN 113722531 A CN113722531 A CN 113722531A
- Authority
- CN
- China
- Prior art keywords
- edge server
- data
- data storage
- mobile device
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/61—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/64—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a data storage method, a device, a system, equipment and a storage medium, and relates to the technical field of computer application, wherein the data storage method comprises the following steps: for each mobile device, determining recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process; for each edge server region, determining an evaluation value for storing data in the edge server region based on the recommended evaluation information and the probability; under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, solving an optimal data storage mode which can enable the total evaluation value to reach the maximum; and storing the data in the target edge server according to the optimal data storage mode. In this manner, the overhead of accessing data can be reduced.
Description
Technical Field
The present invention relates to the field of computer application technologies, and in particular, to a data storage method, apparatus, system, device, and storage medium.
Background
In the field of data access, a remote cloud computing center may store video data on an edge server near a mobile device in advance. Therefore, when watching a video, a user can directly access the nearby edge server to obtain the video data from the edge server, and the video data does not need to be downloaded from a remote cloud computing center, so that the network bandwidth is saved, the access speed of the user is increased, and the service experience of the user is improved.
When there are a plurality of edge servers, all video data may be stored in each edge server, and a user may obtain desired video data from any one edge server. However, the storage space of the edge servers is limited, and when the amount of video data is large, it is difficult or even impossible to store all the video data in each edge server. As such, in a scenario where a plurality of edge servers exist, how to store video data is a matter of great importance.
Disclosure of Invention
The embodiment of the invention aims to provide a data storage method, a data storage device, data storage equipment and a data storage medium, so as to reduce the overhead of data access. The specific technical scheme is as follows:
in a first aspect of the present invention, there is provided a data storage method, including:
for each mobile device, determining recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; determining the probability that the mobile equipment moves to the edge server area based on the position information of the mobile equipment in the moving process;
for each of the edge server regions, determining an evaluation value to store the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers;
solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions;
and storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
Optionally, the data includes a plurality of video data;
the determining an evaluation value to store the data in the edge server region based on the recommended evaluation information and the probability includes:
for each piece of video data, obtaining a sub-evaluation value corresponding to the video data based on the recommended evaluation information that recommends the video data to each mobile device and the probability that each mobile device moves to the edge server area respectively;
and summing the sub-evaluation values respectively corresponding to the video data to obtain the evaluation value of storing all the video data in the edge server area.
Optionally, the solving an optimal data storage manner that can maximize a total evaluation value under a condition that a storage space of data stored in the edge server region is not greater than a storage space of the edge server region includes:
sequentially traversing various data storage modes under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, and determining a total evaluation value corresponding to the data storage modes;
and selecting the maximum value in the total evaluation values corresponding to all the data storage modes, and taking the data storage mode corresponding to the maximum value as the optimal data storage mode.
Optionally, the solving an optimal data storage manner that can maximize a total evaluation value under a condition that a storage space of data stored in the edge server region is not greater than a storage space of the edge server region includes:
taking the storage space of the data stored in the edge server area not more than the storage space of the edge server area as a constraint condition, taking the total evaluation value reaching the maximum as an optimization target, and constructing a data storage model;
and solving the data storage model through a preset intelligent search algorithm to obtain the optimal data storage mode.
Optionally, the data includes a plurality of video data; the recommendation evaluation information is a recommendation score;
the determining recommendation evaluation information recommending the data to the mobile device based on the preference information of the user to the data to be stored in the mobile device comprises:
acquiring historical behavior information of the user;
determining preference information of the user on a plurality of video data respectively based on the historical behavior information;
and determining recommendation scores for recommending the video data to the mobile equipment through a preset video recommendation algorithm according to the preference information of the user on the plurality of video data respectively.
Optionally, the determining, based on the location information of the mobile device in the moving process, a probability that the mobile device moves to the edge server area includes:
acquiring the position information of the mobile equipment in the moving process;
fitting the moving track of the mobile equipment according to the position information of the mobile equipment in the moving process;
predicting a probability that the mobile device moves to an edge server region based on the movement trajectory.
In a second aspect of the present invention, there is also provided a data storage device comprising:
the recommendation module is used for determining recommendation evaluation information for recommending the data to the mobile equipment based on preference information of the user to-be-stored data in the mobile equipment aiming at each mobile equipment;
the track prediction module is used for determining the probability that the mobile equipment moves to the edge server area based on the position information of the mobile equipment in the moving process;
a determination module configured to determine, for each of the edge server regions, an evaluation value for storing the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers;
the solving module is used for solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions;
and the storage module is used for storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
Optionally, the data includes a plurality of video data;
the determining module is specifically configured to, for each piece of video data, obtain a sub-evaluation value corresponding to the video data based on the recommended evaluation information that recommends the video data to each mobile device and the probability that each mobile device moves to the edge server area, respectively; and summing the sub-evaluation values respectively corresponding to the video data to obtain the evaluation value of storing all the video data in the edge server area.
