CN112153393B

CN112153393B - Audio and video processing method based on weak network environment and artificial intelligence service center

Info

Publication number: CN112153393B
Application number: CN202011068362.6A
Authority: CN
Inventors: 刘风华
Original assignee: Nanjing Guiji Intelligent Technology Co ltd
Current assignee: Nanjing Guiji Intelligent Technology Co ltd
Priority date: 2020-10-08
Filing date: 2020-10-08
Publication date: 2021-08-17
Anticipated expiration: 2040-10-08
Also published as: CN112153393A

Abstract

The embodiment of the invention provides an audio and video processing method based on a weak network environment and an artificial intelligence service center, wherein when an audio and video playing device sends an audio and video pushing request to a first audio and video server, the artificial intelligence service center is independently based on to obtain network environment configuration information synchronously sent by the audio and video playing device, meanwhile, the audio and video pushing request is synchronously forwarded to at least one second audio and video server to continue pushing according to the transmission quality information, the network environment configuration information and configuration information of other audio and video servers registered in the artificial intelligence service center when the audio and video playing device is judged to be in the weak network environment according to the transmission quality information and the network environment configuration information, and therefore, the situation that the configuration of the audio and video playing device is not compatible with the audio and video servers to cause that the period of integral data transmission is seriously prolonged is avoided by accurately switching to the other video servers The situation is.

Description

Audio and video processing method based on weak network environment and artificial intelligence service center

Technical Field

The invention relates to the technical field of multimedia data transmission, in particular to an audio and video processing method and an artificial intelligence service center based on a weak network environment.

Background

When the audio and video playing device is in the weak network environment, connection can be repeatedly established with the server side in a circulating mode, and the connection can be tried again after timeout fails, however, in most cases, the weak network environment is mainly caused by the fact that an audio and video server communicated with the audio and video playing device is abnormal or the configuration of the audio and video playing device is incompatible with the audio and video server, so that the period of overall data transmission is seriously prolonged due to the repeatedly-tried scheme, and user experience is reduced.

Disclosure of Invention

In order to overcome the above-mentioned deficiencies in the prior art at least, the present invention aims to provide an audio/video processing method and an artificial intelligence service center based on a weak network environment, wherein when an audio/video playing device sends an audio/video pushing request to a first audio/video server, network environment configuration information synchronously sent by the first audio/video server is obtained based on the artificial intelligence service center alone, and considering that transmission quality information of the audio/video information normally pushed by the first audio/video server is synchronous with the audio/video playing device, therefore, the transmission quality information of the audio/video information pushed by the first audio/video server can be simultaneously obtained from the first audio/video server, and whether the audio/video playing device is in the weak network environment is judged according to the transmission quality information and the network environment configuration information, and when the audio/video playing device is judged to be in the weak network environment, the audio/video processing method and the artificial intelligence service center are based on the transmission quality information, the network environment configuration information and the configuration information of the remaining audio/video servers registered in the artificial intelligence service center, the audio and video push request is synchronously forwarded to at least one second audio and video server to continue to be pushed, so that the situation that the period of overall data transmission is seriously prolonged due to the fact that the configuration of the audio and video playing device is incompatible with the audio and video server is avoided by accurately switching to the other video servers.

In a first aspect, the present invention provides an audio/video processing method based on a weak network environment, which is applied to an artificial intelligence service center, wherein the artificial intelligence service center is in communication connection with a plurality of audio/video playing devices, and the method includes:

according to network environment configuration information synchronously sent when the audio and video playing equipment sends an audio and video pushing request to a first audio and video server, acquiring transmission quality information of audio and video information pushed to the audio and video playing equipment by the first audio and video server based on the audio and video pushing request from the first audio and video server;

judging whether the audio and video playing equipment is in a weak network environment or not according to the transmission quality information and the network environment configuration information;

when the audio and video playing device is judged to be in the weak network environment, the audio and video pushing request is synchronously forwarded to at least one second audio and video server based on the transmission quality information, the network environment configuration information and the configuration information of the audio and video servers registered in the artificial intelligence service center, so that the at least one second audio and video server continues to push the audio and video information to the audio and video playing device based on the audio and video pushing request.

In a possible implementation manner of the first aspect, the step of determining whether the audio/video playing device is in a weak network environment according to the transmission quality information and the network environment configuration information includes:

obtaining transmission quality configuration information from the network environment configuration information;

judging whether the transmission quality configuration information is matched with the transmission quality information;

and when the transmission quality configuration information is not matched with the transmission quality information, judging that the audio and video playing equipment is in a weak network environment.

