Information processing method, device, computer equipment and storage medium

Abstract

The embodiment of the present invention discloses an information processing method, apparatus, computer equipment, and storage medium. The method includes: obtaining characteristic information of a target object, the characteristic information including one or more of domain name information, operator information, location information, and object identification; calling a domain name resolution service selection model to process the characteristic information of the target object and determine a list of candidate domain name resolution servers, the candidate domain name resolution server list including the identification of at least one candidate domain name resolution server, the domain name resolution service selection model being trained based on a data set of pre-labeled domain name resolution servers; and sending the list of candidate domain name resolution servers to a client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server. The embodiment of the present invention can be applied to scenarios such as cloud technology and artificial intelligence, and can improve the efficiency and accuracy of domain name resolution server selection, thereby improving the acceleration quality of games.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information processing method, apparatus, computer equipment, and storage medium. Background Art

[0002] The core function of a game accelerator is acceleration, which primarily relies on intercepting game traffic, the most important of which is Domain Name System (DNS) traffic. The game accelerator resolves the Internet Protocol (IP) address through a DNS server and uses the Transmission Control Protocol / User Datagram Protocol (TCP / UDP) to connect to the IP address for acceleration optimization. The better the network metrics of the IP address resolved by the DNS server, the better the acceleration optimization effect. Therefore, the selection of a DNS server is crucial to the acceleration capabilities of the game accelerator.

[0003] Currently, DNS traffic acceleration typically involves selecting either fixed or scenario-specific DNS servers. However, fixed DNS servers can lead to significant differences in the gaming experience across different games, while scenario-specific DNS servers can be complex to implement, unable to guarantee optimal DNS usage, and difficult to maintain. Therefore, improving the efficiency and accuracy of DNS server selection is an urgent issue. Summary of the Invention

[0004] Embodiments of the present invention provide an information processing method, apparatus, computer device, and storage medium, which can improve the efficiency and accuracy of domain name resolution server selection, thereby enhancing the acceleration quality of games.

[0005] In one aspect, an embodiment of the present invention provides an information processing method, the method comprising:

[0006] Acquire characteristic information of the target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identifier;

[0007] Invoking a domain name resolution service selection model to process characteristic information of the target object and determine a list of candidate domain name resolution servers, the list of candidate domain name resolution servers including an identifier of at least one candidate domain name resolution server, the domain name resolution service selection model being trained based on a dataset of pre-labeled domain name resolution servers;

[0008] The candidate domain name resolution server list is sent to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server.

[0009] In one aspect, an embodiment of the present invention provides an information processing method, the method comprising:

[0010] Sending a service selection request to the control server, where the service selection request includes characteristic information of the target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identifier;

[0011] receiving the candidate domain name resolution server list sent by the control server in response to the service selection request, the list including an identifier of at least one candidate domain name resolution server;

[0012] Sending a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server;

[0013] A target resolution result is determined from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the service traffic of the target object.

[0014] In one aspect, an embodiment of the present invention provides an information processing device, comprising:

[0015] an acquisition unit, configured to acquire characteristic information of a target object, the characteristic information including one or more of domain name information, operator information, location information, and object identification;

[0016] a determination unit, configured to invoke a domain name resolution service selection model to process characteristic information of the target object and determine a list of candidate domain name resolution servers, the list of candidate domain name resolution servers including an identifier of at least one candidate domain name resolution server, the domain name resolution service selection model being trained based on a dataset of pre-labeled domain name resolution servers;

[0017] The sending unit is configured to send the candidate domain name resolution server list to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server.

[0018] In one aspect, an embodiment of the present invention provides an information processing device, comprising:

[0019] a sending unit, configured to send a service selection request to the control server, the service selection request including characteristic information of the target object, the characteristic information including one or more of domain name information, operator information, location information, and object identifier;

[0020] a receiving unit, configured to receive a candidate domain name resolution server list sent by the control server in response to the service selection request, the candidate domain name resolution server list including an identifier of at least one candidate domain name resolution server;

[0021] The sending unit is further configured to send a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server;

[0022] The determination unit is configured to determine a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, wherein the target resolution result is used to accelerate the service traffic of the target object.

[0023] On the one hand, an embodiment of the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the above-mentioned information identification method.

[0024] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is read and executed by a processor of a computer device, the computer device executes the above-mentioned information identification method.

[0025] In one aspect, embodiments of the present application provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the above-described information identification method.

[0026] Through the embodiment of the present application, the client sends a service selection request to the control server, and the service selection request includes characteristic information of the target object, and the characteristic information includes one or more of domain name information, operator information, location information and object identification; the control server calls the domain name resolution service selection model to process the characteristic information of the target object and determines a list of candidate domain name resolution servers, and the candidate domain name resolution server list includes the identification of at least one candidate domain name resolution server, and the domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers; the control server sends the candidate domain name resolution server list to the client; the client sends a domain name resolution request to each candidate domain name resolution server based on the identification of the at least one candidate domain name resolution server; the client determines the target resolution result from the resolution result sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the business traffic of the target object. It should be understood that by selecting the domain name resolution server through this method, the efficiency and accuracy of the domain name resolution server selection can be improved, thereby improving the acceleration quality of the game. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 This is a schematic diagram of a DNS protocol resolution process provided by an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the architecture of an information processing system provided by an embodiment of the present invention;

[0030] Figure 3 This is a flow chart of an information processing method provided by an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of a domain name resolution service selection model provided in an embodiment of the present application;

[0032] Figure 5 This is a schematic diagram of a deep learning model training provided in an embodiment of the present application;

[0033] Figure 6 This is a schematic diagram of determining a target domain name resolution server provided by an embodiment of the present application;

[0034] Figure 7 This is a schematic diagram of a gaming service acceleration process provided by an embodiment of the present application;

[0035] Figure 8 is a flowchart of another information processing method provided by an embodiment of the present invention;

[0036] Figure 9a This is a schematic diagram of an acceleration page provided by an embodiment of the present application;

[0037] Figure 9b is a schematic diagram of an accelerated recording interface provided in an embodiment of the present application;

[0038] Figure 9c is a schematic diagram of an acceleration process interface provided in an embodiment of the present application;

[0039] Figure 9d is a schematic diagram of an acceleration details interface provided in an embodiment of the present application;

[0040] Figure 9e is a schematic diagram of a game interface provided in an embodiment of the present application;

[0041] Figure 10 is a flowchart of another information processing method provided by an embodiment of the present invention;

[0042] Figure 11 is a flowchart of another information processing method provided by an embodiment of the present invention;

[0043] Figure 12 is a structural diagram of an information processing device provided by an embodiment of the present invention;

[0044] Figure 13 is a structural diagram of another information processing device provided by an embodiment of the present invention;

[0045] Figure 14 It is a structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0047] It should be noted that the terms "first" and "second" in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature designated as "first" or "second" may explicitly or implicitly include at least one such feature.

[0048] First, some of the terms involved in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0049] The Domain Name System (DNS) protocol is an internet service that acts as a distributed database that maps domain names to Internet Protocol (IP) addresses, making internet access more convenient. DNS uses Transmission Control Protocol / User Datagram Protocol (TCP / UDP) port 53. Currently, the length of each domain name is limited to 63 characters, and the total length of a domain name cannot exceed 253 characters. The DNS protocol is used to convert domain names to IP addresses (and vice versa).

