Information processing method, device, system and computer readable storage medium
By receiving user wish information, using machine learning models to determine business parameters and configure network slicing, the problem of how to provide appropriate network slicing according to user wishes is solved in 5G network, and a high-quality service experience is achieved.
Patent Information
- Application Number
- CN201910766369.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-08-20
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2039-08-20
AI Technical Summary
In 5G networks, there is currently a lack of specific solutions to how to provide users with appropriate network slicing based on user's wishes.
By receiving user's wish information, using machine learning models to determine business parameters, and sending configuration requests to the network slice orchestration manager to configure matching network slices to provide network slice capabilities, and users can obtain corresponding business services through the application program interface.
It realizes the determination of matching network slices based on user wish information, meet user needs, and improve service quality and user experience.
Smart Images

Figure CN112423312B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of communication technology, and in particular to an information processing method, device, system and computer-readable storage medium. Background Art
[0002] In 5G networks, network slicing can help users realize the desired functions and features, quickly deploy services, and reduce the time to go online.
[0003] There is currently no specific solution on how to provide users with appropriate network slices based on their wishes. Summary of the invention
[0004] A technical problem to be solved by the present disclosure is: how to provide users with appropriate network slices based on user preference information.
[0005] According to some embodiments of the present disclosure, an information processing method is provided, including: receiving a service request sent by a user, the service request including: user's preference information; determining corresponding service parameters based on the user's preference information; determining matching network slice information based on the service parameters; and providing network slice capabilities to the user through an application program interface.
[0006] In some embodiments, the user's intention information is input into a machine learning model to obtain a corresponding business scenario as output; and the corresponding business parameters are determined based on the business scenario.
[0007] In some embodiments, determining the information of the matching network slice based on the business parameters includes: sending a network slice configuration request to the network slice orchestration manager, the network slice configuration request includes the business parameters, so that the network slice orchestration manager configures the matching network slice according to the business parameters; receiving the network slice configuration response returned by the network slice orchestration manager, the network slice configuration response includes the information of the network slice that matches the business parameters.
[0008] In some embodiments, the network slice orchestration manager configures a matching network slice according to business parameters, including: the network slice orchestration manager searches for a matching network slice template according to the business parameters; if the network slice orchestration manager fails to find a matching network slice template, the network slice orchestration manager updates the parameters of an existing network slice template according to the business parameters, or creates a new network slice template to obtain a network slice template corresponding to the business parameters; the network slice orchestration manager schedules and orchestrates network resources according to the network slice template corresponding to the business parameters to generate a corresponding network slice instance.
[0009] In some embodiments, the method also includes: receiving feedback information from feedback users on network slices; and updating parameters of the machine learning model based on the feedback information.
[0010] In some embodiments, the method also includes: receiving a service termination request sent by a user; sending termination information to the network slice orchestration manager so that the network slice orchestration manager deactivates or terminates the instance of the corresponding network slice; receiving the termination result returned by the network slice orchestration manager; and sending the service termination result to the user.
[0011] In some embodiments, the method also includes: receiving an alarm notification sent by the network slice orchestration manager, the alarm notification including an identifier of the network slice; increasing the priority of the network slice corresponding to the identifier to a preset level; sending an alarm processing request to the network slice orchestration manager, the alarm processing request including the increased priority of the network slice; so that the network slice orchestration manager processes the network slice according to the alarm processing request; and receiving an alarm resolution notification sent by the network slice orchestration manager.
[0012] According to some other embodiments of the present disclosure, an information processing device is provided, including: a user information receiving module, used to receive a service request sent by a user, the service request including: user's preference information; a preference information conversion module, used to determine corresponding service parameters according to the user's preference information; a slice determination module, used to determine matching network slice information according to the service parameters; a capability exposure module, used to provide network slice capabilities to users through an application program interface.
[0013] In some embodiments, the intention information conversion module is used to input the user's intention information into a machine learning model to obtain the corresponding business scenario as output; and determine the corresponding business parameters based on the business scenario.
