121 results about "Content popularity" patented technology

A method and system for assigning ranking scores to Internet users of a networking site and a content site in which the networking site enables each user to become associated with other users as friends and in which the content site enables each user to rate content published by other users includes the following operations. Data indicative of the friends of each user is obtained from the networking site and a network popularity rating is assigned to each user based on this data. Data indicative of the ratings assigned to the published content of the users is obtained from the content site and a content popularity rating is assigned to each user based on this data. A ranking score is assigned to each user based on the network popularity and content popularity ratings of the user. The ranking scores are provided to a third party.

A system, method and computer-readable medium for request routing based on content popularity information are provided. A client computer transmits a request for content from a content provider. The content provider utilizes executable code, such as translation request code, for facilitating request routing utilizing popularity information. The translation request code, may direct a client computing device to request further translation request code and / or translation information. Thereafter, the client issues a DNS query with the translated information including popularity information. The content delivery network service provider can then either resolve the DNS query with an IP address of a cache component or transmit another alternative resource identifier that will resolve to the content delivery network service provider. The process can repeat until a DNS nameserver resolves a DNS query from the client computing device.

A system, method and computer-readable medium for request routing based on content popularity information are provided. A client computing device transmits a first DNS query to a content delivery network service provider. The content delivery network service provider transmits an alternative resource identifier in response to the client computing device DNS query. The alternative resource identifier is selected as a function of popularity information pertaining to the requested resource. The client computing device then transmits a second DNS query to the content delivery network service provider. The content delivery network service provider can then either resolve the second DNS query with an IP address of a cache component or transmit another alternative resource identifier that will resolve to the content delivery network service provider. The process can repeat until a DNS nameserver resolves a DNS query from the client computing device.

The invention discloses an information center network mobility management method based on content popularity and belongs to the technical field of next-generation internet technology research. The method includes the steps that, a requester side moves, specifically, the content requester sends an Interest package request, a router in a network receives the Interest message, the local cache is searched first, the Interest message is directly returned to the requester if the content exists in the local cache, and otherwise a PIT table is searched; a proxy node compares the popularity of the content with a popularity threshold value K; a content source moves to a new position and sends a 'handoff completion' message to the proxy node, wherein it is indicated that handoff is completed if an M marking position is '2', and a K marking position is 'NULL'. According to the method, the mobility of mobile nodes in the content center network is achieved, and the mobility management method based on the proxy node and the web cache avoids communication outage caused by single-fault nodes and link failure; once the proxy node fails and can not serve any more, the network can automatically carry out handoff in a web cache mode, and therefore it is guaranteed that communications are conducted normally.

Methods and apparatus for processing requests for content received from customer devices are described. A decision on how to respond to a request for content is made at an edge node based on a locally maintained popularity list. The local popularity list reflects the local popularity of individual pieces of content at the edge node. A white list of content to be cached and served irrespective of popularity is sometimes used in combination with the local popularity list to make decisions as to how to respond to individual requests for content. In some embodiments the edge node decides on one of the following responses to a content request: i) cache and serve the requested content; ii) serve but don't cache the requested content; or iii) redirect the content request to another node, e.g., an alternate serving node, which can respond to the content request.

The invention discloses a content popularity prediction method based on depth learning under SDN architecture. The method comprises the steps that each node calculation resource and link in an SDN network to construct a reconfigurable and distributed depth learning network; the SDN network has an SDN controller and a number of SDN switch nodes; each SDN switch realizes the calculation function of a number of neurons; the neurons are connected with each other through the SDN switch link; each node in the SDN network collects space-time co-distribution data with requested content in real time and uses the data as the input of the depth learning network; a stack-type self-coder is used to carry out characteristic learning on the space-time co-distribution data; and a Softmax classifier is used to predict the content popularity. According to the invention, the reconfiguration of the depth learning network is realized based on the characteristics of programmable and global view centralized control SDN; the number of hidden layers and the nodes of each layer of neuron can be adjusted; and the method is very critical to an ICN analysis system, and can help dynamic routing and caching decisions in the system.