[0050] Domain Name: Also known as a network domain, it is the name of a computer or group of computers on the Internet, consisting of a string of names separated by dots. It is used to identify the location of the computer (sometimes also refers to its geographical location) during data transmission. Because IP addresses are difficult to remember and cannot reveal the name and nature of the address organization, people designed domain names and used DNS to map domain names to IP addresses, making it easier for people to access the Internet without having to remember the IP address string that can be directly read by machines.

[0051] TCP / UDP Protocol: TCP and UDP are the core of the TCP / IP protocol, belonging to the transport layer. TCP provides reliable data transmission in the IP environment, offering services such as data stream transmission, reliability, effective flow control, full-duplex operation, and multiplexing. It uses connection-oriented, end-to-end, and reliable data packet transmission. In simple terms, it establishes a pre-connected channel for the data to be sent before sending the data. UDP, on the other hand, does not provide reliability, flow control, or error recovery for IP. Generally speaking, TCP is suitable for applications with high reliability requirements, while UDP is suitable for applications with low reliability requirements and economical transmission.

[0052] DNS protocol resolution: Domain name system resolution can be generally divided into two steps. The first step is that the local machine sends a DNS request message to the domain name server, which carries the domain name to be queried; the second step is that the domain name server responds with a DNS response message to the local machine, which contains the IP address corresponding to the domain name.

[0053] In the embodiment of the present application, taking the most common Hyper Text Transfer Protocol (HTTP) request "https: / / codm.com" as an example, the DNS protocol resolution process is as follows: Figure 1 As shown in the figure: First, the domain name "codm.com" is converted into an IP. The DNS protocol resolution is used here. The client sends a DNS resolution request carrying the domain name "codm.com" to the DNS server with the IP address "8.8.8.8"; the DNS server returns the resolution result and attaches the IP address "101.32.3.3"; after the client obtains the IP address, it uses the TCP protocol to connect to the HTTP server with the IP address "101.32.3.3", and sends an HTTP protocol request after the connection is successful; the HTTP server with the IP address "101.32.3.3" returns the HTTP request result.

[0054] An information processing method proposed in an embodiment of the present application can be implemented based on cloud technology. Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network in a wide area network or a local area network to realize the calculation, storage, processing, and sharing of data. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model application. It can form a resource pool that can be used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of technical network systems require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the rapid development and application of the Internet industry, each item may have its own identification mark in the future, and all need to be transmitted to the background system for logical processing. Data of different levels will be processed separately. All kinds of industry data require strong system backing support, which can only be achieved through cloud computing.

[0055] Cloud computing refers to the delivery and usage model of Internet technology (IT) infrastructure, enabling on-demand, scalable access to resources over the internet. Broadly speaking, cloud computing refers to the delivery and usage model of services, enabling on-demand, scalable access to services over the internet. These services can be IT-related, software-related, internet-related, or other services. Cloud computing is the product of the convergence of traditional computer and network technologies, including grid computing, distributed computing, parallel computing, utility computing, network storage technologies, virtualization, and load balancing. Driven by the growth of the internet, real-time data streams, and the diversification of connected devices, as well as the demand for search services, social networking, mobile commerce, and open collaboration, cloud computing has rapidly developed. Unlike previous parallel and distributed computing approaches, the emergence of cloud computing will fundamentally revolutionize the entire internet model and enterprise management models.

[0056] Cloud gaming, also known as gaming on demand, is an online gaming technology based on cloud computing. Cloud gaming enables thin clients with relatively limited graphics and data processing capabilities to run high-quality games. In cloud gaming scenarios, the game runs not on the player's terminal but on a cloud server. The cloud server renders the game scene into a video and audio stream, which is then transmitted to the player's terminal over the network. The player's terminal does not need powerful graphics and data processing capabilities; it only needs basic streaming capabilities and the ability to receive player input and send it to the cloud server.

[0057] Among them, the core function of the game accelerator is the acceleration capability, and the acceleration capability is mainly to intercept the game traffic, among which the most important is DNS traffic. For the acceleration of DNS traffic, a fixed DNS server or a scenario-based DNS server is usually selected. However, for a fixed DNS server, the experience of different games will vary greatly; for a scenario-based DNS server, there will be problems such as complex implementation, inability to guarantee the use of the optimal DNS, and difficulty in maintenance. Therefore, in order to improve the efficiency and accuracy of DNS server selection, an embodiment of the present application proposes an information processing solution, specifically obtaining the characteristic information of the target object, and then calling the domain name resolution service selection model to process the characteristic information of the target object, determine a list of candidate domain name resolution servers, and finally send the list of candidate domain name resolution servers to the client, so that the client sends a domain name resolution request to at least one candidate domain name resolution server.

[0058] The information processing scheme proposed in this application is executed by a computer device, which can be a client, which can be understood as a terminal device, such as a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, smart car, etc., but is not limited to this; the computer device can also be a server, such as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Of course, it can also be executed by two computer devices together, such as one computer device as a terminal device and the other computer device as a server, to jointly execute the information processing scheme proposed in this application.

[0059] For example, assuming that the information processing solution proposed in this application is jointly executed by the client and the server, the information processing solution proposed in this application can be implemented using the following information processing system architecture. Figure 2 , Figure 2 This is a schematic diagram of the architecture of an information processing system according to an embodiment of the present application. Figure 2As shown, the information processing system 200 may include one or more clients 201, a control server 202, and one or more candidate domain name resolution servers 203. Of course, the information processing system 200 may also include multiple control servers 202, which is not limited in the embodiment of the present application. Among them, the client 201 is mainly used to execute the relevant steps of the information processing method on the client side, send a service selection request to the control server 202, receive the candidate domain name resolution server list sent by the control server 202, and send a domain name resolution request to each candidate domain name resolution server 203 in the candidate domain name resolution server list; the control server 202 is mainly used to execute the relevant steps of the information processing method on the control server side, obtain the candidate domain name resolution server list, and send the candidate domain name resolution server list to the client 201. The candidate domain name resolution server 203 receives the domain name resolution request sent by the client 201 and responds to the domain name resolution request. The client 201, the control server 202, and the candidate domain name resolution server 203 can realize communication connection, and the connection method may include wired connection and wireless connection, which is not limited here.

[0060] In conjunction with the above-mentioned information processing system, the information processing method of the embodiment of the present application may generally include:

[0061] The client 201 sends a service selection request to the control server 202, and sends the characteristic information of the target object to the control server 202; after the control server 202 obtains the characteristic information of the target object sent by the client 201, it processes the characteristic information of the target object and obtains a list of candidate domain name resolution servers. The control server 202 sends the list of candidate domain name resolution servers to the client 201. After receiving the list of candidate domain name resolution servers, the client 201 sends a domain name resolution request to each candidate domain name resolution server in the list of candidate domain name resolution servers, and determines the target resolution result from the resolution result of each candidate domain name resolution server in response to the domain name resolution request. Of course, the client 201 can also obtain the characteristic information of the target object from other devices after obtaining the target object, and then send the characteristic information to the control server 202, which is not limited here. By selecting the domain name resolution server by this method, the efficiency and accuracy of the domain name resolution server selection can be improved, thereby improving the acceleration quality of the game.

[0062] It can be understood that the system architecture diagram described in the embodiment of the present application is intended to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0063] Based on the above description of the information processing system architecture, the present application embodiment discloses an information processing method, see Figure 3 , is a flow chart of an information processing method disclosed in an embodiment of the present application. The information processing method can be executed by a computer device, which can specifically be the client 201 and the control server 202 in the information processing system. The information processing method can specifically include steps S301 to S305:

[0064] S301. The client sends a service selection request to the control server. The service selection request includes characteristic information of a target object. The characteristic information includes one or more of domain name information, operator information, location information, and object identification.