In a possible implementation manner of the first aspect, the step of synchronously forwarding the audio/video push request to at least one second audio/video server based on the transmission quality information, the network environment configuration information, and configuration information of the remaining audio/video servers registered in the artificial intelligence service center includes:

acquiring target network environment configuration information of a weak network reason associated with the transmission quality information from the network environment configuration information;

acquiring weak network state node information and network protocol information of the weak network state node information from the target network environment configuration information; the network transmission control channels used by the weak network state node information and the network protocol information are first network transmission control channels;

processing the weak network state node information according to the network protocol information to generate state service update information of the weak network state node information;

weak network feature extraction is carried out on the weak network state node information and the state service updating information, and second weak network element information corresponding to first weak network element information corresponding to the state service updating information is determined from the extracted current weak network feature information;

clustering and fusing the first weak network element information and the second weak network element information to obtain third weak network element information;

outputting expanded network state node distribution corresponding to the weak network state node information according to the third weak network element information; the network transmission control channel used by the expanded network state node is a second network transmission control channel;

searching a target audio/video server matched with the distribution of the extended network state nodes according to the configuration information of the rest audio/video servers registered in the artificial intelligence service center to serve as at least one second audio/video server;

and synchronously forwarding the audio and video pushing request to at least one second audio and video server.

In a possible implementation manner of the first aspect, the step of processing the weak network state node information according to the network protocol information to generate state service update information of the weak network state node information includes:

weak network feature extraction is carried out on the weak network state node information, network system identification is carried out on first weak network features corresponding to the obtained weak network state node information, and a first network system node set corresponding to the weak network state node information is obtained according to the identified network system;

weak network feature extraction is carried out on the network protocol information, network type identification is carried out on second weak network features corresponding to the obtained network protocol information, and a second network type node set corresponding to the network protocol information is obtained according to the identified network type;

acquiring first transmission unit information stored in the first network system node set, and converting the first transmission unit information into corresponding first transmission unit configuration;

acquiring second transmission unit information respectively stored by a plurality of key transmission units in the second network type node set, and converting each piece of second transmission unit information into corresponding second transmission unit configuration;

calculating a same transmission unit configuration of each of the second transmission unit configurations as the first transmission unit configuration;

sequencing the same transmission unit configuration corresponding to each second transmission unit configuration, and selecting a plurality of similar transmission unit configurations from the second transmission unit configurations according to a sequencing result;

clustering the configuration of the similar transmission units to obtain a clustering unit cluster;

and determining a sequence formed by the transmission unit services corresponding to the clustering unit cluster as the state service update information of the weak network state node information.

In a possible implementation manner of the first aspect, the step of performing weak network feature extraction on the weak network state node information and the state service update information, and determining, from the extracted current weak network feature information, second weak network element information corresponding to first weak network element information corresponding to the state service update information includes:

weak network feature extraction is carried out on the weak network state node information and the state service updating information, and current weak network feature information mapped in weak network features of the weak network state node information and the state service updating information is obtained; the current weak network characteristic information comprises distribution characteristic information of a plurality of weak network element nodes;

determining similar distribution characteristic information of the first weak network element information from distribution characteristic information of a plurality of weak network element nodes contained in the current weak network characteristic information, and taking the similar distribution characteristic information as the second weak network element information.

In a possible implementation manner of the first aspect, the clustering and fusing the first weak network element information and the second weak network element information to obtain third weak network element information includes:

inputting the first weak network element information and the second weak network element information into a preset state distribution analysis model respectively, so that the state distribution analysis model outputs effective weak network element information of the first weak network element information and the second weak network element information respectively, and a first target weak network element information and a second target weak network element information are obtained;

performing information mining calculation on the first target weak network element information to obtain first network element information mining information; weak network feature extraction is carried out on the first target weak network element information, information mining calculation is carried out on the extracted weak network element information to obtain second network element information mining information, and fusion mining information of the first network element information mining information and the second network element information mining information is calculated to obtain a first weak network element set corresponding to the first target weak network element information;

performing information mining calculation on the second target weak network element information to obtain third network element information mining information, performing weak network feature extraction on the second target weak network element information, performing information mining calculation on the extracted weak network element information to obtain fourth network element information mining information, and calculating fusion mining information of the third network element information mining information and the fourth network element information mining information to obtain a second weak network element set corresponding to the second target weak network element information;

and calculating a fusion network element set of the first weak network element set and the second weak network element set, and taking the obtained fusion network element set as the third weak network element information.

