A cache method, system, device and storage medium of an edge server

Abstract

The application discloses a cache method, system and device of an edge server and a storage medium, and particularly relates to the technical field of data centers, and is applied to the edge server. The method comprises the following steps: acquiring the commuting characteristics of a user according to a data access request of the user; determining the personal hotspot data, the commuting path and the commuting time information of the user according to the commuting characteristics; determining the edge servers sequentially passed through by the user and the time periods in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersing and caching the personal hotspot data to the edge servers in the corresponding time periods according to the time periods in the coverage range of the edge servers. The personal hotspot data and the group hotspot data of the user are cached by the edge server, the data access delay of the user is reduced, and the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data centers, in particular to a cache method, system, device and storage medium of an edge server. BACKGROUND

[0002] At present, with the development of urban traffic, subway travel has become an important tool for urban travel due to its convenience and speed. However, due to the particularity of the construction of the subway, the subway is mainly located below the ground surface, which will cause the communication signal of the mobile terminal used by the user to be poor, which will cause the user to have a high data access delay when using the mobile terminal during subway travel, which will cause the user to have a very poor use experience. SUMMARY

[0003] Therefore, the present application provides a cache method, system, device and storage medium of an edge server, which aims to cache the personal hotspot data and group hotspot data of users through the edge server, thereby reducing the data access delay and improving the user experience.

[0004] In order to achieve the above purpose, the first aspect of the embodiment of the present application provides a cache method of an edge server, applied to an edge server, the method comprising:

[0005] According to the data access request of the user, the commuting characteristics corresponding to the user are obtained;

[0006] According to the application usage characteristics in the commuting characteristics, the personal hotspot data corresponding to the user is determined;

[0007] According to the space characteristics, time characteristics and spatial position of the edge server receiving the data access request in the commuting characteristics, the commuting path and commuting time information of the user are determined;

[0008] According to the commuting path and the commuting time information, the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers are determined;

[0009] According to the time period in which the user is in the coverage range of the edge servers, the personal hotspot data is dispersed and cached to the edge servers in the corresponding time period.

[0010] Optionally, according to the space characteristics, time characteristics and spatial position of the edge server receiving the data access request in the commuting characteristics, the commuting path and commuting time information of the user are determined, comprising:

[0011] comparing each historical commuting path in the spatial features with a spatial position of an edge server receiving the data access request, determining a historical commuting path in the each historical commuting path matching the spatial position as a commuting path of the user;

[0012] determining, according to each target time of a day when the user reaches a starting station in the commuting path and the time features, a current time as a starting time of the user commuting;

[0013] determining, according to the starting time and a travel time interval between each two stations in the time features, a time when the user reaches each station in the commuting path, to obtain commuting time information of the user.

[0014] Optionally, according to the commuting path and the commuting time information, determining each edge server to be sequentially passed through by the user and a time period when the user is in a coverage range of the each edge server, comprises:

[0015] determining, according to each station passed through by the commuting path and a coverage range of each edge server, each edge server to be sequentially passed through by the user and a station in the commuting path covered by the each edge server to be sequentially passed through by the user;

[0016] determining, according to the time when the user reaches each station in the commuting path and the station in the commuting path covered by the each edge server, the time period when the user is in the coverage range of the each edge server.

[0017] Optionally, according to the time period when the user is in the coverage range of the each edge server, dispersing the personal hotspot data to the each edge server in a corresponding time period, comprises:

[0018] determining, according to the time period when the user is in the coverage range of the each edge server, a time length when the user is in the coverage range of the each edge server;

[0019] determining, according to the time length when the user is in the coverage range of the each edge server, a target cache amount of the personal hotspot data to be cached in the each edge server;

[0020] determining, according to the time period when the user is in the coverage range of the each edge server, a target time period of the personal hotspot data to be cached in the each edge server respectively;

[0021] According to the determined target cache amount and target time period of each edge server, cache the personal hotspot data corresponding to the target cache amount in the target time period of each edge server.

[0022] Optionally, according to the time period when the user is in the coverage range of each edge server, the personal hotspot data is cached in the corresponding time period and distributed to each edge server, including:

[0023] According to the commuting path and the historical data access amount of the user passing through the coverage range of each edge server along the commuting path, determine the target cache amount of the personal hotspot data cached to each edge server;

[0024] According to the time period when the user is in the coverage range of each edge server, determine the target time period of caching the personal hotspot data in each edge server respectively;

[0025] According to the determined target cache amount and target time period of each edge server, cache the personal hotspot data corresponding to the target cache amount in the target time period of each edge server.

[0026] Optionally, the method further comprises:

[0027] Determine whether the user's data access request is received in the corresponding target time period of each edge server;

[0028] In the case that the target edge server corresponding to the target time period does not receive the user's data access request in the target time period corresponding to itself among the edge servers, determine whether other edge servers receive the user's data access request in the target time period corresponding to the target edge server;

[0029] In the case that other edge servers receive the user's data access request in the target time period corresponding to the target edge server, update the commuting path and commuting time information of the user according to the spatial feature, the time feature in the commuting feature and the spatial position of the other edge servers.

[0030] Optionally, in the case that other edge servers receive the user's data access request in the target time period corresponding to the target edge server, update the commuting path and commuting time information of the user according to the spatial feature, the time feature in the commuting feature and the spatial position of the other edge servers, including:

[0031] In a case where there is another edge server receiving the data access request of the user in a target time period corresponding to a target edge server, determining whether the other edge server is a first edge server in the edge servers in the sequential route;

[0032] In a case where the other edge server is the first edge server in the edge servers in the sequential route, updating the commuting time information of the user according to the spatial position of the other edge server and the spatial feature and the time feature in the commuting feature.

[0033] Optionally, the method further comprises:

[0034] Determining a data access amount;

[0035] In a case where the data access amount exceeds a first threshold value, determining respective request data corresponding to all data access requests; and determining target request data exceeding a preset proportion in the request data according to the request data.

[0036] Determining the target request data as group hotspot data, and obtaining a data amount of the group hotspot data.

[0037] According to the data amount of the group hotspot data and the determined personal hotspot data of each user, respectively performing caching of the group hotspot data and the personal hotspot data of each user in the edge servers.