[0065] In an embodiment of the present application, the target object may refer to a gaming service, a query service, etc. After the client determines to accelerate the target object, it will send a service selection request to the control server. The service selection request is used to request the control server to select a candidate domain name resolution server whose network indicators meet the first preset conditions, so that the client can determine the target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, thereby achieving acceleration of the target service. Among them, the service selection request includes characteristic information of the target object, and the characteristic information includes one or more of domain name information, operator information, location information and object identification.

[0066] It should be noted that the target object's domain name information can be obtained by parsing DNS packets. The client further obtains the target object's corresponding carrier information, location information, and object identifier. The client sends the domain name information, carrier information, location information, and object identifier to the control server in a service selection request.

[0067] S302. The control server calls a domain name resolution service selection model to process feature information of the target object and determine a list of candidate domain name resolution servers. The list of candidate domain name resolution servers includes an identifier of at least one candidate domain name resolution server. The domain name resolution service selection model is trained based on a dataset of pre-labeled domain name resolution servers.

[0068] In an embodiment of the present application, after the control server receives the service selection request sent by the client, it processes the characteristic information of the target object with the help of the domain name resolution service selection model to determine a list of candidate domain name resolution servers. The client can then determine the domain name resolution server to be finally adopted based on the candidate domain name resolution server list. Among them, the network indicators of the candidate domain name resolution server meet the first preset conditions, and the network indicators include one or more of the update download speed, network delay, jitter rate and packet loss rate. Exemplarily, if the packet loss rate of the candidate domain name resolution server is below 5%, the identifier of the candidate domain name resolution server is added to the candidate domain name resolution server list. Another exemplary method is to determine the candidate domain name resolution servers with the top 3 update download speeds, and use the identifiers of these 3 candidate domain name resolution servers as the candidate domain name resolution server list. Based on this method, the efficiency and accuracy of domain name resolution server selection can be improved, thereby improving the acceleration quality of the game.

[0069] In one possible implementation, calling a domain name resolution service selection model to process characteristic information of the target object and determine a candidate domain name resolution server list includes: calling the domain name resolution service selection model to determine a domain name resolution server library based on operator information and an object identifier included in the characteristic information; and calling the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library. It should be understood that the control server can determine the corresponding domain name resolution server library based on the operator information and the object identifier included in the characteristic information, and then call the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library.

[0070] It should be noted that the domain name resolution server library includes at least one domain name resolution server. The target object's operator information, object identifier, and domain name resolution server library have a corresponding relationship. As shown in Table 1, for the target object with object identifier 1, if the operator information is A, the domain name resolution server library includes domain name resolution server a, domain name resolution server b, and domain name resolution server c; if the operator information is B, the domain name resolution server library includes domain name resolution server c, domain name resolution server d, and domain name resolution server e. For the target object with object identifier 2, if the operator information is A, the domain name resolution server library includes domain name resolution server a, domain name resolution server c, and domain name resolution server d; if the operator information is B, the domain name resolution server library includes domain name resolution server b, domain name resolution server c, and domain name resolution server e.

[0071] Table 1

[0072]

[0073] Optionally, the domain name resolution service selection model is called to process the characteristic information of the target object to determine a list of candidate domain name resolution servers from the domain name resolution server library, including: calling the domain name resolution service selection model to format the operator information and location information included in the characteristic information of the target object to obtain formatted operator information and location information; calling the domain name resolution service selection model to cluster the domain name information included in the characteristic information of the target object to obtain clustered domain name information; calling the domain name resolution service selection model to process the formatted operator information and location information and the clustered domain name information to determine a list of candidate domain name resolution servers from multiple domain name resolution servers included in the domain name resolution server library. It should be understood that before calling the domain name resolution service selection model to process the characteristic information of the target object, it is necessary to format the operator information and location information included in the characteristic information of the target object, cluster the domain name information included in the characteristic information of the target object, and then call the domain name resolution service selection model to process the formatted operator information and location information and the clustered domain name information. Using standardized parameters for processing helps avoid errors caused by coding problems in the system, and the simplification of domain names is more conducive to the convergence of results.

[0074] It should be noted that formatting the operator information and location information included in the characteristic information of the target object can be performed by formatting the operator information and location information into corresponding IDs. For example, if the operator information is A, it is formatted as 1; if the operator information is B, it is formatted as 2. For example, if the location information is M, it is formatted as 00; if the location information is N, it is formatted as 01. Clustering the domain name information included in the characteristic information of the target object can be performed by simplifying the domain name. For example, the three domain names "111.xx.com", "222.xx.com" and "333.xx.com" can be clustered into "xx.com". Of course, these clustering processes also require manual intervention. Not all domain names can be clustered according to a set pattern. For some domain names with a wider range of business coverage, they need to be further subdivided into types, otherwise the results will be inaccurate.

[0075] See Figure 4 , Figure 4This is a schematic diagram of a domain name resolution service selection model provided by an embodiment of the present application, wherein the DNS policy center can be regarded as a domain name resolution service selection model, and the input parts are operator information, location information (such as geographic location), domain name information and object identifier (such as game ID). The domain name resolution service selection model includes a preprocessing module and a deep learning module. The preprocessing module is used to format the operator information and location information included in the characteristic information of the target object, and to cluster the domain name information included in the characteristic information of the target object; then the deep learning module is used to process the standardized parameters, and finally a list of candidate domain name resolution servers is output, which includes the identifier of at least one candidate domain name resolution server.

[0076] For example, the input operator information is A, the location information is M, the domain name information is "111.xx.com", and the game ID is 123. This information is input into the DNS policy center (that is, the domain name resolution service selection model), and the pre-processing module of the DNS policy center is used to format the operator information and location information, resulting in the formatted operator information being 1 and the formatted location information being 00; the pre-processing module is used to cluster the domain name information, resulting in the clustered domain name information being "xx.com". The standardized parameters are then input into the deep learning module of the DNS policy center for processing, and finally a list of candidate domain name resolution servers is output, namely candidate domain name resolution server a, candidate domain name resolution server b, and candidate domain name resolution server c.

[0077] In one possible implementation, the method further includes: obtaining a training dataset, the training dataset including at least one set of training samples, each set of training samples including feature information and annotation data of a sample object, the annotation data including a reference domain name resolution server list corresponding to the feature information; invoking an initialized neural network model to process the feature information of the sample objects included in each set of training samples to obtain a predicted domain name resolution server list; and adjusting model parameters of the initialized neural network model based on the predicted domain name resolution server list and the reference domain name resolution server list to obtain a domain name resolution service selection model. The domain name resolution service selection model is obtained by training the dataset using a deep learning approach.

[0078] First, the training process of the deep learning model is explained. Figure 5 , Figure 5It is a schematic diagram of a deep learning model training provided by an embodiment of the present application, which extracts and summarizes features from the data set so that the machine learning algorithm can make the most of the data to obtain better results. The data set is then divided into a training set, a validation set, and a test set. Among them, the training set is used to train the deep learning model, which is similar to a student's textbook. The student learns to master knowledge based on the content in the textbook. The larger the training set, the better the learning effect of the model we train; the validation set is used to evaluate the model results and then assist the model in adjusting parameters. It is similar to homework. Through it, we can know the learning situation of different students and how fast they progress; the test set is similar to a student's exam. The questions tested are not trained, and the students' ability to draw inferences from one example is tested, that is, the training effect of the model is further tested.