In a possible implementation manner of the first aspect, the step of outputting, according to the third weak network element information, the expanded network state node distribution corresponding to the weak network state node information includes:

acquiring communication port vectors distributed by a plurality of weak network state nodes in the third weak network element information and a weak network state node distribution analysis strategy corresponding to a communication port vector combination distributed by each weak network state node, wherein the communication port vectors distributed by the weak network state nodes comprise a communication port vector distributed by a first weak network state node and a communication port vector distributed by a second weak network state node, and the communication port vector distributed by the first weak network state node and the communication port vector distributed by the second weak network state node are communication port vector combinations with mapping correlation weak network state node distribution between the communication port vectors;

performing link prediction on the third weak network element information to output a first basic link prediction vector corresponding to a communication port vector combination distributed by each first weak network state node and a target link prediction vector corresponding to the third weak network element information;

calculating the degree of association between the target link prediction vector and each first basic link prediction vector to obtain the link prediction vector proximity between the communication port vector distributed by each corresponding first weak network state node and the third weak network element information;

identifying all vector segments in the communication port vector distributed by each first weak network state node and the communication link weight corresponding to the communication port vector distributed by each first weak network state node;

generating a distribution cluster of communication port vectors distributed by corresponding weak network state nodes according to all the vector fragments and the communication link weight;

generating a distribution cluster range corresponding to the communication port vector combination distributed by each weak network state node according to the weak network state node distribution analysis strategy;

obtaining a first statistical description group of each communication port vector distributed by each weak network state node by using each distribution cluster corresponding to the distribution cluster range;

clustering according to the communication port vector combinations distributed by the second weak network state nodes and the first basic link prediction vector corresponding to the communication port vector combination distributed by each weak network state node to obtain a second statistical description group of the communication port vector distributed by each weak network state node;

determining communication port vectors distributed by target weak network state nodes from the communication port vectors distributed by the plurality of weak network state nodes according to a common communication port vector between the first statistical description group and the second statistical description group;

and combining the communication port vectors distributed by the target weak network state nodes with the corresponding first basic link prediction vector to serve as a second link prediction vector, and adding the second link prediction vector to the third weak network element information to output the expanded network state node distribution corresponding to the weak network state node information.

For example, in a possible implementation manner of the first aspect, the weak network state node distribution analysis policy includes a response feature analysis policy for communication port vectors distributed by the weak network state node and a network quality analysis policy corresponding to a combination of the communication port vectors distributed by the weak network state node;

the step of generating a distribution cluster range corresponding to the communication port vector combination distributed by each weak network state node according to the weak network state node distribution analysis strategy comprises the following steps:

performing network quality analysis on the communication port vectors distributed by the weak network state nodes according to the network quality analysis strategy to generate network quality characteristic values corresponding to the communication port vector combinations distributed by the weak network state nodes;

performing response characteristic analysis on the communication port vectors distributed by the weak network state nodes according to the response characteristic analysis strategy to generate response characteristic analysis values corresponding to the communication port vector combinations distributed by the weak network state nodes;

and determining the characteristic value range interval of the network quality characteristic value and the response characteristic analysis value as the distribution cluster range of the communication port vector combination corresponding to the weak network state node distribution.

For example, in a possible implementation manner of the first aspect, the distributed communication port vectors of the weak network state nodes further include a communication port vector of a third weak network state node;

before the step of obtaining, by using each distribution cluster corresponding to the distribution cluster range, a respective first statistical description group of communication port vectors distributed by each weak network state node, the method further includes:

calculating a link prediction disturbance parameter of each reference link prediction object in a reference link prediction object list corresponding to a communication port vector distributed by each first basic link prediction vector relative to the third weak network state node;

fusing all link prediction disturbance parameters corresponding to each first basic link prediction vector combination to obtain a fused link prediction parameter corresponding to each first basic link prediction vector combination;

according to the fusion link prediction parameters corresponding to each first basic link prediction vector combination, arranging all the first basic link prediction vectors in sequence, and determining the respective priority parameters of each first basic link prediction vector according to the arranged sequence of each first basic link prediction vector;

processing the fusion link prediction parameters corresponding to each first basic link prediction vector according to the priority parameters of each first basic link prediction vector to generate weighted fusion link prediction parameters of communication port vectors distributed by each weak network state node;

the step of obtaining a respective first statistical description group of the communication port vectors distributed by each weak network state node by using each distribution cluster corresponding to the distribution cluster range includes:

and clustering the weighted fusion link prediction parameters of the communication port vectors distributed by each weak network state node by using each distribution cluster corresponding to the distribution cluster range to obtain a first statistical description group corresponding to the communication port vector combination distributed by each weak network state node.

