Edge caching method, device and electronic device

Abstract

The present invention provides a method, device and electronic device for edge caching, wherein the method includes: determining the current content requested by the current user; in the case where the current content is not stored, determining the core user access volume and the overall access volume based on the historical access data of multiple first contents in the first storage area within a preset time period; determining the first content that can be eliminated from the multiple first contents based on the core user access volume and the overall access volume; eliminating the first content that can be eliminated, storing the current content in the first storage area, and returning the current content to the current user. The edge caching method, device and electronic device provided by the embodiments of the present invention fully utilize the relationship between users and content, design a cache replacement strategy based on the access characteristics of core users, and can dynamically and real-time update the content in the edge server, so that the edge server can store high-value content, thereby improving the hit rate of user-requested content.

Description

Technical Field

[0001] The present invention relates to the field of edge caching technology, and in particular to an edge caching method, device, electronic device and computer-readable storage medium. Background Art

[0002] At present, with the development of the network, network traffic has exploded, and the amount of data generated has increased significantly. In order to reduce the burden on the backbone network and cloud centers, content that users frequently access (hot content) is often stored in CDN (Content Delivery Network). With the development of 5G networks and the Internet of Things, various applications have flooded into the market, and the number of base stations closer to users than CDN has also increased. Storing highly visited content in base stations closer to users can reduce the latency between users and CDNs and improve the quality of user experience. However, the storage resources of edge base stations are more limited than those of CDN servers. In the scenario of edge base station storage, research on storage replacement strategies for content in applications is more important.

[0003] Existing storage replacement strategies, whether heuristic algorithms or non-heuristic algorithms based on artificial intelligence technology, are designed based on historical access records. However, when these algorithms are used in time periods with less access data, some high-value content is difficult to distinguish. Therefore, the decision advantage of cache replacement based solely on historical access data is small, resulting in a low hit rate for high-value content and poor results. Summary of the invention

[0004] To solve the existing technical problems, the embodiments of the present invention provide an edge caching method, device, electronic device and computer-readable storage medium.

[0005] In a first aspect, an embodiment of the present invention provides an edge caching method, including:

[0006] Determine the current content requested by the current user;

[0007] In the case where the current content is not stored, determining the core user visits and the overall visits according to the historical access data of the plurality of first contents in the first storage area within a preset time period, wherein the core user visits represent the visits to the first content by the core users, and the overall visits represent the visits to the first content by all users;

[0008] Determine, according to the core user visits and the overall visits, first contents that can be eliminated from the plurality of first contents;

[0009] The removable first content is deleted, the current content is stored in the first storage area, and the current content is returned to the current user.

[0010] In a second aspect, an embodiment of the present invention further provides an edge cache device, including:

[0011] A request module, used to determine the current content requested by the current user;

[0012] a data acquisition module, configured to determine, when the current content is not stored, a core user visit amount and an overall visit amount according to historical access data to a plurality of first contents in the first storage area within a preset time period, wherein the core user visit amount represents the visit amount of the core users to the first content, and the overall visit amount represents the visit amount of all users to the first content;

[0013] A processing module, configured to determine first contents that can be eliminated from a plurality of first contents according to the core user visits and the overall visits;

[0014] The storage module is used to delete the deletable first content, store the current content in the first storage area, and return the current content to the current user.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps in any one of the edge caching methods described above.

[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in any one of the edge caching methods described above.

[0017] The edge cache method, device, electronic device and computer-readable storage medium provided by the embodiments of the present invention extract core users from the perspective of accessing users, and use the core user access volume and the overall access volume to comprehensively determine which locally stored content can be eliminated, thereby eliminating unimportant content and storing the current content required by the user locally. This method makes full use of the relationship between users and content, designs a cache replacement strategy based on the access characteristics of core users, and can dynamically and real-time update the content in the edge server, so that the edge server can store high-value content, thereby improving the hit rate of user-requested content; when users access high-value content, the user waiting time can be reduced, achieving the effect of reducing delays and rapid response. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0019] Figure 1 A flow chart of an edge caching method provided by an embodiment of the present invention is shown;

[0020] Figure 2 A flowchart of another edge caching method provided by an embodiment of the present invention is shown;

[0021] Figure 3 A schematic diagram of the structure of an edge cache device provided by an embodiment of the present invention is shown;

[0022] Figure 4 A schematic structural diagram of an electronic device for executing an edge caching method provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0023] The embodiments of the present invention are described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0024] Figure 1 The flowchart of an edge caching method provided by an embodiment of the present invention is shown. The method is executed by an edge server, which may specifically be a base station, etc. Figure 1 As shown, the method includes:

[0025] Step 101: Determine the current content requested by the current user.

[0026] In the embodiment of the present invention, the current user refers to the user who currently initiates a request to access content to the edge server. If a user initiates a request to access a certain content to the edge server, the user can be regarded as the current user, and the content to be accessed by the user can be regarded as the current content. Multiple users can initiate access requests to the edge server, and this embodiment takes one of the users as an example.

