Resource management method and apparatus, communication device and storage medium

Abstract

The present disclosure relates to the technical field of communications, and specifically relates to a resource management method and apparatus, a communication device and a storage medium. The resource management method comprises: determining that the processing of a knowledge base (KB) is required; acquiring resource usage information of at least one candidate device, and on the basis of the resource usage information, predicting future available resources of the candidate device; on the basis of the current available resources and the future available resources of the at least one candidate device, determining at least one processing device from among the at least one candidate device; and allocating the KB to the at least one processing device for processing. On the basis of the present disclosure, when a processing device is selected from among candidate devices, not only are currently available resources of the candidate devices considered, but future available resources of the candidate devices are also considered, thereby being conducive to resources of the selected processing device being well-suited for processing a KB.

Description

Resource management methods and apparatus, communication equipment and storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and more specifically, to resource management methods, resource management devices, communication equipment, and storage media. Background Technology

[0002] In the field of artificial intelligence, knowledge bases can play a supporting role, such as assisting in the machine learning process. Because knowledge bases contain a massive amount of data, processing them requires significant resources. Therefore, it is necessary to allocate system resources rationally to ensure that appropriate equipment is available for processing the knowledge base.

[0003] Summary of the Invention

[0004] Embodiments of this disclosure provide resource management methods and apparatus, communication devices, and storage media to address technical problems in the related art.

[0005] According to a first aspect of the present disclosure, a resource management method is proposed, the method comprising: determining that a knowledge base KB needs to be processed; obtaining resource usage information of at least one candidate device, and predicting the future available resources of the candidate device based on the resource usage information; determining at least one processing device among the at least one candidate device based on the current available resources and future available resources of the at least one candidate device; and allocating the KB to the at least one processing device for processing.

[0006] According to a second aspect of the present disclosure, a resource management apparatus is provided, the module comprising: a processing module configured to determine that a knowledge base KB needs to be processed; a receiving module configured to acquire resource usage information of at least one candidate device and predict the future available resources of the candidate device based on the resource usage information; wherein the processing module is further configured to determine at least one processing device among the at least one candidate device based on the current available resources and future available resources of the at least one candidate device; and a sending module configured to allocate the KB to the at least one processing device for processing.

[0007] According to a third aspect of the present disclosure, a communication device is provided, comprising: one or more processors; wherein the network device is configured to perform the resource management method described in the first aspect.

[0008] According to a fourth aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform the resource management method described in the first aspect.

[0009] According to a fifth aspect of the present disclosure, a program product is provided that, when executed by a communication device, causes the communication device to perform the resource management method described in the first aspect.

[0010] According to embodiments of this disclosure, when KB needs to be processed, a processing device for processing KB can be selected from the candidate devices based on the current and future available resources of the candidate devices, and then the KB can be allocated to the processing device for processing. Since the selection of a processing device from the candidate devices takes into account not only the current available resources of the candidate devices but also the future available resources of the candidate devices, it is beneficial to select a processing device whose resources are well-suited for processing KB. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0013] Figure 1B is a schematic diagram of a semantic communication scenario according to an embodiment of the present disclosure.

[0014] Figure 2 is an interactive schematic diagram illustrating a resource management method according to an embodiment of the present disclosure.

[0015] Figure 3A is a schematic diagram illustrating a centralized training method according to an embodiment of the present disclosure.

[0016] Figure 3B is a schematic diagram illustrating a distributed training according to an embodiment of the present disclosure.

[0017] Figure 3C is a schematic diagram illustrating a federated training according to an embodiment of the present disclosure.

[0018] Figure 4 is a schematic diagram illustrating an application scenario of a resource management method according to an embodiment of the present disclosure.

[0019] Figure 5 is a schematic diagram illustrating a resource management method and a computer network convergence application according to an embodiment of the present disclosure.

[0020] Figure 6 is a schematic block diagram illustrating a resource management device according to an embodiment of the present disclosure.

[0021] Figure 7A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure.

[0022] Figure 7B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0023] Embodiments of this disclosure provide resource management methods and apparatus, communication devices, and storage media.

[0024] In a first aspect, embodiments of this disclosure propose a resource management method, the method comprising: determining that a knowledge base KB needs to be processed; obtaining resource usage information of at least one candidate device, and predicting the future available resources of the candidate device based on the resource usage information; determining at least one processing device among the at least one candidate device based on the current available resources and future available resources of the at least one candidate device; and allocating the KB to the at least one processing device for processing.

[0025] In the above embodiments, when it is necessary to process KB, a processing device for processing KB can be selected from the candidate devices based on the current and future available resources of the candidate devices, and then the KB can be allocated to the processing device for processing. Since the selection of a processing device from the candidate devices takes into account not only the current available resources of the candidate devices but also the future available resources of the candidate devices, it is beneficial to select a processing device whose resources are well-suited for processing KB.

[0026] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: obtaining a Quality of Service (QoS) threshold and / or Experience Quality of Experience (QoE) threshold for the device to be allocated; triggering the at least one processing device to send a processed KB to the device to be allocated based on condition parameters, wherein the condition parameters include at least one of the following: the currently available resources of the at least one processing device; the future available resources of the at least one processing device; and the QoS threshold and / or QoE threshold of the device to be allocated.

[0027] In conjunction with some embodiments of the first aspect, in some embodiments, before triggering the at least one processing device to send the processed KB to the device to be allocated, the method further includes: determining, based on the condition parameters, whether the processed KB can be sent to the device to be allocated; and, if the processed KB cannot be sent to the device to be allocated, adjusting the path used to send the processed KB.

[0028] In conjunction with some embodiments of the first aspect, in some embodiments, before triggering the at least one processing device to send the processed KB to the device to be allocated, the method further includes: determining, based on the condition parameters, whether the processed KB can be sent to the device to be allocated; and, if the processed KB cannot be sent to the device to be allocated, adjusting the resources allocated to at least one of the processing devices.