In a second aspect, an embodiment of the present invention further provides an audio/video processing apparatus based on a weak network environment, which is applied to an artificial intelligence service center, where the artificial intelligence service center is in communication connection with a plurality of audio/video playing devices, and the apparatus includes:

the acquisition module is used for acquiring transmission quality information of the audio and video information pushed to the audio and video playing equipment by the first audio and video server based on the audio and video pushing request from the first audio and video server according to network environment configuration information synchronously sent when the audio and video pushing request is sent to the first audio and video server by the audio and video playing equipment;

the judging module is used for judging whether the audio and video playing equipment is in the weak network environment or not according to the transmission quality information and the network environment configuration information;

a forwarding module, configured to, when it is determined that the audio/video playing device is in a weak network environment, based on the transmission quality information, the network environment configuration information, and configuration information of the remaining audio/video servers registered in the artificial intelligence service center, synchronously forward the audio/video push request to at least one second audio/video server, so that the at least one second audio/video server continues to push audio/video information to the audio/video playing device based on the audio/video push request

In a third aspect, an embodiment of the present invention further provides an artificial intelligence service center, where the artificial intelligence service center includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being communicatively connected with at least one audio/video playing device, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium to execute the audio/video processing method based on the weak network environment in the first aspect or any one of the possible implementation manners in the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed, the computer is caused to execute the audio and video processing method in the weak network environment according to the first aspect or any one of the possible implementation manners of the first aspect.

Based on any one of the above aspects, in the embodiment of the present invention, when the audio/video playing device sends an audio/video pushing request to the first audio/video server, the network environment configuration information synchronously sent by the first audio/video server is obtained based on the artificial intelligence service center alone, and considering that the transmission quality information of the audio/video information normally pushed by the first audio/video server is synchronous with the audio/video playing device, so that the transmission quality information of the audio/video information pushed by the first audio/video server can be simultaneously obtained from the first audio/video server, and whether the audio/video playing device is in a weak network environment is judged according to the transmission quality information and the network environment configuration information, and when the audio/video playing device is judged to be in the weak network environment, the audio/video pushing request is synchronously forwarded to at least one second audio/video server to continue to be pushed based on the transmission quality information, the network environment configuration information, and the configuration information of the remaining audio/video servers registered in the artificial intelligence service center, therefore, the situation that the whole data transmission period is seriously prolonged due to the incompatibility of the configuration of the audio and video playing equipment and the audio and video server is avoided by accurately switching to the other video servers.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic view of an application scenario of an audio/video processing method system based on a weak network environment according to an embodiment of the present invention;

fig. 2 is a schematic flowchart of an audio and video processing method based on a weak network environment according to an embodiment of the present invention;

fig. 3 is a functional module schematic diagram of an audio/video processing method and apparatus based on a weak network environment according to an embodiment of the present invention;

fig. 4 is a schematic block diagram of a structure of an artificial intelligence service center for implementing the audio/video processing method based on the weak network environment according to the embodiment of the present invention.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used in this specification is a method for distinguishing different components, elements, parts or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Fig. 1 is an interaction schematic diagram of an audio and video processing method system 10 in a weak network environment according to an embodiment of the present invention. The audio and video processing method system 10 based on the weak network environment may include an artificial intelligence service center 100 and an audio and video playing device 200 communicatively connected to the artificial intelligence service center 100. The system 10 for audio and video processing under the weak network environment shown in fig. 1 is only one possible example, and in other possible embodiments, the system 10 for audio and video processing under the weak network environment may also include only a part of the components shown in fig. 1 or may also include other components.

In this embodiment, the internet of things cloud artificial intelligence service center 100 and the audio and video playing device 200 in the audio and video processing method system 10 based on the weak network environment may execute the audio and video processing method based on the weak network environment described in the following method embodiment in a matching manner, and the specific steps of the artificial intelligence service center 100 and the audio and video playing device 200 may refer to the detailed description of the following method embodiment.

