Control method and related device

Abstract

The invention provides a control method and a related device. The method comprises the following steps of: generating a control message in a natural language form by using a language model (LM); obtaining semantic information of the control message according to the control message; forming an information payload, the information payload comprising the semantic information of the control message; and sending the information payload. Through the control method and the related device disclosed by the invention, open vocabularies can be supported in control, more efficient communication can be realized, forward and backward compatibility can be supported, and a cross-modal function can be adapted.

Description

Cross-references to related applications

[0001] This application claims priority to U.S. Provisional Application No. 63 / 582,307, filed September 13, 2023. The disclosure of the aforementioned patent application is incorporated herein by reference in its entirety. Technical Field

[0002] This disclosure relates to the field of wireless communication technology, and in particular to a control method, apparatus, device, system and storage medium. Background Technology

[0003] Communication can be divided into three levels: bit communication, semantic communication, and validity communication. For the past 60 years, wireless communication has primarily focused on the lowest level, bit communication—the so-called "technical problem"—ensuring the absolute accuracy of bits transmitted from the sender to the receiver. Validity communication, at the highest level, aims to achieve the ultimate goal of communication—the so-called "validity problem"—ensuring that the semantic meaning conveyed to the receiver elicits the desired behavior at the receiver.

[0004] The purpose of describing this background information is to disclose information that the applicant believes may be relevant to this disclosure, and it is not necessarily an admission that such information constitutes prior art relative to this disclosure. Summary of the Invention

[0005] In a first aspect, embodiments of this disclosure provide a control method, the method comprising:

[0006] Use a language model (LM) to generate control messages in natural language form;

[0007] Obtain the semantic information of the control message based on the control message;

[0008] An information payload is formed, wherein the information payload includes the semantic information of the control message;

[0009] Send the aforementioned information payload.

[0010] The central device generates control messages in natural language and forms an information payload that includes semantic information of the control messages to control user equipment. This allows for support of open vocabularies in control, more efficient communication, forward and backward compatibility, and adaptation to cross-modal functions.

[0011] In one possible implementation of the first aspect, the LM can be a language learning model (LLM).

[0012] In one possible implementation of the first aspect, the method further includes: obtaining registration information of a functional modality, wherein the registration information of the functional modality includes a description of the functional modality, the description being in the natural language form.

[0013] In one possible implementation of the first aspect, the registration information of the functional modality further includes a parameter list of the functional modality.

[0014] In one possible implementation of the first aspect, the method further includes: registering the functional modality with the LM.

[0015] Because the registration information for functional modalities includes descriptions in natural language or a list of parameters, the system can adapt to cross-modal functions and support forward and backward compatibility. Furthermore, when new functional modalities are added, they can be registered along with their corresponding natural language descriptions without changing the system architecture or communication protocols, which improves the system's versatility and makes it more flexible.

[0016] In one possible implementation of the first aspect, the method further includes: recording the registration information of the functional modality. After obtaining the registration information, it can be stored locally for later use, thereby facilitating subsequent maintenance.

[0017] In one possible implementation of the first aspect, the method further includes: recording information indicating a user equipment identifier (ID), wherein the registration information of the functional mode is received from the user equipment. The central device may record the user equipment ID and registration information indicating the user equipment for further use, to more directly invoke the corresponding functional modes of different user equipment without additional communication or negotiation, thereby helping to optimize the utilization of transmission resources.

[0018] In one possible implementation of the first aspect, the method further includes: acquiring semantic information of the functional modality via an embedder based on the description of the functional modality. The embedder can translate, embed, or lexicalize the description in natural language form into semantic information, thereby giving the semantic information a more structured and machine-readable format, and typically a smaller size compared to the description in natural language form.

[0019] In one possible implementation of the first aspect, the method further includes storing the semantic information of the functional modality. After obtaining the semantic information of the functional modality, it can be stored locally for future use, thus eliminating the need to translate the description every time it is used, facilitating subsequent use, reducing the processing overhead of description translation, and lowering communication latency.

[0020] In one possible implementation of the first aspect, the method further includes: transmitting the semantic information of the functional modality. The central device can transmit the semantic information of the functional modality, particularly when the user equipment cannot run any transformation-based embedders, thereby improving system compatibility and flexibility.

[0021] In one possible implementation of the first aspect, before forming the information payload, the method further includes: determining the correlation between the semantic information of the control message and the semantic information of each of at least one registered functional modalities, wherein the semantic information of each of the at least one functional modalities is obtained based on the description of each of the at least one functional modalities.

[0022] In one possible implementation of the first aspect, the method further includes: determining that the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities is less than a threshold; and rejecting the control message.

[0023] The central device determines whether a control message is registered by comparing its semantic information with the semantic information of at least one registered functional modality. If the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modality is below a threshold, the control message is determined to be unregistered, and the central device rejects it. The central device can avoid encoding or transmitting unregistered control messages and can multicast or unicast the control message only to user devices that have registered the corresponding functional modality, thereby saving power consumption for both the central device and user devices, and conserving transmission resources.

[0024] In one possible implementation of the first aspect, obtaining the semantic information of the control message based on the control message includes: determining a portion of the control message that does not contain any parameters; and obtaining the semantic information of the control message through an embedder based on the portion. The generated control message may include a list of parameters (values). The central device can divide the control message into two parts: a first part including the parameter list (if any), and a second part including the remaining parts of the control message. The central device only translates the second part into semantic information. Since the second part translated into semantic information does not include potentially changing parameters (values), the semantic information of the control message can be highly correlated with the semantic information of the corresponding functional modality. This helps the central device determine whether the control message is a registered message, helps the user device determine the corresponding functional modality, reduces computational complexity, and helps standardize the length of the semantic information.

[0025] In one possible implementation of the first aspect, forming the information payload includes:

[0026] A first information payload is formed, wherein the first information payload includes the starting position information of the second transmission opportunity and the length information of the semantic information;

[0027] A second information payload is formed, wherein the second information payload includes the semantic information of the control message, and the second transmission opportunity is used to transmit the second information payload information.

[0028] The central device can generate a first information payload and a second information payload to transmit control messages, which helps to utilize wireless resources more efficiently and provides greater flexibility in error correction and retransmission. Since the first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information, the receiving device can synchronize and correctly receive the second information payload.

[0029] In one possible implementation of the first aspect, the control message further includes a parameter list, and the first information payload further includes the parameter list of the control message.

[0030] In one possible implementation of the first aspect, the method further includes: encoding the second information payload using a first encoding method, wherein the first information payload further includes information from the first encoding method. By including the first encoding method for encoding the second information payload in the first information payload, the user equipment can immediately identify a suitable encoding scheme required for decoding the subsequent second information payload.

[0031] In one possible implementation of the first aspect, the method further includes: encoding the first information payload using a second encoding method.

[0032] In one possible implementation of the first aspect, the first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

[0033] In one possible implementation of the first aspect, the method further includes:

[0034] Based on the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities, the semantic information most relevant to the semantic information of the control message is determined from the semantic information of each of the at least one registered functional modalities.

[0035] Determine at least one user equipment ID or at least one group of user equipment IDs corresponding to the most relevant semantic information, wherein,

[0036] The first information payload further includes the at least one user equipment ID, or the at least one group of user equipment IDs; or the first information payload further includes information indicating the at least one user equipment ID, or information indicating the at least one group of user equipment IDs.

[0037] The central device can determine the specific functional mode targeted by the control message and the corresponding user equipment (UE) or group of UE to which the control message should be sent. This ensures that the control message is delivered to the intended recipient, thereby improving the efficiency and accuracy of the communication system. Furthermore, since the first information payload includes a UE ID or group of UE IDs, or information indicating either a UE ID or group of UE IDs, the receiving UE can determine whether it is the correct recipient based on the first information payload, further improving the efficiency and accuracy of the communication system. When the receiving UE is not the intended recipient, the UE can stop decoding the second information payload, thus saving energy.

[0038] In one possible implementation of the first aspect, the information indicating the at least one user equipment ID includes a first code generated based on the at least one user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or the information indicating the at least one group of user equipment IDs includes a second code generated based on the at least one group of user equipment IDs, wherein the second code includes a mask, a spreading code, or an interleaving code.

[0039] In one possible implementation of the first aspect, the method further includes: generating the first code based on the at least one user equipment ID; or generating the second code based on the at least one group of user equipment IDs.

[0040] User equipment IDs or group user equipment IDs can be indicated by codes generated based on them. Instead of transmitting user equipment identifiers or group user equipment identifiers as part of the primary information payload, they can be used to generate masks, spreading codes, or interleaving codes. This provides greater system flexibility and supports blind detection and early termination to save user equipment power.

[0041] In one possible implementation of the first aspect, the information payload being transmitted includes:

[0042] The first information payload is transmitted during the first transmission opportunity.

[0043] The second information payload is transmitted during the second transmission opportunity.

[0044] The central device can transmit the first information payload and the second information payload during the first and second transmission opportunities, respectively. Therefore, the central device can allocate radio resources more efficiently by assigning different transmission opportunities to each payload, thereby helping to prevent congestion and ensure smooth information transmission.

[0045] In one possible implementation of the first aspect, the first transmitter is located in a control physical channel, and the second transmitter is located in a data physical channel; or both the first and second transmitters are located in the control physical channel; or both the first and second transmitters are located in the data physical channel. These different configurations enable flexible radio resource management and efficient transmission of control and data information within the communication system.

[0046] In one possible implementation of the first aspect, registering the functional modality with the LM comprises: registering the functional modality with the at least one LM by providing the registration information of the functional modality to the at least one LM, wherein the at least one LM includes the LM.

[0047] In one possible implementation of the first aspect, the method further includes: sending configuration information of at least one embedder, wherein the embedder belongs to the at least one embedder.

[0048] In one possible implementation of the first aspect, the configuration information of the at least one embedder is sent via a broadcast message, a multicast message, or a unicast message.

[0049] One or more Learning Models (LMs) can exist, and each LM can include one or more embedders. Functional modalities can be registered to at least one of the LMs. Different LMs or embedders can be compatible with different types of communication systems or used for different application scenarios. Deploying multiple LMs on a central device can enhance the flexibility and customizability of the system. When different embedders are built based on different domains, specializing the vocabulary can significantly reduce the size and cost of the embedders, while also improving the accuracy of relevance calculations.

[0050] In one possible implementation of the first aspect, the configuration information of the at least one embedder includes the architecture and parameters of each of the at least one embedder.

[0051] In one possible implementation of the first aspect, the configuration information of the at least one embedder further includes the embedder ID of each of the at least one embedder.

[0052] The configuration information of an embedder may include the architecture and parameters of each embedder, and may also include the embedder ID of each embedder, so as to configure each embedder to the user device.

[0053] In one possible implementation of the first aspect, the first information payload further includes: information indicating an embedder ID for an embedder used to acquire the semantic information of the control message. The central device may include information indicating an embedder ID for acquiring the semantic information of the control message, thereby improving the accuracy of user equipment decision-making.

[0054] In one possible implementation of the first aspect, the information payload is sent via multicast or unicast messages.

[0055] In one possible implementation of the first aspect, the method further includes:

[0056] In response to the LM generating at least two consecutive control messages more than a preset number of times, the two functional modes corresponding to the at least two consecutive control messages are combined to generate a combined functional mode;

[0057] Send the configuration information for the combined functional mode.

[0058] In one possible implementation of the first aspect, the method further includes: registering the combined functional mode with the LM.

[0059] If the central device continuously generates at least two consecutive control messages for the user equipment, the functional modes corresponding to the at least two control messages can be combined into one functional mode, thereby enhancing efficiency by simplifying the execution of multiple functions when the combined functional mode is invoked once.

[0060] In one possible implementation of the first aspect, there are multiple LMs, wherein each of the multiple LMs has at least one embedder.

[0061] In one possible implementation of the first aspect, the at least one functional mode is registered in one or more of the plurality of LMs, but not in all of the plurality of LMs.

[0062] Multiple control messages (LMs) can exist, and different LMs can be developed by different companies or used for different specific purposes. This can reduce the size and cost of LMs, improve the effectiveness of generated control messages, improve the resource utilization of central equipment, and improve overall efficiency.

[0063] In one possible implementation of the first aspect, the plurality of LMs includes at least one LM compatible with the LTE system.

[0064] In one possible implementation of the first aspect, the plurality of LMs includes at least one LM compatible with a 5G system.

[0065] In one possible implementation of the first aspect, the first LM of the plurality of LMs has a first embedder, the second LM of the plurality of LMs has a second embedder, and the first embedder and the second embedder are constructed based on vocabularies from different domains.