[0079] Therefore, based on the deep learning training method, the specific training process of the domain name resolution service selection model includes:

[0080] 1. Acquisition of training data set: The training data set includes at least one group of training samples, each group of training samples includes characteristic information and annotation data of a sample object, and the annotation data includes a list of reference domain name resolution servers corresponding to the characteristic information. The network indicators of one or more reference domain name resolution servers corresponding to the reference domain name resolution server list all meet the first preset condition, and the network indicators include one or more of update download speed, network delay, jitter rate and packet loss rate. For example, a group of training samples includes characteristic information and annotation data of sample object P, wherein the characteristic information of sample object P includes operator information A, location information M, domain name information "111.xx.com" and object identifier 123. The annotation data of sample object P is the list of reference domain name resolution servers corresponding to the characteristic information, namely domain name resolution server a, domain name resolution server b and domain name resolution server c. The training data set is divided into a training set, a validation set and a test set to facilitate subsequent training and optimization of the model.

[0081] 2. Training process: Call the initialized neural network model to process the feature information of the sample objects included in each group of training samples in the training set to obtain the predicted domain name resolution server list. Then, according to the accuracy between the predicted domain name resolution server list and the reference domain name resolution server list, adjust the model parameters of the initialized neural network model, that is, use the validation set to assist the model in adjusting the parameters. When the training reaches the required number of times, use the test set to test the model. When the accuracy of the model prediction reaches the preset conditions, the training is completed and the domain name resolution service selection model is obtained. Among them, the reference domain name resolution server list can be understood as the "standard answer". By continuously training the model, the predicted domain name resolution server list continues to approach this "standard answer".

[0082] In addition, manual intervention is required for the training dataset. Specific domain names can be set manually. When these domain names appear in the training dataset, they need to be removed from the training dataset. At the same time, the availability of domain name resolution servers needs to be regularly checked. Unavailable domain name resolution servers also need to be removed from the training dataset to prevent clients from selecting unavailable domain name resolution servers.

[0083] It should be noted that the source of the training data set can be the operating environment data corresponding to the operator information, public data sources, data obtained by selecting the model using the domain name resolution service, etc., and the training data set is not static, but is continuously updated in real time according to the latest data to ensure the accuracy of the results.

[0084] S303: The control server sends the candidate domain name resolution server list to the client.

[0085] S304: The client sends a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server.

[0086] In an embodiment of the present application, after the client receives the candidate domain name resolution server list sent by the control server, it sends a domain name resolution request to each candidate domain name resolution server based on the identifier of at least one candidate domain name resolution server in the candidate domain name resolution server list to obtain the resolution result sent by the candidate domain name resolution server in response to the domain name resolution request.

[0087] S305: The client determines a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request. The target resolution result is used to accelerate the service traffic of the target object.

[0088] In an embodiment of the present application, after the client determines the target resolution result, it uses the target resolution result to accelerate the service traffic of the target object. For example, the client determines the target resolution result from the resolution results sent by the three candidate domain name resolution servers in response to the domain name resolution request. The target resolution result includes the resolved IP address. The client uses the TCP protocol to connect to the server corresponding to the IP address, thereby accelerating the service traffic of the target object.

[0089] In one possible implementation, determining the target resolution result from the resolution result sent by each candidate domain name resolution server in response to the domain name resolution request includes: obtaining the response time of each candidate domain name resolution server to the domain name resolution request; obtaining the target domain name resolution server with the shortest response time among the at least one candidate domain name resolution server; and using the resolution result of the target domain name resolution server as the target resolution result.

[0090] For example, a client receives resolution results from three candidate DNS servers in response to a DNS request. The first candidate DNS server responds to the request in 20ms, the second candidate DNS server responds in 30ms, and the third candidate DNS server responds in 80ms. This indicates that the first candidate DNS server has the shortest response time to the request, so the client selects the first candidate DNS server as the target DNS server, and the resolution result from the target DNS server is used as the target resolution result.

[0091] See Figure 6 , Figure 6 This is a schematic diagram of determining a target domain name resolution server provided by an embodiment of the present application. Figure 6 As shown, after the client determines that the target object needs to be accelerated, the client will intercept the domain name data packet of the target object, and by parsing the domain name data packet, the domain name information of the target object corresponding to the DNS data packet can be obtained. The client further obtains the operator information, location information and object identifier of the target object, and sends these information parameters (i.e., domain name information, operator information, location information and object identifier) ​​to the DNS policy center (i.e., domain name resolution service selection model). The DNS policy center will return a list of candidate domain name resolution servers, which includes the identifier of at least one candidate domain name resolution server, i.e. Figure 6In the example, the client identifies the candidate DNS server identified as "8.8.8.8," "1.1.1.1," and "4.2.2.2." The client simultaneously sends a DNS request to these three candidate DNS servers. The response time for the candidate DNS server identified as "8.8.8.8" is 20ms, the response time for the candidate DNS server identified as "1.1.1.1" is 30ms, and the response time for the candidate DNS server identified as "4.2.2.2" is 80ms. Based on the response times of these three candidate DNS servers, the client determines the target DNS server with the shortest response time, namely, the candidate DNS server identified as "8.8.8.8." The client can also send this target DNS server to the DNS policy center, which can use the target object's characteristic information and the target DNS server for further training and updating.

[0092] In one possible implementation, the method further includes: caching the resolution results sent by the at least one candidate domain name resolution server; obtaining a resolution result cache status, the resolution result cache status including one or both of the cached number of resolution results and the cached time; and updating the cached resolution results when the resolution result cache status satisfies a preset update condition. It should be understood that within a certain timeframe, the selected target domain name resolution server corresponding to a target object can be considered stable. Therefore, the resolution results of the target domain name resolution server can be stored to facilitate subsequent direct access to the resolution results of the target domain name resolution server, avoiding multiple network requests for the same domain name, thereby saving domain name resolution time. In addition, a memory management algorithm, such as a least recently used (LRU) algorithm, is introduced to update the cached resolution results. When the number of cached resolution results reaches a preset threshold, infrequently used cached results are deleted to prevent client performance bottlenecks caused by an excessive number of cached results. Furthermore, periodic detection is performed. If the number of cached results does not reach the threshold, older results are deleted to prevent domain name resolution requests from using older data and losing timeliness.

[0093] The above information processing method is described below using a specific example:

[0094] See Figure 7 , Figure 7This is a schematic diagram of a game service acceleration process provided by an embodiment of the present application. Taking the target object as the game service as an example, the game service is accelerated, mainly intercepting the traffic of the game service for acceleration. After the client confirms that the game service is accelerated, it will obtain the domain name rule library of the game and select the optimal line node for acceleration. The domain name rule library stores various types of domain names, such as: a first type of domain name, which is used to represent domain names with higher risks, and this type of domain name cannot be accelerated; a second type of domain name, which is used to represent domain names of non-core traffic, and this type of domain name does not need to be accelerated; a third type of domain name, which is used to represent domain names of core traffic, and this type of domain name needs to be accelerated.

[0095] The client then performs a handshake authentication with the optimal node, obtaining an output vector. This output vector serves as the traffic acceleration credential and virtual IP. The obtained virtual IP and other parameters are configured on a TUN virtual network card. The client then installs this TUN virtual network card to intercept game traffic. The intercepted game IP traffic is then parsed using the DNS protocol to obtain the domain name information for the game service. The client then matches the resolved domain name with a domain name rule library and determines that it is a third-type domain name, thus enabling acceleration for the target object.