Optionally, the solving module is specifically configured to sequentially traverse various data storage manners under a condition that a storage space of data stored in the edge server region is not greater than the storage space of the edge server region, and determine a total evaluation value corresponding to the data storage manner; and selecting the maximum value in the total evaluation values corresponding to all the data storage modes, and taking the data storage mode corresponding to the maximum value as the optimal data storage mode.
Optionally, the solving module is specifically configured to use, as a constraint condition, that a storage space of the data stored in the edge server region is not greater than the storage space of the edge server region, and use, as an optimization target, a data storage model constructed by taking a total evaluation value that reaches a maximum value; and solving the data storage model through a preset intelligent search algorithm to obtain the optimal data storage mode.
Optionally, the data includes a plurality of video data; the recommendation evaluation information is a recommendation score;
the recommendation module is specifically used for acquiring historical behavior information of the user; determining preference information of the user on a plurality of video data respectively based on the historical behavior information; and determining recommendation scores for recommending the video data to the mobile equipment through a preset video recommendation algorithm according to the preference information of the user on the plurality of video data respectively.
Optionally, the trajectory prediction module is specifically configured to obtain position information of the mobile device in a moving process; fitting the moving track of the mobile equipment according to the position information of the mobile equipment in the moving process; predicting a probability that the mobile device moves to an edge server region based on the movement trajectory.
In yet another aspect of the present invention, there is also provided a data storage system, including: a plurality of mobile devices and a plurality of edge servers;
for each mobile device, the mobile device determines recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process, and sending the recommendation evaluation information and the probability to each edge server;
any edge server for determining, for each of the edge server regions, an evaluation value for storing the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers; solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions; and storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
In another aspect of the present invention, there is also provided a data storage device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of the first aspect when executing a program stored in the memory.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the method steps of any one of the above-mentioned first aspects.
In a further aspect of the present invention, there is also provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method steps of any one of the above first aspects.
According to the data storage method, the data storage device, the data storage system, the data storage equipment and the data storage medium, recommendation evaluation information for recommending data to the mobile equipment is determined based on preference information of the data to be stored by a user in the mobile equipment; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process; meanwhile, determining an evaluation value for storing the data in the edge server area based on the recommended evaluation information and the probability; and under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, solving an optimal data storage mode which can enable the sum of the evaluation values of all the edge server areas to be maximum, and storing the data in the target edge server according to the optimal data storage mode. When data is stored under the scene that a plurality of edge servers exist, the preference information of the user to the data in the mobile equipment and the mobility of the user in the mobile equipment are considered, the data is stored in the edge server included in the edge server area corresponding to the optimal data storage mode which can enable the total evaluation value to reach the maximum, the user accesses the data from the target edge server, and the data access overhead can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
FIG. 1 is a flow chart of a data storage method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating determining recommendation evaluation information for recommending data to a mobile device based on preference information of a user to-be-stored data in the mobile device according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a process of determining a probability that a mobile device moves to an edge server area based on location information of the mobile device during a moving process according to an embodiment of the present invention;
fig. 4 is a flowchart of calculating an evaluation value for storing data in an edge server region based on recommended evaluation information and probability in the embodiment of the present invention;
FIG. 5 is a flowchart illustrating an exemplary method for solving an optimal data storage scheme that maximizes a total evaluation value according to an embodiment of the present disclosure;
FIG. 6 is another flowchart illustrating a method for solving an optimal data storage manner that maximizes a total evaluation value according to an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a system for providing a data storage method according to an embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a data storage device according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a data storage device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
On one hand, since the storage space of the edge server is limited, a proper data storage mode needs to be established in a multi-edge server environment, which can be understood as a scene including a plurality of edge servers, so that the overhead of a user for accessing data is reduced. On the other hand, due to the mobility of the user, the mobile device often needs to be switched to different edge servers in the using process, the mobile device obtains data from different edge servers when being located at different positions, and the data stored in the edge servers need to be dynamically adjusted according to the position of the user to meet the requirements.
In order to reduce the overhead of accessing video data by users in a system (a system comprising a plurality of edge servers), on the basis of comprehensively considering user preference and mobility, the embodiment of the invention provides a data storage method, which can be specifically understood as a data storage method based on user recommendation and movement track prediction.
The following describes a data storage method provided by an embodiment of the present invention.
An embodiment of the present invention provides a data storage method, which may include:
for each mobile device, determining recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process;
for each edge server region, determining an evaluation value for storing data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server area comprises one or more edge servers;
under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, solving an optimal data storage mode which can enable the total evaluation value to reach the maximum; the total evaluation value is the sum of the evaluation values of all the edge server areas;
and storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area corresponding to the data storage.