[0029] In conjunction with some embodiments of the first aspect, in some embodiments, the device to be assigned includes at least one of the following: a user equipment; a service instance; a point of arrival (PoA).

[0030] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: determining a processing mode for the KB based on condition parameters, wherein the condition parameters include at least one of the following: currently available resources of the at least one processing device; future available resources of the at least one processing device; and a QoS threshold and / or QoE threshold for the device to be allocated.

[0031] In conjunction with some embodiments of the first aspect, in some embodiments, the processing method includes at least one of the following: centralized processing; distributed processing; and federated processing.

[0032] In conjunction with some embodiments of the first aspect, in some embodiments, determining the processing method for the KB based on condition parameters includes one of the following: if the current available resources and / or future available resources of at least one processing device are greater than a resource threshold, determining that the processing method includes centralized processing; if the current available resources and / or future available resources of at least one processing device are less than or equal to a resource threshold, determining that the processing method includes distributed processing; if the QoS threshold and / or QoE threshold are greater than a set threshold, determining that the processing method includes federated processing.

[0033] Secondly, embodiments of this disclosure provide a resource management apparatus, the module comprising: a processing module configured to determine that a knowledge base KB needs to be processed; a receiving module configured to acquire resource usage information of at least one candidate device and predict the future available resources of the candidate device based on the resource usage information; wherein the processing module is further configured to determine at least one processing device among the at least one candidate device based on the current available resources and future available resources of the at least one candidate device; and a sending module configured to allocate the KB to the at least one processing device for processing.

[0034] Thirdly, embodiments of this disclosure provide a communication device comprising: one or more processors; wherein the network device is configured to perform the resource management method described in any one of the first aspects and optional embodiments thereof.

[0035] Fourthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the resource management method described in any one of the first aspects and optional embodiments thereof.

[0036] Fifthly, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the resource management method described in any one of the first aspects and optional embodiments of the first aspect.

[0037] In a sixth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the resource management method described in any one of the optional embodiments of the first aspect.

[0038] It is understood that the aforementioned resource management device, communication equipment, communication system, storage medium, program product, and computer program are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0039] This disclosure provides resource management methods and apparatus, communication devices, and storage media. In some embodiments, the terms "resource management method" and "information processing method," "communication method," etc., can be used interchangeably; the terms "resource management apparatus" and "information processing apparatus," "communication apparatus," etc., can be used interchangeably; and the terms "information processing system," "communication system," etc., can be used interchangeably.

[0040] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0041] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0042] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0043] In the embodiments of this disclosure, unless otherwise stated, elements expressed in the singular, such as “a,” “an,” “the,” “the,” “the,” “the,” “the,” “the,” “this,” etc., may mean “one and only one,” or “one or more,” “at least one,” etc.

[0044] For example, when using articles such as "a", "an", and "the" in translation, the noun following the article can be understood as either a singular or a plural form.

[0045] In the embodiments disclosed herein, "multiple" refers to two or more.

[0046] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0047] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0048] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0049] The prefixes such as "first" and "second" in the embodiments of this disclosure are only for distinguishing different descriptive objects and do not constitute restrictions on the position, order, priority, number or content of the descriptive objects. For the description of the descriptive objects, please refer to the description in the claims or the context of the embodiments. The use of prefixes should not constitute unnecessary restrictions.

[0050] For example, if the descriptive object is "field," then the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is "level," then the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers; there can be one or more. For example, in "first device," the number of "devices" can be one or more. In addition, objects modified by different prefixes can be the same or different. For example, if the descriptive object is "device," then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the descriptive object is "information," then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0051] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0052] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0053] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0054] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0055] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0056] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0057] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0058] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0059] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0060] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0061] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0062] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0063] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0064] [Correction based on Rule 91, December 19, 2024] As shown in Figure 1A, the communication system 100 includes a processing device 101 and a network device 102, wherein the network device includes at least one of the following: a server, an access network device, and a core network device. The processing device may include at least one of the following: a terminal, an arrival point, a server, and a service instance.

[0065] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0066] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0067] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of the aforementioned one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), or a Next Generation Core (NGC).

[0068] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0069] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0070] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0071] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0072] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0073] In some embodiments, during semantic communication (SemCom), the sending end can use a semantic encoder to semantically encode the information, and then send the encoded information to the receiving end through a channel. The receiving end can use a semantic decoder to semantically decode the received information.

[0074] Figure 1B is a schematic diagram of a semantic communication scenario according to an embodiment of the present disclosure.

[0075] As shown in Figure 1B, semantic encoders and semantic decoders can encompass a variety of tasks.

[0076] For example, a semantic encoder may include buffering, synchronization of streams from different sources, splitting streams, sampling from different streams, and semantic extraction.

[0077] For example, a semantic decoder may include buffering, semantic construction, constructing streams, and synchronization of streams from different sources.

[0078] For example, a semantic encoder can be implemented on edge computing resources of a user device or system. A semantic decoder, on the other hand, can be implemented where semantics are needed (e.g., devices, instances, etc.). Users use the semantic encoder to compress data into semantic segments (or semantics), which are then transmitted to designated instances instead of the original batch of data. These instances, in turn, utilize the semantic decoder to reconstruct the expected output.

[0079] In some embodiments, a knowledge base (KB) can be introduced during semantic communication to ensure the accuracy of semantic understanding. The knowledge base can contain background knowledge, contextual knowledge, etc. Semantic communication can achieve a predefined shared view of the communication goal by using the knowledge base and sharing it a priori among the parties involved in the semantic communication.

[0080] For example, as shown in Figure 1B, the knowledge base can be applied to the semantic extraction task of the semantic encoder or the semantic construction task of the semantic decoder. This disclosure does not limit the specific application of the knowledge base.