[0014] In some embodiments, the slice determination module is used to send a network slice configuration request to the network slice orchestration manager, the network slice configuration request includes business parameters, so that the network slice orchestration manager configures a matching network slice according to the business parameters; and receive a network slice configuration response returned by the network slice orchestration manager, the network slice configuration response includes information about the network slice that matches the business parameters.
[0015] In some embodiments, the user information receiving module is also used to receive feedback information from users on network slices; the willingness information conversion module is also used to update the parameters of the machine learning model based on the feedback information.
[0016] In some embodiments, the user information receiving module is further used to receive a service termination request sent by a user; receive a termination result returned by the network slice orchestration manager; and the capability exposure module is further used to send the service termination result to the user. The device also includes: a slice termination module, which is used to send termination information to the network slice orchestration manager so that the network slice orchestration manager deactivates or terminates the instance of the corresponding network slice.
[0017] In some embodiments, the device also includes: an alarm processing module, used to receive an alarm notification sent by the network slice orchestration manager, the alarm notification includes an identifier of the network slice; increase the priority of the network slice corresponding to the identifier to a preset level; send an alarm processing request to the network slice orchestration manager, the alarm processing request includes the increased priority of the network slice; so that the network slice orchestration manager processes the network slice according to the alarm processing request; receive an alarm resolution notification sent by the network slice orchestration manager.
[0018] According to some further embodiments of the present disclosure, an information processing system is provided, including: a processing device; and a network slice orchestration manager, configured to receive a network slice configuration request sent by the information processing device, the network slice configuration request including business parameters, and configure a matching network slice according to the business parameters; and send a network slice configuration response to the information processing device, the network slice configuration response including information of the network slice matching the business parameters.
[0019] In some embodiments, the network slice orchestration manager is used to search for a matching network slice template based on business parameters; if no matching network slice template is found, the parameters of an existing network slice template are updated according to the business parameters, or a new network slice template is created to obtain a network slice template corresponding to the business parameters; and network resources are scheduled and orchestrated according to the network slice template corresponding to the business parameters to generate a corresponding network slice instance.
[0020] According to some further embodiments of the present disclosure, an information processing system is provided, comprising: a processor; and a memory coupled to the processor, for storing instructions, which, when executed by the processor, causes the processor to execute the steps of the information processing method of any of the aforementioned embodiments.
[0021] According to some further embodiments of the present disclosure, a computer-readable non-transitory storage medium is provided, on which a computer program is stored, wherein when the program is executed by a processor, the steps of the information processing method of any of the aforementioned embodiments are implemented.
[0022] The method disclosed in the present invention can convert the user's intention information into corresponding business parameters, determine the matching network slice according to the business parameters, and then provide the network slice capability to the user through the application program interface, so that the user can obtain the corresponding business service through the network slice. Such a network slice determination method can determine the slice that matches the user's intention information, meet the user's needs, and improve the service quality and user experience.
[0023] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0025] Figure 1 A flowchart illustrating an information processing method according to some embodiments of the present disclosure is provided.
[0026] Figure 2 A schematic flowchart showing information processing methods according to other embodiments of the present disclosure is provided.
[0027] Figure 3 A flowchart diagram showing information processing methods according to some further embodiments of the present disclosure is provided.
[0028] Figure 4 A flowchart diagram showing an information processing method according to some further embodiments of the present disclosure is provided.
[0029] Figure 5 A schematic diagram showing the structure of an information processing device according to some embodiments of the present disclosure.
[0030] Figure 6 A schematic diagram showing the structure of an information processing system according to some embodiments of the present disclosure.
[0031] Figure 7 A schematic diagram showing the structure of an information processing system according to other embodiments of the present disclosure.
[0032] Figure 8 A schematic diagram showing the structure of an information processing system according to some further embodiments of the present disclosure. DETAILED DESCRIPTION
[0033] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.
[0034] This solution is proposed to solve the problem of how to provide users with appropriate network slices based on their preferences. Figure 1 Some embodiments of the information processing method of the present disclosure are described.
[0035] Figure 1 Flowcharts of some embodiments of the information processing method disclosed in the present invention. Figure 1 As shown, the method of this embodiment includes: in steps S102 to S108.