[0038] Optionally, according to the data amount of the group hotspot data and the determined personal hotspot data of each user, respectively performing caching of the group hotspot data and the personal hotspot data of each user in the edge servers, comprises:

[0039] In a case where the data amount of the group hotspot data is in a first preset range, dividing each edge server into a first preset space and a second preset space;

[0040] Performing caching of the group hotspot data through the first preset space of each edge server, and performing caching of the personal hotspot data of each user through the second preset space of each edge server;

[0041] In a case where the data amount of the group hotspot data is in a second preset range, dividing each edge server into a third preset space and a fourth preset space;

[0042] Performing caching of the group hotspot data through the third preset space of each edge server, and performing caching of the personal hotspot data of a user with the highest priority among the users through the fourth preset space of each edge server.

[0043] In a case where the data amount of the group hotspot data is in a third preset range, cache the group hotspot data by all edge servers.

[0044] Optionally, the method further comprises:

[0045] determining whether each edge server of the sequential path receives the data access request of the user;

[0046] in a case where the next edge server of the sequential path receives the data access request of the user, releasing the personal hotspot data cached for the user in the previous edge server of the next edge server.

[0047] Optionally, the method further comprises:

[0048] determining whether the current time is in a rush hour period;

[0049] in a case where the current time is in the rush hour period, determining first group hotspot data according to the respective personal hotspot data of all users;

[0050] cache the first group hotspot data by all edge servers.

[0051] Optionally, the method further comprises:

[0052] determining personal hotspot data of a highest priority user;

[0053] comparing the personal hotspot data of the highest priority user with the first group hotspot data;

[0054] in a case where the personal hotspot data of the highest priority user does not belong to the first group hotspot data, cache the personal hotspot data of the highest priority user by an edge server.

[0055] A second aspect of the embodiments of the present application provides a cache system of an edge server, the system comprising:

[0056] a rush feature acquisition module configured to acquire a rush feature corresponding to a user according to a data access request of the user;

[0057] a personal hotspot data determination module configured to determine personal hotspot data corresponding to the user according to an application usage feature in the rush feature;

[0058] The method comprises the following steps: determining the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request; determining the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersively caching the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0059] The method comprises the following steps: determining the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request; determining the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersively caching the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0060] The method comprises the following steps: determining the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request; determining the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersively caching the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0061] The method comprises the following steps: determining the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request; determining the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersively caching the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0062] The method comprises the following steps: determining the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request; determining the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersively caching the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0063] The method comprises the following steps: determining the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request; determining the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information; and dispersively caching the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0064] The personal hotspot data, the commuting path and the commuting time information of the user are obtained through the commuting characteristics of the user and the spatial position of the edge server receiving the data access request, and then the time period of the coverage range of each edge server in the commuting path is determined, and each edge server caches the personal hotspot data of the user according to the corresponding time period and the user passing sequence. Through the caching method, the user can browse the content of interest in the subway with poor signal through the terminal, reduces the data access delay, and improves the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 is a caching method of an edge server according to an embodiment of the present application;

[0066] Figure 2 is a personal hotspot data caching structure diagram of a caching method of an edge server according to an embodiment of the present application;

[0067] Figure 3 is a hotspot data caching structure diagram of a caching method of an edge server according to an embodiment of the present application;

[0068] Figure 4 is a group hotspot data caching structure diagram of a caching method of an edge server according to an embodiment of the present application;

[0069] Figure 5 is a caching system structure diagram of an edge server according to an embodiment of the present application. DETAILED DESCRIPTION

[0070] The embodiments of the present application will be described below with reference to the accompanying drawings and preferred embodiments, and other advantages and effects of the present application can be easily understood by those skilled in the art from the contents disclosed in the present specification. The present application can also be implemented or applied by different specific embodiments, and the details in the present specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0071] REFERENCE Figure 1 , Figure 1 is a caching method of an edge server according to an embodiment of the present application; Figure 2 is a personal hotspot data caching structure diagram of a caching method of an edge server, the method is applied to an edge server, and the method comprises the following steps:

[0072] S11: According to the data access request of the user, the commuting characteristics corresponding to the user are obtained.

[0073] In this embodiment, the edge server refers to a server located at the edge of the network, used for processing and storing data generated or accessed in a location close to the user. It is usually located at the edge node closest to the user to provide faster response time and better user experience. When the user arrives at a certain subway station, the edge server of the subway station will retrieve the user's commuting characteristics recorded in the edge server database according to the data access request issued by the user.

[0074] S12: Determine the personal hotspot data corresponding to the user according to the application usage feature in the commuting characteristics.

[0075] Specifically, the commuting characteristics retrieved by the edge server include application usage features, spatial features, and time features. Among them, the application usage features include several fixed APPs frequently used by the user, and the edge server determines the APPs that the user is likely to use on the subway according to these APPs frequently used by the user, that is, determines the personal hotspot data corresponding to the user; further, the application usage features can also include page type data frequently browsed by the user when using the APP, and the edge server determines the personal hotspot data of the user according to these frequently used APPs and page type data.

[0076] For example, the user frequently uses a short video APP, and usually browses food and travel related short videos in the short video APP, and the edge server takes the short video APP and the food and travel short videos in it as the personal hotspot data of the user.

[0077] S13: Determine the commuting path and commuting time information of the user according to the spatial feature, the time feature in the commuting characteristics, and the spatial position of the edge server receiving the data access request.

