Communication method, terminal, network equipment, communication device and storage medium

Abstract

The invention relates to a communication method, a terminal, network equipment, a communication device and a storage medium. The communication method comprises the following steps: a terminal sends a first message to a network device, and / or the terminal receives a second message sent by the network device; wherein the first message and / or the second message are / is related to updating of artificial intelligence AI model parameters of the terminal. According to the invention, parameter updating of the terminal AI model is realized.

Description

Communication method, terminal, network device, communication apparatus, and storage medium TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular to a communication method, a terminal, a network device, a communication apparatus, and a storage medium. BACKGROUND

[0002] In recent years, Artificial Intelligence (AI) technology has made continuous breakthroughs in many fields. Terminals have AI computing power and can process AI-related tasks. AI computing power can also be referred to as AI processing capability.

[0003] Regarding the deployment of an AI model, one way is for a network device to transmit a trained AI model to a terminal.

[0004] SUMMARY

[0005] For the parameters of an AI model, how to implement updates is a problem that needs to be solved.

[0006] Embodiments of the present disclosure propose a communication method, a terminal, a network device, a communication apparatus, and a storage medium.

[0007] According to a first aspect of embodiments of the present disclosure, a communication method is proposed, the method comprising: a terminal sending a first message to a network device, and / or the terminal receiving a second message sent by the network device; wherein the first message and / or the second message are related to the update of an Artificial Intelligence (AI) model parameter of the terminal.

[0008] According to a second aspect of embodiments of the present disclosure, a communication method is proposed, the method comprising: a network device receiving a first message sent by a terminal, and / or the network device sending a second message to the terminal; wherein the first message and / or the second message are related to the update of an Artificial Intelligence (AI) model parameter of the terminal.

[0009] According to a third aspect of embodiments of the present disclosure, a communication method is proposed, the method comprising: a terminal sending a first message to a network device, and / or the terminal receiving a second message sent by the network device; wherein the first message and / or the second message are related to the update of an Artificial Intelligence (AI) model parameter of the terminal; the network device receiving the first message, and / or the network device sending the second message.

[0010] According to a fourth aspect of embodiments of the present disclosure, a terminal is proposed, comprising: a transceiver module configured to send a first message to a network device, and / or receive a second message sent by the network device; wherein the first message and / or the second message are related to the update of an Artificial Intelligence (AI) model parameter of the terminal.

[0011] According to a fifth aspect of the embodiments of the present disclosure, a network device is provided, comprising: a transceiver, configured to receive a first message sent by a terminal and / or send a second message to the terminal; wherein the first message and / or the second message is related to updating of an artificial intelligence (AI) model parameter of the terminal.

[0012] According to a sixth aspect of the embodiments of the present disclosure, a communication apparatus is provided, comprising: one or more processors; wherein the terminal is configured to perform the communication method of the first aspect and any one of the first aspect.

[0013] According to a seventh aspect of the embodiments of the present disclosure, a communication apparatus is provided, comprising: one or more processors; wherein the network device is configured to perform the communication method of the second aspect and any one of the second aspect.

[0014] According to an eighth aspect of the embodiments of the present disclosure, a communication system is provided, comprising a terminal and a network device, wherein the terminal is configured to implement the communication method of the first aspect and any one of the first aspect, and the network device is configured to implement the communication method of the second aspect and any one of the second aspect.

[0015] According to a ninth aspect of the embodiments of the present disclosure, a storage medium is provided, which stores instructions, when the instructions are executed on a communication device, causing the communication device to perform the communication method of the first aspect and any one of the first aspect or the second aspect and any one of the second aspect.

[0016] According to a tenth aspect of the embodiments of the present disclosure, a program product is provided, comprising: a computer program, when executed by a communication device, causing the communication device to perform the communication method of the first aspect and any one of the first aspect or the second aspect and any one of the second aspect.

[0017] The present disclosure sends a first message to a network device by a terminal, or receives a second message sent by a network device by the terminal, wherein the first message and / or the second message is a message related to updating of an AI model parameter. Thus, the parameter updating of the terminal AI model is realized. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following describes the drawings required for the embodiments, and the following drawings are only some embodiments of the present disclosure, and do not specifically limit the protection scope of the present disclosure.

[0019] FIG. 1 is a schematic diagram of a communication system architecture according to an embodiment of the present disclosure.

[0020] FIG. 2a is a schematic diagram of a communication method according to an embodiment of the present disclosure.

[0021] FIG. 2b is an interaction diagram of a communication method according to an embodiment of the present disclosure.

[0022] FIG. 3a is a flowchart of a communication method according to an embodiment of the present disclosure.

[0023] FIG. 3b is a flowchart of a communication method according to an embodiment of the present disclosure.

[0024] FIG. 4a is a flowchart of a communication method according to an embodiment of the present disclosure.

[0025] FIG. 4b is a flowchart of a communication method according to an embodiment of the present disclosure.

[0026] FIG. 5 is an interaction diagram of a communication method according to an embodiment of the present disclosure.

[0027] FIG. 6a is a structural diagram of a terminal according to an embodiment of the present disclosure.

[0028] FIG. 6b is a structural diagram of a network device according to an embodiment of the present disclosure.

[0029] FIG. 7a is a structural diagram of a communication device according to an embodiment of the present disclosure.

[0030] FIG. 7b is a structural diagram of a chip according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The present disclosure provides a communication method, a terminal, a network device, a communication apparatus, and a storage medium.

[0032] In a first aspect, the present disclosure provides a communication method, including: a terminal sending a first message to a network device, and / or the terminal receiving a second message sent by the network device; wherein the first message and / or the second message is related to updating of an artificial intelligence (AI) model parameter of the terminal.

[0033] In some optional embodiments of the first aspect, the terminal sending the first message to the network device includes: the terminal determining that a first preset condition is met, and sending the first message to the network device.

[0034] In some optional embodiments of the first aspect, the first preset condition includes at least one of: the terminal having no available AI model parameter; the terminal requesting to deactivate an AI model, and a reason for the request being that complexity of running the AI model is higher than a first threshold; the terminal requesting to deactivate an AI function, the AI function corresponding to at least one AI model, and a reason for the request being that complexity of running the AI function is higher than a second threshold; and the AI model performance of the terminal being lower than a third threshold.

[0035] In some optional embodiments of the first aspect, the first message comprises at least one of: first information used to query whether the network device provides an update service for AI model parameters; second information used to query a first model structure for which the network device supports an AI model providing the update service for AI model parameters; and third information used to indicate a second model structure for which the terminal deploys an AI model.

[0036] In some optional embodiments of the first aspect, the first message comprises the first information, and the method further comprises: receiving, by the terminal, a third message sent by the network device, the third message comprising at least one of: fourth information used to query the second model structure; and fifth information used to indicate the first model structure.

[0037] In some optional embodiments of the first aspect, the method further comprises: receiving, by the terminal, an AI model parameter sent by the network device.

[0038] In some optional embodiments of the first aspect, the second message comprises at least one of: sixth information used to indicate that the network device provides an update service for AI model parameters; seventh information used to indicate a first model structure for which the network device supports an AI model providing the update service for AI model parameters; eighth information used to query whether the terminal has the capability to perform the update of AI model parameters; and ninth information used to instruct the terminal to download AI model parameters.

[0039] In some optional embodiments of the first aspect, the method further comprises: sending, by the terminal, a fourth message to the network device, the fourth message being used to request the network device to perform the update of AI model parameters for an AI model of at least one model structure.

[0040] In a second aspect, a communication method is provided, and the method comprises: receiving, by a network device, a first message sent by a terminal, and / or sending, by the network device, a second message to the terminal; wherein the first message and / or the second message is related to an update of an artificial intelligence (AI) model parameter of the terminal.

[0041] In some optional embodiments of the second aspect, the first message comprises at least one of: first information used to query whether the network device provides an update service of AI model parameters; second information used to query a first model structure for which the network device supports the update service of AI model parameters for an AI model of the first model structure; third information used to indicate a second model structure for which the terminal deploys an AI model.

[0042] In some optional embodiments of the second aspect, the first message comprises the first information, and the method further comprises: sending, by the network device and to the terminal, a third message comprising at least one of: fourth information used to query the second model structure; and fifth information used to indicate the first model structure.