[0036] In step S102, a service request sent by a user is received.
[0037] A user can act as a lessee of network slicing capabilities and send a service request, which includes, for example, the user's willingness information. That is, the user can send a subscription willingness information for the service. The willingness information can be input by the user through a terminal, for example, it can be input through voice, video, text, etc. For methods such as voice or video, it can be converted into a willingness text through existing technologies. The willingness information, for example, is information indicating the user's business needs and willingness, such as "need to provide network services at stadiums / concerts", "need to provide 4K high-definition video conferencing services", "request for autonomous driving", etc.
[0038] In step S104, corresponding service parameters are determined according to the user's intention information.
[0039] In some embodiments, the user's intention information is input into a machine learning model to obtain a corresponding business scenario as output; and the corresponding business parameters are determined based on the business scenario.
[0040] After the machine learning model is pre-trained and the network parameters are determined, the user's willingness information is input into the machine learning model to obtain the output classification, and each category can represent a business scenario. Each business scenario corresponds to different business parameters. For example, a business parameter template can be pre-configured, and the business parameters corresponding to each scenario are configured in the business parameter template. In the business parameter template, the corresponding business parameters can be found according to the determined business scenario.
[0041] For example, the service parameters may include one or more of the following: delay level, rate level, packet loss rate level, jitter level, maximum number of users level, coverage area level, user mobility level, and resource sharing level. They may also be set according to actual service data and are not limited to the examples given. Each service parameter can be divided into different levels according to its normal value range. For example, the delay includes 1 to 2ms, 2 to 3ms... and many other different levels. One or more service parameters and different levels of service parameters are selected to form a service scenario. For example, a service scenario is: delay 1 to 2ms, and the maximum downlink rate is 100Mbps. The finer the granularity of the service parameter division, the more accurately the user's desired information can be met. For example, the delay can be further divided into air interface delay, end-to-end delay, and so on.
[0042] The willingness information annotated with the corresponding business scenarios is used as a training sample, input into the machine learning model to be trained, and the loss function is calculated according to the output results and the corresponding annotations, and the parameters of the machine learning model are adjusted until the convergence conditions are met to obtain the trained machine learning model. The machine learning model is, for example, a neural network model. After the willingness information is input into the machine learning model, it can first be converted into a corresponding feature vector, and the output business scenario can be further determined according to the feature vector.
[0043] In some embodiments, the training samples can be directly labeled with various service parameters. For example, a training sample can be labeled with a delay level of 1, a rate level of 2, etc., and no service parameter level can be represented by 0. In this way, the machine learning model is trained using the training samples. Inputting new willingness information samples into the trained machine learning model can directly output the values corresponding to various service parameters. That is, the user's willingness information is input into the machine learning model to obtain the corresponding service parameters output.
[0044] In some embodiments, business parameters corresponding to different keywords can be preset. A keyword extraction model can be used to extract keywords from the intention information, and the corresponding business parameters can be found based on the keywords. The keyword extraction model can use an existing model. For example, the intention information is "need to provide network services at the stadium / concert", the keyword "stadium / concert" is extracted, and the corresponding business parameters are found as rate levels, for example, including: downlink rate of 200-300Mbps, uplink rate of 50Mbps-100Mbps, and connection density level of 200-2500 / km. 2 .
[0045] In some embodiments, when the intention information includes business parameters, the keywords corresponding to the business parameters in the intention information can be first identified and extracted, and other words in the intention information except the keywords corresponding to the business parameters can be input into the machine learning model to obtain the corresponding business parameters, and the obtained business parameters can be modified according to the keywords corresponding to the business parameters.
[0046] In step S106, information of the matching network slice is determined based on the business parameters.
[0047] In some embodiments, a network slice configuration request is sent to a network slice orchestration manager, and the network slice configuration request includes service parameters. The network slice orchestration manager configures a matching network slice according to the service parameters. A network slice configuration response returned by the network slice orchestration manager is received, and the network slice configuration response includes information about the network slice matching the service parameters. The network slice configuration response may also include: information about whether the network slice configuration is successful. The information about the network slice includes, for example, information such as an identifier of the network slice.