[0081] In some embodiments, machine learning can be performed on the training sample set to obtain a model for semantic decoding as a semantic decoder, and a model for semantic encoding as a semantic encoder. During this process, a knowledge base can be used to assist in constructing the training sample set.

[0082] In addition to storing knowledge bases (KBs), the system may have other processing requirements for KBs, such as training and updating. Since the knowledge base contains a massive amount of information, processing it requires significant resources. Therefore, it is necessary to allocate system resources rationally to ensure that appropriate devices are available for processing KBs.

[0083] Figure 2 is an interactive schematic diagram illustrating a resource management method according to an embodiment of the present disclosure.

[0084] In some embodiments, the resource management method can be executed by a communication device, which may include a terminal or a network device. Taking a network device as an example, it may be a server. For instance, a network device may be a cloud network device, such as a cloud server.

[0085] As shown in Figure 2, the resource management method may include the following steps:

[0086] In step S201, the network device determines that KB needs to be processed.

[0087] In some embodiments, KB processing can be performed periodically, in which case it can be determined when the processing cycle arrives that KB processing is required.

[0088] In some embodiments, KB processing can be performed non-periodicly. For example, it can be determined that KB needs to be processed when a processing request for KB is received (e.g., the processing request can be issued by any device in the system, such as a user device). For example, it can be determined that KB needs to be processed when certain conditions are met (e.g., the system's resources change and the variable is greater than the change threshold; e.g., the system's available resources are large enough and greater than the available threshold).

[0089] It should be noted that the conditions under which a network device determines that KB needs to be processed include, but are not limited to, the situations shown in the above embodiments, and may also include other situations, which are not limited in this disclosure.

[0090] In some embodiments, the system may include various devices, such as user equipment, service devices, service instances (e.g., instances on a service device), network edge devices, etc., wherein a network edge device may also be referred to as a Point of Arrival (PoA). The system resources may include the resources of at least one device in the system.

[0091] In some embodiments, the network device acquires resource usage information of at least one candidate device. For example, the candidate device can be any type of device in the system. The network device can collect resource usage information of the candidate devices, which may include the currently available resources of the candidate devices. In addition, the network device can also predict the future available resources of the candidate devices based on the resource usage information.

[0092] For example, network devices may have a pre-set resource prediction model. This model can be determined based on machine learning, deep learning, or other methods. It can predict the future available resources of the device based on the device's past resource usage information (e.g., available resources at a future point in time or available resources over a future period of time).

[0093] In some embodiments, the network device determines at least one processing device from the at least one candidate device based on the current available resources and future available resources of the at least one candidate device.

[0094] In step S202, the network device allocates the KB to the processing device for processing.

[0095] In some embodiments, since KB data is very large, KB processing may not be completed immediately, and there can be multiple ways to process KB. Some processing methods do not process KB immediately. Therefore, KB processing not only occupies the device's current available resources but may also occupy the device's future available resources. Therefore, when selecting a processing device for processing KB from candidate devices, it is necessary to consider not only the candidate device's current available resources but also its future available resources.

[0096] In some embodiments, processing a KB may include at least one of the following: storing a KB, training a KB, updating a KB, or transferring a KB.

[0097] In some embodiments, the resources may include at least one of the following: storage resources (e.g., for storing KB), processing resources (e.g., for training KB, updating KB), and transmission resources (e.g., for transmitting KB).

[0098] According to embodiments of this disclosure, when KB needs to be processed, a processing device for processing KB can be selected from the candidate devices based on the current and future available resources of the candidate devices, and then the KB can be allocated to the processing device for processing. Since the selection of a processing device from the candidate devices takes into account not only the current available resources of the candidate devices but also the future available resources of the candidate devices, it is beneficial to select a processing device whose resources are well-suited for processing KB.

[0099] In some embodiments, the resource management method further includes: obtaining the Quality of Service (QoS) threshold and / or Quality of Experience (QoE) threshold of the devices to be allocated.

[0100] In some embodiments, the resource management method further includes: triggering the at least one processing device to send the processed KB to the device to be allocated based on condition parameters.

[0101] In some embodiments, the condition parameters include at least one of the following:

[0102] The current available resources of the at least one processing device;

[0103] Future available resources for the at least one processing device;

[0104] The QoS threshold and / or QoE threshold of the device to be assigned.

[0105] In some embodiments, after the processing device completes the processing of the KB (e.g., storage, training, updating, etc.), since the device that needs to use the KB is the device to be allocated, the processing device can send the processed KB to the device to be allocated.

[0106] In some embodiments, the device to be assigned includes at least one of the following: a user equipment; a service instance; and a point of arrival (PoA). For example, the device to be assigned may use a KB for semantic communication.

[0107] In some embodiments, the process of a processing device sending a processed KB to a device to be allocated requires the use of resources (e.g., transmission resources). Therefore, when it is necessary for at least one processing device to send a processed KB to a device to be allocated, the current available resources of at least one processing device and the future available resources of the current available resources of at least one processing device can be considered.

[0108] Furthermore, different devices awaiting allocation may have different requirements for QoS and QoE. For example, this may be reflected in different QoS thresholds and QoE thresholds. A higher QoS threshold indicates a higher requirement for QoS, and a higher QoE threshold indicates a higher requirement for QoE. For devices awaiting allocation with relatively high QoS and / or QoE requirements, the allowable latency for KB transmission is generally relatively low, meaning they need to receive the processed KB relatively quickly.

[0109] Therefore, when it is necessary for at least one processing device to send the processed KB to the device to be allocated, the QoS and / or QoE requirements of the device to be allocated can also be considered. For example, the QoS requirement is characterized by a QoS threshold, and the QoE requirement is characterized by a QoE threshold.