[0043] In some optional embodiments of the second aspect, the method further comprises: sending, by the network device and to the terminal, AI model parameters.

[0044] In some optional embodiments of the second aspect, the sending, by the network device and to the terminal, of the second message comprises: determining, by the network device, that a second preset condition is met, and sending the second message to the terminal.

[0045] In some optional embodiments of the second aspect, the second preset condition comprises at least one of: a transition of an AI model of the terminal from an activated state to a deactivated state; a transition of an AI function of the terminal from an activated state to a deactivated state, the AI function corresponding to at least one AI model; a request of the terminal to deactivate an AI model, and a reason of the request being that a complexity of running the AI model is higher than a first threshold; a request of the terminal to deactivate an AI function, the AI function corresponding to at least one AI model, and a reason of the request being that a complexity of running the AI function is higher than a second threshold; and a performance of an AI model of the terminal being lower than a third threshold.

[0046] In some optional embodiments of the second aspect, the second message comprises at least one of: sixth information used to indicate that the network device provides an update service of AI model parameters; seventh information used to indicate a first model structure for which the network device supports the update service of AI model parameters for an AI model of the first model structure; eighth information used to query whether the terminal has an ability to perform an update of AI model parameters; and ninth information used to instruct the terminal to download AI model parameters.

[0047] In some optional embodiments of the second aspect, the method further includes: receiving, by the network device, a fourth message sent by the terminal, the fourth message being used to request the network device to update AI model parameters of the AI model of at least one model structure.

[0048] In a third aspect, a communication method is provided. The method includes: sending, by a terminal, a first message to a network device, and / or receiving, by the terminal, a second message sent by the network device; wherein the first message and / or the second message is related to updating of artificial intelligence (AI) model parameters of the terminal; receiving, by the network device, the first message, and / or sending, by the network device, the second message.

[0049] In a fourth aspect, a terminal is provided. The terminal includes: a transceiver configured to send a first message to a network device, and / or receive a second message sent by the network device; wherein the first message and / or the second message is related to updating of artificial intelligence (AI) model parameters of the terminal.

[0050] In some optional embodiments of the fourth aspect, the transceiver is configured to send the first message to the network device in the following manner: the terminal determines that a first preset condition is met, and sends the first message to the network device.

[0051] In some optional embodiments of the fourth aspect, the first preset condition includes at least one of the following: the terminal has no available AI model parameters; the terminal requests to deactivate an AI model, and the reason for the request is that a complexity of running the AI model is higher than a first threshold; the terminal requests to deactivate an AI function, the AI function corresponds to at least one AI model, and the reason for the request is that a complexity of running the AI function is higher than a second threshold; an AI model performance of the terminal is lower than a third threshold.

[0052] In some optional embodiments of the fourth aspect, the first message includes at least one of the following: first information used to query whether the network device provides an updating service of AI model parameters; second information used to query a first model structure, the network device supports providing an updating service of AI model parameters for an AI model of the first model structure; and third information used to indicate a second model structure, the terminal deploys an AI model of the second model structure.

[0053] In some optional embodiments of the fourth aspect, the first message includes the first information, and the transceiver is further configured to: receive a third message sent by the network device, the third message including at least one of the following: fourth information used to query the second model structure; and fifth information used to indicate the first model structure.

[0054] In some optional embodiments of the fourth aspect, the transceiver is further configured to: receive, by the terminal, the AI model parameter transmitted by the network device.

[0055] In some optional embodiments of the fourth aspect, the second message comprises at least one of: sixth information indicating that the network device provides an update service for the AI model parameter; seventh information indicating a first model structure, the network device supporting the update service for the AI model of the first model structure; eighth information querying whether the terminal has the capability of updating the AI model parameter; and ninth information indicating that the terminal downloads the AI model parameter.

[0056] In some optional embodiments of the fourth aspect, the transceiver is further configured to: transmit, to the network device, a fourth message for requesting the network device to update the AI model parameter for the AI model of at least one model structure.

[0057] In a fifth aspect, a network device is provided, comprising: a transceiver configured to receive a first message transmitted by a terminal and / or transmit a second message to the terminal; wherein the first message and / or the second message is related to an update of an artificial intelligence (AI) model parameter of the terminal.

[0058] In some optional embodiments of the fifth aspect, the first message comprises at least one of: first information querying whether the network device provides an update service for the AI model parameter; second information querying a first model structure, the network device supporting the update service for the AI model of the first model structure; and third information indicating a second model structure, the terminal deploying the AI model of the second model structure.

[0059] In some optional embodiments of the fifth aspect, the first message comprises the first information, and the method further comprises: transmitting, by the network device, a third message to the terminal, the third message comprising at least one of: fourth information querying the second model structure; and fifth information indicating the first model structure.

[0060] In some optional embodiments of the fifth aspect, the transceiver is further configured to: transmit, to the terminal, the AI model parameter.

[0061] In some optional embodiments of the fifth aspect, the network device transmitting the second message to the terminal comprises: determining, by the network device, that a second preset condition is met, and transmitting the second message to the terminal.

[0062] In some possible embodiments of the fifth aspect, the second preset condition comprises at least one of the following: the AI model of the terminal is switched from an activated state to a deactivated state; an AI function of the terminal is switched from an activated state to a deactivated state, the AI function corresponding to at least one AI model; the terminal requests to deactivate an AI model, and the reason for the request is that a complexity of running the AI model is higher than a first threshold; the terminal requests to deactivate an AI function, the AI function corresponding to at least one AI model, and the reason for the request is that a complexity of running the AI function is higher than a second threshold; an AI model performance of the terminal is lower than a third threshold.

[0063] In some possible embodiments of the fifth aspect, the second message comprises at least one of the following: sixth information used to indicate that the network device provides an update service of an AI model parameter; seventh information used to indicate a first model structure, the network device supporting the update service of the AI model parameter for an AI model of the first model structure; eighth information used to query whether the terminal has an ability to perform an update of an AI model parameter; and ninth information used to instruct the terminal to download an AI model parameter.

[0064] In some possible embodiments of the fifth aspect, the transceiver is further configured to: receive, by the network device, a fourth message sent by the terminal, the fourth message being used to request the network device to perform the update of the AI model parameter for the AI model of the at least one model structure.

[0065] In a sixth aspect, a communication apparatus is provided, comprising: one or more processors; wherein the terminal is configured to implement the first aspect and any one of the communication methods in the first aspect.

[0066] In a seventh aspect, a communication apparatus is provided, comprising: one or more processors; wherein the network device is configured to implement the second aspect and any one of the communication methods in the second aspect.

[0067] In an eighth aspect, a communication system is provided, comprising a terminal and a network device, wherein the terminal is configured to implement the first aspect and any one of the communication methods in the first aspect, and the network device is configured to implement the second aspect and any one of the communication methods in the second aspect.

[0068] In a ninth aspect, a storage medium is provided, which stores instructions, when the instructions run on a communication device, causing the communication device to perform the communication method in the first aspect and any one of the communication methods in the first aspect or the communication method in the second aspect and any one of the communication methods in the second aspect.

[0069] In a tenth aspect, the embodiments of the present disclosure provide a program product, which, when executed by a communication device, causes the communication device to perform the method described in the optional implementation manner of the first aspect or the second aspect.

[0070] In an eleventh aspect, the embodiments of the present disclosure provide a computer program, which, when running on a computer, causes the computer to perform the method described in the optional implementation manner of the first aspect or the second aspect.

[0071] In a twelfth aspect, the embodiments of the present disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the method described in the first aspect or the second aspect.

[0072] It can be understood that the terminal, the access network device, the first network element, the other network element, the core network device, the communication system, the storage medium, the program product, the computer program, the chip or the chip system involved in the embodiments of the present disclosure are used to perform the method proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method, which will not be described here.

[0073] The embodiments of the present disclosure propose a communication method, a terminal, a network device, a communication device and a storage medium. In some embodiments, the communication method and the information processing method, the communication method and the like can be replaced with each other, the communication device and the information processing device, the communication device and the like can be replaced with each other, and the information processing system, the communication system and the like can be replaced with each other.

[0074] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, some or all steps of different embodiments can be combined arbitrarily, and an embodiment can be combined with the optional implementation manners of other embodiments.