[0066] In one possible implementation of the first aspect, the LM has a first embeddinger and a second embeddinger constructed based on vocabularies from different domains.

[0067] Multiple LMs can be compatible with different systems, or a single LM can have multiple embedders, each built based on a vocabulary from a different domain. Specializing the vocabulary can reduce the size and cost of the embedders, while also improving the accuracy of relevance calculation.

[0068] In one possible implementation of the first aspect, the method further includes: registering the LM.

[0069] In one possible implementation of the first aspect, the method further includes: registering at least one embedder of the LM.

[0070] Registration of LMs or their embedders enables the system to recognize and utilize LMs and their embedders, thereby achieving efficient natural language processing and improving system performance.

[0071] Secondly, embodiments of this disclosure provide a control method, the method comprising:

[0072] Acquire information payload, wherein the information payload includes semantic information of control messages;

[0073] Based on the semantic information of the control message, target semantic information is determined from at least one piece of semantic information, wherein each piece of semantic information corresponds to a corresponding functional modality in at least one functional modality, and is obtained based on the description of the corresponding functional modality, the description of the corresponding functional modality being in natural language form;

[0074] Execute the functional modality corresponding to the target semantic information.

[0075] User equipment can acquire information payloads including semantic information from control messages, determine target semantic information based on control messages, and execute corresponding functional modalities. This enables support for open vocabularies in control, achieves more efficient communication, supports forward and backward compatibility, and adapts to cross-modal functions.

[0076] In one possible implementation of the second aspect, the method further includes: encapsulating each of the at least one functional modalities as a calling function, wherein the calling function of the corresponding functional modality includes the description of the corresponding functional modality, or the calling function of the corresponding functional modality includes a parameter list of the corresponding functional modality and the description of the corresponding functional modality.

[0077] In one possible implementation of the second aspect, the calling function includes an application programming interface (API) calling function.

[0078] Since each functional modality can be encapsulated as a function call (such as an API call function), the functional modality can be executed by calling that function call. Function call can be implemented in various programming languages. By encapsulating each functional modality in at least one functional modality as a function call, it facilitates easier integration and use with different programming languages ​​and promotes interoperability between different systems or components that may be developed using different technologies.

[0079] In one possible implementation of the second aspect, the method further includes: sending registration information for each of the at least one functional modalities, wherein the registration information for each functional modality includes the description of the corresponding functional modality, or the registration information for each functional modality includes a parameter list of the corresponding functional modality and the description of the corresponding functional modality.

[0080] Because the registration information for functional modalities includes descriptions in natural language or a list of parameters, the system can adapt to cross-modal functions and support forward and backward compatibility. Furthermore, when new functional modalities are added, they can be registered along with their corresponding natural language descriptions without changing the system architecture or communication protocols, which improves the system's versatility and makes it more flexible.

[0081] In one possible implementation of the second aspect, the acquisition of the information payload includes:

[0082] During the first transmission opportunity, a first information payload is acquired, wherein the first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information of the control message;

[0083] The first information payload is decoded to obtain the starting position information of the second transmission opportunity and the length information of the semantic information of the control message;

[0084] Based on the starting position information of the second transmission opportunity and the length information of the semantic information of the control message, a second information payload is acquired during the second transmission opportunity, wherein the second information payload includes the semantic information of the control message;

[0085] The second information payload is decoded to obtain the semantic information of the control message.

[0086] User equipment can acquire the first information payload and the second information payload during the first transmission opportunity and the second transmission opportunity, respectively. Therefore, by allocating different transmission opportunities for each payload, radio resources can be allocated more efficiently, and the process of acquiring and decoding the information payload ensures reliable retrieval of the semantic information of the control message.

[0087] In one possible implementation of the second aspect, the first information payload further includes: a parameter list of the control message.

[0088] In one possible implementation of the second aspect, the first information payload further includes information about a first encoding method, and the second information payload is decoded using the first encoding method. By including the first encoding method for encoding the second information payload in the first information payload, the user equipment can immediately identify a suitable encoding scheme required for decoding the subsequent second information payload.

[0089] In one possible implementation of the second aspect, a second encoding method is used to decode the first information payload.

[0090] In one possible implementation of the second aspect, the first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

[0091] In one possible implementation of the second aspect, the first information payload further includes: information indicating a user equipment identifier (ID) or information indicating a group of user equipment IDs.

[0092] Since the first information payload includes information indicating the user equipment ID or information indicating the group user equipment ID, the user equipment can determine whether it is the correct receiver based on the first information payload, thereby improving the efficiency and accuracy of the communication system.

[0093] In one possible implementation of the second aspect, the method further includes: acquiring a first code generated based on information indicating a user equipment ID, wherein the code includes a mask, a spreading code, or an interleaving code; or acquiring a second code generated based on information indicating a group user equipment ID, wherein the code includes a mask, a spreading code, or an interleaving code. Instead of transmitting the user equipment identifier or group user equipment identifier as part of the first information payload, the mask, spreading code, or interleaving code can be obtained using the user equipment identifier or group user equipment identifier. This supports blind detection and early termination to save user equipment power consumption.

[0094] In one possible implementation of the second aspect, the method further includes: stopping the decoding of the second information payload in response to determining that the user equipment ID or the group user equipment ID does not match the user equipment ID or group user equipment ID of the user equipment. When the user equipment identifier is indicated in the first information payload, if the user equipment finds that the decoded user equipment ID or group user equipment ID does not match itself, the user equipment can stop decoding the second information payload, thereby saving the user equipment's energy consumption and processing resources.

[0095] In one possible implementation of the second aspect, the method further includes: obtaining configuration information for at least one embedder. Using the configuration information of the at least one embedder, the at least one embedder can be configured to the user device, which can then use the at least one embedder to translate the description of the functional modality into semantic information.

[0096] In one possible implementation of the second aspect, the semantic information of the control message is obtained through a first embeddinger among the at least one embeddingers, and the at least one piece of semantic information of the at least one functional modality is obtained through the first embeddinger. Since the user equipment can compare the semantic information of the control message with candidate semantic information obtained using the same embeddinger, the accuracy and reliability of the comparison results are improved.

[0097] In one possible implementation of the second aspect, the configuration information of the at least one embedder includes the embedder ID of each of the at least one embedder. By including the embedder ID of each of the at least one embedder in the configuration, it is easier to track and manage specific embedders that are in use or that need to be updated or maintained.

[0098] In one possible implementation of the second aspect, the information payload includes information indicating the embedder ID of the first embedder.

[0099] In one possible implementation of the second aspect, the information indicating the embedder ID of the first embedder is carried in the first information payload.

[0100] In one possible implementation of the second aspect, the method further includes:

[0101] Based on the description of each of the at least one functional modalities, one or more pieces of semantic information are obtained through the at least one embeddinger, wherein for each of the at least one functional modalities, each of the at least one embeddingers is used to obtain the corresponding semantic information;

[0102] Store one or more pieces of semantic information.

[0103] The user equipment can use each of at least one embedder to acquire a corresponding semantic information for each of at least one functional modality, and can store the acquired semantic information, thereby enabling the user equipment to quickly access and utilize the semantic information when needed.

[0104] In one possible implementation of the second aspect, the method further includes: obtaining at least one semantic information of the at least one functional modality from the stored one or more semantic information based on the information indicating the embedder ID of the first embedder. When the semantic information of each functional modality has been stored in the user equipment, the user equipment can obtain candidate semantic information from the stored semantic information based on the embedder ID information, thereby determining the target semantic information.

[0105] In one possible implementation of the second aspect, after obtaining the information payload, the method further includes: obtaining at least one piece of semantic information of the at least one functional modality through the first embedder, based on the description of each of the at least one functional modality. In some cases, the candidate semantic information is not stored in the user device, for example, when the user device has limited storage, or when the embedder has just been configured or updated. The user device can obtain the candidate semantic information through the corresponding embedder.

[0106] In one possible implementation of the second aspect, the method further includes receiving the at least one piece of semantic information for the at least one functional modality. The user equipment can receive semantic information from other devices, particularly when the user equipment cannot run any transformation-based embedders, thereby improving system compatibility and flexibility.

[0107] In one possible implementation of the second aspect, determining the target semantic information includes: determining, from the at least one piece of semantic information, the one most relevant to the semantic information of the control message as the target semantic information.

[0108] In one possible implementation of the second aspect, there is more than one functional modality, and the method further includes:

[0109] Obtain configuration information for a combined functional mode, wherein the combined functional mode is composed of at least two functional modes from the one or more functional modes;

[0110] The combined functional modality is encapsulated as a first calling function.

[0111] If the central device continuously generates at least two consecutive control messages for the user equipment, the functional modes corresponding to the at least two control messages can be combined into one functional mode, thereby enhancing efficiency by simplifying the execution of multiple functions when the combined functional mode is invoked once.

[0112] In one possible implementation of the second aspect, the configuration information of the combined functional modal includes a calling order, wherein the first calling function calls the calling functions corresponding to the at least two functional modalities in the calling order.

[0113] Combining functions sequentially calls multiple calling functions. As runtime increases, combined function modalities that encapsulate multiple legacy function modalities in a certain order are created, thereby improving efficiency.

[0114] Thirdly, embodiments of this disclosure provide a first apparatus including modules for performing the control method according to the first aspect or any possible implementation thereof.

[0115] Fourthly, embodiments of this disclosure provide a second apparatus comprising modules for performing the control method according to the second aspect or any possible implementation thereof.

[0116] Fifthly, embodiments of this disclosure provide a third apparatus including a processing circuit for performing the control method according to the first aspect or any possible implementation thereof.

[0117] In a sixth aspect, embodiments of this disclosure provide a fourth apparatus including a processing circuit for performing the control method according to the second aspect or any possible implementation thereof.

[0118] In a seventh aspect, embodiments of this disclosure provide a communication system including a first device according to a third aspect or a third device according to a fifth aspect, and a second device according to a fourth aspect or a fourth device according to a sixth aspect.

[0119] Eighthly, embodiments of this disclosure provide a computer-readable medium storing computer-executable instructions, which, when executed by a processor, cause the processor to perform the control method according to the first aspect or any possible implementation thereof, or according to the second aspect or any possible implementation thereof.

[0120] In a ninth aspect, embodiments of this disclosure provide a computer program product including computer-executable instructions, which, when executed by a processor, cause the processor to perform the control method according to the first aspect or any possible implementation thereof, or according to the second aspect or any possible implementation thereof.

[0121] This disclosure provides a control method and related apparatus. A control message in natural language form is generated using a programming model (LM); semantic information of the control message is obtained based on the control message; an information payload is formed, wherein the information payload includes the semantic information of the control message; and the information payload is transmitted. This allows for support of open vocabularies in control, enables more efficient communication, supports forward and backward compatibility, and adapts to cross-modal functions. Attached Figure Description

[0122] The following drawings, by way of example, illustrate exemplary embodiments of the present disclosure, in which:

[0123] Figure 1 This is a simplified schematic diagram of a communication system according to one or more embodiments of the present disclosure.

[0124] Figure 2 This is a schematic diagram of an exemplary communication system according to one or more embodiments of the present disclosure.

[0125] Figure 3 This is a schematic diagram of the basic component structure of a communication system according to one or more embodiments of the present disclosure.

[0126] Figure 4 This is a block diagram of a device in a communication system according to one or more embodiments of the present disclosure.

[0127] Figure 5 This is a schematic diagram of a communication system.

[0128] Figure 6 This is a communication diagram between the central equipment and the first user equipment.

[0129] Figure 7 This is a schematic diagram of an LLM model according to one or more embodiments of the present disclosure.

[0130] Figure 8 A schematic flowchart of a control method according to one or more exemplary embodiments of the present disclosure is shown.

[0131] Figure 9 A schematic flowchart of a control method according to one or more exemplary embodiments of the present disclosure is shown.

[0132] Figure 10 A schematic flowchart of a registration process according to one or more embodiments of the present disclosure is shown.

[0133] Figure 11 This is a schematic diagram of a central device according to one or more embodiments of the present disclosure.

[0134] Figure 12 This is a schematic diagram of the configuration of an embedder according to one or more embodiments of the present disclosure.

[0135] Figure 13 This is a schematic diagram of functional modes according to one or more embodiments of the present disclosure.

[0136] Figure 14 This is a schematic diagram of functional modes according to one or more embodiments of the present disclosure.

[0137] Figure 15 This is a schematic diagram illustrating an example of obtaining a semantic vector according to one or more embodiments of this disclosure.

[0138] Figure 16 This is a schematic diagram illustrating an example of a user equipment notifying a central device of registration information of a functional mode according to one or more embodiments of the present disclosure.