[0110] For example, triggering at least one processing device to send the processed KB to the device to be allocated based on condition parameters may include at least one of the following:

[0111] For devices to be allocated with relatively high QoS and / or QoE requirements, processing devices with relatively more currently available resources and / or future available resources can be identified to transmit the processed KB.

[0112] For devices with relatively low QoS and / or QoE requirements, processing devices with relatively limited current and / or future available resources can be selected to transmit the processed KB.

[0113] Therefore, it is beneficial to ensure that when different processing devices transmit the processed KB to different devices to be allocated, they can meet the QoS and / or QoE requirements of the different devices to be allocated as much as possible.

[0114] In some embodiments, before triggering the at least one processing device to send the processed KB to the device to be allocated, the method further includes:

[0115] Determine whether the processed KB can be sent to the device to be allocated based on the condition parameters;

[0116] If the processed KB cannot be sent to the device to be allocated, adjust the path used to send the processed KB.

[0117] In some embodiments, in order to send the processed KB to the device to be assigned via the processing device, a path (e.g., a communication connection) between at least one processing device and at least one device to be assigned can be constructed. For example, the path can be determined after the processing device is determined among the candidate devices and before the processed KB is sent to the device to be assigned.

[0118] However, as can be seen from the previous embodiments, since different devices to be allocated may have different requirements for QoS and / or QoE, when sending KB in the application path, it is necessary to consider the current available resources, future available resources, QoS threshold, QoE threshold and other conditional parameters of the processing device so that the KB sending process can meet the QoS and / or QoE requirements of the devices to be allocated.

[0119] Therefore, in this embodiment, before triggering the at least one processing device to send the processed KB to the device to be allocated, the network device can first determine, based on condition parameters, whether the processed KB can be sent to the device to be allocated based on the determined path. For example, if sending the processed KB to the device to be allocated based on the determined path cannot meet the QoS and / or QoE requirements of the device to be allocated, then it can be determined that the processed KB cannot be sent to the device to be allocated; conversely, if sending the processed KB to the device to be allocated based on the determined path can meet the QoS and / or QoE requirements of the device to be allocated, then it can be determined that the processed KB can be sent to the device to be allocated.

[0120] Furthermore, if the determined path cannot send the processed KB to the device to be allocated, the path can be adjusted so that the processed KB can be successfully sent to the device to be allocated through the adjusted path, ensuring that the KB sending process can meet the QoS and / or QoE requirements of the device to be allocated.

[0121] In some embodiments, before triggering the at least one processing device to send the processed KB to the device to be allocated, the method further includes:

[0122] Determine whether the processed KB can be sent to the device to be allocated based on the condition parameters;

[0123] If the processed KB cannot be sent to the device to be allocated, the resources are adjusted to be allocated to at least one of the processing devices.

[0124] In some embodiments, in order to send the processed KB to the device to be assigned via the processing device, a path (e.g., a communication connection) between at least one processing device and at least one device to be assigned can be constructed. For example, the path can be determined after the processing device is determined among the candidate devices and before the processed KB is sent to the device to be assigned.

[0125] However, as can be seen from the previous embodiments, since different devices to be allocated may have different requirements for QoS and / or QoE, when sending KB in the application path, it is necessary to consider the current available resources, future available resources, QoS threshold, QoE threshold and other conditional parameters of the processing device so that the KB sending process can meet the QoS and / or QoE requirements of the devices to be allocated.

[0126] Therefore, in this embodiment, before triggering the at least one processing device to send the processed KB to the device to be allocated, the network device can first determine, based on condition parameters, whether the processed KB can be sent to the device to be allocated based on the determined path. For example, if sending the processed KB to the device to be allocated based on the determined path cannot meet the QoS and / or QoE requirements of the device to be allocated, then it can be determined that the processed KB cannot be sent to the device to be allocated; conversely, if sending the processed KB to the device to be allocated based on the determined path can meet the QoS and / or QoE requirements of the device to be allocated, then it can be determined that the processed KB can be sent to the device to be allocated.

[0127] Furthermore, if the determined path cannot send the processed KB to the device to be allocated, the resources allocated to at least one processing device can be adjusted so that the processed KB can be sent to the device to be allocated through the adjusted resource location, ensuring that the KB sending process can meet the QoS and / or QoE requirements of the device to be allocated.

[0128] In some embodiments, if the determined path cannot send the processed KB to the device to be assigned, the QoS threshold and / or QoE threshold of the device to be assigned may also be adjusted.

[0129] In some embodiments, determining whether the processed KB can be sent to the device to be allocated based on the determined path, according to condition parameters, can be done in one of the following ways:

[0130] Based on the current and / or future available resources of the processing device, the processed KB is sent to the device to be allocated, and it is determined whether the QoS and / or QoE requirements of the device to be allocated are met.

[0131] When sending the processed KB to the device to be allocated using resources that meet the QoS and / or QoE requirements of the device to be allocated, does the resource exceed the current and / or future available resources of the processing device?

[0132] For example, if sending the processed KB to the device to be allocated based on the current and / or future available resources of the processing device does not meet the QoS and / or QoE requirements of the device to be allocated, it can be determined, based on the condition parameters, that the processed KB cannot be sent to the device to be allocated based on the determined path; conversely, if sending the processed KB to the device to be allocated based on the current and / or future available resources of the processing device meets the QoS and / or QoE requirements of the device to be allocated, it can be determined, based on the condition parameters, that the processed KB can be sent to the device to be allocated based on the determined path.

[0133] For example, when sending the processed KB to the device to be allocated using resources that meet the QoS and / or QoE requirements of the device to be allocated, if the resources exceed the current and / or future available resources of the processing device, it can be determined, based on the condition parameters, that the processed KB cannot be sent to the device to be allocated based on the determined path; conversely, when sending the processed KB to the device to be allocated using resources that meet the QoS and / or QoE requirements of the device to be allocated, if the resources do not exceed the current and / or future available resources of the processing device, it can be determined, based on the condition parameters, that the processed KB can be sent to the device to be allocated based on the determined path.