[0078] In this embodiment, the spatial features include various commuting paths frequently taken by the user, such as the user frequently takes the subway to travel between subway station Al and subway station A5 along a fixed route, and travels between subway station A5 and subway station A9 along a fixed route, etc. The temporal features include, for any one of all subway stations in the city, at which time of the day the subway will pass through the any one of all subway stations, for example, the subway stations in the city include stations Al to An, for station Al, the subway will arrive at the station Al at 50 time points a11 to a150 of each day, and for station An, the subway will arrive at the station An at 50 time points an1 to an50 of each day. Meanwhile, the temporal features include, for any two of all subway stations in the city to be sequentially passed through, the travel time interval between the any two of all subway stations, for example, for any two of all subway stations Ax and Ay to be sequentially passed through, the time taken by the subway to travel from Ax to Ay is the travel time interval. The spatial location of the edge server receiving the data access request refers to the location of the edge server receiving the data access request sent by the user. According to the spatial location of the edge server receiving the data access request sent by the user, a commuting path corresponding to the spatial location in the spatial features of the user is determined, and the commuting path is determined as the current commuting path of the user. The commuting path includes each subway station in the commuting path in sequence. Then, based on the temporal features, specific time points of the user reaching each subway station in the commuting path are determined, and the specific time points are the commuting time information of the user.

[0079] For example, the user sends a data access request through a mobile terminal, and the corresponding edge server X receives the data access request. At this time, the edge server X obtains the commuting features of the user, determines, based on the correspondence between the spatial location of the edge server and each commuting path in the commuting features of the user, that the commuting path corresponding to the spatial location of the user and the edge server X is commuting path Z1, and determines the commuting path Z1 as the current commuting path of the user. Then, based on the temporal features in the commuting features, time points of the user reaching each station in the commuting path Z1 are determined.

[0080] S14: determining, according to the commuting path and the commuting time information, each edge server to be sequentially passed through by the user and a time period in the coverage range of the each edge server.

[0081] Specifically, the edge server determines the edge servers that the user will sequentially pass through according to the travel commuting path of the subway that the user rides and the commuting time information of the subway traveling to the area range of each station, and the time period in which the user is in the coverage range of each edge server. Since the edge server has an area coverage range when sending data, that is, the user is in the coverage range of the edge server, the user can receive the cached personal hotspot data provided by the edge server for the user. At the same time, in order for the user to be able to use the commonly used APP and commonly browsed pages on the subway, the coverage ranges of the edge servers need to be connected to each other, so that the user can immediately receive the personal hotspot data provided by the next edge server as soon as the user leaves the coverage range of the previous edge server.

[0082] In addition, in another embodiment, since the distances between stations are different, the coverage range of an edge server can include the area ranges of multiple stations, and therefore only one edge server can be arranged between multiple stations.

[0083] For example, the user rides the subway at station A to station E at 9:05, and the subway will sequentially pass through station B, station C, and station D on the way from station A to station E. Station A, station B, and station E each have an edge server arranged therein, and station C and station D share one edge server. The coverage range of the edge server a of station A is the distance between station A and station B, and the time period of the coverage range is 9:05-9:10. The coverage range of the edge server b of station B is the distance between station B and station C, and the time period of the coverage range is 9:10-9:15. The coverage range of the edge server cd of station C and station D is the distance between station C and station E, and the time period of the coverage range is 9:15-9:20. The user arrives at station E at 9:20 and gets off.

[0084] S15: According to the time period in which the user is in the coverage range of each edge server, the personal hotspot data is scattered and cached to each edge server in the corresponding time period.

[0085] Specifically, after determining the time period in which the subway that the user rides arrives at the coverage range of each edge server, the edge server can send the personal hotspot data to the user when the subway that the user rides travels to the coverage range of the edge server. In order to save the cache space of the edge server, the obtained personal hotspot data of the user can be scattered and cached to each edge server according to the corresponding time period.

[0086] In the embodiment, since the quantity of users commuting is large, in order to better cache the personal hotspot data for the users, the application mainly caches the personal hotspot data for regular commuting users. Thus, the application first determines the regular commuting users for caching the personal hotspot data, specifically: statistics the commuting information of the passengers, the commuting information includes: starting station information, riding time and riding frequency, calculates the commuting information of the passengers through a K-means clustering method, and screens out regular commuting users, the expression of the K-means clustering method is:

[0087]

[0088] Wherein, k=2, indicating two types of commuting users, including regular commuting users and non-regular commuting users, the users of non-regular commuting users will be removed from the personal characteristic data caching; E is a classification result, p is the commuting information of the user, including: starting station information, riding time and riding frequency; C i is a set of two categories; I(·) is a distance function.

[0089] In the embodiment, another embodiment of the application is: using a lognormal distribution method to estimate and extract the commuting path and commuting time information of regular commuting users, based on the extracted commuting path and commuting time information of regular commuting users, and combining the personal hotspot data of regular commuting users, dispersing and caching the personal hotspot data of regular commuting users to each edge server. The expression of the lognormal distribution method is:

[0090]

[0091] Wherein, T p is the commuting path of the regular commuting user; T s is the commuting time information; S s is the subway station information; S r is the time characteristics of the subway; F is a feature set composed of T p , T s , S s , S r ; μ is the feature mean of the commuting information of the regular commuting user; σ 2 is the feature variance of the commuting information of the regular commuting user.

[0092] The cache method of the edge server provided in the application, that is, the user's personal hotspot data is cached in advance, and the edge server sends the personal hotspot data to the user when the user reaches the coverage range of the edge server, so that the data access request sent by the user can be quickly responded, the data access delay is reduced, and the experience of the user riding the subway is improved. Meanwhile, the edge server uses time period-based distributed cache to cache the user's personal hotspot data, improving the utilization and efficiency of the edge server.

[0093] In another embodiment of the application, the commuting path and the commuting time information of the user are determined according to the space feature, the time feature in the commuting feature, and the spatial position of the edge server receiving the data access request, comprising:

[0094] S21: Comparing each historical commuting path in the space feature with the spatial position of the edge server receiving the data access request, and determining the historical commuting path matching the spatial position in the each historical commuting path as the commuting path of the user.

[0095] Specifically, the user sends a data access request through a mobile terminal after reaching a subway station, and the corresponding edge server receives the access request and obtains the commuting feature of the user. Based on each historical commuting path recorded in the space feature of the commuting feature, the edge server compares each historical commuting path with the spatial position of the edge server, determines a commuting path corresponding to the spatial position, and determines the commuting path as the current commuting path of the user.

[0096] S22: According to the commuting path and each target time of reaching the starting station of the commuting path in the time feature, the current time is determined as the starting time of the user's commuting.