The invention discloses an SD-RAN (software defined radio access network)-based whole network cooperative caching management system and method. According to the SD-RAN (software defined radio access network)-based whole network cooperative caching management system and method, a content-popularity mapping table and a wait caching / replacement list are generated through detection and content popularity statistics, and a caching decision is made according to the wait caching / replacement list, and is issued to a caching node, so that caching and update can be carried out; a real-time global caching mapping table is obtained through monitoring the caching decision; and the caching node responds to a content request and delivers corresponding content according to the content request of a user of a current cell; characteristics of limitation of content acquisition delay and the change of the popularity of different content with time and places are fully considered, and a global network view in a control layer of a software defined network is fully utilized, and therefore, the detection range of the popularity of content can be expanded; and based on whole network cooperative caching optimized content arrangement, a situation that content is repeatedly called from a remote-end content server can be avoided, and network overhead can be reduced, and user experience can be improved.

The invention provides an information centric networking caching method based on content popularity prediction, relates to the technical field of communication network data processing, solves a caching redundancy problem in the prior art of information centric networking caching, and improves the sharing efficiency of cached contents. In the method, each node records the content names of all request contents received by each node, and similarities among all contents are calculated and are clustered; the content popularity value of each class of contents which pass through the node is calculated and is subjected to periodic statistics; and a prediction algorithm is used for predicting the content popularity value of each class of contents of a future moment of the node, and the content popularity value is added into the data packet of a hit node; and in a data packet returning process, a content popularity prediction value carried by the data packet is compared with a local content popularity prediction value to determine whether the contents are added into a node cache or not. The method is used for optimizing the cache access of content-based information centric networking.

The invention discloses an edge caching system and method based on content popularity prediction. The method comprises the following steps that: (1) according to the historical request information ofa user, training the preference model of each user in a node coverage region offline; (2) when a request arrives, if requested contents are not in the presence in a cache region, on the basis of the preference model of the user, carrying out the on-line prediction of content popularity; (3) comparing a content popularity prediction value with the minimum value of the content popularity of the cache region, and making a corresponding caching decision; and (4) updating a content popularity value at a current moment, evaluating the preference model of the user, and determining whether the offlinelearning of the preference model of the user is started or not. By use of the method, an edge node can predict the content popularity online and track the change of the content popularity in real time, the corresponding caching decision is made on the basis of the predicted content popularity, so that the edge node is guaranteed to continuously cache hot contents, and a caching hit rate which approaches to an ideal caching method is obtained.

The invention provides a cache policy based on match of content popularity and a node level. The cache policy is applied to a content center wireless network and realizes the match of the content popularity and the node level. Firstly, the cache performance of each node on a forwarding path is evaluated, the cache performance of the node is comprehensively evaluated from three parameters, namely the hops of the node from a user, the betweenness centrality and the replacement rate, wherein a gray correlation method is selected to assess and classify the nodes at the same time. Then, based on the matching probability of the content popularity and the node level, the node makes a cache decision on the content. By adopting the method, the cache space in the content center network is effectively utilized, so that the cache redundancy is reduced.

The invention discloses a content popularity-based CCN cache partition and substitution method, and belongs to the technical field of networks. Popularity of contents is taken into consideration on the basis of the traditional substitution method LRU, and contents with different popularity are partitioned for storage and substitution in node caches. According to the method, the contents with high and low popularity are stored separately according to the high and low popularity of the contents, so that the problem that the contents with low popularity are substituted by the contents with high popularity very soon due to a lower arrival rate is solved, the hit rate of the contents with low popularity is improved, an average hit distance for a user to acquire the contents with low popularity is reduced, and the network performance of the CCN is improved.