In the embodiment of the invention, recommendation evaluation information for recommending data to the mobile equipment is determined based on preference information of the data to be stored by a user in the mobile equipment; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process; meanwhile, determining an evaluation value for storing the data in the edge server area based on the recommended evaluation information and the probability; and under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, solving an optimal data storage mode which can enable the sum of the evaluation values of all the edge server areas to be maximum, and storing the data in the target edge server according to the optimal data storage mode. When data is stored under the scene that a plurality of edge servers exist, the preference information of the user to the data in the mobile equipment and the mobility of the user in the mobile equipment are considered, the data is stored in the edge server included in the edge server area corresponding to the optimal data storage mode which can enable the total evaluation value to reach the maximum, the user accesses the data from the target edge server, and the data access overhead can be reduced.
Fig. 1 is a flowchart of a data storage method according to an embodiment of the present invention. Referring to fig. 1, an embodiment of the present invention provides a data storage method, which may include:
s101, for each mobile device, determining recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; and determining the probability that the mobile device moves to the edge server area based on the position information of the mobile device in the moving process.
The recommendation evaluation information may be understood as a degree of matching of the characterization data with the preference of the user. In one implementation, the recommendation score may be a score of the recommendation. A higher recommendation score indicates a higher degree of matching of the data to the user's preferences.
In one implementation, the data includes a plurality of video data; the recommendation evaluation information is a recommendation score.
In S101, based on preference information of the user in the mobile device for data to be stored, determining recommendation evaluation information for recommending data to the mobile device may include, as shown in fig. 2:
s1011, obtaining the historical behavior information of the user.
The historical behavior information may include information corresponding to access behaviors of the user at historical times. For example, a user watches a video identification, a content abbreviation, etc. of a video.
S1012, based on the historical behavior information, determining preference information of the user for each of the plurality of video data.
And S1013, determining recommendation scores for recommending the video data to the mobile equipment through a preset video recommendation algorithm according to the preference information of the user on the plurality of video data respectively.
In an implementation mode, a video list can be recalled according to characteristics of a user and a scene through a preset video recommendation algorithm to obtain a candidate set which the user may be interested in. The recall algorithm may include a variety of algorithms such as content matching based recall, collaborative filtering based recall, deep learning based recall, and the like. After the candidate set is recalled, the score of the user on the video data can be calculated through the ranking model, and the score is the obtained recommendation score. In addition, video recommendation can be performed on the user according to the scores of the video data.
In the multi-edge server environment, a user may move to other areas to watch videos, the change of the position of the user enables the user to access data provided by different edge servers, in the process of storing the data, in addition to considering preference information of the user to the data, the embodiment of the invention also considers the mobility of the user, and the data stored in each edge server in the embodiment of the invention can be dynamically adjusted according to the probability of moving to the current service range, which is predicted by the movement track of the user.
In an implementation manner, the determining, in S101, a probability that the mobile device moves to the edge server area based on the location information of the mobile device during the moving process, as shown in fig. 3, may include:
and S1014, acquiring the position information of the mobile equipment in the moving process.
And S1015, fitting the moving track of the mobile device according to the position information of the mobile device in the moving process.
In one implementation, a system including a plurality of edge servers may be regionalized. One edge server area may include one or more edge servers. The mobile device may access an edge server within the area to which it belongs nearby to obtain the data. An edge server region can be understood as a trace point. The position information, namely the track points, namely the edge server area where the mobile device is located in the moving process predicts the track points which the mobile device may move to subsequently based on the moving track of the user.
The position information of the mobile device in the moving process can be sampled, the area to which each edge server belongs can be used as a single track point, so that track data of the mobile device is obtained, and the track data can be understood as the combination of a plurality of pieces of position information.
As such, the movement trajectory of the mobile device may be fitted based on the trajectory data. Any fitting method, such as a least squares curve fitting method, and the like, may be employed in the embodiments of the present invention.
And S1016, predicting the probability of the mobile device moving to the edge server area based on the moving track.
The trajectory prediction algorithm may include a markov chain-based prediction algorithm, a kalman filter-based algorithm, and a neural network-based trajectory prediction algorithm, among others.
The user is in the moving process, and the position information of the mobile device corresponding to the user is changed. In the embodiment of the invention, the position information of the mobile equipment in the moving process, particularly the characteristics of the position information of the mobile equipment in the historical moving process, can be mined and analyzed, and if the user moving track can be fitted according to the position information of the mobile equipment in the moving process, the position to which the mobile equipment is likely to move subsequently can be predicted based on the user moving track.
S102, for each edge server region, determines an evaluation value for storing data in the edge server region based on the recommended evaluation information and the probability.
Wherein the edge server area includes one or more edge servers. The number of edge servers included in each edge server zone may be the same or different.
In one implementation, the evaluation value may be represented by a deployment score. And obtaining the evaluation value of the data stored in the edge server by comprehensively considering the recommended evaluation information and the probability.
S103, under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, an optimal data storage mode capable of enabling the total evaluation value to be maximum is solved.
The total evaluation value is the sum of the evaluation values of all the edge server regions.