[0027] Step 102: When the current content is not stored, determine the core user visits and the overall visits based on the historical access data of multiple first contents in the first storage area within a preset time period, where the core user visits represent the visits to the first content by core users, and the overall visits represent the visits to the first content by all users.

[0028] In an embodiment of the present invention, after receiving a request from a current user to access the current content, the edge server may first determine whether the current content is stored locally; if the current content is stored locally, the current content may be directly returned to the current user. If the current content is not stored locally, the edge server stores the current content returned by other servers (e.g., CDN servers). Specifically, the edge server may remove unimportant content stored locally and store the current content locally.

[0029] During a low-visit time period (such as the early morning), the number of users accessing the edge server is relatively small. At this time, it is difficult to accurately determine which content is high-value content during the low-visit time period. The embodiment of the present invention introduces "core users" to improve the content recognition effect for the low-visit time period. Specifically, core users refer to more important users among all users accessing the edge server. For example, the importance of each user can be determined, and one or more users with an importance higher than a threshold (or the highest importance) can be regarded as core users. For example, the number of visits to the edge server by the user in a recent certain time period (such as the previous day, the previous 6 hours, etc.) can be used to represent the importance of the user. The greater the number of visits, the higher the importance of the user; for example, the top 5% of users in terms of visits can be regarded as core users.

[0030] In an embodiment of the present invention, a storage area for storing content is divided in the edge server, which is called "first storage area" in this embodiment, and the content stored in the first storage area is called "first content". When it is necessary to determine which first contents stored locally are high-value contents and which first contents are unimportant contents that can be eliminated, historical access data within a preset time period can be obtained; the preset time period is a pre-set time period, and the preset time period can be a short time period, such as 3 minutes, 10 minutes, etc., and the specific value can be determined based on actual conditions. In addition, the time point corresponding to the preset time period changes in real time, for example, the preset time period is a time period before the time point when the current user sends a request, or the end time point of the preset time period is the same as the time point when the current user sends a request. The historical access data is the data generated when all users access the content (such as the first content) stored in the edge server within the preset time period, and the historical access data includes the access time of each user and the accessed content.

[0031] By counting the historical access data, the number of visits to one or more first contents by each core user can be determined, thereby determining the number of visits by core users; similarly, the number of visits to one or more first contents by all users can be determined, thereby determining the overall number of visits. Among them, each first content can correspond to a corresponding number of core user visits and an overall number of visits. For example, within the preset time period, 10 users visited the edge server, and based on the importance of each user (such as the number of visits), it is determined that 3 of them are core users. For each first content stored in the edge server, the number of visits to the first content by these 3 core users can be determined, thereby determining the number of core user visits; and the number of visits to the first content by all 10 users can be determined, thereby determining the overall number of visits.

[0032] Step 103: determining first contents that can be eliminated from the plurality of first contents according to the core user visits and the overall visits.

[0033] Step 104: Delete the first content that can be deleted, store the current content in the first storage area, and return the current content to the current user.

[0034] In the process of realizing the invention, the inventor discovered through analysis of data that in time periods with less traffic, a certain group of people occupy an important position, and the content they access is more likely to become future hot content. The user group is relatively concentrated, and the accessed content is relatively concentrated. Improving the hit rate of this user group can effectively improve the overall hit rate of the current time period. In an embodiment of the present invention, this part of the user group is referred to as a core user. Generally speaking, among all users, core users are high-frequency application users, and their requests account for more than 90% of the total requests. The content accessed by core users has a high degree of similarity with the overall high-value content. Therefore, from the perspective of core users, it is possible to improve the problem of low hit rate of stored content due to the difficulty in distinguishing some high-value content from non-high-value content.

[0035] The embodiment of the present invention can determine which first content or content can be eliminated by combining the core user visits and the overall visits of the first content. For example, the importance of each first content can be determined by combining the core user visits and the overall visits, and the first content with lower importance can be used as the first content that can be eliminated. For example, the greater the core user visits and the greater the overall visits, the less likely the first content is to be eliminated; on the contrary, the smaller the core user visits and the smaller the overall visits, the easier it is for the first content to be eliminated.

[0036] After determining the first content that can be removed, the first content that can be removed can be deleted from the first storage area, and the current content can be stored in the first storage area instead of the first content that can be removed, so that the current content is stored as a first content in the edge server for user access. The number of first contents that can be removed can be one or more; for example, it is only necessary to ensure that the size of all first contents that can be removed is not less than the size of the current content.

[0037] In addition, optionally, when the current content is not stored locally, the edge server can directly delete the first content that can be deleted and save the current content; or, when the current content is not stored locally, the edge server first determines whether the remaining space for storing content locally can store the current content. When the remaining space can store the current content, the first content that has been stored is not deleted and the current content can be directly stored; when the remaining space cannot store the current content, the above steps 102-104 are executed again, that is, the first content that can be deleted is replaced with the current content.

[0038] An edge caching method provided by an embodiment of the present invention extracts core users from the user's perspective, and uses the core user access volume and the overall access volume to comprehensively determine which locally stored content can be eliminated, thereby eliminating unimportant content and storing the current content required by the user locally. This method makes full use of the relationship between users and content, designs a cache replacement strategy based on the access characteristics of core users, and can dynamically and real-time update the content in the edge server, so that the edge server can store high-value content, thereby improving the hit rate of user-requested content; when users access high-value content, the user's waiting time can be reduced, achieving the effect of reducing delays and rapid response.