[0075] In the embodiments of the present disclosure, the terms and / or descriptions between the embodiments are consistent if there is no special description and logical conflict, and can be referred to each other, and the technical environments in different embodiments can be combined to form a new embodiment according to their inherent logical relationship.

[0076] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and not as a limitation on the present disclosure.

[0077] In the embodiments of the present disclosure, an element expressed in singular form, such as "a", "an", "the", "said", "the aforementioned", "the foregoing", "this", and the like, unless otherwise specified, can represent "one and only one", or can represent "one or more", "at least one", and the like. For example, in the case of using an article such as "a", "an", "the" in English, the noun after the article can be understood as a singular expression, or can be understood as a plural expression.

[0078] In the embodiments of the present disclosure, "plurality" refers to two or more.

[0079] In some embodiments, the terms "at least one of", "one or more", "a plurality of", "multiple", and the like can be replaced with each other.

[0080] In some embodiments, the description manner such as "at least one of A, B", "A and / or B", "A in one case and B in another case", "responding to a case A, responding to another case B", and the like can include the following technical solutions according to the case: A is executed in some embodiments (A is executed regardless of B); B is executed in some embodiments (B is executed regardless of A); A and B are selectively executed in some embodiments (A and B are selected to be executed); A and B are executed in some embodiments (A and B are both executed). When there are more branches such as A, B, C, and the like, it is similar to the above.

[0081] In some embodiments, the description manner such as "A or B" and the like can include the following technical solutions according to the case: A is executed in some embodiments (A is executed regardless of B); B is executed in some embodiments (B is executed regardless of A); A and B are selectively executed in some embodiments (A and B are selected to be executed). When there are more branches such as A, B, C, and the like, it is similar to the above.

[0082] The prefix words of "first", "second" and the like in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute limitation on the position, order, priority, quantity or content of the description objects. The description objects are described in the claims or embodiments, and should not be construed as redundant limitation because of the use of the prefix words. For example, the description object is "field", and the ordinal words before "field" in "first field" and "second field" do not limit the position or order between "fields", and "first" and "second" do not limit whether the "fields" modified thereby are in the same message or not, nor limit the order of "first field" and "second field". For another example, the description object is "level", and the ordinal words before "level" in "first level" and "second level" do not limit the priority between "levels". For another example, the quantity of the description object is not limited by the ordinal words, and can be one or more. For example, "first device", wherein the quantity of "device" can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description object is "device", and "first device" and "second device" can be the same device or different devices, and the types thereof can be the same or different. For another example, the description object is "information", and "first information" and "second information" can be the same information or different information, and the contents thereof can be the same or different.

[0083] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0084] In some embodiments, the terms of "in response to", "in response to determining", "in the case of", "when", "when", "if", "if" and the like can be replaced with each other.

[0085] In some embodiments, the terms of "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", "above" and the like can be replaced with each other, and the terms of "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", "below" and the like can be replaced with each other.

[0086] In some embodiments, the apparatuses and devices can be interpreted as entities, and can also be interpreted as virtual, whose names are not limited to the names described in the embodiments, and in some cases can also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject", etc.

[0087] In some embodiments, "network" can be interpreted as an apparatus contained in the network, for example, access network device, core network device, etc.

[0088] In some embodiments, "access network device (AN device)" can also be referred to as "radio access network device (RAN device)", "base station (BS)", "radio base station", "fixed station", and in some embodiments can also be understood as "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", "bandwidth part (BWP)", etc.

[0089] In some embodiments, a "terminal" or "terminal device" can be referred to as a "user equipment" (UE), a "user terminal," a "mobile station" (MS), a "mobile terminal" (MT), a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, and / or the like.

[0090] In some embodiments, data, information and / or the like can be obtained in compliance with laws and regulations of the country in which the data, information and / or the like is obtained.

[0091] In some embodiments, data, information and / or the like can be obtained after consent is given by a user.

[0092] Further, each element, each row, or each column in a table of an embodiment of the present disclosure can be implemented as an independent embodiment, and a combination of any element, any row, or any column can be implemented as an independent embodiment.

[0093] Currently, the wide application of 5G technology brings great changes to all aspects of people's life. According to the vision of the International Telecommunication Union (ITU), 5G will penetrate into all fields of future society to build a comprehensive information ecosystem centered on users. Among them, the 5G user experience rate can reach 100 megabits per second (Mbit / s) to 1 gigabit (Gbit / s), which can support mobile virtual reality and other extreme business experience; the 5G peak rate can reach 10 Gbit / s to 20 Gbit / s, and the traffic density can reach 10 megabits per second per square meter (Mbit / s / m2), which can support the growth of mobile business traffic by more than 1,000 times in the future; the 5G connection number density can reach 1 million per square meter ( / m2), which can effectively support a large number of Internet of Things devices; the 5G transmission delay can reach milliseconds, which can meet the strict requirements of vehicle networking and industrial control; 5G can support a mobile speed of 500 kilometers per hour (km / h), which can meet good user experience in high-speed rail environments. It can be imagined that 5G as a representative of new infrastructure will rebuild the future information society.

[0094] In recent years, artificial intelligence (AI) technology has made continuous breakthroughs in many fields. The continuous development of intelligent voice, computer vision and other fields not only brings a variety of colorful applications to intelligent terminals, but also has wide application in education, transportation, home, medical care, retail, security and many other fields, bringing convenience to people's life and promoting the industrial upgrading of various industries. AI technology is also accelerating the cross-penetration with other disciplines, and its development integrates knowledge from different disciplines, while also providing new directions and methods for the development of different disciplines.

[0095] In recent research, AI technology is introduced into the wireless air interface, and how AI technology assists the improvement of wireless air interface transmission technology is studied. For example, the following three aspects are included:

[0096] AI-enabled connectivity. That is, using AI methods to improve the performance of communication, such as using AI for beam management.

[0097] Computing power service. That is, the network side can provide computing power to the terminal side, such as helping the terminal to perform model training, model inference, etc.

[0098] Extreme AI service. That is, the transmission pipeline of the network is enhanced to improve the experience of AI application services.

[0099] Regarding the deployment of the AI model, one way is that the network side trains the AI model well, and then transmits the AI model to the terminal. Further, in order to reduce complexity, the terminal can deploy the model structure in advance, and the network side only transmits the model parameters for the model structure deployed by the terminal.

[0100] However, there is no conclusion on how to trigger the parameter update process of the model and the corresponding process.

[0101] Therefore, the present disclosure provides a communication method, which comprises: sending, by a terminal, a first message to a network device, or receiving, by the terminal, a second message sent by the network device, wherein the first message and / or the second message is a message related to the update of the AI model parameters. Thus, the parameter update of the AI model of the terminal is realized.

[0102] FIG. 1 is a schematic diagram of a communication system architecture according to an embodiment of the present disclosure.

[0103] As shown in FIG. 1, the communication system 100 comprises a terminal 101 and a network device 102.

[0104] In some embodiments, the terminal 101 comprises at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-enabled automobile, a smart automobile, a tablet computer (Pad), a wireless transceiver-enabled computer, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, a wireless terminal device in smart home, but is not limited thereto.

[0105] In some embodiments, the network device 102 can comprise at least one of an access network device and a core network device.

[0106] In some embodiments, the access network device is, for example, a node or device that accesses a terminal to a wireless network, and can include at least one of an evolved NodeB (eNB) in a 5G communication system, a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, an access node in a Wi-Fi system, but is not limited thereto.

[0107] In some embodiments, the technical solutions of the present disclosure can be applied to an Open RAN architecture, at which time the interfaces between or within the access network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be realized through software or programs.

[0108] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), where the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the access network device, with part of the protocol layer functions being controlled by the CU, and the remaining part or all of the protocol layer functions being distributed in the DU and controlled by the CU, but is not limited thereto.

[0109] In some embodiments, the core network device can be one device including one or more network elements, or a plurality of devices or device groups including all or part of the above one or more network elements. The network element can be virtual or physical. The core network includes, for example, at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0110] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the technical solutions proposed by the embodiments of the present disclosure. Those skilled in the art can know that, with the evolution of system architecture and the appearance of new business scenarios, the technical solutions proposed by the embodiments of the present disclosure are also applicable to similar technical problems.