[0048] In some embodiments, the network slice orchestration manager searches for a matching network slice template according to the business parameters. If no matching network slice template is found, the parameters of the existing network slice template are updated according to the business parameters, or a new network slice template is created to obtain a network slice template corresponding to the business parameters. According to the network slice template corresponding to the business parameters, the network resources are scheduled and orchestrated to generate a corresponding network slice instance.
[0049] The network slice orchestration manager can save several network slice templates in advance, and can first compare the parameters of the network slice template with the business parameters to determine the network parameter template that matches the business parameters. If no network slice template that matches the business parameters is found, the parameters of the existing network slice template are updated, or a new network slice template is created. For example, the network slice template with the highest degree of match with the business parameters is determined, and it is determined whether the number of mismatches between the parameters of the network slice template and the business parameters exceeds a threshold. If the threshold is exceeded, a new network slice template is created according to the business parameters, otherwise, the network slice template with the highest degree of match is modified according to the business parameters.
[0050] The network slice template can be an information model developed based on SLA (Service Level Agreement) parameters. The SLA parameters can be the same or similar to the business parameters determined based on the willingness information, and the corresponding parameters in the network slice template can be determined based on the business parameters. The matching of the parameters of the network slice template and the business parameters means that the two are the same or the value range of the parameters of the network slice template includes the business parameters.
[0051] Furthermore, after configuring the network template corresponding to the service parameters, the network slice orchestration manager schedules and orchestrates the required network resources according to the network slice template. For example, the network slice template defines the end-to-end SLA, and the end-to-end SLA can be decomposed into the SLA of the sub-slice, and the subnet resources are scheduled according to the sub-slice SLA. The access network resources can be scheduled and orchestrated according to the RAN (Radio Access Network) SLA, the transport network resources can be scheduled and orchestrated according to the TN (Transport Network) SLA, and the core network resources can be scheduled and orchestrated according to the CN (Core Network) SLA.
[0052] In step S108, the network slicing capability is provided to the user through an application program interface.
[0053] The capabilities of the network slice can be extracted and the corresponding API (application programming interface) can be generated. Users can then use the API to obtain business services using the network slice.
[0054] The method of the above embodiment can convert the user's willingness information into corresponding business parameters, determine the matching network slice according to the business parameters, and then provide the network slice capability to the user through the application program interface, so that the user can obtain the corresponding business service through the network slice. Such a network slice determination method can determine the slice that matches the user's willingness information, meet the user's needs, and improve service quality and user experience.
[0055] Combine the following Figure 2 Other embodiments of the information processing method disclosed herein are described.
[0056] Figure 2 Flowcharts of some embodiments of the information processing method disclosed in the present invention. Figure 2 As shown, the method of this embodiment includes: in steps S202 to S216.
[0057] In step S202, the capability opening management platform receives a service request sent by a user, where the service request includes: user's intention information.
[0058] In step S204, the capability opening management platform inputs the user's willingness information into the machine learning model to obtain the corresponding business parameters of the output.
[0059] Before determining the service parameters, the capability opening management platform can perform two-way authentication with the user. The capability opening management platform verifies the user's identity information and determines whether the user has the authority to request network slicing. The user can authenticate the legitimacy of the capability opening management platform to ensure the security of the communication process.
[0060] In step S206, the capability opening management platform sends a network slice configuration request to the network slice orchestration manager, and the network slice configuration request includes service parameters.
[0061] In step S208, the network slice orchestration manager configures a matching network slice according to the business parameters.
[0062] In step S210, the capability opening management platform receives a network slice configuration response returned by the network slice orchestration manager, where the network slice configuration response includes information about the network slice that matches the service parameters.
[0063] In step S212, the capability opening management platform opens the network slicing capabilities to users through the application program interface.
[0064] In step S214, the capability opening management platform receives feedback information from users on network slices.
[0065] The user may submit feedback information to the capability exposure management platform, and the feedback information may include, for example, a satisfaction rating for each service parameter, or feedback text, such as "the delay is too high".
[0066] In step S216, the capability opening management platform updates the parameters of the machine learning model according to the feedback information.