It is simply understood that the data storage manner includes which edge server area each data is stored in. For example, data 1 may correspond to the edge server area 1, data 2 to the edge server area 2, and data 3 to the edge server area 3, i.e., it is understood that data 1 is stored in the edge server area 1, data 2 is stored in the edge server area 2, and data 3 is stored in the edge server area 3.
The storage space of each edge server is limited, and the storage space of the edge server area is the sum of the storage spaces of one or more edge servers constituting the edge server area, the storage space of the edge server area is also limited, so that the storage space of the data stored in the edge server area cannot be larger than the storage space of the edge server area itself.
Solving the optimal data storage mode which can maximize the total evaluation value can be understood as an optimization problem, and the embodiment of the invention can adopt a mode which can realize optimization to solve the optimal data storage mode.
And S104, storing the data in the target edge server according to the optimal data storage mode.
The target edge server is an edge server included in an edge server area where data is to be stored.
And scheduling and deploying the data according to the optimal data storage mode. It can also be understood that the data in the edge server is adjusted according to the optimal data storage manner.
It is understood that an edge server area corresponds to a service range, and a mobile device in the service range corresponding to the edge server area can access data in any edge server included in the edge server area.
In the embodiment of the invention, recommendation evaluation information for recommending data to the mobile equipment is determined based on preference information of the data to be stored by a user in the mobile equipment; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process; meanwhile, based on the recommended evaluation information and the probability, calculating an evaluation value for storing the data in the edge server area; under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, solving an optimal data storage mode which can enable the total evaluation value to reach the maximum; the total evaluation value is the sum of the evaluation values of all the edge server regions, and thus, data is stored in the target edge server in an optimal data storage manner. When data is stored under the scene that a plurality of edge servers exist, the preference information of the user to the data in the mobile equipment and the mobility of the user in the mobile equipment are considered, the data is stored in the edge server included in the edge server area corresponding to the optimal data storage mode which can enable the total evaluation value to reach the maximum, the user accesses the data from the target edge server, and the data access overhead can be reduced. The method and the device can reduce the total overhead of accessing data in the whole system under the environment of the multi-edge server, specifically can reduce network delay, improve service quality and improve user experience.
The data storage method provided by the embodiment of the invention can be applied to a server, and particularly can be a server of a cloud computing center. Specifically, steps S101 to S104 are all performed by the server.
Alternatively, the data storage method provided by the embodiment of the invention can also be applied to a data storage system comprising the server and the mobile device. Specifically, S101 is performed by the mobile device in the data storage system, that is, the mobile device calculates the video recommendation information and the probability and sends the obtained video recommendation information and probability to the server in the data storage system, and the server performs S102 to S104.
In an alternative embodiment, an embodiment of the present invention provides a data storage system, including: a plurality of mobile devices and a plurality of edge servers.
For each mobile device, the mobile device determines recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; and determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process, and sending the recommendation evaluation information and the probability to each edge server.
Any edge server for determining, for each of the edge server regions, an evaluation value for storing the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers; solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions; and storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
That is, each mobile device determines recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; and determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process, and sending the recommendation evaluation information and the probability to each edge server.
Each edge server receives the recommended evaluation information and the probability sent by each mobile device, and for any edge server, the edge server can calculate the evaluation value of storing the data in the edge server area based on the recommended evaluation information and the probability sent by each mobile device, determine the optimal data storage mode according to the evaluation value, and update the data of the edge server based on the optimal data storage mode, namely update the video data stored in the edge server. For example, the optimal data storage manner may describe an edge server area where each data is to be stored, and if an edge server area included in the optimal data storage manner determined by an edge server includes the edge server, the edge server may store the data to be stored to the edge server according to the determined optimal storage manner.
In an alternative embodiment, the data comprises a plurality of video data.
S102: determining an evaluation value for storing data in the edge server region based on the recommended evaluation information and the probability, as shown in fig. 4, may include:
and S1021, aiming at each piece of video data, obtaining a sub-evaluation value corresponding to the video data based on the recommended evaluation information for recommending the video data to each mobile device and the probability that each mobile device moves to the edge server area.
S1022, the sub-evaluation values respectively corresponding to the video data are summed up to obtain an evaluation value for storing all the video data in the edge server region.
The evaluation value corresponding to each edge server region can be obtained for each edge server region.
In an alternative embodiment, S103: under the condition that the storage space of the data stored in the edge server area is not larger than the storage space of the edge server area, solving an optimal data storage manner that can maximize the total evaluation value may include, as shown in fig. 5:
s501, sequentially traversing various data storage modes under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, and determining a total evaluation value corresponding to the data storage modes;
and S502, selecting the maximum value in the total evaluation values corresponding to all the data storage modes, and taking the data storage mode corresponding to the maximum value as the optimal data storage mode.
Namely, the optimal data storage mode is solved in a traversal mode.
The traversal mode searches all possible data storage modes, and selects the data storage mode corresponding to the maximum total evaluation value from all the data storage modes as the optimal data storage mode, so that the accuracy of the traversal mode is higher, the accuracy of the obtained optimal data storage mode is higher, and the optimal data storage mode is more matched with the data preference of the user in the multi-edge server environment and the mobility of the user.