[0097] Specifically, since the time feature records that any one station in all subway stations will pass through at what time in a day, and the known user commuting path, the position of the starting station of the commuting path in a day can be determined, and the subway will pass through the position of the starting station at multiple times, which are the target times. Then, the current time of the user in the subway station is compared with each target time, and the target time closest to the current time and exceeding the current time is selected as the starting time of the user's commuting.

[0098] S23: According to the starting time and the time interval between each two stations in the time feature, the time of the user reaching each station in the commuting path is determined to obtain the commuting time information of the user.

[0099] Specifically, based on the user's commuting path determined in the above embodiment, the commuting path records the sequence of passing through each station, and the starting time of the user to the starting station in the commuting path is determined, and then based on the travel time interval between each two stations in all stations included in the time feature, the specific time of the user to reach each station in the commuting path can be determined. The specific time determined is the commuting time information corresponding to the user's commuting path.

[0100] The embodiment obtains the user's commuting path to be passed and the user's commuting time information to reach each station through the space feature and the time feature, and the spatial position of the edge server receiving the data access request, so that the multiple edge servers distributed in multiple stations can more comprehensively master the time of the user to reach each station, and lay the foundation for further time period caching of personal hotspot data to the user according to the commuting time information.

[0101] In another embodiment of the present application, according to the commuting path and the commuting time information, the user will sequentially pass through each edge server and the time period in the coverage range of the edge server is determined, comprising:

[0102] S31: According to each station passed through by the commuting path and the coverage range of each edge server, the user will sequentially pass through each edge server and the station in the commuting path covered by each edge server is determined.

[0103] Specifically, since the user's commuting path and the coverage range of each edge server are known, based on the sequence of the user passing through each station, the sequence of the user passing through each edge server can be determined. Based on the commuting path and the coverage range of each edge server, the coincident station is determined, which is the station of the commuting path covered by each edge server. For example: edge server a can cover A1-A100 stations, edge server b can cover B1-B100 stations, edge server c can cover C1-C100 stations, and so on. The subway will pass through A1, A2 stations, B1, B2 stations, C1, C2 stations along the commuting path. Since the stations covered by edge server a include A1, A2 stations, since the stations covered by edge server b include B1, B2 stations, and since the stations covered by edge server c include C1, C2 stations, the user will pass through edge server a covering A1 station, A2 station in sequence, then pass through edge server b covering B1 station, B2 station, and then pass through edge server c covering C1 station, C2 station.

[0104] S32: determining a time period when the user is in the coverage of each edge server according to the time when the user reaches each station in the commuting path and the stations in the commuting path covered by each edge server.

[0105] Specifically, since the target time closest to the current time is taken as the starting time of the user's commuting, and the subway running time range is fixed, the specific time when the subway the user takes reaches each station in the commuting path can be determined. Since the stations covered by each edge server have been determined according to the coverage of each edge server, in combination with the time when the subway reaches each station, the time period when the user is in the coverage of each edge server can be determined. For example, the user gets on at station A at 9:05 and reaches station B at 9:10, and since the coverage of edge server a is the distance from station A to station B, the time period when the user is in the coverage of edge server a is 9:05-9:10, and the time periods in the coverage of other edge servers are the same.

[0106] In another embodiment of the present application, the personal hotspot data is cached in the corresponding time period to each edge server according to the time period when the user is in the coverage of each edge server, including:

[0107] S41: determining the time length when the user is in the coverage of each edge server according to the time period when the user is in the coverage of each edge server.

[0108] Specifically, the time length when the user is in the coverage of each edge server can be obtained according to the coverage time period of each edge server determined according to the commuting path and commuting time information of the user. For example, the time period when the user is in the coverage of edge server a is 9:05-9:10, and the time length is 5 minutes.

[0109] S42: determining the target cache amount of the personal hotspot data cached to each edge server according to the time length when the user is in the coverage of each edge server.

[0110] Specifically, since the user needs more personal hotspot data when using the mobile terminal to access data for a longer time, the target cache amount of the personal hotspot data cached in the present application is determined based on the time length when the user is in the coverage of each edge server. Therefore, in the present embodiment, the target cache amount corresponding to the time length when the user is in the coverage of each edge server is determined.

[0111] S43: determining target time periods for performing the cache of the personal hotspot data at the respective edge servers according to the time periods when the user is in the coverage of the respective edge servers.

[0112] Specifically, since the predicted time period of the coverage of the edge server can have errors due to some factors, in order to prevent the edge server from not having the personal hotspot data of the user or having released the personal hotspot data of the user in advance when the user arrives at the coverage of the edge server, the application increases the time period based on the predicted time period of the coverage of the edge server, so as to ensure the accuracy of the personal data sent by the edge server. For example, the user is predicted to be in the coverage of the edge server a from 9:05 to 9:10, and the edge server a needs to cache the personal hotspot data of the user in the target time period of 9:00-9:15 after increasing the time period.

[0113] S44: performing the cache of the personal hotspot data at the respective edge servers according to the respective target cache amounts and the respective target time periods.

[0114] Specifically, since the implementation manners of the data cache of the respective edge servers are the same, the data cache of one edge server is taken as an example for description. After the target cache amount and the target time period corresponding to the edge server are determined, the personal hotspot data of the user with the target cache amount is cached in the edge server in the target time period, and the personal hotspot data with the target cache amount cached in the edge server is deleted after the target time period. Based on the same implementation manner, the respective edge servers cache the personal hotspot data of the user with the target cache amount corresponding to the respective edge servers in the respective target time periods.

[0115] In another embodiment of the application, the cache of the personal hotspot data in the corresponding time periods to the respective edge servers according to the time periods when the user is in the coverage of the respective edge servers comprises:

[0116] S51: determining target cache amounts for performing the cache of the personal hotspot data to the respective edge servers according to the commuting path and the historical data access amounts when the user passes through the coverage of the respective edge servers along the commuting path.

[0117] S52: determining target time periods for performing the cache of the personal hotspot data at the respective edge servers according to the time periods when the user is in the coverage of the respective edge servers.

[0118] S53: According to the determined respective target cache amount and respective target time period, cache the personal hotspot data of the respective target cache amount in the respective target time period of the respective edge server.