[0134] In some embodiments, the processing method for the KB is determined based on condition parameters, wherein the condition parameters include at least one of the following:

[0135] The current available resources of the at least one processing device;

[0136] Future available resources for the at least one processing device;

[0137] The QoS threshold and / or QoE threshold of the device to be assigned.

[0138] In some embodiments, the processing method includes at least one of the following: centralized processing; distributed processing; and consortium processing.

[0139] In some embodiments, determining the processing method for the KB based on condition parameters includes one of the following:

[0140] If the current available resources and / or future available resources of at least one processing device are greater than a resource threshold, it is determined that the processing method includes centralized processing;

[0141] If the current available resources and / or future available resources of the at least one processing device are less than or equal to a resource threshold, it is determined that the processing method includes distributed processing;

[0142] If the QoS threshold and / or QoE threshold are greater than a set threshold, the processing method is determined to include alliance processing.

[0143] In some embodiments, KB processing can be performed using centralized processing, distributed processing, or federated processing.

[0144] For example, taking training as an example, training methods can include centralized training, distributed training, and federated training. These different training methods may differ in terms of resource requirements, QoS and / or QoE requirements of the devices to be assigned, etc.

[0145] For example, centralized training requires relatively more resources. Therefore, centralized training can be used to train KB when the current available resources and / or future available resources of the at least one processing device are relatively abundant (e.g., greater than the resource threshold).

[0146] For example, distributed training requires relatively more resources. Therefore, distributed training can be used to train KB when the current available resources and / or future available resources of the at least one processing device are relatively few (e.g., less than or equal to the resource threshold).

[0147] For example, federated training is beneficial for meeting the QoS and / or QoE requirements of the devices to be assigned. Therefore, when the QoS and / or QoE requirements of the devices to be assigned are relatively high (e.g., the QoS threshold and / or QoE threshold are greater than the set threshold), federated training is determined to be used to train the KB.

[0148] Figure 3A is a schematic diagram illustrating a centralized training method according to an embodiment of the present disclosure.

[0149] As shown in Figure 3A, Semantic Traffic refers to semantic transmission, Training Tasks refers to training tasks, Training Data refers to training data, Updated KBs refers to updating the knowledge base, Service Instances refers to service instances, and Edge Computing Nodes refers to edge computing nodes.

[0150] The centralized training strategy treats each knowledge base training task as an atomic operation and executes them on compute nodes at the network edge or core data center as shown in Figure 3A. This training approach simplifies the process by avoiding the complexity of task decomposition and resource optimization, but may introduce additional computational costs and scheduling latency at the end-to-end layer (described in subsequent embodiments).

[0151] It should be noted that this training method requires significant data transfer from the user (e.g., user device) to edge or core computing nodes, which reduces its feasibility in future scenarios where limited network resources must be allocated to actual traffic. Furthermore, due to the atomic nature of the training task placement, this method lacks flexibility to adapt to future dynamic patterns and may lead to inefficient resource utilization. Moreover, transferring user data to edge or core computing nodes may increase the risk of privacy issues.

[0152] Figure 3B is a schematic diagram illustrating a distributed training according to an embodiment of the present disclosure.

[0153] As shown in Figure 3B, Inter-Layer DNN Data refers to inter-layer DNN data.

[0154] Considering the enhanced capabilities of future user devices, some training tasks can be offloaded to edge or core computing nodes based on distributed training. In this training approach, the end-to-end layer decomposes the training task for each knowledge base into partitions and determines which partitions to allocate to computing nodes in the user devices and infrastructure.

[0155] While dynamically adjusting partitions and resource allocation presents a complex optimization challenge, more efficient resource utilization can be achieved by considering both real-time and predicted resource states. Furthermore, distributed training can decompose the task at the Deep Neural Network (DNN) level, where a single or group of DNN layers forms a partition (also known as split learning). Executing these partitions in a distributed manner across user devices and compute nodes enables the execution of the entire DNN. The computationally intensive or network-intensive classification of partitions is then determined based on activity and predicted resource states, guiding their placement on user devices or compute nodes.

[0156] Figure 3C is a schematic diagram illustrating a federated training according to an embodiment of the present disclosure.

[0157] As shown in Figure 3C, to significantly reduce privacy and security risks and minimize data transfer between users and compute nodes during knowledge base updates, training tasks can be performed on user devices using local data. Since data from a single device may not adequately represent global consistency, the resulting trained model (e.g., updated DNN weights) can be transferred to edge and core compute nodes for hierarchical aggregation (e.g., averaging DNN weights). Guided by the real-time and predicted states of resources and the characteristics of services, including their QoE and / or QoE metrics (e.g., thresholds), the KB deployment manager intermittently replaces the local model with the global model. This conversion ensures that the training process can continue on the updated model; this approach can be called federated training.

[0158] The technical solutions of this disclosure will be illustrated by several further embodiments below.

[0159] Figure 4 is a schematic diagram illustrating an application scenario of a resource management method according to an embodiment of the present disclosure.

[0160] In some embodiments, KB can be applied to semantic communication, which can be applied to various scenarios, such as data reconstruction, information classification, holographic conferencing, etc.

[0161] As shown in Figure 4, taking a holographic conference scenario as an example, in a real holographic conference scenario, users can participate in holographic presentation services in a virtual meeting room. This service integrates functions such as rendering, motion tracking, stereoscopic 3D display, and audio spatialization. Among them, TSN (Time Sensitive Networking), IMAC (Intelligent MAC), FE (Far Edge), NE (Near Edge), and OTN (Optical Transport Network) are used.