However, when the solution space is large, that is, when the possibility of the data storage manner is high, for example, when the data amount and the number of the edge servers are both high, the calculation overhead for traversing all the data storage manners is high. In order to reduce the calculation cost, the optimal storage mode can be solved through an intelligent search algorithm.
In another alternative embodiment, S103: under the condition that the storage space of the data stored in the edge server area is not larger than the storage space of the edge server area, solving an optimal data storage manner that can maximize the total evaluation value may include, as shown in fig. 6:
s601, taking the storage space of the data stored in the edge server area not more than the storage space of the edge server area as a constraint condition, taking the total evaluation value reaching the maximum as an optimization target, and constructing a data storage model.
And constructing a data storage model of all edge servers in the system according to recommendation evaluation information (such as recommendation scores) for recommending data to the mobile device, the probability of moving the mobile device to each edge server area and the limitation of the storage space size of the edge servers, wherein the data storage model can also be understood as a video storage data total score model. And solving the optimal solution of the model, wherein the optimal solution is the optimal storage mode.
And S602, solving the data storage model through a preset intelligent search algorithm to obtain an optimal data storage mode.
The preset intelligent search method may include heuristic search algorithms such as a genetic algorithm, an ant colony algorithm, a particle swarm algorithm, and the like.
The approximate optimal solution can be obtained by using smaller calculation cost through an intelligent search algorithm.
And solving the video data deployment model by taking the particle swarm algorithm as an example, namely obtaining an optimal data storage mode. The particle swarm algorithm is called particle swarmThe basic principle of the Optimization algorithm (PSO) is to find the optimal solution by iteration by initializing a population of random particles. The solution of each optimization problem is called a "particle", and each particle has a speed to determine the distance and direction of its movement, and the candidate solution is evaluated by a fitness function. Let m be the number of edge servers in a region, which can be the number of dimensions of a particle, and v be the velocity of the particle ii＝(vi1,vi2,vi3,...,vim) The position of the particle i is xi＝(xi1,xi2,xi3,...,xim) The optimum position of the particle i is pbesti＝(pi1,pi2,...,pim) The optimal position of the particles in the population is gbest ═ g (gbest)1,gbest2,...,gbestm). The number of initialization particles is n, and each particle is set with a random initial velocity and position. Ith dimension velocity v of k iteration particle iij kThe update formula of (c) can be expressed as:
vij k＝w*vij k-1+c1*r1*(pbestij-xij k-1)+c2*r2*(gbestj-xij k-1)
where w is the inertial weight, c1And c2Represents the constant of acceleration, r1And r2Denotes a random parameter, vij k-1For the (k-1) th iteration particle i, the (j) th dimension velocity, pbestijFor the best position of the i-th dimension of the particle, gbestjRepresenting the optimal position in dimension j. The position update formula of the particle is:
xij k＝xij k-1+vij k-1
wherein x isij kFor the location of the jth dimension, x, of the kth iterative particle iij k-1Is the position of the jth dimension of the (k-1) th iteration particle i.
Calculating the fitness value f of the particle i according to the fitness functioniAnd comparing the fitness value with the individual's optimal position if appropriateIf the previous fitness value is more optimal, the pbest is updatediThe value of (c). The fitness value is also compared with the population optimal position gbest and updated. And after iteration, stopping iteration if the algorithm meets the condition, wherein the gbest is the optimal solution of the video data deployment model.
The following describes a data storage method provided by an embodiment of the present invention with reference to a specific embodiment.
The data storage method provided by the embodiment of the invention is applied to a multi-edge server environment, and can also be understood as a system comprising a plurality of edge servers.
The whole system comprises m edge service points, and E can be used as { E ═ E1,e2,e3,...,emDenotes that the storage space size of the ith edge server is vi. The system contains h mobile devices in total, and C can be used as ═ C1,c2,c3,...,chAnd (c) represents.
The system can be divided into a plurality of areas according to the network service range provided by the edge server, and the mobile devices in each area can access the video data stored in the edge server of the area. The video data stored in the edge server may be represented by D ═ D1,d2,d3，...，dlDenotes, video data dkThe size of the occupied storage space is zk. For simplicity of description, each edge server is divided into one area, that is, one edge server area includes one edge server.
Calculating a video recommendation score: for jth mobile device cjAccording to the preference of the user to the video data, the video data d can be calculated by a video recommendation algorithmkRecommending to a mobile device cjIs classified as scorek j。
Predicting the probability according to the movement track: the position information of the mobile device in the moving process can be sampled, and the area to which each edge server belongs can be used as a single track point, so that the track data of the mobile device can be obtained. Building a rail from collected trajectory dataTrace prediction model, calculating to obtain mobile device cjReach edge Server eiProbability p of belonging areaj i. The mobile device may access an edge server within the area to which it belongs nearby to obtain video data.