[0119] In the embodiment, each edge server can determine the respective data amount required by the user to pass through the coverage range of the edge server by the historical data access amount required by the user to pass through the coverage range of the edge server in the past, and then increase the pre-data amount on the basis of the data amount to prevent the user demand from increasing, so as to determine the respective target cache amount required by the user to pass through the coverage range of the edge server, and each edge server caches the personal hotspot data of the respective target cache amount. For example, when the user travels the commuting path AE by taking the subway in the past, the data amount used when passing through the coverage range of the edge server a is 400 MB, so the edge server a can cache the target cache amount of 400 MB+100 MB, wherein 100 MB is the pre-data amount.

[0120] Similarly, since the time period of the coverage range of the edge server obtained by prediction may have errors due to some factors, in order to prevent the edge server from not having personal hotspot data or having released the personal hotspot data of the user when the user arrives at the coverage range of the edge server, it is necessary to increase the time period of the coverage range of the edge server by a part of time length on the basis of the prediction, and the time period after the increase of the time length is the target time period. Then, according to the respective target time period of each edge server, the respective target cache amount is cached for the personal hotspot data of the user.

[0121] In another embodiment of the present application, the method further comprises:

[0122] S61: Determine whether the respective edge server receives the data access request of the user in the respective target time period.

[0123] Specifically, when the user reaches the coverage range of each edge server, the corresponding edge server receives the data access request of the user. Assuming that the user takes the subway according to the commuting path, the user will send a data access request to the corresponding edge server when passing through each edge server in the commuting path, and then it can be determined whether the user takes the subway according to the commuting path by whether each edge server receives the data access request of the user in the corresponding target time period. In the above example, when the user reaches the A station, according to the commuting characteristics of the user and the current time, it is determined that the user will take the subway along the AE path to the E station, and the starting time is 9:05, the subway will arrive at the B station at 9:10, the time period of the coverage range of the edge server b is 9:10-9:15, and the target time period of the edge server b after the time length is increased is 9:05-9:20. In this target time period, if the user takes the subway according to the commuting path, the edge server b will receive the data access request of the user within 9:05-9:20.

[0124] S62: In the case that the target edge server corresponding to the target time period of the user does not receive the data access request of the user in the target time period of the user, it is determined whether the data access request of the user is received by other edge servers in the target time period corresponding to the target edge server.

[0125] Specifically, if a certain edge server does not receive the data access request sent by the user in the target time period corresponding to the edge server, the edge server is the target edge server. If the data access request of the user is not received by each edge server in the target time period corresponding to the edge server, the target time period corresponding to the target edge server which does not receive the data access request is further used to determine whether the data access request of the user is received by other edge servers in the target time period. In the above example, the edge server b does not receive the data access request of the user within 9:05-9:20, and other edge servers in the non-commuting path starting from the A station are called to determine whether the data access request of the user is received by other edge servers within 9:05-9:20.

[0126] S63: In the case that the data access request of the user is received by other edge servers in the target time period corresponding to the target edge server, the commuting path and the commuting time information of the user are updated according to the spatial characteristics and the time characteristics in the commuting characteristics and the spatial position of the other edge servers.

[0127] Specifically, if no data access request is received by the target edge server in the corresponding target time period, and other edge servers have received data access requests, it is determined that the user's commuting path predicted in the above embodiment is deviated. At this time, according to the spatial feature, the time feature and the spatial position of the edge server receiving the data access request in the user's commuting feature, a new commuting path of the user is determined, and the commuting path information corresponding to the new commuting path is determined. According to the updated commuting path and commuting time information, the coverage range period of each edge server in the commuting path is determined, and the personal hotspot data is scattered and cached in each edge server in the corresponding period, and the personal hotspot data of the user cached by each edge server in the original commuting path is deleted, so that the edge server can have more storage space to cache the personal hotspot data of other users.

[0128] In another embodiment of the present application, in the case that other edge servers receive the data access request of the user in the target time period corresponding to the target edge server, the commuting path and the commuting time information of the user are updated according to the spatial feature, the time feature in the commuting feature and the spatial position of the other edge servers, including:

[0129] S71: In the case that other edge servers receive the data access request of the user in the target time period corresponding to the target edge server, it is determined whether the other edge servers are the first edge server in the sequentially ordered edge servers.

[0130] Specifically, in the case that other edge servers receive the data access request of the user in the target time period corresponding to the target edge server, it is further determined whether the other edge server receiving the data access request of the user is the first edge server in the sequentially ordered edge servers in the commuting path. That is, when the user does not arrive at the first station in the commuting path on time, the subsequent edge servers in the commuting path do not receive the data access request of the user in the corresponding target time period, and the data access request in the target time period should be received by the next edge server, but is received by the first edge server due to the user's delay.

[0131] S72: In the case that the other edge server is the first edge server in the sequentially ordered edge servers, the commuting time information of the user is updated according to the spatial position of the other edge server and the spatial feature and the time feature in the commuting feature.

[0132] Specifically, when it is determined that the user may not have boarded the subway in time due to some reasons, the commuting time information of the user is updated according to the spatial position and spatial characteristics and time characteristics of the first edge server where the user is located, and then the coverage range period of each edge server in the sequential passing-through is determined according to the original commuting path and the updated commuting time information, and the personal hotspot data is scattered and cached in each edge server in the corresponding period according to the coverage range period of each edge server.

[0133] In another embodiment of the present application, as shown in Figure 3 a hotspot data caching structure diagram of a caching method of an edge server is provided, and the method further includes:

[0134] S81: determining a data access amount.

[0135] Specifically, the data access amount can be the number of accesses or the data amount. For example, when a certain word appears in a microblog, 10,000 people click on the word and browse the specific content of the word, at this time, the word corresponds to 10,000 times of access. Determining the data access amount is to determine the total data access amount received by the edge server when all users in the subway perform data access.

[0136] S82: determining the request data corresponding to each data access request in the case where the data access amount exceeds a first threshold.