[0096] Furthermore, the client obtains the operator information, location information, and object identifier of the target object, and then sends a service selection request to the control server. The service selection request includes the characteristic information of the target object, which includes domain name information, operator information, location information, and object identifier. The control server uses the trained domain name resolution service selection model (i.e., DNS policy center) to process the characteristic information of the target object and determine a list of candidate domain name resolution servers, namely, a candidate domain name resolution server identified as "8.8.8.8", a candidate domain name resolution server identified as "1.1.1.1", and a candidate domain name resolution server identified as "4.2.2.2". The control server then sends the list of candidate domain name resolution servers to the client.

[0097] Furthermore, after receiving the candidate domain name resolution server list, the client sends a domain name resolution request to each candidate domain name resolution server in the candidate domain name resolution server list. The candidate domain name resolution server identified as "8.8.8.8" has a response time of 20ms for the domain name resolution request, the candidate domain name resolution server identified as "1.1.1.1" has a response time of 30ms for the domain name resolution request, and the candidate domain name resolution server identified as "4.2.2.2" has a response time of 80ms for the domain name resolution request.

[0098] Finally, the client uses the candidate domain name resolution server with the shortest response time to the domain name resolution request as the target domain name resolution server, that is, the candidate domain name resolution server identified as "8.8.8.8", and uses the resolution result of the target domain name resolution server as the target resolution result. The client uses the target resolution result to accelerate the business traffic of the target object.

[0099] In summary, in an embodiment of the present invention, the client sends a service selection request to the control server, and the service selection request includes characteristic information of the target object, and the characteristic information includes one or more of domain name information, operator information, location information and object identification; the control server calls the domain name resolution service selection model to process the characteristic information of the target object and determines a list of candidate domain name resolution servers, and the candidate domain name resolution server list includes the identification of at least one candidate domain name resolution server, and the domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers; the control server sends the candidate domain name resolution server list to the client; the client sends a domain name resolution request to each candidate domain name resolution server based on the identification of the at least one candidate domain name resolution server; the client determines the target resolution result from the resolution result sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the business traffic of the target object. It should be understood that by selecting the domain name resolution server through this method, the efficiency and accuracy of the domain name resolution server selection can be improved, thereby improving the acceleration quality of the game.

[0100] Based on the above description of the information processing system architecture, the present application embodiment discloses another information processing method, see Figure 8 , is a flow chart of an information processing method disclosed in an embodiment of the present application. The information processing method can be executed by a computer device, which can specifically be the client 201 and the control server 202 in the information processing system. The information processing method can specifically include steps S801 to S810:

[0101] S801: A client obtains an acceleration instruction input for a target object through an acceleration page, where the acceleration page includes at least one object.

[0102] In an embodiment of the present application, a user may input an acceleration instruction for a target object through an acceleration page, and the client obtains the acceleration instruction and then responds to the acceleration instruction.

[0103] Take the game business as an example, Figure 9a As shown, Figure 9a: This is a schematic diagram of an acceleration page provided in an embodiment of the present application. The acceleration interface includes a search bar, a keyboard, at least one acceleration object, and a corresponding acceleration button. Users can search for games that need to be accelerated in the search bar of the acceleration page, such as entering the name of the game to be accelerated "AAA M" in the search bar using the keyboard. At this time, three acceleration objects appear in the acceleration page, namely "AAA M", "AAA M1" and "AAA M2". Users can accelerate by clicking the acceleration button corresponding to the name of the game to be accelerated.

[0104] In addition, after the game is accelerated, the client will record the last game that was successfully accelerated and display it in the "My Acceleration" interface, so that users can directly accelerate the game next time without having to search again. Figure 9b As shown, Figure 9b This is a schematic diagram of an acceleration record interface provided by an embodiment of the present application. The acceleration record interface includes an acceleration mode, a user history acceleration object, and a corresponding acceleration button. Figure 9b As you can see, the user's historical acceleration objects include "AAA M", "BBB M", and "CCC M", and the acceleration mode used is normal acceleration mode. Users can directly accelerate the game name by clicking the acceleration button corresponding to the game name to be accelerated in this interface.

[0105] S802: The client responds to the acceleration instruction and obtains characteristic information of the target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identification.

[0106] In the embodiment of the present application, after receiving the acceleration instruction, the client responds to the acceleration instruction. Taking the target object as a game business as an example, after the client enters the acceleration, it obtains the best acceleration route for the game and the characteristic information of the game, including domain information, operator information, location information and game ID.

[0107] like Figure 9c As shown, Figure 9c This is a schematic diagram of an acceleration process interface provided by an embodiment of the present application, which includes the game name, the selected optimal acceleration line, acceleration progress, and prompt information. Figure 9c As you can see, the game name is "AAA M," the optimal acceleration route is "xx route," and the current acceleration progress is 36%. Because the game uses the normal acceleration mode, the acceleration speed is relatively slow. Therefore, the prompt message reads "Recommend using the advanced speed mode for more stable acceleration." Users can adjust the mode according to their needs.

[0108] In addition, after the acceleration is successful, users can use the acceleration details interface to observe the comparison of network indicators before and after the current game acceleration. Figure 9d As shown, Figure 9d This is a schematic diagram of an acceleration details interface provided by an embodiment of the present application, which includes the game name, acceleration mode, cellular signal, WIFI signal, prompt information, use button, delay information before acceleration, delay information after acceleration, packet loss rate, network indicator graphs before and after acceleration, stop button and start game button. Among them, the game name is "AAA M", the acceleration mode is normal, and the acceleration mode can be adjusted according to the prompt information; the cellular signal is poor and the WIFI signal is none. The delay before acceleration of this game is 114ms, the delay after acceleration is 66ms, and the packet loss rate is 0%. The user can pause the acceleration of the game by clicking the stop button, or click the start game button to start the game. When the user clicks the start game button, as shown Figure 9e As shown, Figure 9e This is a schematic diagram of a game interface provided in an embodiment of the present application. After the game is started, the client will intercept the traffic of the game, thereby accelerating the game.

[0109] S803: The client sends a service selection request to the control server, where the service selection request includes feature information of the target object.

[0110] S804. The control server calls a domain name resolution service selection model to process feature information of the target object and determine a list of candidate domain name resolution servers. The list of candidate domain name resolution servers includes an identifier of at least one candidate domain name resolution server. The domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers.

[0111] The specific implementation of step S803 and step S804 is the same as that of step S301 and step S302, and will not be described in detail here.

[0112] S805: The control server obtains the network status parameters of each domain name resolution server in the domain name resolution server database.

[0113] S806: The control server determines an invalid domain name resolution server from the domain name resolution server database according to the network status parameter of each domain name resolution server.

[0114] S807: The control server deletes the invalid domain name resolution server from the domain name resolution server database.

[0115] In the embodiment of the present application, the network status parameter may specifically refer to a packet loss rate, a latency parameter, etc., which is not limited herein. The control server may obtain the network status parameter of each domain name resolution server in the domain name resolution server library. If the network status parameter of the domain name resolution server fails to meet the second preset condition, the control server may determine the domain name resolution server as an invalid domain name resolution server and delete the invalid domain name resolution server from the domain name resolution server library.