The invention relates to an on-line serial content popularity prediction method based on an autoregressive model. Compared with the prior art, the method overcomes the defect that no on-line serial content popularity prediction method exists in the prior art. The method includes the steps that training data are acquired, wherein crawling of the overall playback amount trend of the on-line serial content is carried out, an HTML source code of an overall playback amount trend page is analyzed, and HTML source codes of single-episode playback amount trend pages are analyzed; the popularity is predicated, wherein the popularity of new serial content is predicated through the autoregressive model. By means of the method, detection of the popularity of the on-line serial content can be achieved, a new index for evaluating the quality of the serial content is designed through model parameters serving as derivatives of a diversion model, and therefore the method has great significance in content recommendation.

A method for updating content. The method includes determining at least one indicator with respect to the content, wherein the at least one indicator is at least one of a user engagement indicator, a content popularity indicator, a content quality indicator, and a content update frequency indicator. The method further includes updating the content based on the at least one indicator, wherein the at least one indicator is dynamically updated.

The invention provides a content name storage structure oriented design method in a content network. Layered nested structures of nested segmented hash tables are aggregated through content names with the same prefix and accordingly the overhead of storage space is reduced; the segmented thought is introduced to segmented hash tables based on hash tables and the segmented hash tables are utilized as basic data structure units in the nested segmented hash tables, a bloom filter and a bit map are added to be utilized as index structures, pre-processing is provided for data entering into corresponding sub-table hash calculation, and accordingly the times of direct operation on storage tables are reduced and the search efficiency is improved; meanwhile a content popularity parameter based chain table method is utilized to solve the hash conflict and reduce the search time of popular content names, the parallel relationship between nodes in the same layer of sub-tables of the segmented hash tables and the nested segmented hash tables is introduced, and accordingly the computing power of a multi-core CPU (Central Processing Unit) can be effectively utilized in the implementation, data insertion, search and deletion operation in the segmented hash tables can be efficiently achieved, and the processing capacity of a content name storage structure is improved.

The media stream delivery system encodes and fragments media streams into numerous media stream fragments maintained on fragment servers. Devices obtain fragments to reconstruct media streams including live real-time media streams for playback on the devices. A device may perform caching of media stream fragments so that particular fragments need not be accessed again from a fragment server. A fragment server or even a content provider can analyze and monitor characteristics of media streams, viewing behavior, content popularity, etc., to identify fragments for caching at the playback devices. Caching indicators along with time period indicators may be included in the media stream fragments.

The embodiments of the invention provide a text content recommendation method. The method comprises the steps of acquiring user identifiers and user attribute tag values corresponding to the user identifiers; acquiring text content and extracting content attribute tag values of the text content; traversing the content attribute tag values, and for the traversed content attribute tag values, acquiring the total visit rate of the content attribute tag values and the user visit ratio and the user recommendation ratio corresponding to each user attribute tag value, and generating tag popularity degree values of the traversed content attribute tag values; generating content popularity degree values of the text content with respect to the user identifiers by calculating the average values of the tag popularity degree values of the content attribute tag values corresponding to the text content, selecting text content according to the content popularity degree values and transmitting the links of the selected text content to terminals corresponding to the user identifiers. The invention also provides a text content recommendation device. According to the invention, the recommendation accuracy is improved.

Embodiments of the present disclosure help content providers identify popular topics based on Internet search data, as well as to quantify the popularity of content addressing those topics. A computer-implemented method according to one embodiment of the present disclosure comprises receiving search data by a computer system; identifying a category related to at least a portion of the search data; determining, by the computer system and based on the search data, a topic for content associated with the identified category; and determining, by the computer system, a score indicative of a level of popularity for the topic, wherein determining the score is based on the search data and on one or more formats for the content associated with the topic.