[0137] Specifically, due to the occurrence of a hot event, the data access amount of the user to the hot event will surge, and the edge server cannot cache the hotspot data corresponding to each hot event due to the storage space limitation, so in order to meet the needs of more users, the present application sets a first threshold for the data access amount, when the data access amount exceeds the first threshold, it indicates that the data will be accessed by more users, and the request data corresponding to each data access request of the user is determined. For example, the user issues multiple data access requests, and the request data corresponding to each data access request is determined.

[0138] S83: determining target request data exceeding a preset proportion in the request data according to the request data.

[0139] Specifically, when the request data of all users to a certain hot event exceeds a preset proportion of all request data, the request data is set as target request data. For example, 80% of the data access requests received by the edge server are for accessing the same hot event, and the request data of the user for accessing the hot event is the target request data.

[0140] S84: Determine the target request data as group hotspot data, and obtain a data amount of the group hotspot data.

[0141] S85: According to the data amount of the group hotspot data and the determined personal hotspot data of each user, respectively cache the group hotspot data and the personal hotspot data of each user in the edge server.

[0142] Specifically, the edge server determines the target request data that multiple people want to browse as group hotspot data, and then obtains the data amount of the group hotspot data, that is, the size of the group hotspot data. Then, according to the data amount of the group hotspot data and the personal hotspot data determined through the user commuting characteristics, the edge server respectively caches the group hotspot data and the personal hotspot data of each user in the limited storage space.

[0143] In another embodiment of the present application, as shown in Figure 4 FIG. 1 is a structural diagram of group hotspot data caching of a caching method of an edge server, according to the data amount of the group hotspot data and the determined personal hotspot data of each user, respectively cache the group hotspot data and the personal hotspot data of each user in the edge server, including:

[0144] S91: In the case that the data amount of the group hotspot data is in a first preset range, divide each edge server into a first preset space and a second preset space.

[0145] S92: Cache the group hotspot data through the first preset space of each edge server, and cache the personal hotspot data of each user through the second preset space of each edge server.

[0146] In this embodiment, since the group hotspot data represents that multiple users may access the hotspot data, the storage space for storing the group hotspot data is divided in the edge server in the present application, and the size of the storage space for the group hotspot data is determined by the data amount of the group hotspot data. At the same time, the size of the data amount is divided by setting a preset range. Among them, the data amount in the first preset range represents that the storage space occupied by the data amount is not much, so when the data amount of the group hotspot data is in the first preset range, each edge server can be divided into a first preset space and a second preset space. Each edge server caches the group hotspot data in the first preset space and caches the personal hotspot data of each user in the second preset space, so that the user can browse the group hotspot data and the personal hotspot data at the same time.

[0147] S93: in the case that the data amount of the group hotspot data is in a second preset range, dividing each edge server into a third preset space and a fourth preset space.

[0148] S94: caching the group hotspot data through the third preset space of each edge server, and caching the personal hotspot data of the user with the highest priority among the users through the fourth preset space of each edge server.

[0149] The data amount in the second preset range represents that the data occupies more storage space, at least more than the storage space occupied by the data amount in the first preset range. Therefore, when the group hotspot data is in the second preset range, each edge server is divided into the third preset space and the fourth preset space, so as to divide more storage space to cache the group hotspot data, and the storage space for the personal hotspot data is correspondingly reduced. At this time, the group hotspot data is cached in the third preset space with larger cache space of each edge server, and the personal hotspot data of the user with the highest priority among the users is cached in the fourth preset space of each edge server, so as to preferentially meet the use experience of the user with the highest priority.

[0150] S95: in the case that the data amount of the group hotspot data is in a third preset range, caching the group hotspot data through all edge servers.

[0151] The data amount in the third preset range represents that the data amount requires large storage space, which is larger than the storage space occupied by the data amount in the first preset range and the second preset range. Therefore, when the group hotspot data is in the third range, the storage space of the edge server is only enough to cache the group hotspot data, and there is no extra space to cache the personal hotspot data of the users.

[0152] In another embodiment of the present application, the method further comprises:

[0153] S101: determining whether the data access request of the user is received by each edge server in the sequential route.

[0154] S102: in the case that the data access request of the user is received by the next edge server in the sequential route, releasing the personal hotspot data cached for the user in the previous edge server of the next edge server.

[0155] Specifically, when the subway taken by the user travels according to the commuting path, if each edge server sequentially passed by receives the user data access request, the user sequentially passes through the coverage range of the next edge server, and sends a data access request to the edge server, and the previous edge server corresponding to the next edge server releases the personal hotspot data cached by the user. The purpose is to relieve the storage pressure of the edge server, so that the edge server can have more space to store the personal hotspot data of another user, and improve the use efficiency and resource utilization of the edge server.

[0156] In another embodiment of the present application, the method further comprises:

[0157] S111: Determine whether the current is in the rush hour period.

[0158] S112: In the case where the current is in the rush hour period, determine the first group hotspot data according to the personal hotspot data corresponding to all users respectively.

[0159] S113: Cache the first group hotspot data through all edge servers.

[0160] Specifically, if the travel period of the subway taken by the user is in the rush hour period, the most frequently browsed data in the personal hotspot data corresponding to all users using edge servers for data access in the subway is taken as the first group hotspot data. All edge servers cache the first group hotspot data, so that the edge server can maximize the satisfaction of the data access requests of multiple users.

[0161] In another embodiment of the present application, the method further comprises:

[0162] S121: Determine the personal hotspot data of the highest priority user.

[0163] S122: Compare the personal hotspot data of the highest priority user with the first group hotspot data.

[0164] S123: In the case where the personal hotspot data of the highest priority user does not belong to the first group hotspot data, cache the personal hotspot data of the highest priority user through the edge server.

[0165] Specifically, to better meet user experience needs, the edge server compares the personal hotspot data of the highest priority user with the hotspot data of the first group most frequently viewed by that user. If the personal hotspot data of the highest priority user does not belong to the first group of hotspot data, the edge server will cache the personal hotspot data of the highest priority user to improve the user experience. For example, if the first group of hotspot data is entertainment news, and the personal hotspot data of the highest priority user indicates that the user frequently views current affairs news, then the edge server will cache personal hotspot data related to current affairs news to meet the browsing needs of the highest priority user for current affairs news.