[0111] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1 or part of the subjects, but are not limited thereto. The subjects shown in FIG. 1 are exemplary, and the communication system can include all or part of the subjects in FIG. 1, or other subjects other than FIG. 1. The number and form of each subject is arbitrary, each subject can be physical or virtual, the connection relationship between each subject is exemplary, each subject can not be connected or can be connected, the connection can be in any way, can be direct connection or indirect connection, can be wired connection or wireless connection.

[0112] Embodiments of the present disclosure 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), 6th generation mobile communication system (6G), 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 (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other communication methods, next-generation system expanded based thereon, and the like. In addition, a plurality of systems can be combined (for example, combination of LTE or LTE-A and 5G, and the like).

[0113] FIG. 2a is a schematic diagram of an interaction of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2a, the embodiment of the present disclosure relates to a communication method for a communication system 100, the method comprising:

[0114] In step S2101, the terminal 101 sends a first message to the network device 102.

[0115] In some embodiments, the network device 102 receives the first message sent by the terminal 101.

[0116] In some embodiments, the first message is related to the update of the AI model parameters of the terminal.

[0117] In some embodiments, the terminal can send the first message to the network device in a case where it is determined that the first preset condition is met.

[0118] In some embodiments, the first preset condition comprises at least one of the following: the terminal has no available AI model parameters; the terminal requests to deactivate the AI model, and the reason for the request is that the complexity of running the AI model is higher than a first threshold; the terminal requests to deactivate an AI function, the AI function corresponds to at least one AI model, and the reason for the request is that the complexity of running the AI function is higher than a second threshold; the AI model performance of the terminal is lower than a third threshold.

[0119] Optionally, the first preset condition can comprise that the terminal has no available AI model parameters. As an example, in the process of deploying the AI model, in order to reduce complexity, the terminal can deploy the model structure in advance, and the network device can send the model parameters to the terminal for the model structure deployed by the terminal. If the terminal has deployed the model structure, but the network device has not sent the model parameters, it can be considered that the terminal has no available AI model parameters. As another example, the model parameters deployed by the terminal can not be suitable for use in the current wireless environment, and it can also be considered that the terminal has no available AI model. If the terminal has no available AI model parameters, the terminal can send the first message to the network device to meet the first preset condition. The first message is related to the update of the AI model parameters of the terminal, for example, the terminal can request the network device to update the AI model parameters, and if the network device responds to the request of the terminal, the network device can send the AI model parameters to the terminal.

[0120] Optionally, the first preset condition can comprise that the terminal requests to deactivate the AI model, and the reason for the request is that the complexity of running the AI model is higher than a first threshold. For example, if the complexity of running the AI model of the terminal is higher than the first threshold, triggering the terminal to request to deactivate the AI model, it can be considered that the first preset condition is met, and the terminal can send the first message to the network device. The first message is related to the update of the AI model parameters of the terminal, for example, the terminal can request the network device to update the AI model parameters, and if the network device responds to the request of the terminal, the network device can send the AI model parameters to the terminal. The update of the AI model parameters can solve the problem of high complexity of running the AI model, so that the terminal does not need to deactivate the AI model, and can continue to perform the AI task based on the AI model updated by the parameters.

[0121] Optionally, the first preset condition comprises that the terminal requests to deactivate the AI function, the AI function corresponds to at least one AI model, and a reason for the request is that a complexity of running the AI function is higher than a second threshold. The running of the AI function can be understood as the running of at least one AI model corresponding to the AI function. The complexity of running the AI function can refer to a sum of complexities of at least one AI model corresponding to the AI function. If the complexity of running the AI function is higher than the second threshold, the terminal triggers the request to deactivate the AI function, and it can be considered that the first preset condition is met. The terminal can send a first message to the network device. The first message is related to the update of the AI model parameter of the terminal, for example, the terminal can request the network device to update the AI model parameter, and if the network device responds to the request of the terminal, the network device can send the AI model parameter to the terminal. The update of the AI model parameter can solve the problem of high complexity of running the AI function, so that the terminal does not need to deactivate the AI function, and can continue to execute the AI task based on the AI model after the parameter update.

[0122] Optionally, the first preset condition comprises that the AI model performance of the terminal is lower than a third threshold. If the performance of the AI model is lower than the third threshold, it can be considered that the first preset condition is met, and the terminal can send a first message to the network device. The first message is related to the update of the AI model parameter of the terminal, for example, the terminal can request the network device to update the AI model parameter, and if the network device responds to the request of the terminal, the network device can send the AI model parameter to the terminal. The update of the AI model parameter can improve the performance of the AI model.

[0123] In some embodiments, the first message comprises at least one of the following: first information for querying whether the network device provides an AI model parameter update service; second information for querying a first model structure, the network device supporting the AI model parameter update service for the AI model of the first model structure; and third information for indicating a second model structure, the terminal deploying the AI model of the second model structure.

[0124] Optionally, the first message can comprise first information for querying whether the network device provides an AI model parameter update service. For example, after determining that the first preset condition is met, the terminal can query whether the network device provides the AI model parameter update service, and if the network device supports, the terminal can request the network device to update the parameter for a certain model structure that needs to be updated. If the network device does not support, the terminal can solve the problem in other ways, for example, the AI model that needs the model parameter update can be deactivated. The name of the first information is not limited, which can also be “first field” and the like. The first information can be understood as the content carried by the first message.

[0125] Optionally, the first message can include second information, the second information being used to query the first model structure, and the network device supporting an AI model providing an update service of AI model parameters for the first model structure. That is, it can be queried which model structures the network device supports for AI model parameter update. For example, after determining that the first preset condition is met, the terminal can query which model structures the network device supports for AI model parameter update. If the AI model structure that the terminal needs to update parameters is included in the model structure (i.e., the first model structure) supported by the network device, the terminal can request the network device to update parameters for a certain model structure that needs to be updated. If the AI model structure that the terminal needs to update parameters is not included in the model structure (i.e., the first model structure) supported by the network device, the terminal can take other ways to solve the problem, for example, the AI model that needs model parameter update can be deactivated. The name of the second information is not limited, which can also be, for example, "second field" and the like. The second information can be understood as the content carried by the first message.

[0126] Optionally, the first message can include third information, the third information being used to indicate the second model structure, and the terminal deploying the AI model of the second model structure. That is, the terminal can inform the network device which model structures, i.e., the second model structure, are deployed in the terminal. The network device can update the model parameters for the second model structure. The name of the third information is not limited, which can also be, for example, "third field" and the like. The third information can be understood as the content carried by the first message.

[0127] In some embodiments, the first message can be used to request the network device to update the parameters of the AI model deployed in the terminal. For example, at least one of the first information, the second information and the third information in the first message can implicitly represent that the terminal requests the network device to update the parameters of the AI model deployed in the terminal. Taking the first information as an example, the network device determines that the terminal needs to update the parameters of the AI model according to the terminal request to query whether the network device provides the update service of AI model parameters. For another example, the first message can include request information, or a request field, to request the network device to update the parameters of the AI model deployed in the terminal.

[0128] In step S2102, the network device 102 sends a third message to the terminal 101.

[0129] In some embodiments, the terminal 101 receives the third message sent by the network device 102.

[0130] In some embodiments, if the first message comprises the first information, i.e., the first information is used to query whether the network device provides the update service of the AI model parameter, if the network device receives the first message and can provide the update service of the AI model parameter, the network device can send a third message to the terminal.

[0131] In some embodiments, the third message comprises at least one of the following: fourth information, the fourth information is used to query the second model structure; and fifth information, the fifth information is used to indicate the first model structure.

[0132] Optionally, the third message can comprise the fourth information, and the fourth information is used to query the second model structure. That is, the fourth information is used to query which AI model the terminal deploys. For example, the first message is only used to query whether the network device provides the update service of the AI model parameter, and the first model structure is not reported. The network device can query the first model structure through the third message.

[0133] Optionally, the third message can comprise the fifth information, and the fifth information is used to indicate the first model structure. That is, the fifth information is used to indicate which model structure the network device supports to update the AI model parameter. For example, the first message is only used to query whether the network device provides the update service of the AI model parameter, and which model structure the network device supports to update the AI model parameter is not queried. The network device can actively inform the terminal which model structure the network device supports to update the AI model parameter. So that the terminal can determine whether to request the network device to update the model structure which needs parameter update on the terminal side.