[0139] Figure 17 This is a schematic diagram illustrating an example of a central device registration function mode according to one or more embodiments of the present disclosure.

[0140] Figure 18 This is a schematic diagram illustrating an example of a central device recording a second user device according to one or more embodiments of the present disclosure.

[0141] Figure 19 This is a schematic diagram illustrating an example of generating control messages according to one or more embodiments of the present disclosure.

[0142] Figure 20 This is a schematic diagram illustrating an example of a correlation comparison process according to one or more embodiments of the present disclosure.

[0143] Figure 21 This is a schematic diagram illustrating an example of a central device encoding and transmitting open-voc control messages in two transmission opportunities, according to one or more embodiments of this disclosure.

[0144] Figure 22 This is a schematic diagram illustrating an example of a user equipment decoding and receiving open-voc control messages in two transmission opportunities, according to one or more embodiments of this disclosure.

[0145] Figure 23 This is a schematic diagram illustrating an example of a user equipment execution process according to one or more embodiments of the present disclosure.

[0146] Figure 24 A schematic diagram of the structure of a first device according to one or more exemplary embodiments of the present disclosure is shown.

[0147] Figure 25 A schematic diagram of the structure of a second device according to one or more exemplary embodiments of the present disclosure is shown. Detailed Implementation

[0148] In the following description, reference is made to the accompanying drawings, which form a part of this disclosure, which illustrate by way of description specific aspects of embodiments of this disclosure or aspects that may be used with embodiments of this disclosure. It should be understood that embodiments of this disclosure can be used in other aspects and include structural or logical variations not depicted in the drawings. Therefore, the following detailed description should not be construed in a limiting sense, and the scope of this disclosure is defined by the appended claims.

[0149] To more clearly describe the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings required for describing the embodiments or the prior art are briefly introduced below.

[0150] Communication can be divided into three levels: bit communication, semantic communication, and validity communication. For the past 60 years, wireless communication has primarily focused on the lowest level, bit communication, the so-called "technical problem," ensuring the absolute accuracy of bits transmitted from the sender to the receiver. Validity communication, at the highest level, aims to achieve the ultimate goal of communication, the so-called "validity problem," ensuring that the semantic meaning conveyed to the receiver elicits the desired behavior at the receiver.

[0151] Wireless communication systems rely heavily on pre-negotiated (standardized) control message content and format, which can lead to forward and / or backward compatibility issues between different communication systems.

[0152] For illustrative purposes, specific exemplary embodiments are explained in detail below with reference to the accompanying drawings.

[0153] The embodiments described herein illustrate information sufficient for practice and explain methods for practicing this subject matter. Those skilled in the art will understand the concepts of the claimed subject matter upon reading the following description with reference to the accompanying drawings, and will recognize that the application of these concepts is not specifically mentioned herein. It should be understood that these concepts and applications are within the scope of this disclosure and the appended claims.

[0154] Furthermore, it should be understood that any module, component, or device disclosing executable instructions herein may include or otherwise access one or more non-transitory computer / processor-readable storage media for storing information, such as computer / processor-readable instructions, data structures, program modules, and / or other data. A non-exhaustive list of examples of non-transitory computer / processor-readable storage media includes: magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices; compact disc read-only memory (CD-ROM), digital video disc or digital multifunction disc (i.e., DVD), Blu-ray disc™, or other optical storage devices; volatile and non-volatile, removable and non-removable media, random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other storage technologies implemented in any method or technology. Any such non-transitory computer / processor storage medium may be part of, or accessed by, a device / apparatus. Computer / processor-readable / executable instructions used to implement the methods, applications, or modules described herein may be stored by such non-transitory computer / processor-readable storage media or otherwise preserved.

[0155] Furthermore, in this disclosure, when used in conjunction with the terms "comprising" or "including" in the claims and / or specification, the words "a" or "an" may refer to "one," but also have the same meaning as "one or more," "at least one," and "one or more," unless expressly otherwise specified. Similarly, the word "another" may refer to at least a second or more, unless expressly otherwise specified.

[0156] The terms “coupled to,” “coupled,” or “connected” as used herein may have several different meanings depending on the context in which they are used. For example, as used herein, the terms “coupled to,” “coupled,” or “connected” may indicate that two elements or devices are directly connected to each other, or are mechanically connected to each other via one or more intermediate elements or devices, depending on the specific context. The term “and / or” as used herein, when associated with a list of multiple items, means to include any one or more of the items that make up the list.

[0157] This disclosure provides a two-stage control message passing system method and apparatus for a wireless system. The wireless system includes a central device (also called a core device, such as a base station, core network, etc.) and at least one user equipment (such as a UE or other device). The following example illustrates a scenario where the central device transmits partial control messages to the user equipment. It should be noted that the scenario where the user equipment transmits partial control messages to the central device can be included in this disclosure in the same manner.

[0158] Figure 1 This is a simplified schematic diagram of a communication system according to one or more embodiments of the present disclosure.

[0159] refer to Figure 1 A simplified schematic diagram of a communication system is provided as an illustrative, not limiting, example. Communication system 100 (which may be...) Figure 1 The wireless system 100 includes a radio access network 120. The radio access network 120 can be a next-generation (e.g., sixth-generation, 6G or later) radio access network, or a traditional (e.g., 5G, 4G, 3G or 2G) radio access network. One or more communication electronic devices (EDs) 110a, 110b, 110c, 110d, 110e, 110f, 110g, 110h, 110i, 110j (commonly referred to as 110) can interconnect with each other or connect to one or more network nodes (170a, 170b, commonly referred to as 170) within the radio access network 120. A core network 130 can be part of the communication system 100 and can depend on or be independent of the radio access technology used in the communication system 100. Furthermore, the communication system 100 includes a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160.

[0160] Uplink messages / data transmitted between the central device (e.g., network node 170) and the sensing device (e.g., ED 180) can be carried in higher-level signaling such as RRC signaling or MAC layer signaling. Alternatively, these messages / data can be carried in physical layer signaling (e.g., UCI). Alternatively, these messages / data can be carried in a combination of higher-level signaling and physical signaling. It should be noted that "message" in this disclosure can be replaced with "information," which can be carried in a single message or more than one single message. Downlink messages / data transmitted between the central device and ED 110 can be carried in higher-level signaling such as RRC signaling or MAC layer signaling. Alternatively, these messages / data can be carried in physical layer signaling (e.g., UCI). Alternatively, these messages / data can be carried in a combination of higher-level signaling and physical signaling. It should be noted that "message" in this disclosure can be replaced with "information," which can be carried in a single message or more than one single message.

[0161] A custom network energy-saving implementation method could be considered, in which operators manually perform energy saving based on heuristics, traffic load management and balancing.

[0162] Figure 2 This is a schematic diagram of an exemplary communication system according to one or more embodiments of the present disclosure.

[0163] Figure 2 An exemplary communication system 100 is illustrated. Generally, the communication system 100 enables multiple wireless or wired components to transmit data and other content. The purpose of the communication system 100 may be to provide content such as voice, data, video, and / or text via broadcast, multicast, and unicast. The communication system 100 can operate by sharing resources such as carrier spectrum bandwidth among its constituent components. The communication system 100 may include terrestrial communication systems and / or non-terrestrial communication systems. The communication system 100 can provide a wide range of communication services and applications (e.g., earth monitoring, remote sensing, passive sensing and positioning, navigation and tracking, autonomous delivery and mobility, etc.). The communication system 100 can provide high availability and robustness through the joint operation of terrestrial and non-terrestrial communication systems. For example, integrating a non-terrestrial communication system (or components thereof) into a terrestrial communication system can create a heterogeneous network that can be considered as comprising multiple layers. Compared to traditional communication networks, heterogeneous networks can achieve better overall performance through efficient multi-link joint operation, more flexible function sharing, and faster physical layer link switching between terrestrial and non-terrestrial networks.

[0164] Terrestrial communication systems and non-terrestrial communication systems can be considered subsystems of a communication system. Figure 2In the example shown, communication system 100 includes electronic devices (EDs) 110a, 110b, 110c, and 110d (commonly referred to as ED110), radio access networks (RANs) 120a and 120b, a non-terrestrial communication network 120c, a core network 130, a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160. RANs 120a and 120b include corresponding base stations (BSs) 170a and 170b, which are commonly referred to as terrestrial transmit and receive points (T-TRPs) 170a and 170b. The non-terrestrial communication network 120c includes an access node 172, which is commonly referred to as a non-terrestrial transmit and receive point (NT-TRP) 172. Based on the similarity of the reference numerals in the attached figures, it can be inferred that the non-terrestrial communication network 120c can be considered a radio access network, and its operation is similar to that of RAN 120a and 120b. The non-terrestrial communication network 120c may include at least one non-terrestrial network (NTN) device and at least one corresponding terrestrial network device, wherein the at least one NTN device acts as a transport layer device, and the at least one corresponding terrestrial network device acts as a radio access network node, which communicates with the ED through the NTN device.

[0165] Alternatively or additionally, any ED 110 can be used to connect, access, or communicate with any T-TRP 170a, 170b, NT-TRP 172, Internet 150, core network 130, PSTN 140, other network 160, or any combination thereof. In some examples, ED 110a can perform uplink and / or downlink transmissions with T-TRP 170a via terrestrial air interface 190a. In some examples, ED 110a, 110b, 110c, and 110d can also communicate directly with each other via one or more sidelink air interfaces 190b. In some examples, ED 110d can perform uplink and / or downlink transmissions with NT-TRP 172 via non-terrestrial air interface 190c.

[0166] Air interfaces 190a and 190b can use similar communication technologies, such as any suitable wireless access technology. For example, communication system 100 can implement one or more channel access methods in air interfaces 190a and 190b, such as code division multiple access (CDMA), space division multiple access (SDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or single-carrier FDMA (SC-FDMA), also known as discrete Fourier transform spread OFDMA (DFT-s-OFDMA). Air interfaces 190a and 190b can utilize other higher-dimensional signal spaces, which may involve combinations of orthogonal and / or non-orthogonal dimensions.

[0167] The non-terrestrial air interface 190c enables communication between the ED 110d and one or more NT-TRP 172s via a wireless link or simply via a link. In some examples, the link is a dedicated connection for unicast transmission, a connection for broadcast transmission, or a connection between a group of ED 110s and one or more NT-TRP 172s for multicast transmission.

[0168] RANs 120a and 120b communicate with core network 130 to provide various services, such as voice, data, and other services, to EDs 110a, 110b, and 110c. RANs 120a and 120b and / or core network 130 may communicate directly or indirectly with one or more other RANs (not shown), which may or may not be directly served by core network 130, and may or may not use the same radio access technology as RANs 120a, RAN 120b, or both. Core network 130 may also serve as a gateway access between (i) RANs 120a and 120b or EDs 110a, 110b, and 110c, or both, and (ii) other networks (e.g., PSTN 140, Internet 150, and other networks 160). Additionally, some or all of the EDs in EDs 110a, 110b, and 110c may include the ability to communicate with different wireless networks via different radio links using different radio technologies and / or protocols. ED 110a, 110b, and 110c can communicate with a service provider or exchange (not shown) via a wired communication channel and with the Internet 150, but not wirelessly (or also wirelessly). PSTN 140 may include a circuit-switched telephone network for providing plain old telephone service (POTS). The Internet 150 may include a network of computers and / or subnets (intranets) and incorporate protocols such as Internet Protocol (IP), Transmission Control Protocol (TCP), and User Datagram Protocol (UDP). ED 110a, 110b, and 110c may be multimode devices capable of operating under various wireless access technologies and may include multiple transceivers supporting such operation.

[0169] Figure 3 This is a schematic diagram of the basic component structure of a communication system according to one or more exemplary embodiments of this disclosure.

[0170] Figure 3Another example of an ED 110 and base stations 170a, 170b, and / or 170c is shown. The ED 110 is used to connect people, objects, machines, etc. The ED 110 can be widely used in various scenarios, such as cellular communication, device-to-device (D2D), vehicle-to-everything (V2X), peer-to-peer (P2P), machine-to-machine (M2M), machine-type communications (MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), mixed reality (MR), metaverse, digital twins, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery, and mobility, etc.