[0039] Optionally, in the process of using the core user visits and the overall visits to determine the first content that can be eliminated, the core user visits and the overall visits can be used as two parallel data, and the importance of each first content can be determined by, for example, a weighted method, but the effect of evaluating the value of content in this method is generally poor. In order to effectively distinguish between high-value content and non-high-value content stored locally at the local visit volume stage, the embodiment of the present invention uses a time series to represent the core user visits and the overall user visits, and determines the importance of each first content based on the overall comprehensiveness of all first content, thereby determining the first content that can be eliminated.

[0040] Specifically, the embodiment of the present invention divides the preset time period into multiple time periods, the core user visits include the visits to the first content by the core users in multiple time periods within the preset time period, and the overall visits include the visits to the first content by all users in multiple time periods within the preset time period. For example, each unit time (such as 1 minute) in the preset time period can be regarded as a time period, so as to determine the visits to the first content by the core users in each time period and the visits to the first content by all users, and then generate the core user visits and overall visits in the form of time series determined by the time period as the division unit. For example, the preset time period can be divided into four time periods, and then the visits to the first content in each time period can be determined, so that the core user visits and overall visits in the form of a four-dimensional array can be determined.

[0041] The above step 103 of "determining the first content that can be eliminated from the plurality of first contents according to the core user visits and the overall visits" includes steps A1-A3:

[0042] Step A1: splice the core user visits and overall visits of multiple first contents into an evaluation matrix.

[0043] In the embodiment of the present invention, the core user visits and the overall visits of each first content are spliced ​​together with the first content as a unit to generate a higher-dimensional array, and the arrays of all first contents are combined together to generate a matrix containing the core user visits and the overall visits of all first contents. In this embodiment, the matrix is ​​called an evaluation matrix. For example, there are m first contents stored in the first storage area, and the preset time period can be divided into n time periods, so the core user visits and the overall visits are both n-dimensional values; for each first content, a 2n-dimensional array can be spliced, and all first contents are arranged in the column direction, so that an m×2n evaluation matrix can be generated.

[0044] Step A2: Determine the importance of each first content according to the evaluation matrix.

[0045] In the embodiment of the present invention, the evaluation matrix includes the core user visits and the overall visits of all first contents. Based on the evaluation matrix as a whole, the importance of each first content can be relatively determined, so that the size relationship of the importance of each first content can be more accurately determined, and the first content with lower importance can be more accurately determined.

[0046] Optionally, the importance of each first content may be determined using a covariance matrix. The above step A2 "determining the importance of each first content according to an evaluation matrix" includes:

[0047] Step A21: Determine a covariance matrix of an evaluation matrix, wherein rows and columns of the evaluation matrix represent the first content and time period respectively.

[0048] In the embodiment of the present invention, as described above, the evaluation matrix includes an array obtained by splicing the core user visits and the overall visits of each first content, and the rows and columns of the evaluation matrix can represent the first content and the time period respectively. Among them, "the rows and columns of the evaluation matrix can represent the first content and the time period respectively" means: the rows of the evaluation matrix represent the first content and the columns represent the time period; or, the rows of the evaluation matrix represent the time period and the columns represent the first content.

[0049] In the process of determining the covariance matrix of the evaluation matrix, all elements represented by the time period in the evaluation matrix are taken as a group, and the covariance between each two time periods is determined in turn, thereby generating the covariance matrix of the evaluation matrix. For example, the evaluation matrix is ​​an m×2n matrix, that is, each column of the evaluation matrix corresponds to a time period. Since there is a process of splicing the core user visits and the overall visits, the evaluation matrix corresponds to twice the number of time periods (i.e., 2n). In this embodiment, each column in the evaluation matrix can be taken as a group, and the covariance between the two columns can be determined in pairs, so that a 2n×2n covariance matrix can be generated.

[0050] Step A22: extract the maximum eigenvalue of the covariance matrix, and determine the maximum eigenvector corresponding to the maximum eigenvalue.

[0051] Step A23: Multiply the evaluation matrix by the maximum eigenvector to determine the evaluation value of each first content, and use the evaluation value as the importance of the first content.

[0052] In the embodiment of the present invention, the covariance matrix is ​​a symmetric matrix, and the maximum eigenvalue of the covariance matrix can be determined, and the eigenvector corresponding to the maximum eigenvalue, that is, the maximum eigenvector, can be determined; wherein, determining the maximum eigenvalue and the maximum eigenvector of the matrix is ​​an existing mature technology and will not be described in detail here. Since the number m of the first content stored in the first storage area may be different at different times, and the number n of time periods included in the preset time period can be pre-set, and n can be a fixed value, this embodiment takes all elements represented by the time period in the evaluation matrix as a group, and determines the covariance between each two time periods in turn, so that the generated covariance matrix is ​​always a matrix of uniform specifications, that is, a 2n×2n covariance matrix, which is convenient for processing the covariance matrix of uniform specifications at different times and determining the maximum eigenvector, which can simplify the processing process and reduce the difficulty of development.