The invention relates to a cache method based on content popularity and a device thereof. The method comprises the following steps: dividing a time into a plurality of time slots, wherein the plurality of the time slots are previous k time slots of a current time slot, and the length of each of the time slots is T; learning content objects of the previous k time slots and obtaining a historical popularity of the content objects in the previous k time slots, wherein the k is a natural number; predicting the popularity of the content objects in a future time slot according to the historical popularity to obtain predicted popularity; modeling cache decisions of the content objects into a 0-1 knapsack model according to the predicted popularity; and solving the 0-1 knapsack model via a popularity priority greedy cache algorithm, obtaining a cache priority according to a solving result, and caching the content objects according to the cache priority. According to the cache method based on the content popularity and the device thereof, the problems of low cache accuracy and cache performance due to a fact that the content popularity is not considered or the content popularity is not set in the prior art are solved, the cache accuracy as well as the performance of a cache system is greatly improved, and the practicability is relatively strong.

The invention discloses a construction method of an ISP and CP combined content distribution mechanism based on edge cache. The method comprises the following steps: acquiring network content request data, and extracting content related information; analyzing a network content popularity feature, and designing a content popularity model; deploying the content at a network edge according to the content popularity model; counting the load of a CP content source server, and computing CP service cost; analyzing the load of an ISP network node and the traffic transmitted by a link, and computing ISP network service cost; computing the cost caused by cache importing according to the deployed cache capacity; constructing a yield model of the ISP and CP combined service based on the edge cache; and analyzing the relation among various factors in the designed model, and verifying the effectiveness of the designed model in a simulation way.

The present invention relates to a network visit statistical method which is used for the counting of the programs watched by the terminal user in the content distribution network. The content distribution network includes a central node server and a plurality of rim node servers, with the central node server storing all the programs and the rim node servers storing the most popular programs. The method includes the following steps: first, obtaining the actual watching time in each dialogue; second, counting the content marks of the aforesaid programs in each dialogue; last, summarizing all the marks of the aforesaid programs. The network visit statistical method provided by the present invention can reflect the popularity of the programs veritably, and the content distribution network can achieve reasonable distribution of the programs in the network according to the actual statistical result so as to improve the efficiency of the content distribution network.

Provided is a method for content popularity extraction from a distributed hash table (DHT). The method includes receiving, by a first node, a request message from a second node of a peer-to-peer network. Accessing, by the first node, information associated with the request message, the information indicating a content item and a content demand. And determining, by the first node, a content popularity of a plurality of content items based on the information.

The invention discloses a proactive caching method based on content popularity and movement rules of users. By introducing social relationship mining, users in a small cellular network are subjected to community division, and according to a Zipf law, content popularity distribution of each community is analyzed; by a frequent pattern mining algorithm, the movement rules of the users are mined, andaccording to a rule confidence degree, probability distribution that the user accesses each base station in a next time period is acquired; and according to content request distribution of the usersand probability distribution of accessing to each base station, under limited cache capacity of each base station, a cache hit ratio is maximized by optimizing a caching strategy. By adopting the proactive caching method disclosed by the invention, a return load can be reduced, and a user delay is reduced; and meanwhile, the method has the decomposition characteristic and is low in algorithm complexity.

The invention discloses a named data network adaptive caching strategy for vehicle networking;by extracting the number of request prefix occurrences of Vj1, Vj2, and Vj3 in the data packet return pathof the previous time window, requesting the average of the number of occurrences of the prefix to calculate the content popularity, and calculating the interval hop count of the data packet buffer ofthe node;calculating the interval hops of the node's Data packet cache. The invention combines cache content and traffic flow dynamic characteristics, and proposes a cache decision based on content popularity and vehicle density, and caches data packets by hopping.Calculating the interval hops of the node's Data packet cache based on the content popularity in the named data network. Then, the vehicle density is adaptively adjusted to adjust the hop count, and the data packet is cached by the hop to effectively release the buffer space, thereby solving the problem of homogenization cache and low cache efficiency, optimizing the overall performance of the vehicle networking, reducing congestion, reducing the network overhead, reducing the cache redundancy in the network, avoiding the problem of broadcast storm, and improving the utilization rate of network resources and the overall network performance.