Constructing a data storage model: in particular the data storage model may be understood as a video data storage model. Set up video d in systemjHas a data storage mode of xikCan pass through xik1 indicates video data dkStored in an edge server eiIn (1). At eiAccording to the calculation to obtain the mobile equipment cjMedium video data dkIs recommended score ofk jAnd cjMove to edge Server eiProbability p ofj iGet the edge server eiThe evaluation value of video data storage, specifically, the video storage score g can be understood asiComprises the following steps:
where l denotes the amount of video data.
In addition, edge server eiThe video data stored in (1) needs to satisfy the limitation of the storage space of the edge server itself, and the usage formula can be expressed as:
after the video storage score of each edge server is obtained, the total score of all edge servers in the system can be calculated as:
the video data storage model aims to determine a video data storage mode x under the limit condition of the storage space of an edge serverikSo thatThe total score of video data storage in the system is the largest.
Solving a video data storage model: as can be seen from the formula of the total score, the video deployment problem can be modeled as an integer programming problem. The model can be solved by using a conventional method (a traversal mode) or an intelligent search algorithm to obtain an optimal video data storage mode in the system. And storing the video data on the corresponding edge server according to the optimal video data storage mode.
In the embodiment of the present invention, all the steps may be completed by a server of the cloud computing center.
Or, the steps of calculating the video recommendation score and predicting the probability according to the movement track may be performed by the mobile device, that is, the mobile device calculates the video recommendation score and predicts the probability according to the movement track, and sends the obtained video recommendation score and probability to a server of the cloud computing center, and the server constructs a data storage model and solves a video data storage model according to the video recommendation score and probability.
In an implementation manner, the system to which the data storage method provided by the embodiment of the present invention is applied may include a cloud computing center, a mobile device, and an edge server. As shown in fig. 7, the cloud computing center includes a deployment decision module. The mobile device comprises a video recommending module, a position sampling module, a track predicting module and a network communication module. The edge server comprises a network communication module and a video storage module.
The video recommendation module is used for calculating a video recommendation score for recommending videos to each mobile device according to a video recommendation algorithm.
And the position sampling module is used for sampling the position information of the mobile equipment in the moving process of the mobile equipment to obtain the moving track data of the mobile equipment.
And the track prediction module is used for fitting the moving track according to the moving track data of the mobile equipment, constructing the moving track prediction module according to the moving track and predicting the probability of the mobile equipment reaching the edge server.
And the network communication module is used for network communication between the mobile equipment and the edge server, and the mobile equipment accesses the video data stored in the edge server through the network communication module.
And the video storage module is used for storing the video data in the edge server.
And the deployment decision module is positioned in the cloud computing center and used for computing the total score of all the edge servers in the system through the video recommendation score of each edge server and the probability corresponding to the mobile equipment. And constructing a video data storage module and solving to obtain an optimal video data storage mode, and storing the video data according to the optimal video data storage mode.
In the embodiment of the invention, the preference of the user to the video data and the mobility of the user are comprehensively considered, the video data storage model is constructed under the limiting condition of the storage space of the edge server, and the optimal video data storage mode is obtained by solving. The optimal video data storage mode can give full play to the advantages of edge calculation, reduce the network overhead of accessing videos and improve the use experience of users. The method comprises the steps of storing video data by using an edge server, constructing a video data storage model according to video recommendation scores and the probability that the mobile equipment moves to the edge server, which is obtained by predicting the movement track, solving an optimal video data storage mode obtained by the video data storage model, storing each video data in the edge server according to the video data storage mode, and enabling a user to access the video data in the corresponding edge server to watch videos.
Corresponding to the data storage method provided in the foregoing embodiment, an embodiment of the present invention further provides a data storage device, as shown in fig. 8, which may include:
a recommending module 801, configured to determine, for each mobile device, recommendation evaluation information for recommending data to the mobile device based on preference information of the user to-be-stored data in the mobile device;
a trajectory prediction module 802, configured to determine, based on location information of the mobile device in a moving process, a probability that the mobile device moves to the edge server area;
a determining module 803, configured to determine, for each edge server region, an evaluation value for storing data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server area comprises one or more edge servers;
a solving module 804, configured to solve an optimal data storage manner that can maximize a total evaluation value under a condition that a storage space of data stored in the edge server region is not greater than a storage space of the edge server region; the total evaluation value is the sum of the evaluation values of all the edge server areas;
the storage module 805 is configured to store the data in the target edge server according to the optimal data storage manner, where the target edge server is an edge server included in an edge server area where the data is to be stored.
Optionally, the data comprises a plurality of video data;
the determining module 803 is specifically configured to, for each piece of video data, obtain a sub-evaluation value corresponding to the video data based on recommended evaluation information that is recommended to each mobile device for the video data and a probability that each mobile device moves to an edge server area; and summing the sub-evaluation values respectively corresponding to the video data to obtain the evaluation value for storing all the video data in the edge server area.