[0162] To achieve this experience, software instances of these functionalities can be loaded onto available compute nodes. The user's video, audio, and motion data are then transmitted to these instances via their specified network paths. These instances collaborate in a predetermined order specified in the service's functional chain mapping. The resulting presentation content is then transmitted back to the user's device, such as headphones, mobile phone, tablet, PC, TV, or headset. Throughout this process, factors such as service QoS and / or QoE requirements and resource availability must be adhered to.

[0163] For example, in mobile networks (or cellular networks), the above scenario could fall under the category of 6G services, which are supported by an integrated cloud network infrastructure that incorporates technologies such as deterministic networking, time-sensitive networking, and smart media access control.

[0164] In holographic conferencing scenarios, semantic encoders can extract spatial, visual, and auditory semantics (such as location, gestures, and ambient sounds), while semantic decoders capture interactions between users, the environment, and virtual elements for realistic rendering and presentation of the holographic meeting. Employing semantics not only reduces resource consumption and improves efficiency (because it eliminates the need to transmit raw batch data, requiring only the semantics extracted during encoding, resulting in a relatively small data footprint), but also optimizes resource orchestration. By understanding the semantics of user requests, prioritization can be applied, giving the highest priority to critical semantics to ensure seamless service responses, and similar requests can be directed to shared computing nodes and network paths.

[0165] In the system implementing the scenario, service providers (e.g., users facilitating holographic conferencing scenarios) register services, including functional instances (e.g., rendering, motion tracking, etc.). Registered services include semantic communication, and the knowledge base applied to this semantic communication (the KB to be processed can be one KB or multiple KBs) also needs to be enabled, and its own lifelong learning tasks (e.g., training tasks) need to be introduced to ensure the KBs remain updated.

[0166] Users initiate requests to access registered services within the system, establishing end-to-end connections. These connections manage the semantic transmission to the instance of the requested service. The processed data (e.g., a real-time rendered holographic conference scene) is then transmitted back to the user.

[0167] Resource allocation for service instances and user requests is performed through a multi-layered, Computing Network Convergence (CNC) authorized resource orchestration framework (CNCO). This framework implements decisions at network edge devices (e.g., PoAs), which serve as entry points for requests into the system. CNCO uses KBs associated with each service within the PoAs to understand the semantics of the transport and integrates this into the decision-making process. This ensures that users, service instances, and PoAs have access to the latest KBs, aiming to minimize the impact of knowledge management and orchestration activities on actual service provisioning.

[0168] Figure 5 is a schematic diagram illustrating a resource management method and a computer network convergence application according to an embodiment of the present disclosure.

[0169] Resource management methods can be implemented based on the Knowledge Base Management and Orchestration (KB-MANO) framework. During implementation, the KB-MANO framework can interact with CNCO.

[0170] The KB-MANO framework addresses the knowledge refinement problem by integrating lifelong learning-supported knowledge base training strategies and dynamically switching between them based on available resource information received from the CNCO. Furthermore, guided by monitoring information provided by the CNCO, it manages the organization of knowledge base distribution among users, instances, and PoAs through proactive measures initiated by service levels.

[0171] As shown in Figure 5, CNCO can include three modules: an end-to-end orchestrator (E2E Orchestrator), a compute orchestrator (integrated with a network orchestrator), and compute nodes (integrated with network resources).

[0172] In some embodiments, the end-to-end orchestrator can enable advanced joint coordination of compute and network resources, involving E2E system monitoring and proactive service management, while providing orchestration guidelines to the domain orchestrator for E2E optimization.

[0173] The computation orchestrator can perform domain-level resource monitoring and allocation, and follow the instructions issued by the E2E orchestrator.

[0174] Compute nodes can perform resource-level monitoring and configuration, and follow the instructions of their domain orchestrator.

[0175] In some embodiments, the KB-MANO framework may include three layers: an end-to-end (E2E) layer, a network domain layer (integrating the compute domain layer), and a network resource layer (integrating the compute resource layer). The following provides illustrative descriptions of these three layers within the KB-MANO framework.

[0176] In some embodiments, the end-to-end (E2E) layer may include four modules: an end-to-end memory bank module, an end-to-end workload analyzer module, a knowledge base refinement manager module, and a knowledge base deployment manager module. The end-to-end layer can assume responsibility for high-level decisions related to knowledge refinement and scheduling.

[0177] The end-to-end memory bank module collects computation and network usage data from CNCO's E2E orchestrator and stores it in a memory bank over time. Additionally, it receives performance metrics of all user activity services from CNCO. This information can be collected anonymously to maintain user privacy.

[0178] The end-to-end workload analysis module can accumulate collected data over past time periods and predict future usage patterns across compute and network domains based on this data. It can also predict QoS and / or QoE trends for each active service (e.g., on user devices, or within instances). The results are then stored in a memory. For example, based on machine learning (ML) techniques, scalable long short-term memory (xLSTM) and transformer models are used to analyze the collected historical and temporal data, thereby enabling predictions of future states.

[0179] The knowledge base refinement management module relies on current and anticipated resource status to allocate resources for KB updates. This primarily involves two steps: selecting a knowledge base training method, such as assessing the suitability of distributed versus centralized processing based on current and future resource availability; and then placing the knowledge base training tasks on computing resources and establishing a data transmission network path from the user (e.g., the device to be allocated) to the designated computing node (e.g., the processing device). Since these training tasks are implemented and executed by the service provider (e.g., the entity responsible for holographic conference setup), the data remains in their custody, thus mitigating privacy concerns.

[0180] The knowledge base deployment association module can distribute the latest KB version to users, service instances, and PoAs. The distribution process can depend on the QoS and / or QoE thresholds of the active services, as well as current and anticipated network resources. High sensitivity to subtle quality changes can improve network resource utilization for KB distribution, thus ensuring continuous updates across the entire system. Conversely, using more lenient thresholds reduces network consumption but leads to lower semantic transcoding accuracy.