[0171] Each ED 110 represents any suitable end-user equipment for wireless operation and may include (or be referred to as): user equipment / device (UE), wireless transmit / receive unit (WTRU), mobile station, fixed or mobile subscriber unit, cellular phone, station (STA), machine-type communication (MTC) device, personal digital assistant (PDA), smartphone, laptop, computer, tablet, wireless sensor, consumer electronics, smartbook, vehicle, automobile, truck, bus, train, or IoT device, wearable device (such as watch, glasses, head-mounted device, etc.), industrial equipment, or means of the above devices or constituting the above devices (e.g., communication module, modem, or chip), etc. Future generations of ED 110 may be referred to using other terms. Base stations 170a and 170b are T-TRPs, referred to below as T-TRP 170. Alternatively... Figure 3As shown, NT-TRP is referred to as NT-TRP 172 below. Each ED 110 connected to T-TRP 170 and / or NT-TRP 172 can be dynamically or semi-statically turned on (i.e., established, activated, or enabled), turned off (i.e., released, deactivated, or disabled), and / or configured in response to one or more of connectivity availability and connectivity necessity.

[0172] ED 110 includes a transmitter 201 and a receiver 203 coupled to one or more antennas 204. Only one antenna 204 is shown in the figure to avoid congestion. One, some, or all of the antennas 204 may also be panels. The transmitter 201 and receiver 203 may be integrated as a transceiver, etc. The transceiver is used to modulate data or other content for transmission through at least one antenna 204 or a network interface controller (NIC). The transceiver is also used to demodulate data or other content received through at least one antenna 204. Each transceiver includes any suitable structure for generating signals for wireless or wired transmission and / or for processing signals received wirelessly or wiredly. Each antenna 204 includes any suitable structure for transmitting and / or receiving wireless or wired signals.

[0173] ED 110 includes at least one memory 208. Memory 208 stores instructions and data used, generated, or collected by ED 110. For example, memory 208 may store software instructions or modules executed by one or more processing units (e.g., processor 210) for implementing some or all of the functions and / or embodiments described herein. Each memory 208 includes any suitable one or more volatile and / or non-volatile storage and retrieval devices. Any suitable type of memory can be used, such as random access memory (RAM), read-only memory (ROM), hard disk, optical disk, subscriber identity module (SIM) card, memory stick, secure digital (SD) memory card, on-processor cache, etc.

[0174] ED 110 may also include one or more input / output devices (not shown) or interfaces (e.g., Figure 1(Wired interface of Internet 150 in the network). Input / output devices or interfaces support interaction with users or other devices in the network. Each input / output device or interface includes any suitable structure for providing or receiving information from the user and / or for network interface communication. For example, suitable structures include speakers, microphones, keypads, keyboards, displays, touchscreens, etc.

[0175] ED 110 includes a processor 210 for performing operations including: operations related to preparing uplink transmissions to NT-TRP 172 and / or T-TRP 170; operations related to processing downlink transmissions received from NT-TRP 172 and / or T-TRP 170; and operations related to processing sidelink transmissions to and from another ED 110. Processing operations related to preparing uplink transmissions may include operations such as encoding, modulation, transmit beamforming, and generating symbols for transmission. Processing operations related to processing downlink transmissions may include operations such as receive beamforming, demodulation, and decoding of received symbols. According to an embodiment, the downlink transmissions may be received by receiver 203 (possibly using receive beamforming), and processor 210 may extract signaling from the downlink transmissions (e.g., by detecting and / or decoding signaling). Examples of signaling may be reference signals transmitted by NT-TRP 172 and / or T-TRP 170. In some embodiments, processor 210 performs transmit beamforming and / or receive beamforming based on beam direction indication (e.g., beam angle information (BAI)) received from T-TRP 170. In some embodiments, processor 210 may perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as operations related to detecting synchronization sequences, decoding, and acquiring system information. In some embodiments, processor 210 may perform channel estimation using reference signals received from NT-TRP 172 and / or T-TRP 170.

[0176] Although not shown, processor 210 may be part of transmitter 201 and / or receiver 203. Although not shown, memory 208 may be part of processor 210.

[0177] The processor 210, the processing components of the transmitter 201, and the processing components of the receiver 203 may each be implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 208). Alternatively, some or all of the processing components of the processor 210, the transmitter 201, and the receiver 203 may be implemented using hardware accelerators such as a programmable field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a graphics processing unit (GPU), or an artificial intelligence (AI) accelerator.

[0178] In some implementations, the T-TRP 170 may have other names, such as base station, basetransceiver station (BTS), wireless base station, network node, network device, network-side device, transmit / receive node, NodeB, evolved NodeB (eNodeB or eNB), home eNodeB, next-generation NodeB (gNB), transmission point (TP), site controller, access point (AP), wireless router, relay station, ground node, ground network device, ground base station, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. The T-TRP 170 can be a macro BS, pico BS, relay node, host node, or a combination thereof. T-TRP 170 may refer to the aforementioned equipment or to a component within the aforementioned equipment (e.g., a communication module, modem, or chip).

[0179] In some embodiments, the various parts of T-TRP 170 may be distributed. For example, some modules in T-TRP 170 may be located remotely from the device housing the antenna 256 of T-TRP 170 and may be coupled to the device housing the antenna 256 via a communication link (not shown) sometimes referred to as a fronthaul (such as a common public radio interface (CPRI)). Therefore, in some embodiments, the term "T-TRP 170" may also refer to network-side modules that perform processing operations such as determining the location of ED 110, resource allocation (scheduling), message generation, and encoding / decoding, which are not necessarily part of the device housing the antenna 256 of T-TRP 170. These modules may also be coupled to other T-TRPs. In some embodiments, T-TRP 170 may actually be multiple T-TRPs operating together to serve ED 110 through cooperative multicast and other methods.

[0180] T-TRP 170 includes at least one transmitter 252 and at least one receiver 254 coupled to one or more antennas 256. Only one antenna 256 is shown in the figure to avoid congestion. One, some, or all of the antennas 256 may also be panels. The transmitter 252 and receiver 254 may be integrated as a transceiver. T-TRP 170 also includes a processor 260 for performing operations related to: preparing downlink transmissions to be transmitted to ED 110, processing uplink transmissions received from ED 110, preparing backhaul transmissions to be transmitted to NT-TRP 172, and processing transmissions received from NT-TRP 172 via backhaul. Processing operations related to preparing downlink or backhaul transmissions may include operations such as encoding, modulation, precoding (e.g., multiple-input multiple-output (MIMO) precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to transmissions received in the uplink or via backhaul may include receiving beamforming, demodulating received symbols, and decoding received symbols. Processor 260 may also perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as generating the contents of a synchronization signal block (SSB) and generating system information. In some embodiments, processor 260 also generates a beam direction indication, such as a BAI, which can be scheduled for transmission by scheduler 253. Processor 260 may perform other network-side processing operations described herein, such as determining the location of ED 110 and determining the deployment location of NT-TRP 172. In some embodiments, processor 260 may generate signaling to configure one or more parameters of ED 110 and / or one or more parameters of NT-TRP 172. Any signaling generated by processor 260 is transmitted by transmitter 252. It should be noted that the term "signaling" as used herein may also be referred to as control signaling. Signaling can be transmitted in physical layer control channels (e.g., physical downlink control channel (PDCCH)). In this case, the signaling can be called dynamic signaling. Signaling transmitted in the downlink physical layer control channel can be called downlink control information (DCI). Signaling transmitted in the uplink physical layer control channel can be called uplink control information (UCI). Signaling transmitted in the sidelink physical layer control channel can be called sidelink control information (SCI).Signaling can be included in higher-layer (e.g., above the physical layer) data packets transmitted in physical layer data channels (e.g., physical downlink shared channel, PDSCH). In this case, the signaling can be called higher-layer signaling, static signaling, or semi-static signaling. Higher-layer signaling can also refer to radio resource control (RRC) protocol signaling or media access control-control element (MAC-CE) signaling.

[0181] Scheduler 253 may be coupled to processor 260. Scheduler 253 may be included within T-TRP 170 or may operate separately from T-TRP 170. Scheduler 253 may schedule uplink, downlink, lateral link, and / or backlink transmissions, including issuing scheduling authorizations and / or configuring schedule-free (e.g., "configured authorization") resources. T-TRP 170 also includes memory 258 for storing information and data. Memory 258 stores instructions and data used, generated, or collected by T-TRP 170. For example, memory 258 may store software instructions or modules executed by processor 260 for implementing some or all of the functions and / or embodiments described herein.

[0182] Although not shown, processor 260 may be part of transmitter 252 and / or receiver 254. Furthermore, although not shown, processor 260 may implement scheduler 253. Although not shown, memory 258 may be part of processor 260.

[0183] The processing components of processor 260, scheduler 253, transmitter 252, and receiver 254 may each be implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 258). Alternatively, some or all of the processing components of processor 260, scheduler 253, transmitter 252, and receiver 254 may be implemented using dedicated circuitry such as a programmable FPGA, hardware accelerator (e.g., GPU or AI accelerator), or ASIC.

[0184] Although the NT-TRP 172 is shown as an example of a drone only, it can be implemented in any suitable non-terrestrial form, such as satellites and high-altitude platforms including international mobile communication base stations and unmanned aerial vehicles. Furthermore, in some implementations, the NT-TRP 172 may have other names, such as a non-terrestrial node, a non-terrestrial network device, or a non-terrestrial base station. The NT-TRP 172 includes a transmitter 272 and a receiver 274 coupled to one or more antennas 280. Only one antenna 280 is shown in the figure to avoid congestion. One, some, or all of the antennas may also be panels. The transmitter 272 and receiver 274 may be integrated as a transceiver. The NT-TRP 172 also includes a processor 276 for performing operations related to: preparing downlink transmissions to be sent to ED 110, processing uplink transmissions received from ED 110, preparing backhaul transmissions to be sent to T-TRP 170, and processing transmissions received from T-TRP 170 via backhaul. Processing operations related to preparing downlink or backhaul transmissions may include operations such as encoding, modulation, precoding (e.g., MIMO precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to processing transmissions received in the uplink or via backhaul may include operations such as receive beamforming, demodulating received symbols, and decoding received symbols. In some embodiments, processor 276 performs transmit beamforming and / or receive beamforming based on beam direction information (e.g., BAI) received from T-TRP 170. In some embodiments, processor 276 may generate signaling to configure one or more parameters of ED 110. In some embodiments, NT-TRP 172 implements physical layer processing but does not implement higher-level functions such as medium access control (MAC) or radio link control (RLC) layer functions. Since this is only an example, in general, NT-TRP 172 may implement higher-level functions in addition to physical layer processing.

[0185] The NT-TRP 172 also includes a memory 278 for storing information and data. Although not shown, a processor 276 may form part of the transmitter 272 and / or the receiver 274. Although not shown, the memory 278 may form part of the processor 276.

[0186] The processing components of processor 276, transmitter 272, and receiver 274 can each be implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 278). Alternatively, some or all of the processing components of processor 276, transmitter 272, and receiver 274 can be implemented using dedicated circuitry such as a programmable FPGA, hardware accelerator (e.g., GPU or AI accelerator), or ASIC. In some embodiments, NT-TRP 172 can actually be multiple NT-TRPs operating together to serve ED110 via cooperative multicast or similar methods.

[0187] T-TRP 170, NT-TRP 172 and / or ED 110 may include other components, but these components have been omitted for clarity.

[0188] One or more steps of the methods in the embodiments provided herein can be derived from... Figure 4 The corresponding unit or module is executed. Figure 4 This is a block diagram of a device in a communication system according to one or more exemplary embodiments of the present disclosure. Figure 4 Units or modules in devices or apparatuses such as ED110, T-TRP 170, or NT-TRP 172 are illustrated. For example, signals may be transmitted by a transmitting unit or transmitting module. Signals may be received by a receiving unit or receiving module. Signals may be processed by a processing unit or processing module. Other steps may be performed by an artificial intelligence (AI) module or a machine learning (ML) module. The corresponding units or modules may be implemented using hardware, one or more components or devices executing software, or a combination thereof. For example, one or more units or modules may be circuits such as integrated circuits. Examples of integrated circuits include programmable FPGAs, GPUs, or ASICs. For example, one or more of these units or modules may be logical functions, such as logical functions executed by circuits, by a portion of an integrated circuit, or by software instructions executed by a processor. It should be understood that if these modules are implemented using software executed by a processor, etc., then these modules may be retrieved by the processor, wholly or partially, individually or collectively, for processing, or in one or more instances as needed, and these modules themselves may include instructions for further deployment and instantiation.

[0189] Further details regarding ED 110, T-TRP 170, and NT-TRP 172 are known to those skilled in the art. Therefore, these details are omitted herein.

[0190] For decades, bit-based communication has been a focus of industry, primarily due to its efficiency—optimizing the transmission of more bits at the lowest wireless cost. This has led to extensive research into channel coding and source coding theories to guide the design of forward error correction (FEC) coding schemes, modulation schemes, and lossy or lossless compression schemes in engineering. However, this emphasis has overshadowed another crucial aspect of communication: transmission effectiveness (the sender triggering the receiver's expected behavior).