[0166] In this embodiment, one optional implementation method for determining group hotspot data is as follows: Under the Apache Hadoop framework, all user application usage data is collected, processed in parallel, and feature extracted to obtain application usage feature information. Hotspot applications are determined using formula (1):

[0167]

[0168] Where A represents the application's usage characteristics, and the function H(·) is a function that statistically calculates the usage frequency and data access frequency of each application. This indicates a popular application.

[0169] In this embodiment, since the hot data originates from hot applications, it is targeted at hot applications. Group hotspot data Principal Component Analysis (PCA) was used to determine the method, and the expression for PCA is shown in the following formula (2):

[0170]

[0171] in, It is a popular application All data that was accessed, It is a popular application In the group hotspot data, P is the feature matrix obtained by the PCA algorithm. Its size is determined by the specific feature matrix λ. The relationship between the feature matrix λ and the feature matrix P is as follows (3).

[0172]

[0173] Among them, C is the most popular application. The covariance matrix of all accessed data, where ω represents the hotspot application. The feature vectors of all accessed data, T is the transpose matrix.

[0174] In the embodiment, the value of the feature matrix λ is adjusted to control the number of data determined as the group hotspot data, when the resources of the edge server are sufficient, the threshold is adjusted to a larger value, so that more data can be determined as the group hotspot data for caching; when the resources of the edge server are insufficient, the threshold is adjusted to a smaller value, so that less data is determined as the group hotspot data for caching.

[0175] Based on the same inventive concept, an embodiment of the present application provides a cache system of an edge server, as shown in Figure 5 The cache system structure diagram 500 of the edge server is provided, and the system comprises:

[0176] The commuting feature acquisition module is configured to acquire the commuting feature corresponding to the user according to the data access request of the user.

[0177] The personal hotspot data determination module is configured to determine the personal hotspot data corresponding to the user according to the application use feature in the commuting feature.

[0178] The commuting information determination module is configured to determine the commuting path and the commuting time information of the user according to the space feature, the time feature in the commuting feature and the spatial position of the edge server receiving the data access request.

[0179] The edge server determination module is configured to determine the edge servers sequentially passed by the user and the time period in the coverage range of the edge servers according to the commuting path and the commuting time information.

[0180] The data cache module is configured to cache the personal hotspot data to the edge servers in the corresponding time period according to the time period in which the user is in the coverage range of the edge servers.

[0181] Based on the same inventive concept, another embodiment of the present application provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps in the dehumidification method of the storage device according to any one of the above embodiments of the present application.

[0182] Based on the same inventive concept, another embodiment of the present application provides a readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the steps in the dehumidification method of the storage device according to any one of the above embodiments of the present application.

[0183] The application provides a cache method, system and device of an edge server and a storage medium, wherein the personal hotspot data and the group hotspot data are cached in advance in the edge server, so that low-latency access services are provided for all users, the data access efficiency is improved, and the resource consumption of the edge server is reduced as a whole; the data access latency of the user is optimized from multiple dimensions such as time characteristics, space characteristics and application use characteristics in combination with the commuting characteristics and the subway operation law of the user, and the effectiveness of data access is ensured. The application can realize joint optimization of data access from the aspects of groups and individuals, so that the edge server dispersed cache hotspot data strategy has high practical value.

[0184] Those skilled in the art should understand that the embodiments of the application can be provided as a method, device or computer program product. Therefore, the embodiments of the application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the embodiments of the application can adopt a computer program product in the form of being implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0185] The embodiments of the application are described with reference to flowcharts and / or block diagrams according to the methods, terminal devices (systems) and computer program products of the embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing terminal devices to produce a machine, so that the instructions executed by the computer or other programmable data processing terminal devices produce a device implemented in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0186] These computer program instructions can also be stored in a computer readable storage medium that can guide the computer or other programmable data processing terminal devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a product including instruction devices that implement the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0187] These computer program instructions can also be loaded into a computer or other programmable data processing terminal device, so that a series of operational steps are performed on the computer or other programmable terminal device to generate a computer-implemented process, thus the instructions executed on the computer or other programmable terminal device provide a process for implementing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0188] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they get the basic inventive concept. Therefore, the appended claims are intended to cover all the changes and modifications falling within the scope of the embodiments of the present application.

[0189] Finally, it should be noted that, in the present text, the relational terms such as first and second, and the like, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover non-exclusive inclusions, so that a process, method, article, or terminal device including a list of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article, or terminal device. Without more limitations, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device including the element.

[0190] The above describes in detail the cache method, system, device and storage medium of an edge server provided by the present application. The principles and implementation manners of the present application are described by using specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges can be changed. In summary, the content of the present description should not be understood as a limitation of the present application.

Claims

1. A cache method of an edge server, characterized by, The method is applied to an edge server, and the method comprises: According to a data access request of a user, a commuting feature corresponding to the user is obtained; According to an application usage feature in the commuting feature, personal hotspot data corresponding to the user is determined; According to a space feature, a time feature and a space position of an edge server receiving the data access request in the commuting feature, a commuting path and commuting time information of the user are determined; According to the commuting path and the commuting time information, each edge server sequentially passed through by the user and a time period in a coverage range of the each edge server are determined; According to the time period in which the user is in the coverage range of the each edge server, the personal hotspot data is scattered and cached to the each edge server in a corresponding time period.

2. The cache method of the edge server according to claim 1, wherein, According to a space feature, a time feature and a space position of an edge server receiving the data access request in the commuting feature, a commuting path and commuting time information of the user are determined, comprising: Each historical commuting path in the space feature is compared with the space position of the edge server receiving the data access request, and a historical commuting path matching the space position in the each historical commuting path is determined as the commuting path of the user; According to each target time of arriving at a starting station of the commuting path in the time feature, a current time is determined as a starting time of commuting of the user in combination with a nearest target time in the each target time; According to the starting time and a travel time interval between each two stations in the time feature, a time of the user arriving at each station in the commuting path is determined, so as to obtain the commuting time information of the user.