[0067] If it is a feedback text, the keyword extraction model can be used to extract keywords, and the semantic recognition model can be used to match the corresponding business parameters, and the business parameters corresponding to the network slice currently applied by the feedback user can be corrected according to the feedback information. The feedback user's willingness information is annotated with the corrected business parameters, and the feedback user's willingness information and the corresponding annotated information are used as training samples to retrain the machine learning model. When correcting the business parameters, if the feedback information includes specific values of the business parameters, the correction can be made according to the specific values. If the feedback information does not include specific values, it can be adjusted according to the preset step size. In the case where a small number of feedback users are dissatisfied with the business parameters corresponding to the network slice, the parameters of the corresponding network slice can be directly adjusted according to the feedback information of these users.
[0068] In the above embodiment, the capability exposure management platform and the network slice orchestration manager can be integrated to reduce the information interaction process.
[0069] The method of the above embodiment can provide users with suitable network slices based on user preference information, and can further adjust the machine learning model based on user feedback information, so that the model can more accurately convert user preference information into business parameters, thereby providing users with more suitable network slices, further meeting users' business needs, and improving user experience.
[0070] Combine the following Figure 3 Some further embodiments of the information processing method of the present disclosure are described.
[0071] Figure 3 Flowcharts of some embodiments of the information processing method disclosed in the present invention. Figure 3 As shown, the method of this embodiment includes: in steps S302 to S310.
[0072] In step S302, the capability opening management platform receives a service termination request sent by a user.
[0073] The service termination request includes information about the service that the user wants to terminate.
[0074] In step S304, the capability opening management platform sends a termination message to the network slice orchestration manager, which includes the service information that the user wants to terminate.
[0075] Before sending the termination information, the capability exposure management platform can perform two-way authentication with the user and send the termination information after the authentication is passed.
[0076] In step S306, the network slice orchestration manager deactivates or terminates the instance of the corresponding network slice.
[0077] The network slice orchestration manager determines the instance of the corresponding network slice based on the service information that the user wants to terminate, and deactivates or terminates it.
[0078] In step S308, the capability opening management platform receives the termination result returned by the network slice orchestration manager.
[0079] The network slice orchestration manager returns a message indicating successful termination.
[0080] In step S310, the capability opening management platform sends a service termination result to the user.
[0081] In the above embodiment, the capability opening management platform and the network slice orchestration manager can be integrated to reduce the information interaction process. In the above embodiment, the slice service is terminated in time according to the needs of the user, and the network resources are released for other services, thereby improving resource utilization and enhancing user experience.
[0082] Combine the following Figure 4 Some further embodiments of the information processing method of the present disclosure are described.
[0083] Figure 4 Flowcharts of some further embodiments of the information processing method disclosed herein. Figure 4 As shown, the method of this embodiment includes: in steps S402 to S410.
[0084] In step S402, the capability opening management platform receives an alarm notification sent by the network slice orchestration manager, where the alarm notification includes an identifier of the network slice.
[0085] The network slice orchestration manager is responsible for managing the life cycle of network slice templates and network slice instances. The network slice orchestration manager sends an alarm notification when a network slice failure or anomaly is found. The life cycle management of network slice instances includes, for example, preparation, configuration, instantiation, activation, operation, termination or deactivation. Configuration is the orchestration and scheduling of network slices according to business parameters. After the network slicing capability is opened to users, when users need to perform business, they send business requests through APIs, and the network slice orchestration manager instantiates, activates and runs the network slices according to the business requests.
[0086] In step S404, the capability opening management platform increases the priority of the network slice corresponding to the identifier to a preset level.
[0087] In step S406, the capability opening management platform sends an alarm processing request to the network slice orchestration manager, and the alarm processing request includes the increased priority of the network slice.
[0088] In step S408, the network slice orchestration manager processes the network slice according to the alarm processing request.
[0089] The network slice orchestration manager processes each network slice according to its priority, and the network slices with increased priority will be processed first.