[0191] For a receiver to perform an operation as the sender expects, the receiver and sender need to pre-negotiate protocols to map the expected operation (observation or execution) into bits. In the modern wireless industry, these pre-negotiated protocols form an important part of the wireless standards that each device follows. For example, in a wireless system, a new expected operation mapped to a few bits of a control message (or information within a message) cannot be used until it is standardized and hardware compatible with that standard is deployed.

[0192] Fourth generation (4) th generation (4G) and fifth generation (5G) th The control messaging system in current communication systems such as 5G (generation, 5G) systems (i.e., systems using pre-negotiated protocols for control messages) is a closed-vocabulary system, accessible only to transmission-related control messages, downlink control information (DCI), and uplink control information (UCI). A significant portion of the 5G wireless standard is specifically designed for the content and format of DCI and UCI. On the receiving side, pre-negotiated functions (operations and their parameters) are carefully mapped to certain bits of control messages with specific formats. When a new transmission technology emerges (e.g., from 4G to 5G), some new related control messages require years of standardization meetings and implementations before they can be added to DCI and UCI, or defined as new DCI and UCI formats. Similarly, when an older transmission technology is phased out, older control messages also require years of meetings and implementations before they can be removed from DCI and UCI. With the accelerated evolution of future transmission technologies, the need to update DCI and UCI will also accelerate, and the current closed-vocabulary control messaging system will become an obstacle to flexible replacement.

[0193] Since 5G, Ultra Reliable Low Latency Communication (URLLC) has been considered one of the key application characteristics of wireless systems. Recent AI technologies are accelerating the development of autonomous vehicles and robots, increasing the demand for low latency and high reliability communication. However, these applications cannot utilize the most reliable and fastest wireless channels because the control messages in these applications are not open to wireless technologies (such as 5G), can only be processed as data, and can only be transmitted through data channels.

[0194] Each anticipated operation is specifically defined and mapped to a number of bits in a control message. This definition and mapping requires thorough pre-negotiation and is written into the radio standard, then implemented in all user equipment (UE) and network nodes (e.g., base stations). Intended operations include specific observation or execution function modes. For example, a control message requesting the receiver to measure the current "received signal power" (e.g., reference signal received power (RSRP)) is a specific "observation" function mode (it does not change the receiver's state); while another control message requesting the receiver to configure its "carrier frequency" is a specific "execution" function mode (it changes the receiver's state). Understandably, the communication protocol associates one control message with one function mode and another control message with another function mode. Control messages are cross-modal.

[0195] Modern cellular wireless systems such as 5G include a central device (e.g., BTS, gNodeB, eNodeB) and at least one user equipment (e.g., UE, user, terminal, IoT device, etc.). In 5G, the central device is responsible for managing and maintaining the overall communication quality of all user equipment associated with it. See [link to documentation]. Figure 5 and Figure 6 . Figure 5 This is a schematic diagram of a communication system. Figure 6 This is a communication diagram between the central equipment and the first user equipment.

[0196] The central equipment primarily performs management and maintenance tasks through the control plane of the wireless system. The control plane includes physical layer control channels (e.g., downlink PDCCH and uplink PUCCH) and a portion of physical layer data channels (e.g., downlink PDSCH and uplink PUCCH), as well as several carefully standardized control messages. Typically, most control messages are robustly encoded (using lower coding rates and modulation schemes), without HARQ (to achieve shorter latency), and transmitted via the physical control channels. The content, format, location, and length of the standardized control messages are clearly defined and specified to ensure strict adherence by all devices. Typically, standardized control messages are short enough to form a small block to fit the DCI. Optionally, if the standardized control messages are long enough, they can also be transmitted via the physical data channels.

[0197] Certain bits in the standardized control message indicate the required functional mode, which is an observation (measurement) operation and / or an execution (configuration or setup) operation. The standard document explicitly specifies (through offline pre-negotiation) which bits are associated with which functional mode, and both the central equipment and user equipment are aligned with this standard document.

[0198] Certain bits in the standardized control message represent parameter values ​​for the functional mode. The standard document explicitly specifies (through offline pre-negotiation) which bits and how many bits are associated with which parameters of the functional mode, and both the central equipment and user equipment are aligned with this standard document.

[0199] Adding a new functional modality means updating certain bits in the standardized control message, which can take years to reach consensus within the standardization body and be implemented by all new devices. For example, because the number of bits allocated to a parameter value is fixed, the quantization of that value cannot be updated until a change in the number of bits is agreed upon within the standardization body and implemented by all new devices.

[0200] The central equipment generates standardized control messages by precisely padding bits according to a pre-negotiated standard. The central equipment then encodes the control messages using some pre-negotiated modulation and coding scheme (MCS) and transmits them to the user equipment on transmission opportunities within the physical radio allocation (control channel or data channel).

[0201] The user equipment receives control messages from the transport opportunity and decodes them according to the pre-negotiated MCS. The user equipment can then execute functional modes using parameter values ​​based on the decoded bits in the control message.

[0202] Natural language is one of the few carriers that supports both open vocabularies and forward and backward compatibility, while also enabling cross-modal functionality. To date, all theories, rules, laws, devices, knowledge, gadgets, and even wireless standards have been developed and stored in natural language. However, directly embedding sentences in natural language (e.g., word-for-word embedding via the American Standard Code for Information Interchange (ASIC)) is highly sensitive to word order and sentence format. For example, "set the carrier frequency to 3.5 GHz" is considered different from "the carrier frequency should be set to 3.5 GHz," even though they are semantically similar. Or, "What is the current received signal power?" and "The received signal power is very high" constitute a semantically similar question and answer pair. For decades, no machine has been able to understand flexible and open natural language sentences, and no heuristic method has been able to map and compare natural language sentences within a general semantic domain.

[0203] Large language models (LLMs) enable machines to “understand” sentences in natural language forms. While the primary goal of an LLM is extraction or prediction (generation) within sentences, each LLM may contain components that embed sentences in natural language forms into a semantic domain. Typically, these embedding components are implemented using deep neural networks based on Transformers and trained through contrastive learning with a large number of training samples. This paves the way for machines to “understand” and “compare” different sentences within a semantic domain.

[0204] Modern wireless systems suffer from at least one of the following problems. First, the content and format of control messages in wireless communication standards are pre-negotiated (standardized), forming a closed vocabulary within a semantic context used only for transmission. Control messages manage and maintain the entire wireless communication system, given the most reliable and fastest physical channel. However, this resource or capability is not open to other applications, especially ultra-reliable low-latency communication (URLLC) applications, including autonomous vehicles or robots. For example, control messages such as an autonomous vehicle's "emergency braking" can only be transmitted as data over the physical data channel. Second, the pre-negotiated (standardized) control messages in wireless communication standards have issues with forward and backward compatibility. Some "obsolete" control messages still occupy some resource space in the physical channel, while some new control messages (for new technologies) cannot be added until a new standard is released (e.g., several years later). This diminishes the ability of wireless systems to benefit from state-of-the-art transmission technologies.

[0205] Current wireless systems rely heavily on pre-negotiated (standardized) control message content and format, primarily because machines cannot understand semantic meaning. Effective communication has long been considered a propagation theory, as only humans can understand the semantic meaning of sentences and perform the intended actions.

[0206] The present invention discloses a method, apparatus, and system that utilize AI technology in the field of natural language models to improve the control message passing system in a communication system from a closed vocabulary to an open vocabulary, in order to solve at least one of the above two problems: providing openness for other applications and supporting forward and backward compatibility.

[0207] This disclosure provides a two-stage control message passing system method and apparatus for a wireless system. The wireless system includes a central device (also called a core device, such as a base station, core network, etc.) and at least one user equipment (such as a UE or other device). The following example illustrates a scenario where the central device transmits partial control messages to the user equipment. It should be noted that the scenario where the user equipment transmits partial control messages to the central device can be included in this disclosure in the same manner.

[0208] The central device generates control messages in the form of natural language sentences. These control messages contain a description of the functional modality and one or more parameter values ​​associated with that functional modality. The functional modality is the expected operation implemented at the user equipment.

[0209] The central device uses a Transformer-based deep neural network to embed descriptions of functional modalities in natural language sentences into semantic embeddings or lexical units.

[0210] The central device can update the user device with a Transformer-based deep neural network during the pre-negotiation phase. Typically, pre-negotiation does not occur frequently.

[0211] The central device encodes both the parameter values ​​and the semantic embedding. In the first phase of the wireless physical channel, the central device transmits a control message indicating the encoded parameter values, and then in the second phase of the wireless physical channel, it transmits the encoded semantic embedding to the user equipment. In the first phase transmission, the central device transmits (e.g., in the control message) an indicator along with the encoded parameter values. The indicator indicates the start position and length of the semantic embedding in the second phase transmission.

[0212] The user equipment implements at least one functional modality. Each functional modality comprises an API function that triggers the required physical operations and a description in natural language. The user equipment embeds the description of the functional modality from a natural language sentence into a semantic embedding or lexical unit using a Transformer-based deep neural network acquired during a pre-negotiation phase, as a functional semantic embedding. The user equipment can generate a semantic embedding once and store it for future use, or it can generate a semantic embedding each time it receives at least one control message.

[0213] When the user equipment (UE) receives a portion of the control message from the central device in the first phase, it decodes it to obtain an indicator and parameter values. Then, based on this indicator, the UE receives another portion of the control message transmitted in the second phase. The UE decodes this portion to obtain the query semantic embedding. The UE can measure the relevance (or correlation) between the query semantic embedding and its functional semantic embeddings. If the UE finds a strong correlation between the query semantic embedding and one of its functional embeddings, it can use the decoded parameter values ​​associated with the query semantic embedding to invoke the API function associated with the most relevant functional embedding. If the UE fails to find any sufficiently strong correlation between the query semantic embedding and any of its functional embeddings, it performs no action.

[0214] LLM's Embedding Model

[0215] The central equipment primarily schedules and manages user equipment through the control plane of the wireless system. The control plane includes multiple physical layer channels and multiple control messages. Unlike 5G, this invention includes some open-vocabulary control messages in natural language form to achieve forward and backward compatibility in wireless communication.

[0216] These control messages are called open-vocabulary control messages in natural language form. The main reasons for using natural language instead of artificial language (such as 5G standards) include at least one of the following:

[0217] Natural language is the de facto best semantic "standard" for almost everything. Discussions, development, writing, and standardization of wireless systems (such as 4G and 5G) are all conducted in natural languages ​​(such as English).

[0218] Inference based on a powerful LLM model can generate a series or a set of open-vocabulary control messages in natural language form. If modern wireless systems can leverage the ever-expanding LLM model, they can support control messages in natural language form.

[0219] It is generally accepted that a "man-in-the-loop" mechanism should be maintained during both the training and inference phases of an LLM model. During training, the "man-in-the-loop" mechanism helps to regulate the behavior of the LLM model, ensuring it conforms to safety and ethical guidelines; during inference, it facilitates backtracking and accumulating real-world samples for human review. Both phases require the system to support control messages in natural language.

[0220] In this disclosure, the central device should use an LLM to generate a series of control messages in natural language. How the LLM is constructed depends on the specific implementation. Enterprises or operators can gain efficiency advantages through their own LLM models. Enterprises can also continuously improve their LLM models through human-in-the-loop reinforcement learning, thereby updating the LLM's generative model.

[0221] A typical LLM model may include several components: an encoder that translates, embeds, or lexicallyizes sentences in natural language form into semantic embeddings; a generator or predictor that generates a series of semantic embeddings; and a decoder that translates the generated semantic embeddings back into sentences or messages in natural language form. In some LLM models, the generator and decoder are tightly coupled together.

[0222] There is a degree of randomness in LLM models. For example, two semantic embeddings in the same input sentence in natural language form are not exactly the same. However, these two semantic embeddings are highly correlated because their inner product is high.

[0223] Semantic embeddings have many names, such as semantic vectors, semantic lexical units, and lexical units. In some LLM models, semantic embeddings exist in tensor form, while in others they exist in matrix form. Typically, longer sentences in natural language form produce longer semantic embeddings. To adapt semantic embeddings to the wireless physical layer, an embedder is proposed:

[0224] Regularize semantic embeddings into vectors (semantic vectors); for example, simply vectorize them using tensors or matrices;

[0225] A finite number of fixed-length semantic vectors are predefined, and then the semantic vectors are regularized to one of these fixed lengths. Generally, longer sentences will be regularized into longer semantic vectors;

[0226] In the following discussion, these semantic vectors of one of fixed lengths will be referred to as "semantic vectors";

[0227] The encoder component of the LLM and the above regularization are referred to as "embedders".