[0053] Among them, the maximum eigenvector is a vector of twice the number of time periods. By multiplying the evaluation matrix with the maximum eigenvector, an array (or vector) containing the number of elements of the first content can be determined. Each element in the array (or vector) is the evaluation value of the corresponding first content, and the evaluation value can represent the importance of the corresponding first content.

[0054] In the embodiment of the present invention, "multiplying the evaluation matrix by the maximum eigenvector" can be evaluation matrix × maximum eigenvector, or maximum eigenvector × evaluation matrix, which can be determined based on actual conditions. For example, m first contents are stored in the first storage area, and the preset time period can be divided into n time periods; if the evaluation matrix is ​​an m×2n matrix, and the maximum eigenvector is a 2n×1 vector, then the evaluation matrix × maximum eigenvector can be multiplied. Alternatively, if the evaluation matrix is ​​a 2n×m matrix, and the maximum eigenvector is a 2n×1 vector, then the maximum eigenvector × evaluation matrix can be multiplied.

[0055] Step A3: The first content with the lowest importance is taken as the first content that can be eliminated.

[0056] In the embodiment of the present invention, after determining the importance of all first contents, the first contents with the lowest importance can be used as first contents that can be eliminated. Moreover, if necessary, the first contents with the second lowest importance (i.e., the first contents with the lowest importance among other first contents except the first contents with the lowest importance) can also be used as first contents that can be eliminated. The number of first contents that can be eliminated in this embodiment is not limited and can be selected based on actual conditions.

[0057] Optionally, in order to further prevent high-value content from being eliminated and improve the hit rate of high-value content, in the method provided by the embodiment of the present invention, the edge server is further provided with a second storage area for storing high-value content. Specifically, the method further includes:

[0058] Step B1: Divide the second storage area, and store the second content in the second storage area; the first content and the second content are both content that needs to be stored locally, and the importance of the second content is higher than that of the first content.

[0059] In the embodiment of the present invention, the storage area for storing content in the edge server includes a first storage area and a second storage area, the content stored in the first storage area is called the first content, the content stored in the second storage area is called the second content, and the first content and the second content are both content that needs to be stored locally; for example, all content that needs to be stored in the edge server is divided into the first storage area or the first storage area for storage. Among them, the second storage area is used to store high-value content, that is, the importance of the second content is higher than the importance of the first content.

[0060] When it is necessary to determine which content is to be stored in the first storage area and which content is to be stored in the second storage area, the importance of each content can be simply determined based on the number of visits to each content. The higher the number of visits, the greater the importance. Therefore, the first few contents with larger visits can be stored as the second content in the second storage area, and the remaining contents that can be stored can be stored as the first content in the first storage area. Alternatively, the importance of each content that needs to be stored (not just the first content) can be determined based on a method similar to the above steps A1-A2, and then the content with higher importance can be stored as the second content in the second storage area.

[0061] In addition, the embodiment of the present invention can optionally dynamically update the size of the second storage area so as to be able to dynamically and adaptively store high-value content. The operation of updating the size of the second storage area (hereinafter referred to as the update operation) can be performed once every period of time. For example, the update operation can be performed periodically, such as once every one minute, three minutes, etc. Specifically, the process of the above step B1 "dividing the second storage area" can include:

[0062] Step B11: When the space size of the second storage area needs to be updated, determine the coefficient a of the current update period t ,and: Among them, t represents the current update period, t-1 represents the previous update period, and a t-1 represents the coefficient of the last update period, represents the content hit rate of the first storage area in the last update period, Indicates the content hit rate of the second storage area in the previous update period.

[0063] In the embodiment of the present invention, the period between two update time points is called an update period. When a certain update time point is reached, the space size of the second storage area that needs to be updated can be determined, and the update period starting from the update time point is taken as the current update period, which can be represented by t; the previous update period of the current update period is called the "previous update period", which is represented by t-1. A dynamically changing coefficient is set for each update period, such as the coefficient of the current update period t is a t , using the hit rate of the two storage areas (the first storage area and the second storage area), the coefficient is adjusted. If the hit rate of the second storage area is high, the space of the second storage area is increased in the next update operation, otherwise it is reduced. The increase or decrease is determined by the coefficient.

[0064] Specifically, the coefficient a of the current update period t The coefficient a of the previous update period t-1 , the hit rate of the content in the first storage area Content hit rate of the second storage area Determined together, please refer to the above formula for details. In the last update period, if the content hit rate of the second storage area is The larger the coefficient a of the current update period is, t The larger it is, the more high-value content there is in the previous update period. At this time, the space size of the second storage area can be further increased in the current update period. Among them, the content hit rate of the storage area (including the first storage area and the second storage area) refers to the ratio between the frequency of access to the content stored in the storage area and the total access request frequency within a period of time (such as a certain update period). For example, within an update period (such as one minute), content A is requested to be accessed 10 times, content B is requested to be accessed 5 times, and content C is requested to be accessed 4 times. If two contents A and B are stored in the storage area, the content hit rate of the storage area = (10+5) / (10+5+4) = 15 / 19.