In order to solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of an audio and video processing method based on a weak network environment according to an embodiment of the present invention, where the audio and video processing method based on a weak network environment according to the embodiment may be executed by the artificial intelligence service center 100 shown in fig. 1, and the audio and video processing method based on a weak network environment is described in detail below.

Step S110, according to the network environment configuration information synchronously sent when the audio/video playing device 200 sends the audio/video pushing request to the first audio/video server, obtaining, from the first audio/video server, transmission quality information of the audio/video information that is pushed by the first audio/video server to the audio/video playing device 200 based on the audio/video pushing request.

Step S120, determining whether the audio/video playing device 200 is in the weak network environment according to the transmission quality information and the network environment configuration information.

Step S130, when it is determined that the audio/video playing device 200 is in the weak network environment, based on the transmission quality information, the network environment configuration information, and the configuration information of the remaining audio/video servers registered in the artificial intelligence service center, synchronously forwarding the audio/video push request to the at least one second audio/video server, so that the at least one second audio/video server continues to push the audio/video information to the audio/video playing device 200 based on the audio/video push request.

In this embodiment, when sending the audio/video push request to the first audio/video server, the audio/video playing device 200 may synchronously send the corresponding network environment configuration information to the artificial intelligence service center 100, so that it is not necessary for the user to manually upload the network environment configuration information when the user is in a weak network state. Also, since the network environment configuration information generally occupies a small number of bytes, it can be transmitted to the artificial intelligence service center 100 quickly even in a weak network environment.

In this embodiment, when it is determined that the audio/video playing device 200 is in the weak network environment, the audio/video push request may be synchronously forwarded to the at least one second audio/video server based on the transmission quality information, the network environment configuration information, and the configuration information of the remaining audio/video servers registered in the artificial intelligence service center, so that the at least one second audio/video server may continue to push the audio/video information to the audio/video playing device 200 based on the audio/video push request. For example, in some preferred implementation manners, at least one second audio/video server may obtain a playing progress of current audio/video playing information in advance, and then obtain the audio/video information located after the playing progress based on the playing progress to push, or when the number of the second audio/video servers exceeds two, obtain the audio/video information located at different stages after the playing progress to push, so that the pushing efficiency may be further improved.

Based on the above design, in this embodiment, the network environment configuration information synchronously sent by the artificial intelligence service center is acquired based on the artificial intelligence service center alone, meanwhile, when the audio/video playing device 200 is determined to be in the weak network environment according to the transmission quality information and the network environment configuration information, based on the transmission quality information, the network environment configuration information, and the configuration information of the remaining audio/video servers registered in the artificial intelligence service center, the audio/video push request is synchronously forwarded to at least one second audio/video server for continuous push, so that the situation that the period of the whole data transmission is seriously lengthened due to incompatibility between the configuration of the audio/video playing device 200 itself and the audio/video servers is avoided by accurately switching to the remaining video servers.

In a possible implementation manner, for step S120, it is considered that the actual transmission quality is not necessarily related to the weak network state, but may also be related to the configuration of the user itself, so to improve the determination accuracy of the weak network environment, the transmission quality configuration information may be obtained from the network environment configuration information, and then it is determined whether the transmission quality configuration information matches the transmission quality information, and when the transmission quality configuration information does not match the transmission quality information, it is determined that the audio/video playing device 200 is in the weak network environment.

In one possible implementation, step S130 may be implemented by the following exemplary sub-steps, which are described in detail below.

Substep S131 obtains target network environment configuration information of the weak network cause associated with the transmission quality information from the network environment configuration information.

And a substep S132, acquiring the weak network state node information and the network protocol information of the weak network state node information from the target network environment configuration information. And the network transmission control channels used by the weak network state node information and the network protocol information are first network transmission control channels.

And a substep S133, processing the weak network state node information according to the network protocol information, and generating state service update information of the weak network state node information.

For example, in some possible implementation manners, weak network feature extraction may be performed on weak network state node information, network system identification may be performed on a first weak network feature corresponding to the obtained weak network state node information, and a first network system node set corresponding to the weak network state node information may be obtained according to the identified network system. And then, weak network feature extraction is carried out on the network protocol information, network type identification is carried out on second weak network features corresponding to the obtained network protocol information, and a second network type node set corresponding to the network protocol information is obtained according to the identified network type.