[0228] Embedded models are components of LLM models; see [link / reference]. Figure 7The figure is a schematic diagram of an LLM model. In fact, compared to generators and decoders that typically contain billions of neurons, the embedding model is the smallest, simplest, and least energy-intensive component in an LLM model.

[0229] Figure 7 A typical LLM model is illustrated. A sentence in natural language form is input into the LLM model. This sentence is first embedded into semantic embeddings via a deep neural network (e.g., the transform-based deep neural network-1 in the figure). These semantic embeddings are then fed into a generator or predictor, which generates a series of semantic embeddings following the input semantic embeddings. This series of semantic embeddings is then translated into a sentence in natural language form by a decoder. Optionally, the generator and decoder can be combined using a deep neural network (e.g., another transform-based deep neural network-2 in the figure).

[0230] A functional mode is an operation performed by a user equipment. Operations include observation and / or execution. When a user equipment performs an observation operation, it measures certain states or conditions. When a user equipment performs an execution operation, it changes certain states or conditions. A functional mode can be an observation operation, an execution operation, or both.

[0231] Figure 8 A schematic flowchart of a control method according to one or more exemplary embodiments of this disclosure is shown. The method may be implemented by a first device. Optionally, the first device may be a central device or other device with similar functionality (e.g., the first device may be a chip), without limitation herein. Figure 8 As shown, the method may include the following steps.

[0232] S810: Uses LM to generate control messages in natural language form.

[0233] In this embodiment, the central device uses a Language Learning Model (LM) to generate control messages in natural language form. In one possible implementation, the control message can be an open-vocabulary control message used to control the functional modalities of the user device. In another possible implementation, the LM can be a language learning model (LLM).

[0234] In one possible implementation, the control message may also include a list of parameters. Parameters can be values ​​or parameters required for the correct execution of the functional modality, such as specific parameters, settings, or data inputs.

[0235] S820: Obtain the semantic information of the control message based on the control message.

[0236] In this embodiment, the central device obtains the semantic information of the control message based on the control message. Semantic information, in this disclosure, also refers to semantic vectors, semantic embeddings, semantic lexical units, etc. Semantic information can be the meaning or semantic numerical representation of words, phrases, sentences, or documents.

[0237] In one possible implementation, the central device can determine the portion of the control message that does not contain any parameters, and based on this portion, obtain the semantic information of the control message through an embedder. Considering that the control message may include a list of parameters, the central device can divide the control message into two parts: a first part including the parameter list (if any), and a second part including the remainder of the control message. The central device can then translate only the second part into semantic information. Since the parameters in the control message are typically variable in length and content, and the length of the semantic information depends on the length and complexity of the input message, which can vary considerably and result in semantic information of varying lengths, obtaining the semantic information of the control message based on the portion that does not contain any parameters helps to standardize the length of the semantic information. Furthermore, if parameters are included in the translation process, noise and variability in the semantic representation may be introduced, making it more difficult to compare and analyze the semantic relationships between different pieces of semantic information.

[0238] To obtain semantic information, the central device can select a length and use an embedder to translate the portion that does not contain any parameters into semantic information.

[0239] In one implementation, the central device can determine the correlation between the semantic information of the control message and the semantic information of each of at least one registered functional modalities, wherein the semantic information of each of the at least one functional modalities is obtained based on the description of each of the at least one functional modalities. The semantic information of each of the at least one functional modalities can be stored in the central device or translated from the description of the functional modalities at use.

[0240] In one implementation, the central device can determine the correlation between the semantic information of a control message and the semantic information of each of the at least one registered functional modalities. When the correlation is determined to be below a threshold, the central device can reject the control message. When the correlation between the semantic information of a control message and the semantic information of each of the at least one registered functional modalities is below the threshold, it can be determined that the control message is not registered, and the central device will reject the unregistered control message. The central device can avoid encoding or transmitting unregistered control messages, and can multicast or unicast the control message only to user equipment that has registered the corresponding functional modalities, thereby saving power consumption for both the central device and user equipment, and saving transmission resources.

[0241] S830: Form an information payload, wherein the information payload includes semantic information of the control message.

[0242] In this embodiment, in order to transmit control messages, the central device forms an information payload that includes semantic information of the control messages. The semantic information has a more structured and machine-readable format and is typically smaller in size than the control messages, thereby making communication more efficient and saving transmission resources.

[0243] S840: Transmits message payload.

[0244] In this embodiment, the central device transmits the information payload after forming it. The central device may transmit the first information payload during a first transmission opportunity and the second information payload during a second transmission opportunity. In one implementation, the central device may multicast or unicast the information payload to user equipment that has registered the relevant functional modes, thereby saving power consumption of the user equipment.

[0245] In one implementation, the central device can form a first information payload, wherein the first information payload includes the start position information of the second transmission opportunity and the length information of semantic information; the central device can form a second information payload, wherein the second information payload includes the semantic information of the control message, and the second transmission opportunity is used to transmit the second information payload information.

[0246] In one implementation, the central device may transmit a first information payload during a first transmission opportunity and a second information payload during a second transmission opportunity.

[0247] The central device allocates a segment of radio resources for control messages. The first portion of the radio resources is reserved for standardizing control messages. The second portion of the radio resources is allocated to open vocabulary control messages, which include at least a first open vocabulary control message.

[0248] By reserving a segment of wireless resources for control messages and allocating separate portions for standardized and open-vocabulary messages, the central device can ensure that these messages are transmitted efficiently without interference from other data transmissions.

[0249] The central equipment can allocate specific time slots or time intervals to different transmission opportunities. This can be achieved through pre-determined scheduling or by dynamically allocating time slots based on resource availability and demand.

[0250] The first and second information payloads can be encoded and transmitted during different transmission opportunities, which helps to utilize wireless resources more efficiently and provides greater flexibility in error correction and retransmission.

[0251] Since the first information payload includes the starting position information of the second transmission opportunity and the length information of the semantic information, the receiving device is able to synchronize and correctly receive the second information payload.

[0252] In one implementation, the control message further includes a parameter list, and the first information payload also includes the parameter list of the control message. If the control message also includes a parameter list, then the parameter list is included in the first information payload to be transmitted.

[0253] In one implementation, the central device may encode the second information payload using a first encoding method, wherein the first information payload also includes information about the first encoding method. The encoding method used by the second information payload may be explicitly or implicitly indicated by the first information payload. By including the first encoding method for encoding the second information payload in the first information payload, the user equipment can immediately identify the appropriate encoding scheme required for decoding the subsequent second information payload.

[0254] In one implementation, the central device may use a second encoding method to encode the first information payload. The second encoding method may be the same as or different from the first encoding method, and no restriction is placed here.

[0255] In one implementation, the first coding method includes a first modulation and coding scheme (MCS), and the second coding method includes a second MCS. Both the first and second coding methods can be MCS. In another possible implementation, the first and second coding methods can be other coding methods suitable for wireless transmission, such as pulse amplitude modulation (PAM), frequency shift keying (FSK), phase shift keying (PSK), quadrature amplitude modulation (QAM), etc.

[0256] In one implementation, the central device can determine the semantic information most relevant to the semantic information of the control message from the semantic information of each of the at least one registered functional modes, based on the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modes; it can determine at least one user equipment ID or at least one group of user equipment IDs corresponding to the most relevant semantic information, wherein the first information payload may further include: at least one user equipment ID, or at least one group of user equipment IDs; or the first information payload may further include information indicating at least one user equipment ID, or information indicating at least one group of user equipment IDs.

[0257] The central device can store a mapping between each registered functional modality and its corresponding information indicating at least one user equipment ID or at least one group of user equipment IDs. In one possible implementation, the central device can store the mapping between each registered functional modality and its user equipment ID or group of user equipment IDs. The central device can calculate the relevance between the semantic information of the control message and the semantic information of each of the at least one registered functional modality, and then determine the semantic information most relevant to the semantic information of the control message. When the most relevant semantic information is determined, the central device can retrieve the corresponding information indicating at least one user equipment ID or the information indicating at least one group of user equipment IDs, or either the user equipment ID or the group of user equipment IDs, from its database or associated records.

[0258] The central device can determine the specific functional mode to which the control message is targeted, and determine the corresponding user equipment or group of user equipment that should receive the control message based on the correlation between the semantic information of the control message and the semantic information of each functional mode in at least one registered functional mode. This ensures that the control message can be delivered to the intended recipient, thereby improving the efficiency and accuracy of the communication system.

[0259] The first information payload may include at least one user equipment ID or at least one group of user equipment IDs, or information indicating at least one user equipment ID or at least one group of user equipment IDs. Therefore, the receiving user equipment can determine whether it is the correct recipient based on the first information payload, thereby improving the efficiency and accuracy of the communication system. When the receiving user equipment is not the expected recipient, decoding of the second information payload can be stopped, thus saving energy consumption of the user equipment.

[0260] In one implementation, the information indicating at least one user equipment ID may include a first code generated based on at least one user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or the information indicating at least one group of user equipment IDs includes a second code generated based on at least one group of user equipment IDs, wherein the second code includes a mask, a spreading code, or an interleaving code.

[0261] In one implementation, the central device can generate a first code based on at least one user equipment ID; or a second code based on at least one group of user equipment IDs. The central device can apply a code generation algorithm that takes at least one user equipment ID or at least one group of user equipment IDs as input and generates the required mask, spreading code, or interleaving code. This algorithm typically involves mathematical operations or encoding techniques to convert the identifier into a code suitable for its intended use. The code generation algorithm can be at least one of the following: a hash algorithm, a pseudorandom number generator (PRNG), Reed-Solomon coding or convolutional coding, a symmetric-key block cipher (such as the Advanced Encryption Standard (AES)), simple bitwise operations, etc. The hash algorithm can be SHA-256, MD5, or other cryptographic hash functions used to generate a fixed-size hash value from the user equipment identifier.

[0262] In one implementation, the first transmission opportunity is located in the control physical channel, and the second transmission opportunity is located in the data physical channel; or both the first and second transmission opportunities are located in the control physical channel; or both the first and second transmission opportunities are located in the data physical channel. The data physical channel can be a physical downlink shared channel (PDSCH). The control physical channel can be a physical downlink control channel (PDCCH). When the first transmission opportunity is located in the control physical channel (e.g., PDCCH) and the second transmission opportunity is located in the data physical channel (e.g., PDSCH), the first transmission opportunity can arrive at the user equipment before the second opportunity.

[0263] When both the first and second transmission opportunities are located in the control physical channel, the order in which the first and second transmission opportunities arrive at the user equipment depends on the specific scheduling and transmission process defined by the cellular communication standard being used (e.g., LTE, 5G NR).

[0264] When both the first and second transmission opportunities are located in a data physical channel (e.g., PDSCH), the first and second transmission opportunities can be scheduled simultaneously or rapidly and continuously on the same data physical channel.

[0265] From a wireless resource perspective, it is not mandatory for a transmission opportunity to reach the first user equipment before a second opportunity. Several possible approaches exist:

[0266] The first transmission opportunity is located in the control physical channel (e.g., PDCCH); the second transmission opportunity is located in the data physical channel (e.g., PDSCH).

[0267] Both the first and second transmission opportunities are located in the control physical channel (e.g., PDCCH).

[0268] Both the first and second transmission opportunities are located in the data physical channel (e.g., PDSCH).

[0269] In the top-level architecture, the central device sends control messages in natural language to user devices that perform functional modes.

[0270] The central device generates control messages in natural language and forms an information payload that includes semantic information of the control messages to control user equipment. This allows for support of open vocabularies in control, more efficient communication, forward and backward compatibility, and adaptation to cross-modal functions.

[0271] Figure 9 A schematic flowchart of a control method according to one or more exemplary embodiments of this disclosure is shown. The method may be implemented by a second device. Optionally, the second device may be a user equipment or other device with similar functionality (e.g., the second device may be a chip), without limitation herein. Figure 9 As shown, the method may include the following steps.

[0272] S910: Obtain the information payload, wherein the information payload includes the semantic information of the control message.

[0273] In this embodiment, the user equipment obtains an information payload from the central device, which includes semantic information of a control message. The control message is in natural language form and is used to instruct the receiver to perform a specific operation. The semantic information of the control message can be the meaning of the control message or a numerical representation of its semantics.