[0116] For example, the network status parameter is a packet loss rate, and the domain name resolution server database includes domain name resolution server A, domain name resolution server B, and domain name resolution server C. The second preset condition is that the packet loss rate of the domain name resolution server is less than 5%. In this case, the packet loss rate of domain name resolution server A is 2%, the packet loss rate of domain name resolution server B is 0%, and the packet loss rate of domain name resolution server C is 6%. Therefore, the packet loss rate of domain name resolution server C fails to meet the second preset condition, and domain name resolution server C is determined to be an invalid domain name resolution server and is deleted from the domain name resolution server database.

[0117] S808: The control server sends the candidate domain name resolution server list to the client.

[0118] S809: The client sends a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server.

[0119] S810: The client determines a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request. The target resolution result is used to accelerate the service traffic of the target object.

[0120] The specific implementation of steps S808 to S810 is the same as that of steps S303 to S305 and will not be described in detail here.

[0121] In summary, in an embodiment of the present invention, a client obtains an acceleration instruction input for a target object through an acceleration page, and the acceleration page includes at least one object; the client responds to the acceleration instruction and obtains characteristic information of the target object, and the characteristic information includes one or more of domain name information, operator information, location information and object identification; the client sends a service selection request to a control server, and the service selection request includes the characteristic information of the target object; the control server calls a domain name resolution service selection model to process the characteristic information of the target object and determines a list of candidate domain name resolution servers, and the candidate domain name resolution server list includes the identification of at least one candidate domain name resolution server, and the domain name resolution service selection model is based on a data set of pre-marked domain name resolution servers. The control server obtains the network status parameters of each domain name resolution server in the domain name resolution server library; the control server determines the invalid domain name resolution server from the domain name resolution server library according to the network status parameters of each domain name resolution server; the control server deletes the invalid domain name resolution server from the domain name resolution server library; the control server sends the candidate domain name resolution server list to the client; the client sends a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server; the client determines the target resolution result from the resolution result sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the business traffic of the target object. It should be understood that the selection of the domain name resolution server by this method can improve the efficiency and accuracy of the selection of the domain name resolution server, thereby improving the acceleration quality of the game.

[0122] Based on the above description of the information processing system architecture, the present application embodiment discloses an information processing method, see Figure 10 , is a flow chart of an information processing method disclosed in an embodiment of the present application. The information processing method can be executed by a computer device, which can specifically be the control server 202 in the information processing system. The information processing method can specifically include steps S1001 to S1003:

[0123] S1001. Acquire characteristic information of a target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identification.

[0124] S1002. Call a domain name resolution service selection model to process feature information of the target object and determine a list of candidate domain name resolution servers. The list of candidate domain name resolution servers includes an identifier of at least one candidate domain name resolution server. The domain name resolution service selection model is trained based on a dataset of pre-labeled domain name resolution servers.

[0125] S1003: Send the candidate domain name resolution server list to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server.

[0126] The specific implementation of step S1002 and step S1003 is the same as that of step S302 and step S303, and will not be described in detail here.

[0127] In summary, in an embodiment of the present invention, characteristic information of a target object is obtained, and the characteristic information includes one or more of domain name information, operator information, location information, and object identification; a domain name resolution service selection model is called to process the characteristic information of the target object, and a list of candidate domain name resolution servers is determined, and the list of candidate domain name resolution servers includes the identification of at least one candidate domain name resolution server, and the domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers; the list of candidate domain name resolution servers is sent to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server. It should be understood that the control server selects the domain name resolution server through this method, which can improve the efficiency and accuracy of the domain name resolution server selection, thereby improving the acceleration quality of the game.

[0128] Based on the above description of the information processing system architecture, the present application embodiment discloses an information processing method, see Figure 11 , is a flow chart of an information processing method disclosed in an embodiment of the present application. The information processing method can be executed by a computer device, which can specifically be the client 201 in the information processing system. The information processing method can specifically include steps S1101 to S1104:

[0129] S1101. Send a service selection request to a control server. The service selection request includes characteristic information of a target object. The characteristic information includes one or more of domain name information, operator information, location information, and object identification.

[0130] S1102: Receive the candidate domain name resolution server list sent by the control server in response to the service selection request, including the identifier of at least one candidate domain name resolution server.

[0131] S1103: Send a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server.

[0132] S1104: Determine a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, and use the target resolution result to accelerate the service traffic of the target object.

[0133] Among them, the specific implementation methods of step S1101, step S1103 and step S1104 are the same as the specific implementation methods of step S301, step S304 and step S305, and are not repeated here.

[0134] In summary, in an embodiment of the present invention, the list of candidate domain name resolution servers received from the control server in response to the service selection request includes the identifier of at least one candidate domain name resolution server; a domain name resolution request is sent to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server; and a target resolution result is determined from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the business traffic of the target object. It should be understood that selecting a domain name resolution server through this method can improve the efficiency and accuracy of domain name resolution server selection, and the client uses the optimal domain name resolution server to accelerate the game.

[0135] It is understandable that in the specific implementation of this application, related data such as the client's location information and operator information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0136] Based on the above information processing method, an embodiment of the present invention provides an information processing device. Figure 12 , is a schematic diagram of the structure of an information processing device provided by an embodiment of the present invention. The information processing device 1200 can run the following units:

[0137] An acquiring unit 1201 is configured to acquire characteristic information of a target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identifier;

[0138] A determining unit 1202 is configured to invoke a domain name resolution service selection model to process characteristic information of the target object and determine a list of candidate domain name resolution servers, the list of candidate domain name resolution servers including an identifier of at least one candidate domain name resolution server, the domain name resolution service selection model being trained based on a dataset of pre-labeled domain name resolution servers;

[0139] The sending unit 1203 is configured to send the candidate domain name resolution server list to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server.

[0140] In one embodiment, the determination unit 1202, when calling the domain name resolution service selection model to process the characteristic information of the target object and determine the candidate domain name resolution server list, is specifically used to: call the domain name resolution service selection model to determine the domain name resolution server library based on the operator information and object identifier included in the characteristic information; call the domain name resolution service selection model to process the characteristic information of the target object to determine the candidate domain name resolution server list from the domain name resolution server library.

[0141] In one embodiment, the determination unit 1202, when calling the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library, is specifically used to: call the domain name resolution service selection model to format the operator information and location information included in the characteristic information of the target object to obtain formatted operator information and location information; call the domain name resolution service selection model to cluster the domain name information included in the characteristic information of the target object to obtain clustered domain name information; call the domain name resolution service selection model to process the formatted operator information and location information and the clustered domain name information to determine a candidate domain name resolution server list from multiple domain name resolution servers included in the domain name resolution server library.

[0142] In one embodiment, the device also includes a processing unit, which is used to: obtain network status parameters of each domain name resolution server in the domain name resolution server library; determine an invalid domain name resolution server from the domain name resolution server library based on the network status parameters of each domain name resolution server; and delete the invalid domain name resolution server from the domain name resolution server library.

[0143] In one embodiment, the processing unit is further used to: obtain a training data set, the training data set includes at least one group of training samples, each group of training samples in the at least one group of training samples includes feature information and annotation data of a sample object, and the annotation data includes a reference domain name resolution server list corresponding to the feature information; call the initialized neural network model to process the feature information of the sample objects included in each group of training samples to obtain a predicted domain name resolution server list; adjust the model parameters of the initialized neural network model according to the predicted domain name resolution server list and the reference domain name resolution server list to obtain a domain name resolution service selection model.