[0065] Step B12: Determine the number of contents k in the current update period based on the locally stored contents accessed in the previous update period t-1 and the previous update period t-2. t , and the top k important t The size corresponding to the content of k is used as the space size of the second storage area in the current update period; and t =num(H t-1 ∩H t-2 )×a t ; Among them, H t-1 represents the local storage content accessed in the last update period t-1, H t-2 Indicates the locally stored content accessed in the last update period t-2, num(H t-1 ∩H t-2 ) represents the number of locally stored contents accessed in both the previous update period t-1 and the previous update period t-2.

[0066] In the embodiment of the present invention, the last update period of the last update period is called the "previous update period", which can be represented by t-2. Based on the historical access data of the edge server, the content stored in the edge server accessed by all users in the last update period t-1 and the previous update period t-2 can be determined, that is, H t-1 and H t-2 ; It is then possible to determine which content stored in the edge server is accessed during the two update periods (the last update period t-1, the last update period t-2), and thus the number of accessed content num (H t-1 ∩H t-2 ). This embodiment uses coefficient a t This number is adjusted to determine the number of contents k that the second storage area should store in the current update period.t , that is, the second storage area should store k t content, and then the space size of the second storage area is set to the top k in terms of importance. t The size of the contents corresponding to the top k t The content of each storage unit is stored as the second content in the second storage area.

[0067] The method provided by the embodiment of the present invention can store relatively important and high-value content as second content in the second storage area by dividing the first storage area and the second storage area in the edge server; when it is necessary to determine which content can be eliminated, it is not necessary to determine the importance of the second content, which can reduce redundant calculations and improve processing efficiency; and, except for update operations, high-value second content will not be eliminated, which can ensure the hit rate of high-value second content and further avoid the mistaken elimination of high-value content during the low-visit stage.

[0068] The following is an overall description of a process of the edge caching method through an embodiment. Figure 2 As shown, the method includes steps 201-209.

[0069] Step 201: Obtain a request sent by the current user for accessing current content.

[0070] Step 202: Determine whether the local storage area contains the current content. If not, proceed to step 203, otherwise proceed to step 209.

[0071] The local storage area includes a first storage area and a second storage area. As long as one of the two storage areas contains the current content, it can be considered that the current content is stored.

[0072] Step 203: Determine whether the remaining space in the local storage area can store the current content. If not, proceed to step 204, otherwise proceed to step 208.

[0073] Among them, since the space size of the second storage area is adjusted only when it needs to be updated, at this time, it is only necessary to determine whether the remaining space of the first storage area can store the current content.

[0074] Step 204: Determine whether the space size of the second storage area needs to be updated, if so, proceed to step 205, otherwise proceed to step 206.

[0075] Step 205: Determine the space size of the second storage area according to the coefficient of the current update period, store important second content in the second storage area, and store the remaining content as first content in the first storage area, and then continue to step 206.

[0076] Those skilled in the art will appreciate that the above steps 204-205 may be performed after step 203, or may be performed at other locations, such as after step 201 or 202, or before step 201. At this time, if it is determined in step 203 that storage is not possible, the subsequent step 206 is directly executed.

[0077] Step 206: Determine the importance of the plurality of first contents according to the core user visits and the overall visits, and take the first content with the lowest importance as the first content that can be eliminated and eliminate it.

[0078] Step 207: Determine again whether the remaining space in the first storage area can store the current content. If not, execute step 206 again, otherwise proceed to step 208.

[0079] Step 208: Store the current content as the first content in the first storage area.

[0080] Step 209: Return the current content to the current user.

[0081] The following describes the application process of the edge caching method in detail through a specific scenario.

[0082] For example, an edge server (such as a base station) can store 6 contents. Currently, the edge server stores 5 contents A, B, C, D, and E. The corresponding access users and time are shown in Table 1. For the convenience of description, this embodiment does not consider the size difference of different contents, that is, the size of all contents is the same, and the access time in the table is accurate to minutes. In addition, users U1, U2, and U3 are always core users, that is, the core user set is {U1, U2, U3}.

[0083] Table 1

[0084] Serial number content Access User Access time 1 A U1, U2, U3, U4 1:22、1:22、1:22、1:23 2 B U1, U2, U5 1:22、1:22、1:23 3 C U2, U4 1:21、1:22 4 D U4, U1 1:24、1:24 5 E U6, U7, U1 1:22、1:23、1:24

[0085] If the edge server receives requests from user U2 to watch content F at 1:24, user U3 to watch content B at 1:24, and user U1 to watch content M at 1:25, the specific processing process of these requests is as follows:

[0086] When user U2 requests to watch content F, although content F is not stored locally, the edge server can store 6 contents, but currently only stores 5. Therefore, the remaining space of the edge server can store the content F. At this time, the content F can be directly stored and returned to user U2.