[0090] After receiving the alarm notification, the capability exposure management platform can stop publishing the API of the network slice and send a notification to the user. Alternatively, after receiving the alarm processing request from the capability exposure management platform, the network slice orchestration manager can replace the abnormal network element or network function in the network slice with a backup network element or network function to keep providing services to users.
[0091] In step S410, the capability opening management platform receives an alarm resolution notification sent by the network slice orchestration manager.
[0092] If the network slice API release was stopped before, after receiving the alarm resolution notification, the capability exposure management platform can re-release the corresponding network slice API and notify the corresponding users.
[0093] In the above embodiment, the capability opening management platform and the network slice orchestration manager can be integrated to reduce the information interaction process. The network slice orchestration manager manages the network slices to timely discover abnormal slices, and cooperates with the capability management platform to handle abnormal slices in a timely manner, thereby ensuring the service quality of the network slices and improving the user experience.
[0094] The present disclosure also provides an information processing device, which can be set in the capability opening management platform of any of the above embodiments. Figure 5Give a description.
[0095] Figure 5 Figure 1 is a structural diagram of some embodiments of the information processing device disclosed in the present invention. Figure 5 As shown, the device 50 of this embodiment includes: a user information receiving module 502, a willingness information conversion module 504, a slice determination module 506, and a capability opening module 508.
[0096] The user information receiving module 502 is used to receive a service request sent by a user, where the service request includes user's willingness information.
[0097] The willingness information conversion module 504 is used to determine corresponding service parameters according to the user's willingness information.
[0098] In some embodiments, the intention information conversion module 504 is used to input the user's intention information into a machine learning model to obtain the corresponding business scenario of the output; and determine the corresponding business parameters according to the business scenario.
[0099] In some embodiments, the user information receiving module 502 is further used to receive feedback information from users on the network slice. The willingness information conversion module 504 is also used to update the parameters of the machine learning model according to the feedback information.
[0100] The slice determination module 506 is used to determine the information of the matching network slice based on the business parameters.
[0101] In some embodiments, the slice determination module 506 is used to send a network slice configuration request to the network slice orchestration manager, the network slice configuration request includes business parameters, so that the network slice orchestration manager configures a matching network slice according to the business parameters; and receive a network slice configuration response returned by the network slice orchestration manager, the network slice configuration response includes information about the network slice that matches the business parameters.
[0102] The capability exposure module 508 is used to provide network slicing capabilities to users through an application programming interface.
[0103] In some embodiments, the user information receiving module 502 is further used to receive a service termination request sent by a user. The capability opening module 508 is further used to send a service termination result to the user. The device 50 also includes: a slice termination module 510, which is used to send termination information to the network slice orchestration manager so that the network slice orchestration manager deactivates or terminates the instance of the corresponding network slice; and receives the termination result returned by the network slice orchestration manager.
[0104] In some embodiments, the device 50 also includes: an alarm processing module 512, which is used to receive an alarm notification sent by the network slice orchestration manager, the alarm notification includes an identifier of the network slice; increase the priority of the network slice corresponding to the identifier to a preset level; send an alarm processing request to the network slice orchestration manager, the alarm processing request includes the increased priority of the network slice; so that the network slice orchestration manager processes the network slice according to the alarm processing request; receive an alarm resolution notification sent by the network slice orchestration manager.
[0105] The present disclosure also provides an information processing system, Figure 6 Give a description.
[0106] Figure 6 FIG. 1 is a structural diagram of some embodiments of the information processing system disclosed in the present invention. Figure 6 As shown, the system 60 of this embodiment includes: the information processing device 50 of any of the aforementioned embodiments; and a network slice orchestration manager 62.
[0107] The network slice orchestration manager 62 is used to receive a network slice configuration request sent by an information processing device, the network slice configuration request includes business parameters, and configures a matching network slice according to the business parameters; and send a network slice configuration response to the information processing device, the network slice configuration response includes information about the network slice that matches the business parameters.
[0108] In some embodiments, the network slice orchestration manager 62 is used to search for a matching network slice template based on business parameters; if no matching network slice template is found, the parameters of an existing network slice template are updated according to the business parameters, or a new network slice template is created to obtain a network slice template corresponding to the business parameters; and network resources are scheduled and orchestrated according to the network slice template corresponding to the business parameters to generate a corresponding network slice instance.