[0134] In some embodiments, the names of the fourth information and the fifth information are not limited, which can be, for example, “fourth field” and “fifth field”.

[0135] In some embodiments, the name of the third message is not limited, which can be, for example, “response message”.

[0136] It can be understood that the step S2102 is optional. For example, if the first message comprises the third information, the network device does not need to carry the fourth information in the third message. That is, if the terminal reports the second model structure in the first message, the network device does not need to query the second model structure through the first message again. Therefore, the step S2102 can be omitted.

[0137] In step S2103, the network device 102 sends the AI model parameter to the terminal 101.

[0138] In some embodiments, the terminal 101 receives the AI model parameter sent by the network device 102.

[0139] In some embodiments, the first message can be used to request the network device to update the parameters of the AI model deployed by the terminal. The network device can update the parameters of the AI model deployed by the terminal in response to the request of the first message.

[0140] For example, at least one of the first information, the second information and the third information in the first message can imply that the terminal requests the network device to update the parameters of the AI model deployed by the terminal. The network device can update the parameters of the AI model with a high running complexity on the terminal side higher than a first threshold, i.e., the network device can send the parameters of the AI model with a high running complexity higher than the first threshold. Or, at least one AI model corresponding to an AI function with a high running complexity higher than a second threshold can be updated, i.e., the network device can send the parameters of at least one AI model corresponding to the AI function with a high running complexity higher than the first threshold. The present disclosure does not list all examples.

[0141] For another example, the first message can contain request information for requesting the network device to update the parameters of the AI model deployed by the terminal. The network device sends the AI model parameters to the terminal in response to the request.

[0142] In some embodiments, the network device can actively update the parameters of the AI model structure according to the second model result reported in the first message.

[0143] The communication method related to the embodiments of the present disclosure can include at least one of steps S2101-S2103. Steps S2101-S2103 can be implemented as separate embodiments, and each embodiment can be combined and adjusted in order as long as there is no contradiction. For example, step S2101 can be implemented as an independent embodiment, but is not limited thereto.

[0144] In some embodiments, steps S2102 and S2103 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0145] In some embodiments, other optional implementations described before or after the description corresponding to FIG. 2a can be referred to.

[0146] FIG. 2b is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2b, the embodiments of the present disclosure relate to a communication method for a communication system 100, and the above method includes:

[0147] Step S2201, the network device 102 sends a second message to the terminal 101.

[0148] In some embodiments, the terminal 101 receives the second message sent by the network device 102.

[0149] In some embodiments, the second message is related to an update of an artificial intelligence (AI) model parameter of the terminal.

[0150] In some embodiments, the network device can send the second message when a second preset condition is met.

[0151] In some embodiments, the second preset condition comprises at least one of the following: the AI model of the terminal is switched from an activated state to a deactivated state; an AI function of the terminal is switched from an activated state to a deactivated state, the AI function corresponding to at least one AI model; the terminal requests to deactivate the AI model, and the reason for the request is that a complexity of running the AI model is higher than a first threshold; the terminal requests to deactivate the AI function, the AI function corresponding to at least one AI model, and the reason for the request is that a complexity of running the AI function is higher than a second threshold; and the AI model performance of the terminal is lower than a third threshold.

[0152] Optionally, the second preset condition can comprise that the AI model of the terminal is switched from an activated state to a deactivated state. For example, the terminal can deactivate the AI model by itself. If the network device determines that the AI model of the terminal is switched from an activated state to a deactivated state, it can be considered that the second preset condition is met, and the network device can send the second message to the terminal. Illustratively, the terminal can deactivate the AI model because there is no available AI model parameter, or the performance of the AI model is lower than a third threshold. Or, the AI model can be deactivated because the complexity of running the AI model is higher than a first threshold. Or, at least one AI model corresponding to the AI function can be deactivated because the complexity of running the AI function is higher than a second threshold. And the network device sends the second message to the terminal based on the AI model being switched from an activated state to a deactivated state, so as to update the parameter of the AI model, thereby solving the above-mentioned exemplary problems leading to the deactivation of the AI model.

[0153] Optionally, the second preset condition can comprise that the AI function of the terminal is switched from an activated state to a deactivated state. For example, the terminal can deactivate the AI function by itself. If the network device determines that the AI function of the terminal is switched from an activated state to a deactivated state, it can be considered that the second preset condition is met, and the network device can send the second message to the terminal.

[0154] Optionally, the second preset condition can comprise that the terminal requests to deactivate the AI model, and carries a reason for the request, the reason being that a complexity of running the AI model is higher than a first threshold. For example, the terminal requests the network device to deactivate the AI model, and carries a reason for the request, the reason being that a complexity of running the AI model is higher than a first threshold. The network device can send a second message to the terminal. It can be understood that the network device can deactivate the AI model in response to the request of the terminal, and send the second message. The network device can also not deactivate the AI model of the terminal in response to the request of the terminal, but send the second message. If subsequent parameter updating of the AI model fails, the AI model can be considered for deactivation. Of course, the examples provided in the disclosure are not limited.

[0155] Optionally, the second preset condition can comprise that the terminal requests to deactivate the AI function, the AI function corresponding to at least one AI model, and a reason for the request being that a complexity of running the AI function is higher than a second threshold. For example, the terminal requests the network device to deactivate the AI function, and carries a reason for the request, the reason being that a complexity of running the AI function is higher than a second threshold. The network device can send a second message to the terminal.

[0156] Optionally, the second preset condition can comprise that the AI model performance of the terminal is lower than a third threshold. If the network device determines that the AI model performance of the terminal is lower than a third threshold, it can be considered that the second preset condition is met, and the network device can send a second message to the terminal.

[0157] In some embodiments, the second message comprises at least one of the following: sixth information used to indicate that the network device provides an update service of AI model parameters; seventh information used to indicate a first model structure, the network device supporting the update service of AI model parameters for the AI model of the first model structure; eighth information used to query whether the terminal has the capability of performing the update of AI model parameters; and ninth information used to instruct the terminal to download AI model parameters.

[0158] Optionally, the second message can comprise sixth information used to indicate that the network device provides an update service of AI model parameters. That is, the network device can actively inform the terminal of the update service of AI model parameters provided by the network device in the case where it is determined that the second preset condition is met. If the terminal requests the network device to update the parameters of the AI model deployed by the terminal after receiving the second message, the network device can send AI model parameters to the terminal.

[0159] Optionally, the second message can comprise seventh information, the seventh information being used to indicate a first model structure, and the network device supporting an update service of AI model parameters of an AI model of the first model structure. That is, the network device can actively inform the terminal of which model structures the network device supports the update of AI model parameters of the AI model under the condition that the second preset condition is met.

[0160] Optionally, the second message can comprise eighth information, the eighth information being used to query whether the terminal has the capability of updating the AI model parameters. For example, if the terminal has the capability of updating the AI model parameters, the network device can send the AI model parameters to the terminal so that the terminal updates based on the AI model parameters. If the terminal does not have the capability of updating the AI model parameters, the network device can not send the AI model parameters to the terminal, avoiding unnecessary signaling consumption.

[0161] Optionally, the second message can comprise ninth information, the ninth information being used to instruct the terminal to download the AI model parameters. For example, the network device can not directly send the AI model parameters to the terminal, but instruct the terminal to download the AI model parameters, and the terminal decides whether to download the AI model parameters. For example, if the terminal can not need to update the AI model parameters, or the remaining power, the remaining storage space, etc. of the AI do not support the update of the AI model, the terminal can also not download the AI model parameters. The network device does not directly send the AI model parameters, so as to avoid unnecessary resource waste and avoid causing storage burden of the terminal.

[0162] In some embodiments, the names of the sixth information to the ninth information are not limited, which can be, for example, “sixth field”··· “ninth field” and the like.

[0163] In some embodiments, the name of the second message is not limited, which can be, for example, “update message” and the like.

[0164] In step S2202, the terminal 101 sends a fourth message to the network device 102.

[0165] In some embodiments, the network device 102 receives the fourth message sent by the terminal 101.