[0087] When user U3 requests to watch content B, since the content B is stored locally, the content B can be directly sent to user U3. At this time, the access user and time can be updated as shown in Table 2:

[0088] Table 2

[0089] Serial number content Access User Access time 1 A U1, U2, U3, U4 1:22、1:22、1:22、1:23 2 B U1, U2, U5, U3 1:22、1:22、1:23、1:24 3 C U2, U4 1:21、1:22 4 D U4, U1 1:24、1:24 5 E U6, U7, U1 1:22、1:23、1:24 6 F U2 1:24

[0090] When user U1 requests to watch content M at 1:25, since the content M is stored locally and the local storage area is full, it is necessary to determine the content that can be removed.

[0091] In this embodiment, the preset time period is set to 3 minutes, and each minute corresponds to a time period. For the convenience of description, taking the user U1 requesting to watch content M at 1:25:01 as an example, only the access data of the three time periods of 1:22, 1:23, and 1:24 need to be considered, so the access data of 1:21 in Table 2 can be deleted, and Table 3 is generated:

[0092] Table 3

[0093] Serial number content Access User Access time 1 A U1, U2, U3, U4 1:22、1:22、1:22、1:23 2 B U1, U2, U5, U3 1:22、1:22、1:23、1:24 3 C U4 1:22 4 D U4, U1 1:24、1:24 5 E U6, U7, U1 1:22、1:23、1:24 6 F U2 1:24

[0094] In addition, the embodiment of the present invention stores contents A and B as relatively important second contents in the second storage area, and stores contents C, D, E, and F as first contents in the first storage area. The core users include U1, U2, and U3. Based on the access data corresponding to Table 3, the visits of the core users and all users to each first content in each time period (1:22, 1:23, and 1:24) can be determined, thereby determining the core user visits and overall visits of each first content; since the preset time period is divided into three time periods, the core user visits and overall visits can be expressed as a three-dimensional array, as shown in Table 4:

[0095] Table 4

[0096] Serial number First content Core user visits Overall visits Total visits 1 C [0,0,0] [1,0,0] 1 2 D [0,0,1] [0,0,2] 2 3 E [0,0,1] [1,1,1] 3 4 F [0,0,1] [0,0,1] 1

[0097] The core user visits and overall visits of all first contents are concatenated and combined into a 4×6 evaluation matrix X, which is:

[0098]

[0099] Taking all the elements represented by the time period in the evaluation matrix X as a group, a 6×6 covariance matrix can be obtained, and then the 6×1 maximum eigenvector can be determined. Multiplying the evaluation matrix X by the maximum eigenvector, a one-dimensional array containing four elements can be obtained, and these four elements represent the evaluation values ​​of content C, D, E, and F respectively. After calculation, the evaluation value of content C is the smallest and its importance is the lowest, so content C can be used as the first content to be eliminated, and the content C can be deleted, and the content M requested by the user can be stored in the first storage area. At this time, the access user and time can be seen in the following Table 5:

[0100] Table 5

[0101]

[0102]

[0103] The above describes in detail the edge caching method provided by the embodiment of the present invention. The method can also be implemented by a corresponding device. The following describes in detail the edge caching device provided by the embodiment of the present invention.

[0104] Figure 3 FIG. 1 is a schematic diagram showing the structure of an edge cache device provided by an embodiment of the present invention. Figure 3 As shown, the edge cache device includes:

[0105] The request module 31 is used to determine the current content requested by the current user;

[0106] A data acquisition module 32 is used to determine the core user visits and the overall visits according to the historical access data of the first contents in the first storage area within a preset time period when the current content is not stored, wherein the core user visits represent the visits of the core users to the first contents, and the overall visits represent the visits of all users to the first contents;

[0107] A processing module 33, configured to determine first contents that can be removed from a plurality of first contents according to the core user visits and the overall visits;

[0108] The storage module 34 is used to delete the removable first content, store the current content in the first storage area, and return the current content to the current user.

[0109] Based on the above embodiment, the core user visits include visits to the first content by the core user in multiple time periods within the preset time period, and the overall visits include visits to the first content by all users in multiple time periods within the preset time period;

[0110] The processing module 33 determines the first content that can be removed from the plurality of first contents according to the core user visits and the overall visits, including:

[0111] splicing the core user visits and the overall visits of the plurality of first contents into an evaluation matrix;

[0112] determining the importance of each of the first contents according to the evaluation matrix;

[0113] The first content with the lowest importance is regarded as the first content that can be eliminated.

[0114] Based on the above embodiment, the processing module 33 determines the importance of each first content according to the evaluation matrix, including:

[0115] Determine a covariance matrix of the evaluation matrix, wherein rows and columns of the evaluation matrix represent the first content and the time period respectively;

[0116] Extracting the maximum eigenvalue of the covariance matrix, and determining the maximum eigenvector corresponding to the maximum eigenvalue;

[0117] The evaluation matrix is ​​multiplied by the maximum eigenvector to determine an evaluation value of each of the first contents, and the evaluation value is used as the importance of the first contents.

[0118] Based on the above embodiment, the device further includes a division module, which is used to:

[0119] The second storage area is divided, and the second content is stored in the second storage area; the first content and the second content are both content that needs to be stored locally, and the importance of the second content is higher than that of the first content.