[0181] In some embodiments, the network domain layer may include three modules: a domain memory bank module, a domain workload analyzer module, and a domain knowledge base manager module. The network domain layer can supervise the allocation of resources within the domain to optimize and organize knowledge.

[0182] The domain memory bank module, located in the network domain, can receive historical data on network graph availability from the CNCO network orchestrator and store it in a memory bank, as well as resource usage predictions from the domain-level workload analyzer.

[0183] The domain workload analysis module can predict the future use of a domain.

[0184] The domain knowledge base management module can determine the network path for data transmission (e.g., between users and assigned compute nodes) and KB distribution based on the selected KB training method, current and predicted network usage, and KB distribution. If no feasible network path exists for transmitting user data or distributing the latest KBs, the module prompts the end-to-end layer to re-evaluate and optimize its chosen strategy to suit current network conditions. Path feasibility is affected when the necessary bandwidth exceeds a threshold set to protect actual network traffic. Excessive latency in bandwidth-feasible paths prevents KBs from being updated in a timely manner within predefined time limits specified by the QoS and / or QoE requirements of their associated services. If this situation is identified, compute capacity will be readjusted for assigned tasks.

[0185] In some embodiments, the network resource layer may include three modules: a resource memory bank module, a resource workload analyzer module, and a resource KB manager module. The network resource layer can manage resource allocation to enable knowledge extraction and arrangement between network devices and computing nodes.

[0186] Specifically, the resource memory bank module can collect availability information (e.g., available resources) from various resource elements, predict their future states, and store this data in the resource memory bank. The historical window size (Tr) of this layer is kept to a minimum to reduce resource consumption during the prediction process and capture subtle fluctuations in resource levels.

[0187] The resource workload analysis module can predict the future use of resources.

[0188] The knowledge base management module can dynamically adjust KB refinement and / or schedule allocated capacity using the aforementioned availability information and its future state. On network devices, this adjustment includes (re)allocating bandwidth to transfer user data from users to training tasks, or prioritizing traffic allocation to distribute the latest KBs from training tasks to users, service instances, or PoAs. On compute nodes, adjustment requires (re)scaling the compute, memory, and storage capacity allocated to training tasks, or migrating them to nodes accessible via allocated network paths. If this is not feasible, the KB refinement resource manager notifies the domain layer to reallocate resources at the domain level (e.g., adjust paths).

[0189] The communication method involved in the embodiments of this disclosure may include at least one of steps S201 to S202. For example, step S201 may be implemented as a standalone embodiment, step S202 may be implemented as a standalone embodiment, and step S201+S202 may be implemented as a standalone embodiment, but is not limited thereto.

[0190] In some embodiments, steps S201 and S202 may be performed in an alternate order or simultaneously.

[0191] In some embodiments, step S201 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0192] In some embodiments, step S202 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0193] In some embodiments, other optional implementations described before or after the specification corresponding to FIG2 may be referred to.

[0194] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0195] In some embodiments, “get,” “obtain,” “get,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0196] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transmit,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0197] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0198] Corresponding to the aforementioned embodiments of the resource management method, this disclosure also provides embodiments of the resource management device.

[0199] Figure 6 is a schematic block diagram illustrating a resource management device according to an embodiment of the present disclosure. For example, the resource management device can be applied to a network device. As shown in Figure 6, the resource management device includes: a processing module 601, a receiving module 602, and a sending module 603.

[0200] In some embodiments, the processing module is configured to determine that the knowledge base KB needs to be processed; the receiving module is configured to obtain resource usage information of at least one candidate device; wherein, the processing module is further configured to predict the future available resources of the candidate device based on the resource usage information, and determine at least one processing device among the at least one candidate device based on the current available resources and future available resources of the at least one candidate device; the sending module is configured to allocate the KB to the at least one processing device for processing.

[0201] In some embodiments, the receiving module is further configured to acquire the Quality of Service (QoS) threshold and / or Quality of Experience (QoE) threshold of the device to be allocated; the sending module is further configured to trigger the at least one processing device to send the processed KB to the device to be allocated based on condition parameters, wherein the condition parameters include at least one of the following: the current available resources of the at least one processing device; the future available resources of the at least one processing device; and the QoS threshold and / or QoE threshold of the device to be allocated.

[0202] In some embodiments, the processing module is further configured to determine whether the processed KB can be sent to the device to be allocated based on the condition parameters; and if the processed KB cannot be sent to the device to be allocated, to adjust the path used to send the processed KB.

[0203] In some embodiments, the processing module is further configured to determine whether the processed KB can be sent to the device to be allocated based on the condition parameters; if the processed KB cannot be sent to the device to be allocated, the resources are adjusted to be allocated to at least one of the processing devices.

[0204] In some embodiments, the device to be assigned includes at least one of the following: a user equipment; a service instance; a point of arrival (PoA).

[0205] In some embodiments, the processing module is further configured to determine the processing method for the KB based on condition parameters, wherein the condition parameters include at least one of the following: the current available resources of the at least one processing device; the future available resources of the at least one processing device; and the QoS threshold and / or QoE threshold of the device to be allocated.

[0206] In some embodiments, the processing method includes at least one of the following: centralized processing; distributed processing; and consortium processing.

[0207] In some embodiments, the processing module is configured to: determine that the processing method includes centralized processing when the current available resources and / or future available resources of at least one processing device are greater than a resource threshold; determine that the processing method includes distributed processing when the current available resources and / or future available resources of at least one processing device are less than or equal to a resource threshold; and determine that the processing method includes federated processing when the QoS threshold and / or QoE threshold are greater than a set threshold.

[0208] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0209] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0210] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0211] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0212] Figure 7A is a schematic diagram of the structure of the communication device 7100 proposed in an embodiment of this disclosure. The communication device 7100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 7100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0213] As shown in Figure 7A, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 7100 can be used to execute any of the above methods. Optionally, one or more processors 7101 can be used to invoke instructions to cause the communication device 7100 to execute any of the above methods.