[0144] In summary, the characteristic information of the target object is obtained, and the characteristic information includes one or more of domain name information, operator information, location information, and object identification; the domain name resolution service selection model is called to process the characteristic information of the target object and determine a list of candidate domain name resolution servers, and the candidate domain name resolution server list includes the identification of at least one candidate domain name resolution server, and the domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers; the candidate domain name resolution server list is sent to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server. It should be understood that the control server selects the domain name resolution server through this method, which can improve the efficiency and accuracy of the domain name resolution server selection, thereby improving the acceleration quality of the game.

[0145] Based on the above information processing method, an embodiment of the present invention provides an information processing device. Figure 13 , is a schematic diagram of the structure of an information processing device provided by an embodiment of the present invention. The information processing device 1300 can run the following units:

[0146] The sending unit 1301 is configured to send a service selection request to the control server, where the service selection request includes characteristic information of the target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identifier;

[0147] The receiving unit 1302 is configured to receive a candidate domain name resolution server list sent by the control server in response to the service selection request, where the candidate domain name resolution server list includes an identifier of at least one candidate domain name resolution server;

[0148] The sending unit 1301 is further configured to send a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server;

[0149] The determining unit 1303 is configured to determine a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, where the target resolution result is used to accelerate the service traffic of the target object.

[0150] In one embodiment, the determination unit 1303, when determining the target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, is specifically used to: obtain the response time of each candidate domain name resolution server to the domain name resolution request; obtain the target domain name resolution server with the shortest response time from the at least one candidate domain name resolution server; and use the resolution result of the target domain name resolution server as the target resolution result.

[0151] In one embodiment, the device also includes a processing unit, which is used to: cache the resolution results sent by the at least one candidate domain name resolution server; obtain the resolution result cache status, which includes one or both of the cache quantity and cache time of the resolution results; when the resolution result cache status meets the preset update conditions, update the cached resolution results.

[0152] In one embodiment, the sending unit 1301, before sending a service selection request to the control server, is further used to: obtain an acceleration instruction input for a target object through an acceleration page, the acceleration page including at least one object; in response to the acceleration instruction, obtain characteristic information of the target object, the characteristic information including one or more of domain name information, operator information, location information and object identification.

[0153] In summary, the list of candidate domain name resolution servers received from the control server in response to the service selection request includes the identifier of at least one candidate domain name resolution server; a domain name resolution request is sent to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server; and a target resolution result is determined from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the business traffic of the target object. It should be understood that selecting a domain name resolution server through this method can improve the efficiency and accuracy of domain name resolution server selection, and the client can use the optimal domain name resolution server to accelerate the game.

[0154] Based on the above-mentioned information processing method and information processing apparatus embodiments, the present invention provides a computer device. The computer device described herein corresponds to the aforementioned server. Figure 14 , is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. The computer device 1400 may include at least: a processor 1401, a communication interface 1402, and a computer storage medium 1403. The processor 1401, the communication interface 1402, and the computer storage medium 1403 may be connected via a bus or other means.

[0155] The computer storage medium 1403 may be stored in the memory 1404 of the computer device 1400. The computer storage medium 1403 is used to store a computer program, which includes program instructions. The processor 1401 is used to execute the program instructions stored in the computer storage medium 1403. The processor 1401 (also known as the CPU (Central Processing Unit)) is the computing core and control core of the computer device 1400. It is suitable for implementing one or more instructions, specifically for loading and executing:

[0156] Acquire characteristic information of a target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identifier; call a domain name resolution service selection model to process the characteristic information of the target object, and determine a list of candidate domain name resolution servers, where the list of candidate domain name resolution servers includes an identifier of at least one candidate domain name resolution server, and the domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers; and send the list of candidate domain name resolution servers to a client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server.

[0157] In one embodiment, the processor 1401, when calling the domain name resolution service selection model to process the characteristic information of the target object and determine the candidate domain name resolution server list, is specifically used to: call the domain name resolution service selection model to determine the domain name resolution server library based on the operator information and object identifier included in the characteristic information; call the domain name resolution service selection model to process the characteristic information of the target object to determine the candidate domain name resolution server list from the domain name resolution server library.

[0158] In one embodiment, the processor 1401, when calling the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library, is specifically used to: call the domain name resolution service selection model to format the operator information and location information included in the characteristic information of the target object to obtain formatted operator information and location information; call the domain name resolution service selection model to cluster the domain name information included in the characteristic information of the target object to obtain clustered domain name information; call the domain name resolution service selection model to process the formatted operator information and location information and the clustered domain name information to determine a candidate domain name resolution server list from multiple domain name resolution servers included in the domain name resolution server library.

[0159] In one embodiment, the processor 1401 is further used to: obtain network status parameters of each domain name resolution server in the domain name resolution server library; determine an invalid domain name resolution server from the domain name resolution server library based on the network status parameters of each domain name resolution server; and delete the invalid domain name resolution server from the domain name resolution server library.

[0160] In one embodiment, the processor 1401 is further used to: obtain a training data set, the training data set including at least one group of training samples, each group of training samples in the at least one group of training samples including feature information and annotation data of a sample object, the annotation data including a reference domain name resolution server list corresponding to the feature information; call the initialized neural network model to process the feature information of the sample objects included in each group of training samples to obtain a predicted domain name resolution server list; adjust the model parameters of the initialized neural network model according to the predicted domain name resolution server list and the reference domain name resolution server list to obtain a domain name resolution service selection model.

[0161] In summary, the characteristic information of the target object is obtained, and the characteristic information includes one or more of domain name information, operator information, location information, and object identification; the domain name resolution service selection model is called to process the characteristic information of the target object and determine a list of candidate domain name resolution servers, and the candidate domain name resolution server list includes the identification of at least one candidate domain name resolution server, and the domain name resolution service selection model is trained based on a data set of pre-labeled domain name resolution servers; the candidate domain name resolution server list is sent to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server. It should be understood that the control server selects the domain name resolution server through this method, which can improve the efficiency and accuracy of the domain name resolution server selection, thereby improving the acceleration quality of the game.

[0162] Based on the above-mentioned information processing method and information processing apparatus embodiments, the present invention provides a computer device. The computer device described herein corresponds to the aforementioned server. Figure 14 , is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. The computer device 1400 may include at least: a processor 1401, a communication interface 1402, and a computer storage medium 1403. The processor 1401, the communication interface 1402, and the computer storage medium 1403 may be connected via a bus or other means.

[0163] The computer storage medium 1403 may be stored in the memory 1404 of the computer device 1400. The computer storage medium 1403 is used to store a computer program, which includes program instructions. The processor 1401 is used to execute the program instructions stored in the computer storage medium 1403. The processor 1401 (also known as the CPU (Central Processing Unit)) is the computing core and control core of the computer device 1400. It is suitable for implementing one or more instructions, specifically for loading and executing:

[0164] A service selection request is sent to a control server, wherein the service selection request includes characteristic information of a target object, wherein the characteristic information includes one or more of domain name information, operator information, location information, and object identification; the candidate domain name resolution server list sent by the control server in response to the service selection request includes the identification of at least one candidate domain name resolution server; a domain name resolution request is sent to each candidate domain name resolution server based on the identification of the at least one candidate domain name resolution server; a target resolution result is determined from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, wherein the target resolution result is used to accelerate the processing of the business traffic of the target object.

[0165] In one embodiment, the processor 1401, when determining the target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, is specifically used to: obtain the response time of each candidate domain name resolution server to the domain name resolution request; obtain the target domain name resolution server with the shortest response time from the at least one candidate domain name resolution server; and use the resolution result of the target domain name resolution server as the target resolution result.