3. The cache method of edge server according to claim 2, wherein, According to the commuting path and the commuting time information, each edge server sequentially passed through by the user and a time period in a coverage range of the each edge server are determined, comprising: According to each station passed through by the commuting path and a coverage range of each edge server, each edge server sequentially passed through by the user and a station in the commuting path covered by the each edge server sequentially passed through by the user are determined; According to a time of the user arriving at each station in the commuting path and a station in the commuting path covered by each edge server, a time period in which the user is in the coverage range of the each edge server is determined.

4. The cache-invalidation method of a edge server according to claim 1, wherein, According to the time period in which the user is in the coverage range of the each edge server, the personal hotspot data is scattered and cached to the each edge server in a corresponding time period, comprising: According to the time period in which the user is in the coverage range of the each edge server, a time length in which the user is in the coverage range of the each edge server is determined; According to the time length in which the user is in the coverage range of the each edge server, a target cache amount of the personal hotspot data cached to the each edge server is determined; According to the time period in which the user is in the coverage range of the each edge server, a target time period of the personal hotspot data cached to the each edge server is determined. According to the determined target cache amount and target time period of each edge server, cache the personal hotspot data corresponding to the target cache amount in the target time period of each edge server.

5. The cache-invalidation method of a edge server according to claim 1, wherein, According to the time period when the user is in the coverage range of each edge server, cache the personal hotspot data to each edge server in the corresponding time period, including: According to the commuting path and the historical data access amount when the user passes through the coverage range of each edge server along the commuting path, determine the target cache amount of the personal hotspot data cached to each edge server; According to the time period when the user is in the coverage range of each edge server, determine the target time period of caching the personal hotspot data in each edge server respectively; According to the determined target cache amount and target time period of each edge server, cache the personal hotspot data corresponding to the target cache amount in the target time period of each edge server.

6. The cache-invalidation method of a edge server according to claim 5, wherein, The method further comprises: Determine whether the data access request of the user is received in the corresponding target time period of each edge server; In the case that the target edge server corresponding to the target time period of the target edge server does not receive the data access request of the user in the target time period, determine whether the data access request of the user is received by other edge servers in the target time period corresponding to the target edge server; In the case that the data access request of the user is received by other edge servers in the target time period corresponding to the target edge server, update the commuting path and commuting time information of the user according to the spatial feature, time feature in the commuting feature and the spatial position of the other edge server.

7. The cache-invalidation method of a edge server according to claim 1, wherein, In the case that the data access request of the user is received by other edge servers in the target time period corresponding to the target edge server, update the commuting path and commuting time information of the user according to the spatial feature, time feature in the commuting feature and the spatial position of the other edge server, including: In the case that the data access request of the user is received by other edge servers in the target time period corresponding to the target edge server, determine whether the other edge server is the first edge server in the sequence of each edge server; In the case that the other edge server is the first edge server in the sequence of each edge server, update the commuting time information of the user according to the spatial position of the other edge server and the spatial feature, time feature in the commuting feature.

8. The cache-invalidation method of a edge server according to claim 1, wherein, The method further comprises: Determine the data access amount; In the case that the data access amount exceeds the first threshold, determine the request data corresponding to each data access request; According to the request data, determine the target request data in the request data that exceeds the preset proportion; Determine the target request data as the group hotspot data, and obtain the data amount of the group hotspot data; According to the data volume of the group hotspot data and the determined personal hotspot data of each user, the caching of the group hotspot data and the personal hotspot data of each user is respectively performed in the edge server.

9. The cache method of edge server according to claim 8, wherein, According to the data volume of the group hotspot data and the determined personal hotspot data of each user, the caching of the group hotspot data and the personal hotspot data of each user is respectively performed in the edge server, including: In the case that the data volume of the group hotspot data is in a first preset range, each edge server is divided into a first preset space and a second preset space; The caching of the group hotspot data is performed through the first preset space of each edge server, and the caching of the personal hotspot data of each user is performed through the second preset space of each edge server; In the case that the data volume of the group hotspot data is in a second preset range, each edge server is divided into a third preset space and a fourth preset space; The caching of the group hotspot data is performed through the third preset space of each edge server, and the caching of the personal hotspot data of the user with the highest priority among the users is performed through the fourth preset space of each edge server; In the case that the data volume of the group hotspot data is in a third preset range, the caching of the group hotspot data is performed through all edge servers.

10. The cache-invalidation method of a edge server according to claim 1, wherein, The method further includes: determining whether the data access request of the user is received by each edge server in the sequential path; in the case that the data access request of the user is received by a next edge server in each edge server in the sequential path, releasing the personal hotspot data cached for the user in a previous edge server of the next edge server.

11. The cache-invalidation method of a edge server according to claim 1, wherein, The method further includes: determining whether the current time is in a rush hour period; in the case that the current time is in a rush hour period, determining first group hotspot data according to the personal hotspot data of all users; the caching of the first group hotspot data is performed through all edge servers.

12. The cache method of edge server according to claim 11, wherein, The method further includes: determining the personal hotspot data of the user with the highest priority; comparing the personal hotspot data of the user with the highest priority with the first group hotspot data; in the case that the personal hotspot data of the user with the highest priority does not belong to the first group hotspot data, the caching of the personal hotspot data of the user with the highest priority is performed through an edge server.

13. A cache system of an edge server, characterized by, The system includes: a commuting feature acquisition module configured to acquire a commuting feature of a user according to a data access request of the user; a personal hotspot data determination module configured to determine personal hotspot data of the user according to an application usage feature in the commuting feature; a commuting information determination module configured to determine a commuting path and commuting time information of the user according to a space feature, a time feature in the commuting feature, and a spatial position of an edge server receiving the data access request. An edge server passing edge server determining module is configured to determine, according to the commuting path and the commuting time information, each edge server that the user will sequentially pass through and a time period in a coverage range of the each edge server; A data caching module is configured to cache the personal hotspot data to the each edge server in a corresponding time period according to a time period in which the user is in the coverage range of the each edge server.

14. An electronic device, comprising: Comprise: A processor, a memory, and a computer program stored on the memory and running on the processor, the computer program, when executed by the processor, implements the steps in the caching method of an edge server according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the steps in the caching method of an edge server according to any one of claims 1 to 12.

Images