[0274] In one implementation, the information payload may include a first information payload and a second information payload. The first information payload may be transmitted during a first transmission opportunity, and the second information payload may be transmitted during a second transmission opportunity. The first information payload may include the start position information of the second transmission opportunity and the length information of the semantic information of the control message. The user equipment may acquire the first information payload during the first transmission opportunity and decode the first information payload to obtain the start position information of the second transmission opportunity and the length information of the semantic information of the control message. The user equipment may acquire the second information payload during the second transmission opportunity based on the start position information of the second transmission opportunity and the length information of the semantic information of the control message, wherein the second information payload includes the semantic information of the control message. After acquiring the second information payload, the user equipment may decode the second information payload to obtain the semantic information of the control message.

[0275] The first and second transmission opportunities do not indicate the order in which the first and second information payloads arrive at the user equipment. In other words, from a radio resource perspective, it is not mandatory for a transmission opportunity to arrive at the user equipment before the second opportunity. Encoding and transmitting the first and second information payloads during different transmission opportunities helps to utilize radio resources more efficiently and provides greater flexibility in error correction and retransmission.

[0276] The first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information of the control message. Therefore, the receiving device can synchronize and correctly receive the second information payload according to the first information payload.

[0277] In one implementation, the first information payload also includes a parameter list for control messages. The control messages generated by the central device may include the parameter list, which can be included in the first information payload to be transmitted when the central device only translates the portion of the control message that does not contain any parameters into semantic information.

[0278] In one implementation, the first information payload further includes information from the first encoding method, and the second information payload is decoded using the first encoding method. In another implementation, the first information payload is decoded using a second encoding method. The second encoding method can be the same as or different from the first encoding method; no restriction is placed here.

[0279] In one implementation, the first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS. In another possible implementation, the first and second encoding methods can be other encoding methods suitable for wireless transmission, such as pulse amplitude modulation (PAM), frequency shift keying (FSK), phase shift keying (PSK), quadrature amplitude modulation (QAM), etc.

[0280] The user equipment can use a second encoding method to decode the first information payload to obtain the parameter list of the control message, the starting position of the second transmission opportunity, the length of the semantic information, and the first encoding method. Using these, the user equipment can obtain the second information payload and decode it to obtain the semantic information.

[0281] S920: Based on the semantic information of the control message, determine the target semantic information from at least one semantic information, wherein each semantic information in the at least one semantic information corresponds to a corresponding functional modality in at least one functional modality, and is obtained based on the description of the corresponding functional modality, the description of the corresponding functional modality being in natural language form.

[0282] In this embodiment, the user equipment (UE) determines the target semantic information by comparing a semantic vector obtained from the network device with all its candidate semantic information. Each candidate semantic information corresponds to a corresponding functional modality in at least one functional modality of the UE. The candidate semantic information is obtained based on a description of the corresponding functional modality in natural language form. This candidate semantic information can be stored in the UE or retrieved whenever needed. The description of the corresponding functional modality uses natural language form to describe the corresponding functional modality.

[0283] In one implementation, the user equipment can determine the target semantic information from at least one piece of semantic information that is most relevant to the semantic information of the control message. The user equipment can calculate the relevance or similarity between the semantic information obtained from the central device and all its candidate semantic information. Based on the relevance calculation, the target semantic information is identified as the most relevant semantic information.

[0284] In one implementation, the first information payload further includes information indicating a user equipment identifier (ID) or information indicating a group of user equipment IDs. Because the first information payload includes information indicating a user equipment ID or information indicating a group of user equipment IDs, the user equipment can determine whether it is the correct receiver based on the first information payload, thereby improving the efficiency and accuracy of the communication system.

[0285] In one implementation, the user equipment can obtain a first code generated based on information indicating the user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or the user equipment can obtain a second code generated based on information indicating the group of user equipment IDs, wherein the second code includes a mask, a spreading code, or an interleaving code. The user equipment can decode the obtained code to obtain information indicating the user equipment ID or information indicating the group of user equipment IDs from the obtained code.

[0286] In one implementation, in response to determining that the User Equipment ID or Group User Equipment ID does not match the User Equipment ID or Group User Equipment ID of the User Equipment, the User Equipment can stop decoding the second information payload. When the User Equipment Identifier is indicated in the first information payload, if the User Equipment discovers that the decoded User Equipment ID or Decoded Group User Equipment ID does not match itself, the User Equipment can stop decoding the second information payload, thereby saving the User Equipment's energy consumption and processing resources.

[0287] In one implementation, after acquiring the information payload, the user equipment can obtain at least one piece of semantic information for each of the at least one functional modalities through a first embedder, based on the description of each functional modality. The first embedder is used to obtain the semantic information of control messages included in the information payload. That is, the user equipment can compare the semantic information of the control messages with candidate semantic information obtained using the same embedder, thus improving the accuracy and reliability of the comparison results. In some cases, the candidate semantic information is not stored in the user equipment, for example, when the user equipment has limited storage, or when the embedder has just been configured or updated. The user equipment can obtain the candidate semantic information through the corresponding embedder.

[0288] In one implementation, information indicating the embedder ID of the first embedder can be carried in the information payload. In another implementation, when the information payload is transmitted via a first information payload and a second information payload, information indicating the embedder ID of the first embedder can be carried in the first information payload. The first embedder is an embedder used to acquire semantic information included in the information payload. In one implementation, the first information payload further includes information indicating the embedder ID of the embedder used to acquire semantic information of control messages. By including information indicating the embedder ID of the embedder used to acquire semantic information of control messages in the information payload (e.g., the first information payload), the accuracy of the user device's decisions regarding semantic information can be improved.

[0289] In one implementation, the semantic information of the control message is obtained through a first embedder in at least one embedder, and correspondingly, at least one piece of semantic information of at least one functional modality is obtained through the first embedder. That is, target semantic information can be determined from candidate semantic information obtained by the same embedder used to obtain the semantic information included in the information payload. Since the user equipment can compare the semantic information with the candidate semantic information obtained using the same embedder, the accuracy and reliability of the comparison results are improved.

[0290] In one implementation, a user equipment (UE) can acquire one or more pieces of semantic information through at least one embeddinger, based on the description of each of the at least one functional modalities. For each functional modality, each embeddinger is used to acquire corresponding semantic information, and the UE can store one or more pieces of semantic information. The UE can use each embeddinger to acquire corresponding semantic information for each of the at least one functional modalities and can store the acquired semantic information, thereby enabling the UE to quickly access and utilize the semantic information when needed.

[0291] In one implementation, the user equipment can retrieve at least one semantic information of at least one functional modality from one or more stored semantic information based on information indicating the embedder ID of the first embedder. When the semantic information of each functional modality has been stored in the user equipment, the user equipment can retrieve candidate semantic information from the stored semantic information based on the embedder ID information, thereby determining the target semantic information.

[0292] In one implementation, the central device can send semantic information about the functional modalities. Correspondingly, the user device can obtain at least one piece of semantic information about at least one functional modality. Especially when the user device cannot run any transformation-based embedders, it can obtain the semantic information about the functional modalities from the central device instead of translating the descriptions of the functional modalities itself. This approach improves system compatibility and flexibility.

[0293] S930: Execute the functional modality corresponding to the target semantic information.

[0294] In this embodiment, after determining the target semantic information, the user equipment executes a functional mode corresponding to the target semantic information.

[0295] User equipment can acquire information payloads including semantic information from control messages, determine target semantic information based on control messages, and execute corresponding functional modalities. This enables support for open vocabularies in control, achieves more efficient communication, supports forward and backward compatibility, and adapts to cross-modal functions.

[0296] Figure 10 A schematic flowchart illustrating a registration process according to one or more embodiments of this disclosure is shown. Figure 10 As shown, the method may include the following steps.

[0297] S1010: The user equipment sends registration information for a functional modality, wherein the registration information for the functional modality includes a description of the functional modality in natural language form.

[0298] In this embodiment, the user equipment sends registration information of the functional modality to the central device. The registration information includes a description of the functional modality, which is in natural language form. In one possible implementation, the registration information may also include a list of parameters for the functional modality.

[0299] Real-world user equipment includes multiple states as well as multiple observation and execution functions. A functional modality includes at least one observation function for reading at least one state or at least one execution function for changing at least one state.

[0300] A functional mode is an operation performed by a user equipment. Operations include observation and / or execution. When a user equipment performs an observation operation, it measures certain states or conditions. When a user equipment performs an execution operation, it changes certain states or conditions. A functional mode can be an observation operation, an execution observation, or both.

[0301] In one implementation, the user equipment may encapsulate each of at least one functional modality as a calling function, wherein the calling function of the corresponding functional modality includes a description of the corresponding functional modality, or the calling function of the corresponding functional modality includes a parameter list and a description of the corresponding functional modality. The calling function is used to interact with the corresponding function by sending requests and processing the data returned by the corresponding function.

[0302] In one possible implementation, the calling function includes an application programming interface (API) calling function. An API is a set of rules, protocols, and tools that enable different software applications to communicate and interact with each other. An API defines the methods and data formats that applications can use to exchange information and request services from each other.

[0303] Since function calls (such as API call functions) can be implemented in various programming languages, it is easier to integrate and use with different programming languages ​​by encapsulating each functional modality in at least one functional modality as a function call, and it promotes interoperability between different systems or components that may be developed using different technologies.

[0304] In one possible implementation, the user device can use other technologies to implement the functionality for interacting with the functional modality. For example, the system can directly call the functional modality using the syntax of a suitable programming language; this approach may be suitable for smaller applications or when the functional modality is tightly coupled to the rest of the application's logic. Alternatively, if the functional modality is provided as a library or software development kit (SDK), the system can directly integrate and use the library functions in the application code. Yet another example is that in a distributed system, the functional modality can be implemented as a standalone service accessible over a network. The system can interact with the functional modality using standard communication protocols such as Representational State Transfer (REST), gRPC, or message queues.

[0305] In one implementation, the user equipment (UE) may send registration information for each of at least one functional mode, wherein the registration information for each functional mode includes a description of the corresponding functional mode, or the registration information for each functional mode includes a parameter list and a description of the corresponding functional mode. The UE may send the registration information to the central device to register the functional modes with the LM. In one possible implementation, the LM may be an LLM (Limited LLM).

[0306] Because the registration information for functional modalities includes only a description in natural language or a list of parameters, the system can adapt to cross-modal functions and support forward and backward compatibility. Furthermore, when new functional modalities are added, they can be registered along with their corresponding natural language descriptions without changing the system architecture or communication protocol, which improves the system's versatility and makes it more flexible.

[0307] In this embodiment, the central device can obtain the registration information of the functional modality from the user equipment.

[0308] S1020: The central device registers the functional mode with the LM.

[0309] In this embodiment, after obtaining registration information from the user equipment, the central device registers the functional modality with the LM. In one implementation, the registration information of the functional modality may further include a parameter list of the functional modality.

[0310] In one implementation, the central device can register a functional mode with at least one LM by providing registration information of the functional mode to at least one LM, wherein the at least one LM includes LM1. The system may have one or more LMs. The central device can register a functional mode with at least one LM from one or more LMs by providing registration information of the functional mode to at least one LM. That is, when the system has multiple LMs, the central device can register a functional mode with one LM from the multiple LMs, or it can register a functional mode with multiple LMs from the multiple LMs, which can be determined according to actual needs.

[0311] In one implementation, the central device can record registration information for functional modes. After obtaining the registration information, the central device can store it locally for later use, thereby facilitating subsequent maintenance.

[0312] In one implementation, the central device may also record information indicating the user equipment ID, wherein it receives registration information of functional modes from the user equipment. The central device may associate the user equipment ID information with the corresponding functional modes and may record this association, wherein it receives registration information of the functional modes from the user equipment. That is, the central device may record the user equipment ID information indicating the user equipment, as well as a description and parameter list (if any) of the functional modes possessed by the user equipment.

[0313] In one possible implementation, the central device can maintain a data structure or database that maps information indicating user equipment IDs (e.g., user equipment identifiers) to registered functional modalities. Whenever a user equipment registers a new functional modality or sends information related to that functional modality, the central device can update this mapping accordingly.

[0314] The central device can record the user equipment ID and registration information of the user equipment for further use, so as to more directly invoke the corresponding functional modes of different user equipment without additional communication or negotiation, thereby helping to optimize the utilization of transmission resources.

[0315] In one implementation, the central device can also acquire semantic information of the functional modality through an embedder based on the functional modality description. The embedder is included in the LM and registered in the system. The central device can use the embedder to translate, embed, or lexicalize the natural language description of the functional modality into semantic information. The semantic information has a more structured and machine-readable format.

[0316] In one implementation, the central device can also store semantic information of the functional modality. After acquiring the semantic information of the functional modality, the central device can store the semantic information of the functional modality for later use, thereby facilitating subsequent maintenance.

[0317] In one possible implementation, the central device can translate the description of the functional modality into semantic information whenever needed, rather than storing the semantic information.