Optionally, the solving module 804 is specifically configured to sequentially traverse various data storage manners under the condition that a storage space of data stored in the edge server area is not greater than a storage space of the edge server area, and determine a total evaluation value corresponding to the data storage manner; and selecting the maximum value in the total evaluation values corresponding to all the data storage modes, and taking the data storage mode corresponding to the maximum value as the optimal data storage mode.
Optionally, the solving module 804 is specifically configured to use, as a constraint condition, that a storage space of the data stored in the edge server region is not greater than a storage space of the edge server region, and use, as an optimization target, that the total evaluation value reaches a maximum value, to construct a data storage model; and solving the data storage model through a preset intelligent search algorithm to obtain an optimal data storage mode.
Optionally, the data comprises a plurality of video data; recommending evaluation information as a recommendation score;
a recommending module 801, configured to obtain historical behavior information of a user; determining preference information of a user on a plurality of video data respectively based on the historical behavior information; and determining recommendation scores for recommending the video data to the mobile equipment by a preset video recommendation algorithm according to the preference information of the user on the plurality of video data.
Optionally, the trajectory prediction module 802 is specifically configured to obtain location information of the mobile device in the moving process; fitting the moving track of the mobile equipment according to the position information of the mobile equipment in the moving process; based on the movement trajectory, a probability of the mobile device moving to the edge server region is predicted.
The embodiment of the present invention further provides a data storage device, as shown in fig. 9, which includes a processor 901, a communication interface 902, a memory 903 and a communication bus 904, where the processor 901, the communication interface 902, and the memory 903 complete mutual communication through the communication bus 904.
A memory 903 for storing computer programs;
the processor 901 is configured to implement the method steps of the data storage method in the above embodiments when executing the program stored in the memory 903.
The communication bus mentioned in the above data storage device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the data storage device and other devices.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In a further embodiment of the present invention, a computer-readable storage medium is further provided, which has stored therein instructions, which, when run on a computer, cause the computer to perform the method steps of the data storage method in the above-mentioned embodiment.
In a further embodiment provided by the present invention, there is also provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method steps of the data storage method of the above embodiment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus, the device, the computer-readable storage medium, and the computer program product embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and in relation to the description, reference may be made to some of the description of the method embodiments.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method of storing data, comprising:
for each mobile device, determining recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; determining the probability that the mobile equipment moves to the edge server area based on the position information of the mobile equipment in the moving process;
for each of the edge server regions, determining an evaluation value to store the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers;
solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions;
and storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
2. The method of claim 1, wherein the data comprises a plurality of video data;
the determining an evaluation value to store the data in the edge server region based on the recommended evaluation information and the probability includes:
for each piece of video data, obtaining a sub-evaluation value corresponding to the video data based on the recommended evaluation information that recommends the video data to each mobile device and the probability that each mobile device moves to the edge server area respectively;
and summing the sub-evaluation values respectively corresponding to the video data to obtain the evaluation value of storing all the video data in the edge server area.
3. The method according to claim 1, wherein the solving of the optimal data storage manner capable of maximizing the total evaluation value under the condition that the storage space of the data stored in the edge server region is not larger than the storage space of the edge server region comprises:
sequentially traversing various data storage modes under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area, and determining a total evaluation value corresponding to the data storage modes;
and selecting the maximum value in the total evaluation values corresponding to all the data storage modes, and taking the data storage mode corresponding to the maximum value as the optimal data storage mode.
4. The method according to claim 1, wherein the solving of the optimal data storage manner capable of maximizing the total evaluation value under the condition that the storage space of the data stored in the edge server region is not larger than the storage space of the edge server region comprises:
taking the storage space of the data stored in the edge server area not more than the storage space of the edge server area as a constraint condition, taking the total evaluation value reaching the maximum as an optimization target, and constructing a data storage model;
and solving the data storage model through a preset intelligent search algorithm to obtain the optimal data storage mode.
5. The method of claim 1, wherein the data comprises a plurality of video data; the recommendation evaluation information is a recommendation score;
the determining recommendation evaluation information recommending the data to the mobile device based on the preference information of the user to the data to be stored in the mobile device comprises:
acquiring historical behavior information of the user;
determining preference information of the user on a plurality of video data respectively based on the historical behavior information;
and determining recommendation scores for recommending the video data to the mobile equipment through a preset video recommendation algorithm according to the preference information of the user on the plurality of video data respectively.
6. The method of claim 1, wherein determining the probability of the mobile device moving to an edge server area based on the location information of the mobile device during the movement comprises:
acquiring the position information of the mobile equipment in the moving process;
fitting the moving track of the mobile equipment according to the position information of the mobile equipment in the moving process;
predicting a probability that the mobile device moves to an edge server region based on the movement trajectory.