[0166] In one embodiment, the processor 1401 is further used to: cache the resolution results sent by the at least one candidate domain name resolution server; obtain the resolution result cache status, which includes one or both of the cache quantity and cache time of the resolution results; and update the cached resolution results when the resolution result cache status meets the preset update conditions.

[0167] In one embodiment, the processor 1401, before sending a service selection request to the control server, is further used to: obtain an acceleration instruction input for a target object through an acceleration page, where the acceleration page includes at least one object; and respond to the acceleration instruction to obtain characteristic information of the target object, where the characteristic information includes one or more of domain name information, operator information, location information, and object identification.

[0168] In summary, the list of candidate domain name resolution servers received from the control server in response to the service selection request includes the identifier of at least one candidate domain name resolution server; a domain name resolution request is sent to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server; and a target resolution result is determined from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the business traffic of the target object. It should be understood that selecting a domain name resolution server through this method can improve the efficiency and accuracy of domain name resolution server selection, and the client can use the optimal domain name resolution server to accelerate the game.

[0169] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to execute all or part of the steps of the above methods in each embodiment of the present application. Among them, the aforementioned storage medium may include: U disk, mobile hard disk, magnetic disk, optical disk, read-only memory (English: Read-Only Memory, abbreviated: ROM) or random access memory (English: Random Access Memory, abbreviated: RAM) and other media that can store program code.

[0170] Those skilled in the art will appreciate that the units and steps of each example described in conjunction with the embodiments disclosed in this application can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0171] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer storage medium or transmitted via a computer storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0172] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An information processing method, characterized in that: include: Acquire characteristic information of the target object, the characteristic information including domain name information, operator information, location information and object identifier; Invoking a domain name resolution service selection model to process characteristic information of the target object and determine a list of candidate domain name resolution servers, the list of candidate domain name resolution servers including an identifier of at least one candidate domain name resolution server, the domain name resolution service selection model being trained based on a dataset of pre-labeled domain name resolution servers; Sending the candidate domain name resolution server list to the client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server; The calling of the domain name resolution service selection model to process the characteristic information of the target object and determine a list of candidate domain name resolution servers includes: Calling a domain name resolution service selection model to determine a domain name resolution server library based on the operator information and object identifier included in the feature information; The domain name resolution service selection model is called to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library.

2. The method according to claim 1, characterized in that The calling of the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library includes: Calling the domain name resolution service selection model to format the operator information and location information included in the characteristic information of the target object to obtain formatted operator information and location information; Calling the domain name resolution service selection model to perform clustering processing on the domain name information included in the characteristic information of the target object to obtain clustered domain name information; The domain name resolution service selection model is called to process the formatted operator information and location information and the clustered domain name information to determine a candidate domain name resolution server list from the multiple domain name resolution servers included in the domain name resolution server library.

3. The method according to claim 1 or 2, characterized in that The method further comprises: Obtaining network status parameters of each domain name resolution server in the domain name resolution server library; Determining an invalid domain name resolution server from the domain name resolution server database according to the network status parameter of each domain name resolution server; The invalid domain name resolution server is deleted from the domain name resolution server database.

4. The method according to claim 1 or 2, characterized in that The method further comprises: Acquire a training data set, the training data set including at least one set of training samples, each set of training samples in the at least one set of training samples including feature information and annotation data of a sample object, the annotation data including a reference domain name resolution server list corresponding to the feature information; Calling the initialized neural network model to process feature information of the sample objects included in each group of training samples to obtain a predicted domain name resolution server list; The model parameters of the initialized neural network model are adjusted according to the predicted domain name resolution server list and the reference domain name resolution server list to obtain a domain name resolution service selection model.

5. An information processing method, characterized in that: include: Sending a service selection request to a control server, the service selection request including characteristic information of a target object, the characteristic information including domain name information, operator information, location information, and an object identifier; the service selection request is used to instruct the control server to call a domain name resolution service selection model to determine a domain name resolution server library based on the operator information and object identifier included in the characteristic information, and to call the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library, the candidate domain name resolution server list including the identifier of at least one candidate domain name resolution server; receiving the candidate domain name resolution server list sent by the control server in response to the service selection request; Sending a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server; A target resolution result is determined from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, and the target resolution result is used to accelerate the service traffic of the target object.

6. The method according to claim 5, characterized in that Determining a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request includes: Obtaining the response time of each candidate domain name resolution server to the domain name resolution request; Obtaining a target domain name resolution server with the shortest response time corresponding to the at least one candidate domain name resolution server; The resolution result of the target domain name resolution server is used as the target resolution result.

7. The method according to claim 5 or 6, characterized in that The method further comprises: caching the resolution result sent by the at least one candidate domain name resolution server; Obtaining a parsing result cache status, where the parsing result cache status includes one or both of a cache quantity and a cache time of the parsing results; When the parsing result cache status meets a preset update condition, the cached parsing result is updated.

8. The method according to claim 5 or 6, characterized in that Before sending the service selection request to the control server, the method further includes: Acquire an acceleration instruction input for a target object through an acceleration page, wherein the acceleration page includes at least one object; In response to the acceleration instruction, characteristic information of the target object is acquired, where the characteristic information includes one or more of domain name information, operator information, location information, and object identification.

9. An information processing device, characterized in that The device comprises: An acquisition unit, configured to acquire characteristic information of a target object, wherein the characteristic information includes domain name information, operator information, location information, and object identifier; a determination unit, configured to invoke a domain name resolution service selection model to process characteristic information of the target object and determine a list of candidate domain name resolution servers, the list of candidate domain name resolution servers including an identifier of at least one candidate domain name resolution server, the domain name resolution service selection model being trained based on a dataset of pre-labeled domain name resolution servers; a sending unit, configured to send the candidate domain name resolution server list to a client, so that the client sends a domain name resolution request to the at least one candidate domain name resolution server; The determining unit is specifically configured to: Calling a domain name resolution service selection model to determine a domain name resolution server library based on the operator information and object identifier included in the feature information; The domain name resolution service selection model is called to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library.

10. An information processing device, characterized in that: The device comprises: a sending unit, configured to send a service selection request to a control server, the service selection request including characteristic information of a target object, the characteristic information including domain name information, operator information, location information, and an object identifier; the service selection request being configured to instruct the control server to invoke a domain name resolution service selection model to determine a domain name resolution server library based on the operator information and object identifier included in the characteristic information, and to invoke the domain name resolution service selection model to process the characteristic information of the target object to determine a candidate domain name resolution server list from the domain name resolution server library, the candidate domain name resolution server list including an identifier of at least one candidate domain name resolution server; a receiving unit, configured to receive the candidate domain name resolution server list sent by the control server in response to the service selection request; The sending unit is further configured to send a domain name resolution request to each candidate domain name resolution server based on the identifier of the at least one candidate domain name resolution server; The determination unit is configured to determine a target resolution result from the resolution results sent by each candidate domain name resolution server in response to the domain name resolution request, wherein the target resolution result is used to accelerate the service traffic of the target object.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores one or more computer programs, and the one or more computer programs are suitable for being loaded by a processor and executing the information processing method according to any one of claims 1 to 4 or any one of claims 5 to 8.

12. A computer program product or a computer program, characterized in that The computer program product comprises a computer program, and the computer program is suitable for being loaded by a processor and executing the information processing method according to any one of claims 1 to 4 or any one of claims 5 to 8.

Images