[0109] The information processing system in the embodiments of the present disclosure, such as the information processing device and the network slice orchestration manager in the system, can be implemented by various computing devices or computer systems. Figure 7 as well as Figure 8 Give a description.
[0110] Figure 7 FIG. 1 is a structural diagram of some embodiments of the information processing system disclosed in the present invention. Figure 7 As shown, the system 70 of this embodiment includes: a memory 710 and a processor 720 coupled to the memory 710 , and the processor 720 is configured to execute the information processing method in any of some embodiments of the present disclosure based on the instructions stored in the memory 710 .
[0111] The memory 710 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.
[0112] Figure 8 FIG. 1 is a structural diagram of some other embodiments of the information processing system disclosed in the present invention. Figure 8 As shown, the system 80 of this embodiment includes: a memory 810 and a processor 820, which are similar to the memory 710 and the processor 720 respectively. It can also include an input and output interface 830, a network interface 840, a storage interface 850, etc. These interfaces 830, 840, 850 and the memory 810 and the processor 820 can be connected, for example, via a bus 860. Among them, the input and output interface 830 provides a connection interface for input and output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 840 provides a connection interface for various networked devices, for example, it can be connected to a database server or a cloud storage server. The storage interface 850 provides a connection interface for external storage devices such as SD cards and USB flash drives.
[0113] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0114] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0117] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.
Claims
1. An information processing method, comprising: Receiving a service request sent by a user, the service request including: the user's intention information; Determining corresponding service parameters according to the user's willingness information includes: in the case where the willingness information includes service parameters, identifying keywords corresponding to the service parameters in the willingness information, extracting the keywords, using other words in the willingness information except the keywords corresponding to the service parameters to input into a machine learning model, obtaining corresponding service parameters, and modifying the obtained service parameters according to the keywords corresponding to the service parameters, wherein the service parameters include: one or more of: delay level, rate level, packet loss rate level, jitter level, maximum number of users level, coverage area level, user mobility level, and resource sharing level; Determine information of a matching network slice according to the service parameters; Providing the capabilities of the network slice to the user through an application program interface; Receive feedback information from a feedback user on the network slice, wherein the feedback information includes feedback text; Extracting keywords from the feedback text using a keyword extraction model, and matching them to corresponding business parameters using a semantic recognition model; The matched service parameters are modified according to the feedback text, wherein when the matched service parameters are modified, if the feedback text includes a specific value of the matched service parameter, the modification is performed according to the specific value; if the feedback text does not include the specific value of the matched service parameter, the modification is performed according to a preset step size; The intention information of the feedback user is annotated using the corrected business parameters, and the intention information of the feedback user and the corresponding annotated information are used as training samples to retrain the machine learning model.
2. The method according to claim 1, wherein: The information of determining the matching network slice according to the service parameters includes: Sending a network slice configuration request to a network slice orchestration manager, wherein the network slice configuration request includes the service parameters, so that the network slice orchestration manager configures a matching network slice according to the service parameters; Receive a network slice configuration response returned by the network slice orchestration manager, where the network slice configuration response includes information about a network slice that matches the service parameters.
3. The method according to claim 2, wherein: The network slice orchestration manager configures a matching network slice according to the service parameters, including: The network slice orchestration manager searches for a matching network slice template according to the service parameters; When no matching network slice template is found, the network slice orchestration manager updates the parameters of the existing network slice template according to the service parameters, or creates a new network slice template to obtain a network slice template corresponding to the service parameters; The network slice orchestration manager schedules and orchestrates network resources according to the network slice template corresponding to the business parameters to generate corresponding network slice instances.
4. The method according to claim 1, further comprising: receiving a service termination request sent by the user; Sending termination information to the network slice orchestration manager so that the network slice orchestration manager deactivates or terminates the instance of the corresponding network slice; Receiving a termination result returned by the network slice orchestration manager; A service termination result is sent to the user.