7. A data storage device, comprising:
the recommendation module is used for determining recommendation evaluation information for recommending the data to the mobile equipment based on preference information of the user to-be-stored data in the mobile equipment aiming at each mobile equipment;
the track prediction module is used for determining the probability that the mobile equipment moves to the edge server area based on the position information of the mobile equipment in the moving process;
a determination module configured to determine, for each of the edge server regions, an evaluation value for storing the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers;
the solving module is used for solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions;
and the storage module is used for storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
8. A data storage system, comprising: a plurality of mobile devices and a plurality of edge servers;
for each mobile device, the mobile device determines recommendation evaluation information for recommending the data to the mobile device based on preference information of the user to-be-stored data in the mobile device; determining the probability of the mobile equipment moving to the edge server area based on the position information of the mobile equipment in the moving process, and sending the recommendation evaluation information and the probability to each edge server;
any edge server for determining, for each of the edge server regions, an evaluation value for storing the data in the edge server region based on the recommended evaluation information and the probability; wherein the edge server region comprises one or more edge servers; solving an optimal data storage mode which can enable a total evaluation value to reach the maximum under the condition that the storage space of the data stored in the edge server area is not larger than that of the edge server area; the total evaluation value is the sum of the evaluation values of all the edge server regions; and storing the data in a target edge server according to the optimal data storage mode, wherein the target edge server is an edge server included in an edge server area where the data are to be stored.
9. The data storage device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-6 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111050189.1A CN113722531A (en) | 2021-09-08 | 2021-09-08 | Data storage method, device, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111050189.1A CN113722531A (en) | 2021-09-08 | 2021-09-08 | Data storage method, device, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113722531A true CN113722531A (en) | 2021-11-30 |
Family
ID=78682619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111050189.1A Pending CN113722531A (en) | 2021-09-08 | 2021-09-08 | Data storage method, device, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113722531A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121512A (en) * | 2017-12-22 | 2018-06-05 | 苏州大学 | A kind of edge calculations services cache method, system, device and readable storage medium storing program for executing |
| CN110213627A (en) * | 2019-04-23 | 2019-09-06 | 武汉理工大学 | Flow medium buffer distributor and its working method based on multiple cell user mobility |
| CN112749010A (en) * | 2020-12-31 | 2021-05-04 | 中南大学 | Edge calculation task allocation method for fusion recommendation system |
-
2021
- 2021-09-08 CN CN202111050189.1A patent/CN113722531A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121512A (en) * | 2017-12-22 | 2018-06-05 | 苏州大学 | A kind of edge calculations services cache method, system, device and readable storage medium storing program for executing |
| CN110213627A (en) * | 2019-04-23 | 2019-09-06 | 武汉理工大学 | Flow medium buffer distributor and its working method based on multiple cell user mobility |
| CN112749010A (en) * | 2020-12-31 | 2021-05-04 | 中南大学 | Edge calculation task allocation method for fusion recommendation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10959113B2 (en) | Automatic performance monitoring and health check of learning based wireless optimization framework | |
| US11499831B2 (en) | Effective indoor localization using geo-magnetic field | |
| US20130346351A1 (en) | Assessing accuracy of trained predictive models | |
| CN109982104B (en) | Motion-aware video prefetching and cache replacement decision method in motion edge calculation | |
| CN107210955B (en) | System, device and method for distributed content interest prediction and content discovery | |
| CN113574554A (en) | Operating a supply chain using a causal model | |
| AU2012250923A1 (en) | Predictive analytical modeling accuracy assessment | |
| CN106250381B (en) | System and method for determining column layout of tabular storage | |
| JP2007317068A (en) | Recommending device and recommending system | |
| KR20190143072A (en) | Method and system for adaptive bitrate publishing | |
| CN115767596A (en) | Edge collaborative caching method for user-oriented mobility and preference in edge calculation | |
| Wang et al. | Edge intelligence in motion: Mobility-aware dynamic DNN inference service migration with downtime in mobile edge computing | |
| Liu et al. | Deep learning video analytics through online learning based edge computing | |
| Nine et al. | Big data transfer optimization based on offline knowledge discovery and adaptive sampling | |
| US11556828B2 (en) | Systems and methods for selecting content using a multiple objective, multi-arm bandit model | |
| CN113722531A (en) | Data storage method, device, system, equipment and storage medium | |
| CN111506104B (en) | Method and device for planning position of unmanned aerial vehicle | |
| US11625599B2 (en) | Ranking user comments on media using reinforcement learning optimizing for session dwell time | |
| Zhang et al. | Personalized quality centric service recommendation | |
| US20160234279A1 (en) | Site-based server selection | |
| Qu et al. | Optimizing Dynamic Cache Allocation in Vehicular Edge Networks: A Method Combining Multi-Source Data Prediction and Deep Reinforcement Learning | |
| Sakr et al. | Meta-reinforcement learning for edge caching in vehicular networks | |
| Tao et al. | Content popularity prediction in fog-rans: A bayesian learning approach | |
| CN116010041A (en) | Method, apparatus and computer program product for scheduling navigation resources | |
| Huang et al. | Multi-Objective Deep Reinforcement Learning for Computation Offloading and Trajectory Control in UAV-Base Station Assisted MEC |
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 |