The invention provides a cooperative caching method of content-centric networking. The method comprises the following steps: classifying network nodes to obtain a node cluster with a cluster ID, and performing level setting on the nodes in the node cluster; if that content packets are cached in the current node is detected after the current node receives an interest packet endowed with the cluster ID transmitted by the user terminal, generating a first content packet into which the cluster ID of the interest packet is added, and returning the first content packet through a reverse path of the interest packet; and if a first preset condition is satisfied when an intermediate node receives the first content packet, caching the first content packet by the intermediate node, and continually returning the first content packet through the reverse path of the interest packet when that the first content packet exists in a PIT table is determined. Through adoption of the cooperative caching method, caching is performed by a cluster head node within a network range, and is performed on the basis of network content popularity in the cluster, so that the content diversity of the cluster head node is ensured, and the hit rate and acquisition speed of network contents are increased.

The invention relates to a content popularity prediction method and device based on artificial intelligence, a computer readable storage medium and computer equipment. The method comprises the steps of determining content of to-be-predicted popularity; performing interaction quantity characteristic analysis according to the interaction quantity of the content to obtain interaction quantity characteristics of the content in the distribution process; performing content feature analysis on the content data corresponding to the content to obtain content features of the content; performing producerfeature analysis according to the producer data of the content producer associated with the content to obtain producer features of the content; and performing content popularity prediction in combination with the interaction quantity characteristics, the content characteristics and the producer characteristics to obtain a popularity prediction result of the content. According to the scheme provided by the invention, the accuracy of content popularity prediction can be improved.

One embodiment of the present invention provides a system for ranking content popularity in a content-centric network (CCN) content cache. During operation, the system receives an interest in a piece of content stored in the content cache, services the interest by accessing the piece of content, updates a service rate associated with the piece of content, updates system-wide service rate statistics, and determines a popularity level associated with the piece of content based on the updated service rate and the updated system-wide service rate statistics.

The invention discloses a content popularity prediction and edge caching method based on deep learning. The method comprises the following steps: (1) preprocessing content popularity data; (2) offlinetraining the neural network to obtain a popularity prediction model and a content classifier; (3) obtaining the category of the content by a content classifier, and predicting the popularity of the content online by using a prediction model of the corresponding category; and (4) comparing the popularity predicted values of all the contents, and making a corresponding cache decision. According tothe invention, under the condition that only the characteristic of content request frequency is used; the edge nodes are enabled to predict popularity of different contents online and track popularitychanges of the contents in real time, and a corresponding caching decision is made based on the predicted content popularity, so that the edge nodes are ensured to continuously cache hot contents, and a caching hit rate which is asymptotically close to an ideal caching method is obtained.

The invention discloses a CCN caching method based on content popularity and node importance. On the basis of carrying out ranking on the content popularity, a centrality of a node is considered; whenrequest contents are returned along an original path, the contents are cached on a node with the maximum node centrality; after the node is full cached, a content popularity ranking table is generated in the node; then popularity of newly arrived contents is respectively compared to the maximum and minimum popularity in the node; and then whether the new contents are cached in the node is decided. A simulation result shows that according to the scheme, a routing node cache hit ratio is improved; and an average hop count of acquired contents is reduced.

In a method for the dynamic content discovery in a distributed caching network the distribution of content popularity and its access frequency rate are used to determine the most appropriate mapping method(s) to use.

The invention discloses a method for constructing an energy-efficient network content distribution mechanism based on edge caching, and the method comprises the following specific steps: constructinga system model according to the change of a network service mode, and deploying content at the edge of a network according to the system model; according to the network edge deployment content, constructing network power consumption models of ISP and CP, and performing constraint and simplification; and performing optimization solution on the network power consumption model based on reinforcementlearning. According to the method, the problem that existing research basically aims at prediction angles such as content popularity and cache hit rate and lacks an optimal routing scheme based on machine learning to solve the ISP and CP cooperative energy consumption problem is solved, a centralized system model is established for ISP and CP power consumption by researching behavior changes of network participants in an edge cache environment, machine learning is used to carry out distributed online and offline solution, and a calculation result is compared with a theoretical value.