On this basis, the first transmission unit information stored in the first network system node set can be acquired, the first transmission unit information is converted into the corresponding first transmission unit configuration, the second transmission unit information stored in each of the plurality of key transmission units in the second network system node set is acquired, and each piece of second transmission unit information is converted into the corresponding second transmission unit configuration. Therefore, the same transmission unit configuration of each second transmission unit configuration and the first transmission unit configuration can be calculated, the same transmission unit configuration corresponding to each second transmission unit configuration is sorted, and a plurality of similar transmission unit configurations are selected from the plurality of second transmission unit configurations according to the sorting result. Therefore, clustering processing can be carried out on the configuration of the plurality of similar transmission units to obtain a clustering unit cluster, and then a sequence formed by the transmission unit services corresponding to the clustering unit cluster is determined as the state service update information of the weak network state node information.

For example, in some possible implementation manners, weak network feature extraction may be performed on the weak network state node information and the state service update information to obtain current weak network feature information mapped in the weak network features of the weak network state node information and the state service update information. The current weak network characteristic information includes distribution characteristic information of a plurality of weak network element nodes. Then, similar distribution characteristic information of the first weak network element information is determined from distribution characteristic information of a plurality of weak network element nodes contained in the current weak network characteristic information, and the similar distribution characteristic information is used as second weak network element information.

And a substep S134, performing weak network feature extraction on the weak network state node information and the state service update information, and determining second weak network element information corresponding to the first weak network element information corresponding to the state service update information from the extracted current weak network feature information.

And a substep S135, performing clustering fusion on the first weak network element information and the second weak network element information to obtain third weak network element information.

For example, in some possible implementation manners, the first weak network element information and the second weak network element information may be respectively input into a preset state distribution analysis model, so that the state distribution analysis model respectively outputs respective effective weak network element information of the first weak network element information and the second weak network element information, and the first target weak network element information and the second target weak network element information are obtained. Meanwhile, information mining calculation is carried out on the first target weak network element information, and first network element information mining information is obtained. Weak network feature extraction is carried out on the first target weak network element information, information mining calculation is carried out on the extracted weak network element information to obtain second network element information mining information, and fusion mining information of the first network element information mining information and the second network element information mining information is calculated to obtain a first weak network element set corresponding to the first target weak network element information.

On the basis, information mining calculation can be performed on second target weak network element information to obtain third network element information mining information, weak network feature extraction is performed on the second target weak network element information, information mining calculation is performed on the extracted weak network element information to obtain fourth network element information mining information, fusion mining information of the third network element information mining information and the fourth network element information mining information is calculated, and a second weak network element set corresponding to the second target weak network element information is obtained. In this way, a fused network element set of the first weak network element set and the second weak network element set can be calculated, and the obtained fused network element set is used as the information of the third weak network element.

And a substep S136, outputting the expanded network state node distribution corresponding to the weak network state node information according to the third weak network element information.

It should be noted that the network transmission control channel used by the expanded network state node is the second network transmission control channel.

And a substep S137 of searching a target audio/video server matched with the distribution of the extended network state nodes according to the configuration information of the rest audio/video servers registered in the artificial intelligence service center to serve as at least one second audio/video server.

And a substep S138, synchronously forwarding the audio/video push request to at least one second audio/video server.

Exemplarily, in the sub-step S136, it can be implemented by the following exemplary embodiments, which are described as follows.

(1) And acquiring communication port vectors distributed by a plurality of weak network state nodes in the third weak network element information and a weak network state node distribution analysis strategy corresponding to the communication port vector combination distributed by each weak network state node, wherein the communication port vectors distributed by the weak network state nodes comprise the communication port vector distributed by the first weak network state node and the communication port vector distributed by the second weak network state node.

For example, the communication port vector distributed by the first weak network state node and the communication port vector distributed by the second weak network state node are the communication port vector combination with the mapping relationship between the communication port vectors distributed by the weak network state nodes.

(2) And performing link prediction on the third weak network element information to output a first basic link prediction vector corresponding to the communication port vector combination distributed by each first weak network state node and a target link prediction vector corresponding to the third weak network element information.

(3) And calculating the degree of association between the target link prediction vector and each first basic link prediction vector to obtain the link prediction vector proximity between the communication port vector distributed by each corresponding first weak network state node and the third weak network element information.

(4) All vector segments in the communication port vector distributed by each first weak network state node and the communication link weight corresponding to the communication port vector distributed by each first weak network state node are identified.