[0166] In some embodiments, the fourth message is used to request the network device to update the AI model parameter of the AI model of the at least one model structure. For example, if the network device indicates in the second message that it provides the update service of the AI model parameter, the terminal can send the fourth message to the network device to request the update of the AI model parameter. For another example, if the network device indicates the first model structure in the second message, and the terminal determines that the model structure that needs to be updated includes in the first model structure, the fourth message can be sent to the network device. For another example, if the network device queries in the second message whether the terminal has the capability of updating the AI model parameter, the terminal can feed back to the network device whether it has the capability of updating the AI model parameter. If the terminal has the capability of updating the AI model parameter, and the terminal has the model structure that needs to be updated, the fourth message can be sent to the network device.

[0167] The communication method related to the embodiments of the present disclosure can include at least one of step S2201 to step S2202. Step S2201 to step S2202 can be implemented as separate embodiments, and each embodiment can be combined and adjusted in order without contradiction. For example, step S2201 can be implemented as an independent embodiment, but is not limited thereto.

[0168] In some embodiments, step S2202 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0169] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2b can be referred to.

[0170] FIG. 3a is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3a, the embodiment of the present disclosure relates to a communication method, which is executed by the terminal 101, and the above method includes:

[0171] Step S3101, sending a first message.

[0172] The optional implementation of step S3101 can refer to the optional implementation of step S2101 of FIG. 2a and other related parts in the embodiments related to FIG. 2a, which will not be described here.

[0173] In some embodiments, the terminal 101 sends the first message to the network device 102, but is not limited thereto, and can send the first message to other devices.

[0174] Step S3102, obtaining a third message.

[0175] The optional implementation of step S3102 can refer to the optional implementation of step S2102 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0176] In some embodiments, the terminal 101 receives the third message sent by the network device 102, but is not limited thereto, and can also receive the third message sent by other subjects.

[0177] In some embodiments, the terminal 101 obtains the third message specified by the protocol.

[0178] In some embodiments, the terminal 101 obtains the third message from the upper layer(s).

[0179] In some embodiments, the terminal 101 processes to obtain the third message.

[0180] In some embodiments, step S3102 is omitted, and the first terminal 101 autonomously implements the function indicated by the third message, or the above function is default or default.

[0181] Step S3103, obtaining AI model parameters.

[0182] The optional implementation of step S3103 can refer to the optional implementation of step S2103 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0183] In some embodiments, the terminal 101 receives the AI model parameters sent by the network device 102, but is not limited thereto, and can also receive the AI model parameters sent by other subjects.

[0184] In some embodiments, the terminal 101 obtains the AI model parameters specified by the protocol.

[0185] In some embodiments, the terminal 101 obtains the AI model parameters from the upper layer(s).

[0186] In some embodiments, the terminal 101 processes to obtain the AI model parameters.

[0187] In some embodiments, step S3103 is omitted, and the first terminal 101 autonomously implements the function indicated by the AI model parameters, or the above function is default or default.

[0188] FIG. 3b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 3b, the embodiment of the present disclosure relates to a communication method, which is executed by the terminal 101, and the above method comprises:

[0189] Step S3201, obtaining a second message.

[0190] The optional implementation of step S3201 can refer to the optional implementation of step S2201 in FIG. 2b, and other associated parts in the embodiments involved in FIG. 2b, which will not be repeated here.

[0191] In some embodiments, the terminal 101 receives the second message sent by the network device 102, but is not limited thereto, and can also receive the second message sent by other subjects.

[0192] In some embodiments, the terminal 101 acquires the second message specified by the protocol.

[0193] In some embodiments, the terminal 101 acquires the second message from the upper layer(s).

[0194] In some embodiments, the terminal 101 processes to obtain the second message.

[0195] In some embodiments, step S3201 is omitted, and the terminal 101 autonomously implements the function indicated by the second message, or the above function is default or default.

[0196] Step S3202, sending a fourth message.

[0197] The optional implementation of step S3202 can refer to the optional implementation of step S2202 in FIG. 2b, and other associated parts in the embodiments involved in FIG. 2b, which will not be repeated here.

[0198] In some embodiments, the terminal 101 sends the fourth message to the network device 102, but is not limited thereto, and can also send the fourth message to other devices.

[0199] FIG. 4a is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 4a, the embodiment of the present disclosure relates to a communication method, which is performed by the network device 102, and the above method comprises:

[0200] Step S4101, acquiring a first message.

[0201] The optional implementation of step S4101 can refer to the optional implementation of step S2101 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0202] In some embodiments, the network device 102 receives the first message sent by the terminal 101 in response to detecting that the radio link quality corresponding to the first reference signal resource on the first reference signal resource set is lower than the first threshold value, but is not limited thereto, and can also receive the first message sent by other subjects.

[0203] In some embodiments, the network device 102 obtains the first message as specified by a protocol.

[0204] In some embodiments, the network device 102 obtains the first message from upper layer(s).

[0205] In some embodiments, the network device 102 processes to obtain the first message.

[0206] In some embodiments, step S4101 is omitted, and the network device 102 autonomously implements the function indicated by the first message, or the above function is default or default.

[0207] Step S4102, sending a third message.

[0208] The optional implementation of step S4102 can refer to the optional implementation of step S2102 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0209] In some embodiments, the network device 102 sends the third message to the terminal 101, but is not limited thereto, and can send the third message to other entities.

[0210] Step S4103, sending an AI model parameter.

[0211] The optional implementation of step S4103 can refer to the optional implementation of step S2103 in FIG. 2a, and other associated parts in the embodiments involved in FIG. 2a, which will not be repeated here.

[0212] In some embodiments, the network device 102 sends the AI model parameter to the terminal 101, but is not limited thereto, and can send the AI model parameter to other entities.

[0213] FIG. 4b is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 4b, the embodiment of the present disclosure relates to a communication method, which is performed by the network device 102, and the above method comprises:

[0214] Step S4201, sending a second message.

[0215] The optional implementation of step S4201 can refer to the optional implementation of step S2201 in FIG. 2b, and other associated parts in the embodiments involved in FIG. 2b, which will not be repeated here.

[0216] In some embodiments, the network device 102 sends the second message to the terminal 101, but is not limited thereto, and can send the second message to other entities.

[0217] Step S4202, obtaining a fourth message.

[0218] The optional implementation of step S4202 can refer to the optional implementation of step S2202 in FIG. 2b, and other associated parts in the embodiments related to FIG. 2b, which are not described herein again.

[0219] In some embodiments, the network device 102 receives the fourth message sent by the terminal 101 in response to detecting that the radio link quality corresponding to the first reference signal resource on the first reference signal resource set is lower than the first threshold value, but is not limited thereto, and can also receive the fourth message sent by other subjects.

[0220] In some embodiments, the network device 102 obtains the fourth message specified by the protocol.

[0221] In some embodiments, the network device 102 obtains the fourth message from the upper layer(s).

[0222] In some embodiments, the network device 102 processes to obtain the fourth message.

[0223] In some embodiments, step S4202 is omitted, and the network device 102 autonomously implements the function indicated by the fourth message, or the above function is default or default.

[0224] FIG. 5 is an interaction diagram of a communication method according to an embodiment of the present disclosure. As shown in FIG. 5, the embodiment of the present disclosure relates to a communication method, and the above method comprises:

[0225] Step S5101, the terminal 101 sends a first message to the network device 102, or the terminal 101 receives a second message sent by the network device 102.

[0226] Step S5102, the network device 102 receives the first message, or the network device 102 sends the second message.

[0227] In some embodiments, the above method can include the method of the above embodiments related to the communication system 100, the terminal 101, and the network device 102, which are not described herein again.

[0228] The present disclosure provides a communication method, which is as follows:

[0229] In some embodiments, the terminal side sends a first message to the network or the network sends a second message to the terminal. The first message and / or the second message are related to the terminal side model parameter update

[0230] In some embodiments, the terminal side sends a first message to the network or the network sends a second message to the terminal in response to satisfying a preset condition. The preset condition includes any one of the following conditions:

[0231] There is no available model parameter at the terminal side, and the terminal side sends a first message to the network;

[0232] The AI function or AI model at the terminal side is switched from an activated state to a deactivated state, and the network sends a second message to the terminal;

[0233] The performance of the AI function or AI model at the terminal side does not meet a first threshold, and the terminal side sends a first message to the network or the network sends a second message to the terminal side;

[0234] The terminal side requests to deactivate the AI model or AI function, and determines that the reason for closing the model is high running complexity, and the terminal side sends a first message to the network or the network sends a second message to the terminal side.