[0214] In some embodiments, the communication device 7100 further includes one or more transceivers 7102. When the communication device 7100 includes one or more transceivers 7102, the transceiver 7102 performs at least one of the communication steps (e.g., steps S201, S202, but not limited thereto) in the above method, such as sending and / or receiving, while the processor 7101 performs at least one of other steps (e.g., steps S201, S202, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, sending unit, transmitter, sending circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0215] In some embodiments, the communication device 7100 further includes one or more memories 7103 for storing data. Optionally, all or part of the memories 7103 may be located outside the communication device 7100. In optional embodiments, the communication device 7100 may include one or more interface circuits 7104. Optionally, the interface circuits 7104 are connected to the memories 7102 and can be used to receive data from the memories 7102 or other devices, and to send data to the memories 7102 or other devices. For example, the interface circuits 7104 can read data stored in the memories 7102 and send the data to the processor 7101.

[0216] The communication device 7100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 7100 described in this disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0217] Figure 7B is a schematic diagram of the structure of the chip 7200 according to an embodiment of this disclosure. For cases where the communication device 7100 can be a chip or a chip system, the schematic diagram of the chip 7200 shown in Figure 7B can be referred to, but is not limited thereto.

[0218] Chip 7200 includes one or more processors 7201. Chip 7200 is used to perform any of the above methods.

[0219] In some embodiments, chip 7200 further includes one or more interface circuits 7202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 7200 further includes one or more memories 7203 for storing data. Optionally, all or part of the memories 7203 may be located outside chip 7200. Optionally, interface circuit 7202 is connected to memory 7203, and interface circuit 7202 can be used to receive data from memory 7203 or other devices, and interface circuit 7202 can be used to send data to memory 7203 or other devices. For example, interface circuit 7202 can read data stored in memory 7203 and send the data to processor 7201.

[0220] In some embodiments, the interface circuit 7202 performs at least one of the communication steps (e.g., steps S201, S202, but not limited thereto) in the above-described method, such as sending and / or receiving. For example, the interface circuit 7202 performing the communication steps (e.g., steps S201, S202, but not limited thereto) refers to the interface circuit 7202 performing data interaction between the processor 7201, the chip 7200, the memory 7203, or the transceiver device. In some embodiments, the processor 7201 performs at least one of other steps (e.g., steps S201, S202, but not limited thereto).

[0221] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0222] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 7100, cause the communication device 7100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0223] This disclosure also provides a program product that, when executed by the communication device 7100, causes the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0224] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

Claims

1. A resource management method characterized by, The method includes: It has been determined that the knowledge base KB needs to be processed; Obtain resource usage information for at least one candidate device, and predict the future available resources of the candidate device based on the resource usage information; Based on the current and future available resources of the at least one candidate device, at least one processing device is determined from the at least one candidate device; The KB is assigned to the at least one processing device for processing.

2. The method of claim 1, wherein, The method further includes: Obtain the Quality of Service (QoS) threshold and / or Experience Quality of Evidence (QoE) threshold for the devices to be assigned; Based on conditional parameters, at least one processing device is triggered to send the processed KB to the device to be allocated, wherein the conditional parameters include at least one of the following: The current available resources of the at least one processing device; Future available resources for the at least one processing device; The QoS threshold and / or QoE threshold of the device to be assigned.

3. The method of claim 2, wherein, Before triggering the at least one processing device to send the processed KB to the device to be allocated, the method further includes: Determine whether the processed KB can be sent to the device to be allocated based on the condition parameters; If the processed KB cannot be sent to the device to be allocated, adjust the path used to send the processed KB.

4. The method according to claim 2 or 3, characterized in that, Before triggering the at least one processing device to send the processed KB to the device to be allocated, the method further includes: Determine whether the processed KB can be sent to the device to be allocated based on the condition parameters; If the processed KB cannot be sent to the device to be allocated, the resources are adjusted to be allocated to at least one of the processing devices.

5. The method according to any one of claims 2 to 4, characterized in that, The devices to be assigned include at least one of the following: User equipment; Service instances; Arrival point PoA.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The processing method for the KB is determined based on condition parameters, wherein the condition parameters include at least one of the following: The current available resources of the at least one processing device; Future available resources for the at least one processing device; The QoS threshold and / or QoE threshold of the device to be assigned.

7. The method of claim 6, wherein, The processing method includes at least one of the following: Centralized processing; Distributed processing; Alliance-style processing.

8. The method of claim 7, wherein, The method for processing the KB based on condition parameters includes one of the following: If the current available resources and / or future available resources of at least one processing device are greater than a resource threshold, it is determined that the processing method includes centralized processing; If the current available resources and / or future available resources of the at least one processing device are less than or equal to a resource threshold, it is determined that the processing method includes distributed processing; If the QoS threshold and / or QoE threshold are greater than a set threshold, the processing method is determined to include alliance processing.

9. A resource management apparatus characterized by comprising: The device includes: The processing module is configured to determine when the knowledge base KB needs to be processed; The receiving module is configured to acquire resource usage information of at least one candidate device; wherein the processing module is further configured to predict the future available resources of the candidate device based on the resource usage information, and determine at least one processing device among the at least one candidate device based on the current available resources and future available resources of the at least one candidate device. The sending module is configured to allocate the KB to the at least one processing device for processing.

10. A communication device, characterized by include: One or more processors; The communication device is used to execute the resource management method according to any one of claims 1 to 8.

11. A storage medium, the storage medium storing instructions, wherein, When the instruction is executed on the communication device, the communication device performs the resource management method according to any one of claims 1 to 8.

12. A program product, characterized by When the above-mentioned program product is executed by a communication device, the communication device performs the resource management method according to any one of claims 1 to 8.

Images