5. The method according to claim 1, further comprising: Receive an alarm notification sent by a network slice orchestration manager, where the alarm notification includes an identifier of the network slice; Raising the priority of the network slice corresponding to the identifier to a preset level; Sending an alarm processing request to the network slice orchestration manager, wherein the alarm processing request includes the increased priority of the network slice; So that the network slice orchestration manager processes the network slice according to the alarm processing request; Receive an alarm resolution notification sent by the network slice orchestration manager.
6. An information processing device, comprising: A user information receiving module is used to receive a service request sent by a user, wherein the service request includes: the user's willingness information; The intention information conversion module is used to determine the corresponding service parameters according to the intention information of the user, including: in the case where the intention information includes the service parameters, identifying the keywords corresponding to the service parameters in the intention information, extracting the keywords, using other words in the intention information except the keywords corresponding to the service parameters to input into the machine learning model, to obtain the corresponding service parameters, and modifying the obtained service parameters according to the keywords corresponding to the service parameters, wherein the service parameters include: one or more of the delay level, rate level, packet loss rate level, jitter level, maximum number of users level, coverage area level, user mobility level, and resource sharing level; A slice determination module, used to determine information of a matching network slice according to the service parameters; A capability exposure module, used to provide the capability of the network slice to the user through an application program interface; The user information receiving module is further used to receive feedback information from a feedback user on the network slice, wherein the feedback information includes feedback text; The intention information conversion module is also used to extract keywords in the feedback text using a keyword extraction model, and match corresponding business parameters using a semantic recognition model; modify the matched business parameters according to the feedback text, wherein when modifying the matched business parameters, if the feedback text includes a specific value of the matched business parameter, modify it according to the specific value; if the feedback text does not include the specific value of the matched business parameter, adjust it according to a preset step size; use the modified business parameters to annotate the intention information of the feedback user, use the intention information of the feedback user and the corresponding annotated information as training samples, and retrain the machine learning model.
7. The device according to claim 6, wherein: The slice determination module is used to send a network slice configuration request to the network slice orchestration manager, the network slice configuration request includes the business parameters, so that the network slice orchestration manager configures a matching network slice according to the business parameters; and receive a network slice configuration response returned by the network slice orchestration manager, the network slice configuration response includes information about the network slice that matches the business parameters.
8. The device according to claim 6, wherein: The user information receiving module is also used to receive a service termination request sent by the user; The capability opening module is further used to send a service termination result to the user; The device also includes: A slice termination module, used to send termination information to the network slice orchestration manager so that the network slice orchestration manager deactivates or terminates the instance of the corresponding network slice; Receive the termination result returned by the network slice orchestration manager.
9. The apparatus according to claim 6, further comprising: An alarm processing module, used to receive an alarm notification sent by the network slice orchestration manager, wherein the alarm notification includes an identifier of the network slice; Raising the priority of the network slice corresponding to the identifier to a preset level; sending an alarm processing request to the network slice orchestration manager, wherein the alarm processing request includes the increased priority of the network slice; So that the network slice orchestration manager processes the network slice according to the alarm processing request; Receive an alarm resolution notification sent by the network slice orchestration manager.
10. An information processing system comprising: The information processing device according to any one of claims 6 to 9; as well as The network slice orchestration manager is used to receive a network slice configuration request sent by the information processing device, the network slice configuration request includes the business parameters, and configure a matching network slice according to the business parameters; and send a network slice configuration response to the information processing device, the network slice configuration response includes information of a network slice matching the business parameters.
11. The system according to claim 10, wherein: The network slice orchestration manager is used to search for a matching network slice template according to the business parameters; if no matching network slice template is found, the parameters of the existing network slice template are updated according to the business parameters, or a new network slice template is created to obtain a network slice template corresponding to the business parameters; and network resources are scheduled and orchestrated according to the network slice template corresponding to the business parameters to generate a corresponding network slice instance.
12. An information processing system comprising: processor; as well as A memory coupled to the processor, for storing instructions, wherein when the instructions are executed by the processor, the processor executes the information processing method according to any one of claims 1 to 5.
13. A computer-readable non-transitory storage medium having a computer program stored thereon, wherein: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