[0235] In some embodiments, the first message includes one of the following contents:

[0236] a) querying whether the network provides a model parameter update service and / or querying which model structures the network supports for parameter update;

[0237] b) informing the network of the model structures supported by the terminal side and requesting the network to send model parameters.

[0238] In some embodiments, the second message includes one of the following contents:

[0239] a) indicating to the user that the network has a function of providing model parameter update and / or indicating to the terminal which model structures the network supports for update;

[0240] b) querying whether the terminal has the capability of model parameter update;

[0241] c) instructing the terminal to perform model parameter download update;

[0242] In some embodiments, in response to the first message for querying whether the network provides a model parameter update service, when the network side receives the first message, the network can provide a model parameter update service in response, and the network sends a third message, which includes one of the following contents:

[0243] a) the network queries the AI model structure types supported by the terminal;

[0244] b) the network sends to the terminal which AI model structures the network side supports for parameter update.

[0245] In some embodiments, in response to the first message for requesting the network to perform model parameter update, and the network side has model parameters corresponding to the model structures supported by the terminal, the network sends the model parameters to the terminal.

[0246] In some embodiments, the second message is used to indicate to the terminal a parameter update of a model structure supported by the network, and the terminal sends a fourth message to the network to request the network to perform the parameter update for a certain specific model structure.

[0247] The embodiments of the present disclosure also provide a device for implementing any of the above methods, for example, a device including units or modules for implementing the steps performed by the terminal in any of the above methods. For another example, another device is provided, including units or modules for implementing the steps performed by the network device (such as an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0248] It should be understood that the division of each unit or module in the above device is only a logical function division, and all or part of them can be integrated into one physical entity or physically separated in actual implementation. In addition, the units or modules in the device can be implemented in the form of processor calling software: for example, the device includes a processor connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit or module of the device, wherein the processor is, for example, a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is a memory in the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuit, and the functions of part or all of the units or modules can be implemented by the design of the hardware circuit, and the hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), and the functions of part or all of the units or modules are implemented by the design of the logical relationship between the elements in the circuit; for another example, in another implementation, the hardware circuit is a programmable logic device (PLD), and taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to implement the functions of part or all of the units or modules. All units or modules of the above device can be implemented by processor calling software, or all units or modules can be implemented by hardware circuit, or part of the units or modules can be implemented by processor calling software, and the remaining part can be implemented by hardware circuit.

[0249] In the embodiments of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and running capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), a digital signal processor (DSP), and the like. In another implementation, the processor can implement certain functions through a logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In the reconfigurable hardware circuit, the processor loads a configuration document to implement the configuration of the hardware circuit. It can be understood that the processor loads instructions to implement the functions of the above part or all units or modules. In addition, 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), a deep learning processing unit (DPU), and the like.

[0250] FIG. 6a is a structural schematic diagram of a terminal according to an embodiment of the present disclosure. As shown in FIG. 6a, the terminal 6100 can include at least one of a transceiver module 6101 and a processing module 6102. The transceiver module 6101 is configured to send a first message to a network device and / or receive a second message sent by the network device, and the first message and / or the second message is related to updating of an artificial intelligence (AI) model parameter of the terminal.

[0251] In some embodiments, the transceiver module 6101 sends the first message to the network device in the following manner: the terminal determines that a first preset condition is met, and sends the first message to the network device.

[0252] In some embodiments, the first preset condition comprises at least one of the following: the terminal has no available AI model parameter; the terminal requests to deactivate an AI model, and the reason for the request is that the complexity of running the AI model is higher than a first threshold; the terminal requests to deactivate an AI function, the AI function corresponds to at least one AI model, and the reason for the request is that the complexity of running the AI function is higher than a second threshold; and the AI model performance of the terminal is lower than a third threshold.

[0253] In some embodiments, the first message comprises at least one of the following: first information used to query whether the network device provides an update service of an AI model parameter; second information used to query a first model structure, the network device supports the update service of the AI model parameter for an AI model of the first model structure; and third information used to indicate a second model structure, the terminal deploys an AI model of the second model structure.

[0254] In some embodiments, the first message comprises the first information, and the transceiver 6101 is further configured to: receive a third message sent by the network device, the third message comprising at least one of the following: fourth information used to query the second model structure; and fifth information used to indicate the first model structure.

[0255] In some embodiments, the transceiver 6101 is further configured to: receive, by the terminal, an AI model parameter sent by the network device.

[0256] In some embodiments, the second message comprises at least one of the following: sixth information used to indicate that the network device provides an update service of an AI model parameter; seventh information used to indicate a first model structure, the network device supports the update service of the AI model parameter for an AI model of the first model structure; eighth information used to query whether the terminal has the capability of performing the update of the AI model parameter; and ninth information used to indicate that the terminal downloads an AI model parameter.

[0257] In some embodiments, the transceiver 6101 is further configured to: send, to the network device, a fourth message used to request the network device to perform the update of the AI model parameter for an AI model of at least one model structure.

[0258] FIG. 6b is a structural schematic diagram of a network device according to an embodiment of the present disclosure. As shown in FIG. 6b, the network device 6200 can include at least one of a transceiver module 6201 and a processing module 6202. The transceiver module 6201 is configured to receive a first message sent by a terminal and / or send a second message to the terminal. The first message and / or the second message are related to updating of an artificial intelligence (AI) model parameter of the terminal.

[0259] In some embodiments, the first message includes at least one of: first information used to query whether the network device provides an AI model parameter updating service; second information used to query a first model structure, the network device supporting the AI model parameter updating service for an AI model of the first model structure; and third information used to indicate a second model structure, the terminal deploying an AI model of the second model structure.

[0260] In some embodiments, the first message includes the first information, and the method further includes: sending, by the network device, a third message to the terminal, the third message including at least one of: fourth information used to query the second model structure; and fifth information used to indicate the first model structure.

[0261] In some embodiments, the transceiver module 6201 is further configured to send an AI model parameter to the terminal.

[0262] In some embodiments, the network device sends the second message to the terminal, including: determining, by the network device, that a second preset condition is met, and sending the second message to the terminal.

[0263] In some embodiments, the second preset condition includes at least one of: the AI model of the terminal is converted from an activated state to a deactivated state; an AI function of the terminal is converted from an activated state to a deactivated state, the AI function corresponding to at least one AI model; the terminal requests to deactivate an AI model, and the reason for the request is that a complexity of running the AI model is higher than a first threshold; the terminal requests to deactivate an AI function, the AI function corresponding to at least one AI model, and the reason for the request is that a complexity of running the AI function is higher than a second threshold; and an AI model performance of the terminal is lower than a third threshold.

[0264] In some embodiments, the second message comprises at least one of: sixth information used to indicate that the network device provides an update service for AI model parameters; seventh information used to indicate a first model structure, the network device supports the update service for AI model parameters for an AI model of the first model structure; eighth information used to query whether the terminal has the capability of performing the update of AI model parameters; and ninth information used to instruct the terminal to download AI model parameters.

[0265] In some embodiments, the transceiver module 6201 is further configured to: receive, by the network device, a fourth message sent by the terminal, the fourth message being used to request the network device to perform the update of AI model parameters for an AI model of at least one model structure.

[0266] FIG. 7a is a structural schematic diagram of a communication device according to an embodiment of the present disclosure. The communication device 7100 can be a network device, a terminal, a chip, a chip system, or a processor supporting the network device to implement any of the above methods, or a chip, a chip system, or a processor supporting the terminal to implement any of the above methods. Optionally, the network device can be an access network device, a core network device, etc. Optionally, the terminal can be a user equipment, etc. The communication device 7100 can be used to implement the methods described in the above method embodiments, and details can be referred to the descriptions in the above method embodiments.

[0267] As shown in FIG. 7a, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a special-purpose processor, etc., for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device, execute programs, and process data of the programs. The communication device 7100 is used to execute any of the above methods. Optionally, the communication device can be a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.