(5) And generating a distribution cluster of the communication port vectors distributed by the corresponding weak network state nodes according to all the vector fragments and the communication link weights.

(6) And generating a distribution cluster range corresponding to the communication port vector combination distributed by each weak network state node according to the weak network state node distribution analysis strategy.

For example, the weak network state node distribution analysis policy includes a response characteristic analysis policy for the communication port vectors distributed by the weak network state node and a network quality analysis policy corresponding to the communication port vector combination distributed by the weak network state node.

Therefore, the network quality analysis can be carried out on the communication port vectors distributed by the weak network state nodes according to the network quality analysis strategy, and the network quality characteristic values corresponding to the communication port vector combinations distributed by the weak network state nodes are generated. Meanwhile, response characteristic analysis is carried out on the communication port vectors distributed by the weak network state nodes according to the response characteristic analysis strategy, and response characteristic analysis values corresponding to the communication port vector combinations distributed by the weak network state nodes are generated. In this way, the range interval of the characteristic values of the network quality characteristic value and the response characteristic analysis value can be determined as the distribution cluster range of the communication port vector combination corresponding to the weak network state node distribution.

(7) And obtaining a first statistical description group of the communication port vector distributed by each weak network state node by using each distribution cluster corresponding to the distribution cluster range.

(8) And clustering according to the communication port vector combinations distributed by the second weak network state nodes and the first basic link prediction vector corresponding to the communication port vector combination distributed by each weak network state node to obtain a second statistical description group of the communication port vector distributed by each weak network state node.

(9) And determining the communication port vectors distributed by the target weak network state nodes from the communication port vectors distributed by the plurality of weak network state nodes according to the common communication port vectors between the first statistical description group and the second statistical description group.

(10) And combining the communication port vectors distributed by the target weak network state nodes with the corresponding first basic link prediction vector to serve as a second link prediction vector, and adding the second link prediction vector into the third weak network element information to output the expanded network state node distribution corresponding to the weak network state node information.

It is worth noting that the communication port vector distributed by the weak network state node can also comprise a communication port vector distributed by a third weak network state node.

For example, before (7), a link prediction perturbation parameter of each reference link prediction object in the reference link prediction object list corresponding to the communication port vector distributed by each first basic link prediction vector relative to the third weak network state node may be calculated, and then all link prediction perturbation parameters corresponding to each first basic link prediction vector combination may be fused to obtain a fused link prediction parameter corresponding to each first basic link prediction vector combination. Therefore, the fused link prediction parameters corresponding to each first basic link prediction vector can be combined according to each first basic link prediction vector, all the first basic link prediction vectors are arranged in sequence, the priority parameter of each first basic link prediction vector is determined according to the sequence after the arrangement of each first basic link prediction vector, and therefore the weighted fused link prediction parameters of the communication port vectors distributed by each weak network state node can be generated by processing the fused link prediction parameters corresponding to each first basic link prediction vector according to the priority parameter of each first basic link prediction vector.

Thus, in (7), the weighted fusion link prediction parameters of the communication port vectors distributed by each weak network state node can be clustered by using each distribution cluster corresponding to the distribution cluster range, so as to obtain a first statistical description group corresponding to the communication port vector combination distributed by each weak network state node.

Fig. 3 is a schematic diagram of functional modules of an audio/video processing device 300 based on a weak network environment according to an embodiment of the present invention, and this embodiment may perform functional module division on the audio/video processing device 300 based on the weak network environment according to a method embodiment executed by the artificial intelligence service center 100, that is, the following functional modules corresponding to the audio/video processing device 300 based on the weak network environment may be used to execute each method embodiment executed by the artificial intelligence service center 100. The audio/video processing device 300 based on the weak network environment may include an obtaining module 310, a determining module 320, and a forwarding module 330, and the functions of the functional modules of the audio/video processing device 300 based on the weak network environment are described in detail below.

The obtaining module 310 is configured to obtain, from the first audio/video server, transmission quality information of the audio/video information that is pushed by the first audio/video server to the audio/video playing device 200 based on the audio/video push request, according to the network environment configuration information that is synchronously sent when the audio/video playing device 200 sends the audio/video push request to the first audio/video server. The obtaining module 310 may be configured to perform the step S110, and the detailed implementation of the obtaining module 310 may refer to the detailed description of the step S110.

The determining module 320 is configured to determine whether the audio/video playing device 200 is in a weak network environment according to the transmission quality information and the network environment configuration information. The determining module 320 may be configured to perform the step S120, and the detailed implementation of the determining module 320 may refer to the detailed description of the step S120.