[0120] Based on the above embodiment, the partitioning module partitions the second storage area including:

[0121] When the space size of the second storage area needs to be updated, the coefficient a of the current update period is determined. t ,and: Among them, t represents the current update period, t-1 represents the previous update period, and a t-1 represents the coefficient of the last update period, represents the content hit rate of the first storage area in the last update period, Indicates the content hit rate of the second storage area in the last update period;

[0122] Determine the number of contents k in the current update period based on the locally stored contents accessed in the previous update period t-1 and the previous update period t-2 t , and the top k importantt The size corresponding to the content of k is used as the space size of the second storage area in the current update period; and t =num(H t-1 ∩H t-2 )×a t ;

[0123] Among them, H t-1 represents the local storage content accessed in the last update period t-1, H t-2 Indicates the locally stored content accessed in the last update period t-2, num(H t-1 ∩H t-2 ) represents the number of locally stored contents accessed in both the previous update period t-1 and the previous update period t-2.

[0124] In addition, an embodiment of the present invention further provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned edge caching method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0125] For details, see Figure 4 As shown, an embodiment of the present invention further provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0126] In the embodiment of the present invention, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned edge caching method embodiment is implemented.

[0127] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0128] In an embodiment of the present invention, the bus architecture (represented by bus 1110), bus 1110 may include any number of interconnected buses and bridges, and bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150.

[0129] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an Accelerate Graphical Port (AGP), a processor, or a local bus using any of a variety of bus architectures. By way of example and not limitation, such architectures include: Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA), Peripheral Component Interconnect (PCI) bus.

[0130] The processor 1120 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processors include: a general-purpose processor, a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), a programmable logic array (PLA), a microcontroller unit (MCU) or other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located in multiple different chips.

[0131] Processor 1120 can be a microprocessor or any conventional processor. The method steps disclosed in conjunction with the embodiments of the present invention can be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a readable storage medium known in the art, such as a random access memory (RAM), a flash memory (FlashMemory), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a register, etc. The readable storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware.

[0132] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, the embodiments of the present invention will not be further described.

[0133] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer system, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, and a stylus.

[0134] It should be understood that in an embodiment of the present invention, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above-mentioned network may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless local area network (WLAN), a wide area network (WAN), a wireless wide area network (WWAN), a metropolitan area network (MAN), the Internet, a public switched telephone network (PSTN), a plain old telephone service network (POTS), a cellular telephone network, a wireless network, a wireless fidelity (Wi-Fi) network, and a combination of two or more of the above-mentioned networks. For example, the cellular telephone network and the wireless network can be a Global System for Mobile Communications (GSM) system, a Code Division Multiple Access (CDMA) system, a Worldwide Interoperability for Microwave Access (WiMAX) system, a General Packet Radio Service (GPRS) system, a Wideband Code Division Multiple Access (WCDMA) system, a Long Term Evolution (LTE) system, a LTE Frequency Division Duplex (FDD) system, a LTE Time Division Duplex (TDD) system, an Advanced Long Term Evolution (LTE-A) system, a Universal Mobile Telecommunications (UMTS) system, an Enhanced Mobile Broadband (Enhance Mobile Broadband, eMBB) system, a massive Machine Type of Communication (mMTC) system, an Ultra-Reliable Low Latency Communications (UltraReliable Low Latency Communications, uRLLC) system, etc.

[0135] It should be understood that the memory 1150 in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0136] Volatile memory includes: Random Access Memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as: Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchronous Link Dynamic Random Access Memory (SLDRAM) and Direct Rambus RAM (DRRAM). The memory 1150 of the electronic device described in the embodiment of the present invention includes but is not limited to the above and any other suitable types of memory.

[0137] In the embodiment of the present invention, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0138] Specifically, the operating system 1151 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various applications, such as a media player (Media Player) and a browser (Browser), which are used to implement various application services. The program for implementing the method of the embodiment of the present invention may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer system executable instructions that perform specific tasks or implement specific abstract data types.

[0139] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned edge caching method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0140] Computer readable storage media include: permanent and non-permanent, removable and non-removable media, which are tangible devices that can retain and store instructions for use by instruction execution devices. Computer readable storage media include: electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, and any suitable combination of the above. Computer readable storage media include: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassette storage, magnetic tape disk storage or other magnetic storage devices, memory sticks, mechanical encoding devices (such as punched cards or raised structures in grooves with instructions recorded thereon) or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined in the embodiments of the present invention, computer-readable storage media do not include temporary signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (such as light pulses passing through fiber optic cables), or electrical signals transmitted through wires.

[0141] In the several embodiments provided in the present application, it should be understood that the disclosed devices, electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one location or distributed over multiple network units. Some or all of the units may be selected according to actual needs to solve the problem to be solved by the embodiments of the present invention.

[0143] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or part of the contribution to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (including: a personal computer, a server, a data center or other network device) to perform all or part of the steps of the method described in each embodiment of the present invention. The above-mentioned storage medium includes various media that can store program codes as listed above.