[0268] In some embodiments, the communication device 7100 further includes one or more memories 7102 used to store instructions. Optionally, all or part of the memory 7102 can also be outside the communication device 7100.

[0269] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the transceiver 7103 performs the communication steps S2101 such as sending and / or receiving in the above methods, and the processor 7101 performs other steps.

[0270] In some embodiments, the transceiver can include a receiver and / or a transmitter, which can be separate or integrated together. Optionally, the terms transceiver, transceiving unit, transceiver, transceiving circuit, etc. can be replaced by each other, the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced by each other, and the terms receiver, receiving unit, receiver, receiving circuit, etc. can be replaced by each other.

[0271] In some embodiments, the communication device 7100 can include one or more interface circuits 7104. Optionally, the interface circuit 7104 is connected with the memory 7102, and the interface circuit 7104 can be used to receive signals from the memory 7102 or other devices, and can be used to send signals to the memory 7102 or other devices. For example, the interface circuit 7104 can read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0272] The communication device 7100 described in the above embodiments can be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 can not be limited by Figure 7a. The communication device can be a standalone device or can be part of a larger device. For example, the communication device can be: 1) a standalone integrated circuit (IC), or a chip, or a chip system or subsystem; (2) a set of one or more ICs, which can optionally also include storage components for storing data, programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, intelligent terminal device, cellular phone, wireless device, handset, mobile unit, vehicle-mounted device, network device, cloud device, artificial intelligence device, etc.; (6) other, etc.

[0273] Figure 7b is a schematic diagram of a chip structure according to an embodiment of the present disclosure. For the case where the communication device 7100 is a chip or a chip system, the structure of the chip 7200 can be referred to the schematic diagram of the chip 7200 shown in Figure 7b, but is not limited thereto.

[0274] The chip 7200 includes one or more processors 7201, and the chip 7200 is configured to execute any of the above methods.

[0275] In some embodiments, the chip 7200 further includes one or more interface circuits 7202. Optionally, the interface circuit 7202 is connected with the memory 7203, and the interface circuit 7202 can be used to receive signals from the memory 7203 or other devices, and can be used to send signals to the memory 7203 or other devices. For example, the interface circuit 7202 can read instructions stored in the memory 7203 and send the instructions to the processor 7201.

[0276] In some embodiments, the interface circuit 7202 performs communication steps S2101 such as transmitting and / or receiving in the above-described methods, and the processor 7201 performs other steps.

[0277] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, and the like can be replaced by each other.

[0278] In some embodiments, the chip 7200 further includes one or more memories 7203 for storing instructions. Optionally, all or part of the memories 7203 can be outside the chip 7200.

[0279] The disclosure also proposes a storage medium having instructions stored thereon, which, when executed on the communication device 7100, causes 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 is not limited to this, and it can also be a storage medium readable by other devices. Optionally, the storage medium can be a non-transitory storage medium, but is not limited to this, and it can also be a transitory storage medium.

[0280] The disclosure also proposes a program product which, 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.

[0281] The disclosure also proposes a computer program which, when executed on a computer, causes the computer to perform any of the above methods.

Claims

1. A communication method characterized by comprising: The method comprises: The terminal sends a first message to the network device, and / or the terminal receives a second message sent by the network device; The first message and / or the second message are related to updating of artificial intelligence (AI) model parameters of the terminal.

2. The method of claim 1, wherein, The terminal sends a first message to the network device, comprising: The terminal determines that a first preset condition is met, and sends a first message to the network device.

3. The method of claim 2, wherein, The first preset condition comprises at least one of the following: The terminal has no available AI model parameters; The terminal requests to deactivate an AI model, and the reason for the request is that complexity of running the AI model is higher than a first threshold value; The terminal requests to deactivate an AI function, the AI function corresponds to at least one AI model, and the reason for the request is that complexity of running the AI function is higher than a second threshold value; AI model performance of the terminal is lower than a third threshold value.

4. The method according to any one of claims 1 to 3, characterized in that, The first message comprises at least one of the following: First information used to query whether the network device provides an AI model parameter updating service; Second information used to query a first model structure, the network device supports providing an AI model parameter updating service for an AI model of the first model structure; Third information used to indicate a second model structure, the terminal deploys an AI model of the second model structure.

5. The method of claim 4, wherein, The first message comprises the first information, and the method further comprises: The terminal receives a third message sent by the network device, the third message comprising at least one of the following: Fourth information used to query the second model structure; Fifth information used to indicate the first model structure.

6. The method according to any one of claims 2-5, characterized in that, The method further comprises: The terminal receives AI model parameters sent by the network device.

7. The method of claim 1, wherein, The second message comprises at least one of the following: Sixth information used to indicate that the network device provides an AI model parameter updating service; Seventh information used to indicate a first model structure, the network device supports providing an AI model parameter updating service for an AI model of the first model structure; Eighth information used to query whether the terminal has the capability of updating AI model parameters; Ninth information used to indicate that the terminal downloads AI model parameters.

8. The method of claim 7, wherein, The method further comprises: The terminal sends a fourth message to the network device, the fourth message being used to request the network device to update AI model parameters of AI models of at least one model structure.

9. A communication method characterized by comprising: The method comprises: The network device receives a first message sent by a terminal, and / or the network device sends a second message to the terminal; The first message and / or the second message are related to updating of artificial intelligence (AI) model parameters of the terminal.

10. The method of claim 9, wherein, The first message comprises at least one of the following: First information used to query whether the network device provides an AI model parameter updating service; Second information used for querying a first model structure, the network device supporting an AI model parameter update service for an AI model of the first model structure; Third information used for indicating a second model structure, the terminal deploying an AI model of the second model structure.

11. The method of claim 10, wherein, The first message includes the first information, and the method further includes: The network device sends a third message to the terminal, the third message including at least one of the following: Fourth information used for querying the second model structure; Fifth information used for indicating the first model structure.

12. The method according to any of claims 10-11, characterized by, The method further includes: The network device sends an AI model parameter to the terminal.

13. The method of claim 9, wherein, The network device sends a second message to the terminal, including: The network device determines that a second preset condition is met, and sends the second message to the terminal.

14. The method of claim 13, wherein, The second preset condition includes at least one of the following: The AI model of the terminal is converted from an activated state to a deactivated state; The AI function of the terminal is converted from an activated state to a deactivated state, the AI function corresponding to at least one AI model; The terminal requests to deactivate an AI model, and the reason for the request is that the complexity of running the AI model is higher than a first threshold value; The terminal requests to deactivate an AI function, the AI function corresponding to at least one AI model, and the reason for the request is that the complexity of running the AI function is higher than a second threshold value; The AI model performance of the terminal is lower than a third threshold value.

15. The method according to any one of claims 9-14, characterized in that, The second message includes at least one of the following: Sixth information used for indicating that the network device provides an AI model parameter update service; Seventh information used for indicating a first model structure, the network device supporting an AI model parameter update service for an AI model of the first model structure; Eighth information used for querying whether the terminal has the capability of updating an AI model parameter; Ninth information used for indicating that the terminal downloads an AI model parameter.

16. The method of claim 15, wherein, The method further includes: The network device receives a fourth message sent by the terminal, the fourth message being used for requesting the network device to update an AI model parameter of an AI model of at least one model structure.

17. A terminal, characterized by Including: A transceiver module, configured to send a first message to a network device and / or receive a second message sent by the network device; wherein the first message and / or the second message are related to an artificial intelligence (AI) model parameter update of the terminal.

18. A network device, comprising: Including: A transceiver module, configured to receive a first message sent by a terminal and / or send a second message to the terminal; wherein the first message and / or the second message are related to an artificial intelligence (AI) model parameter update of the terminal.

19. A communications device, characterized by Including: One or more processors; wherein the processor is configured to perform the communication method of any one of claims 1-8.

20. A communications device, characterized by Including: One or more processors; wherein the processor is configured to perform the communication method of any one of claims 9-16.

21. A storage medium, characterized by Including: The storage medium stores instructions which, when executed on the communication device, cause the communication device to perform the communication method of any one of claims 1-8 or 9-16.

22. A program product, characterized by comprising: A computer program which, when executed by a communication device, causes the communication device to perform the communication method of any one of claims 1-8 or 9-16.

Images