The forwarding module 330 is configured to, when it is determined that the audio/video playing device 200 is in the weak network environment, synchronously forward the audio/video push request to the at least one second audio/video server based on the transmission quality information, the network environment configuration information, and the configuration information of the remaining audio/video servers registered in the artificial intelligence service center, so that the at least one second audio/video server continues to push the audio/video information to the audio/video playing device 200 based on the audio/video push request. The forwarding module 330 may be configured to perform the step S130, and the detailed implementation of the forwarding module 330 may refer to the detailed description of the step S130.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the obtaining module 310 may be a processing element separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the processing element of the apparatus calls and executes the functions of the obtaining module 310. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when some of the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call program code. As another example, these modules may be integrated together, implemented in the form of a system-on-a-chip (SOC).

Fig. 4 is a schematic diagram illustrating a hardware structure of an artificial intelligence service center 100 for implementing the audio/video processing method in the weak network-based environment according to an embodiment of the present invention, and as shown in fig. 4, the artificial intelligence service center 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.

In a specific implementation process, at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120 (for example, the obtaining module 310, the determining module 320, and the forwarding module 330 included in the audio/video processing apparatus 300 under the weak network environment shown in fig. 3), so that the processor 110 may execute the audio/video processing method under the weak network environment according to the above method embodiment, where the processor 110, the machine-readable storage medium 120, and the transceiver 140 are connected through the bus 130, and the processor 110 may be configured to control a transceiving action of the transceiver 140, so as to perform data transceiving with the aforementioned audio/video playing device 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the artificial intelligence service center 100, which implement principles and technical effects similar to each other, and details of this embodiment are not described herein again.

In the embodiment shown in fig. 4, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The machine-readable storage medium 120 may comprise high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus 130 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus 130 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the buses in the figures of the present invention are not limited to only one bus or one type of bus.

In addition, an embodiment of the present invention further provides a readable storage medium, where a computer execution instruction is stored in the readable storage medium, and when a processor executes the computer execution instruction, the audio/video processing method in the weak network environment is implemented.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Such as "one possible implementation," "one possible example," and/or "exemplary" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "one possible implementation," "one possible example," and/or "exemplary" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. An audio and video processing method based on a weak network environment is characterized by being applied to an artificial intelligence service center, wherein the artificial intelligence service center is in communication connection with a plurality of audio and video playing devices, and the method comprises the following steps:

when the audio and video playing equipment is judged to be in a weak network environment, the audio and video pushing request is synchronously forwarded to at least one second audio and video server based on the transmission quality information, the network environment configuration information and the configuration information of the audio and video servers registered in the artificial intelligence service center, so that the at least one second audio and video server continues to push the audio and video information to the audio and video playing equipment based on the audio and video pushing request;

the step of judging whether the audio and video playing device is in the weak network environment according to the transmission quality information and the network environment configuration information comprises the following steps:

when the transmission quality configuration information is not matched with the transmission quality information, judging that the audio and video playing equipment is in a weak network environment;

the step of synchronously forwarding the audio and video push request to at least one second audio and video server based on the transmission quality information, the network environment configuration information and the configuration information of the rest audio and video servers registered in the artificial intelligence service center comprises the following steps:

2. The audio and video processing method based on the weak network environment according to claim 1, wherein the step of processing the weak network state node information according to the network protocol information to generate the state service update information of the weak network state node information includes:

3. The weak network environment-based audio/video processing method according to claim 1, wherein the weak network feature extraction is performed on the weak network state node information and the state service update information, and the step of determining, from the extracted current weak network feature information, second weak network element information corresponding to first weak network element information corresponding to the state service update information includes:

4. The audio and video processing method based on the weak network environment according to claim 1, wherein the step of clustering and fusing the first weak network element information and the second weak network element information to obtain a third weak network element information comprises:

5. The weak network environment-based audio/video processing method according to claim 1, wherein the step of outputting the expanded network state node distribution corresponding to the weak network state node information according to the third weak network element information includes:

6. An artificial intelligence service center, characterized in that the artificial intelligence service center comprises a processor, a machine-readable storage medium and a network interface, the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being connected with at least one online service terminal in a communication manner, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, instructions or codes in the machine-readable storage medium to execute the audio/video processing method based on the weak network environment according to any one of claims 1 to 5.