[0145] In the description of the embodiments of the present invention, those skilled in the art should know that the embodiments of the present invention can be implemented as methods, devices, electronic devices and computer-readable storage media. Therefore, the embodiments of the present invention can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the embodiments of the present invention can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0146] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM), flash memories, optical fibers, compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices or any combination of the above. In an embodiment of the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device, or device.

[0147] The computer program code contained in the above-mentioned computer-readable storage medium can be transmitted using any appropriate medium, including: wireless, wire, optical cable, radio frequency (RF) or any suitable combination thereof.

[0148] The computer program code for performing the operation of the embodiments of the present invention can be written in assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or in one or more programming languages ​​or a combination thereof, wherein the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as C language or a similar programming language. The computer program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on a remote computer, and completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer or to an external computer through any type of network, including a local area network (LAN) or a wide area network (WAN).

[0149] The embodiments of the present invention describe the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0150] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0151] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0152] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0153] The above is only a specific implementation of the embodiment of the present invention, but the protection scope of the embodiment of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the embodiment of the present invention, which should be included in the protection scope of the embodiment of the present invention. Therefore, the protection scope of the embodiment of the present invention should be based on the protection scope of the claims.

Claims

1. A method for edge caching, characterized in that: include: Determine the current content requested by the current user; In the case where the current content is not stored, determining the core user visits and the overall visits according to the historical access data of the plurality of first contents in the first storage area within a preset time period, wherein the core user visits represent the visits to the first content by the core users, and the overall visits represent the visits to the first content by all users; Determine, according to the core user visits and the overall visits, first contents that can be eliminated from the plurality of first contents; Deleting the deletable first content, storing the current content in the first storage area, and returning the current content to the current user; The core user visits include visits to the first content by the core users in multiple time periods within the preset time period, and the overall visits include visits to the first content by all users in multiple time periods within the preset time period; The determining, according to the core user visits and the overall visits, the first content that can be removed from the plurality of first contents includes: splicing the core user visits and the overall visits of the plurality of first contents into an evaluation matrix; determining the importance of each of the first contents according to the evaluation matrix; The first content with the lowest importance is regarded as the first content that can be eliminated; Determining the importance of each of the first contents according to the evaluation matrix includes: Determine a covariance matrix of the evaluation matrix, wherein rows and columns of the evaluation matrix represent the first content and the time period respectively; Extracting the maximum eigenvalue of the covariance matrix, and determining the maximum eigenvector corresponding to the maximum eigenvalue; The evaluation matrix is ​​multiplied by the maximum eigenvector to determine an evaluation value of each of the first contents, and the evaluation value is used as the importance of the first contents.

2. The method according to claim 1, characterized in that Also includes: The second storage area is divided, and the second content is stored in the second storage area; the first content and the second content are both content that needs to be stored locally, and the importance of the second content is higher than that of the first content.

3. The method according to claim 2, characterized in that The dividing of the second storage area comprises: When the space size of the second storage area needs to be updated, the coefficient a of the current update period is determined. t ,and: ; where t represents the current update period, t-1 represents the previous update period, and a t-1 represents the coefficient of the last update period, represents the content hit rate of the first storage area in the last update period, Indicates the content hit rate of the second storage area in the last update period; Determine the number of contents k in the current update period based on the locally stored contents accessed in the previous update period t-1 and the previous update period t-2 t , and the top k important t The size corresponding to the content of is used as the space size of the second storage area in the current update period; and ; Among them, H t-1 represents the local storage content accessed in the last update period t-1, H t-2 represents the locally stored content accessed during the last update period t-2, Indicates the number of locally stored contents accessed in both the last update period t-1 and the last update period t-2.

4. An edge cache device, characterized in that: include: A request module, used to determine the current content requested by the current user; a data acquisition module, configured to determine, when the current content is not stored, a core user visit amount and an overall visit amount according to historical access data to a plurality of first contents in the first storage area within a preset time period, wherein the core user visit amount represents the visit amount of the core users to the first content, and the overall visit amount represents the visit amount of all users to the first content; A processing module, configured to determine first contents that can be eliminated from a plurality of first contents according to the core user visits and the overall visits; A storage module, used for deleting the deletable first content, storing the current content in the first storage area, and returning the current content to the current user; The core user visits include visits to the first content by the core users in multiple time periods within the preset time period, and the overall visits include visits to the first content by all users in multiple time periods within the preset time period; The processing module determines the first content that can be removed from the plurality of first contents according to the core user visits and the overall visits, including: splicing the core user visits and the overall visits of the plurality of first contents into an evaluation matrix; determining the importance of each of the first contents according to the evaluation matrix; The first content with the lowest importance is regarded as the first content that can be eliminated; The processing module determines the importance of each first content according to the evaluation matrix, including: Determine a covariance matrix of the evaluation matrix, wherein rows and columns of the evaluation matrix represent the first content and the time period respectively; Extracting the maximum eigenvalue of the covariance matrix, and determining the maximum eigenvector corresponding to the maximum eigenvalue; The evaluation matrix is ​​multiplied by the maximum eigenvector to determine an evaluation value of each of the first contents, and the evaluation value is used as the importance of the first contents.

5. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the edge cache method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the edge cache method according to any one of claims 1 to 3 are implemented.

Images