[0318] In one possible implementation, if another user device (e.g., a second user device) has the same functional mode (e.g., a first functional mode) as the user device (e.g., the first user device), and the second user device also sends the registration information of the first functional mode to the central device, then the central device can add the user device ID of the second user device to the existing association of the first functional mode.

[0319] In one implementation, when multiple LMs exist, the user equipment can register functional modes with one or some of the LMs, or with all of them. After registering a functional mode with one of the LMs, the central device can notify other LMs of the functional mode registration information as needed. Deploying multiple LMs on the central device enhances the system's flexibility and customizability.

[0320] In one implementation, the central device can send configuration information for at least one embedder, wherein the embedder belongs to at least one embedder. The LM can register its embedders with the system, which may include the central device and user devices. The central device can send the embedder's configuration information to the user device to register the embedder with the user device. When an embedder is introduced or updated, the central device can send configuration information to the user device, including the embedder's architecture and parameters (neuron values), etc. In one possible implementation, the configuration information for at least one embedder is sent via broadcast, multicast, or unicast messages.

[0321] Accordingly, the user equipment can obtain configuration information for at least one embedder. After obtaining the configuration information, the user equipment can register or update at least one embedder.

[0322] In one implementation, multiple embedders (e.g., including a first embedder and a second embedder) can be registered in the system. These multiple embedders can be included in the same LM or in different LMs.

[0323] For example, when a second embedder exists and is introduced or updated, the central device can transmit the configuration of the second embedder to all user devices. In some cases, the first LM model may have a first embedder and a second embedder; in other cases, the first LM model has a first embedder and the second LM model has a second embedder.

[0324] In one implementation, the configuration information of at least one embedder also includes the embedder ID of each of the at least one embedder. The central device can notify the user equipment of the embedder ID of each of the at least one embedder, especially when multiple embedders exist. By including the embedder ID of each of the at least one embedder in the configuration information, it is easier to track and manage specific embedders that require updates or maintenance.

[0325] In one implementation, the central device and the user device can acquire semantic information of a functional modality using the same embedder, based on the description of the functional modality included in the registration information. Due to the inherent randomness or variability of the embedder, the semantic information of the functional modality acquired by the central device and the user device may not be exactly the same. However, despite this variability, a strong semantic correlation still exists between the semantic information acquired by the central device and the semantic information acquired by the user device. Randomness in the embedding process may introduce slight changes in the output semantic information, even if the input description remains unchanged. These changes can be attributed to factors such as the specific initialization of the embedder parameters or the randomness of certain neural network operations.

[0326] Several scenarios may arise when the system has at least two embedders. In one possible implementation, there are multiple LMs, each of which has at least one embedder. The system can have multiple LMs, each of which has at least one embedder. In another possible implementation, at least one LM in the system has multiple embedders.

[0327] In one implementation, at least one functional mode is registered in one or more LMs, but not in all of them. When multiple LMs exist in the system, a functional mode may be registered in one or more LMs, but not in all of them. Therefore, the overall system size can be reduced, and the resources of the central device can be optimized.

[0328] In one implementation, the multiple LMs may include at least one LM compatible with an LTE system. In another implementation, the multiple LMs may include at least one LM compatible with a 5G system. The multiple LMs may also include different LMs compatible with different communication systems. That is, different LMs may have different registered functional modes.

[0329] In one possible implementation, a first LM among multiple LMs can have a first embeddinger, a second LM among multiple LMs can have a second embeddinger, and the first and second embeddingers can be constructed based on vocabularies from different domains. In another implementation, an LM can have a first embeddinger and a second embeddinger constructed based on vocabularies from different domains. That is, the system can have multiple embeddingers, and at least two of the multiple embeddingers can be constructed based on vocabularies from different domains. Specializing the vocabulary can reduce the size and cost of the embeddingers, while also improving the accuracy of relevance calculation.

[0330] For example, the system has a first embedder and a second embedder. Several advantageous scenarios exist:

[0331] Scenario 1: The system can have two LM models: a first LM model and a second LM model. For example, the first LM model is developed for compatibility with LTE systems. The open-vocabulary control messages generated by the first LM model can generate functional modes supported by the LTE standard. The second LM model is developed for compatibility with 5G systems. The open-vocabulary control messages generated by the second LM model can generate functional modes supported by the 5G standard. Some functional modes (such as massive MIMO and polar codes) are not included in the first LM model. Therefore, the first LM model has a first embeddinger, and the second LM model has a second embeddinger.

[0332] Scenario 2: The system has one LM model but two embedders. For example, the first embedder is based on a vocabulary from the IoT industrial domain, and the second embedder is based on a vocabulary from the urban security domain. Specializing the vocabulary can significantly reduce the size and cost of the embedders, while also improving the accuracy of relevance calculations.

[0333] In one implementation, in response to the LM generating at least two consecutive control messages more than a preset number of times, the central device can combine the functional modes corresponding to the at least two consecutive control messages to generate a combined functional mode, and can send the configuration information of the combined functional mode. In another implementation, after generating the combined functional mode, the central device can register the combined functional mode with the LM. In practical applications, the central device can always generate at least two consecutive control messages through the LM. When the central device uses the LM to generate at least two consecutive control messages more than the preset number of times, the central device can negotiate with the user equipment to generate a combined functional mode. That is, at least two functional modes corresponding to at least two consecutive control messages can be combined into one functional mode, thereby enhancing efficiency by simplifying the execution of multiple functions in a single call to the combined functional mode.

[0334] In one implementation, when more than one functional modality exists, the user equipment can obtain configuration information for a combined functional modality. This combined functional modality is composed of at least two functional modalities from the existing functional modality, and the user equipment can encapsulate the combined functional modality into a first calling function. In another implementation, the configuration information for the combined functional modality may include a calling order, and the first calling function calls the calling functions corresponding to at least two functional modalities in that order. The combined function sequentially calls multiple calling functions. As runtime increases, combined functional modalities encapsulating multiple older functional modalities in a certain order are created, thereby improving efficiency.

[0335] For ease of understanding, exemplary scenarios of the control method of this disclosure are described below. It should be noted that these examples are for illustration only and should not be construed as limiting the technical solutions of this disclosure.

[0336] Figure 7A typical LLM model is illustrated. A sentence in natural language form is input into the LLM model. This sentence is first embedded into semantic embeddings via a deep neural network (e.g., the transform-based deep neural network-1 in the figure). These semantic embeddings are then fed into a generator or predictor, which generates a series of semantic embeddings following the input semantic embeddings. This series of semantic embeddings is then translated into a sentence in natural language form by a decoder. Optionally, the generator and decoder can be combined using a deep neural network (e.g., another transform-based deep neural network-2 in the figure).

[0337] like Figure 11 As shown in Scenario 1, the first LLM model can register its first embedder with the system, where the central device and at least one first user device register the first embedder. When the first embedder is introduced or updated, the central device will configure the first embedder (including architecture and parameters (neuron values)) to all user devices via broadcast, multicast, and unicast.

[0338] When a second embedder exists and is introduced or updated, the central device can transmit the second embedder to all user devices. In some cases, the first LLM model can have both a first and a second embedder; in others, the first LLM model has a first embedder and the second LLM model has a second embedder. For example, the first embedder may be in English and the second embedder may be in Chinese, or the first embedder may be generic and the second embedder may be specific to IoT (smaller and faster).

[0339] Because LLMs can be implemented independently, a central device can have more than one LLM model, such as... Figure 11 Scenario 2 is shown in the example. For instance, the first LLM model is built by company A for green energy equipment management; the second LLM model is built by company B for smart city traffic sensors. Detailed information for each LLM model can be found in the description above.

[0340] When configuring an embedder, if there is more than one embedder, the central device can notify all user devices of the embedder identifier, see below. Figure 12 .

[0341] Register functional modalities to the system

[0342] A functional mode is an operation performed by a user equipment. Operations include observation and / or execution. When a user equipment performs an observation operation, it measures certain states or conditions. When a user equipment performs an execution operation, it changes certain states or conditions. A functional mode can be an observation operation, an execution observation, or both. Figure 13Examples of two states are given, namely state #1 and state #2. To access a state (state #1 and state #2), a function is required. Assume a function can only access one state at a time. This function can either modify the state (an execution function, such as "SetState#1(value)") or read the state (an observation function, such as "Result = ReadState#1(void)", "IsState#1HigherThan(value)", or "IsState#1InRangeBetween(value1, value2)"), or both read and modify the state (an execution and observation function).

[0343] At least one first functional modality is enabled, equipped, or implemented on at least one first user device. To enable the central device to use the first functional modality enabled on the first user device, the system registers the first functional modality into the system if it is new or updated to the system.

[0344] On the first user device, the first functional modality can be encapsulated as at least one first application programming interface (API) call function, see [link to relevant documentation]. Figure 14 The first API call function can be in various programming languages, such as C, Java, Python, C++, assembly, etc. The first API call function can have a first parameter list. The first API call function can have a first description, which uses natural language to describe the first functional modality. It should be noted that a functional modality can be implemented through a series of API functions, but it is best to implement one functional modality through a single API function. Figure 14 The functional modalities shown include the API, parameter list, and description in natural language.

[0345] Optionally, such as Figure 15 As shown, the first user device can translate the first description into a first semantic vector (or a batch of first semantic vectors of different lengths) using a first embedding device and then store it. Alternatively, the first user device can translate the first description into a second semantic vector (or a batch of second semantic vectors of different lengths) using a second embedding device and then store it. Alternatively, the first user device can translate the first description into a first semantic vector using the first embedding device without storing it. Due to the inherent randomness of the first embedding device, the first semantic vectors generated by the first embedding device may not be completely identical, but they will be very similar in the semantic domain.

[0346] like Figure 16As shown, the first user equipment can notify the central device of the first functional mode by transmitting a first description and a first parameter list to the central device. The first user equipment transmits the first description of the first functional mode to the central device so that the central device can register the first functional mode into the system.

[0347] After receiving the first description and the first parameter list, the central device can register the first functional modality to the first LLM model by providing the first description and the first parameter list. Optionally, if a second LLM model exists, the central device can register the first functional modality to the second LLM model by providing the first description and the first parameter list.

[0348] Optionally, such as Figure 17 As shown, the central device can translate the first description into a third semantic vector (or a third batch of semantic vectors of different lengths) using a first embedder and then store it. Preferably, the central device can associate the first user equipment identifier with the first functional modality. Alternatively, if a second embedder exists, the central device can translate the first description into a fourth semantic vector (or a fourth batch of semantic vectors of different lengths) using the second embedder and then store it. Alternatively, the central device can translate the first description into a third semantic vector using the first embedder without storing it. Due to the randomness of the first embedder, the third semantic vector generated by the first embedder may not be exactly the same, but they are very close in the semantic domain.

[0349] like Figure 18 As shown, if the second user equipment has the same first functional mode, the second user equipment can provide the central device with a first description and a first parameter list. The central device can add the second user equipment identifier to the first functional mode. That is, if the first functional mode has been registered, the central device can record the second user equipment that supports the first functional mode.

[0350] If the second user equipment has a second functional modality (new or updated), the second user equipment can provide the central device with a second description and a second parameter list. The central device can use the second functional modality to record the second user equipment identifier. Conversely, the central device can notify the first LLM model provider of the second functional modality by providing the second description and the second parameter list to the first LLM model provider. Optionally, if there is more than one LLM model provider, the central device can notify the second LLM model provider of the second functional modality by providing the second description and the second parameter list to the second LLM model provider.

[0351] Although the first user device and the central device translate the same first description using the same first embedder, the first semantic vector and the third semantic vector may not be exactly the same due to the randomness inherent in the first embedder. However, the first semantic vector and the third semantic vector have a strong semantic correlation.

[0352] If the central device consistently generates at least two consecutive open-vocabulary control messages for the user equipment, it indicates that two functional modalities can be combined into one functional modality. The central device and the user equipment can negotiate to generate a third functional modality with a third functional API. The third API function sequentially calls the two functional APIs. As runtime increases, new functional modalities are created that encapsulate multiple older functional modalities in a certain order, thereby improving efficiency.

[0353] like Figure 19 As shown, the central device generates at least one first open-vocabulary control message using a first LLM model. The first control message in natural language form may include a list of parameters (values) and is specific to a first functional modality on a first user device.

[0354] The central device divides the first open vocabulary (Open-Voc) control message into two parts: the first part includes a parameter list (if any), and the second part includes the rest of the first open vocabulary control message.

[0355] The central device can select a first length and translate the second part of the first open vocabulary control message into a fifth semantic vector through a first embedder.

[0356] The central device can translate the description of the first functional modality into a third semantic vector through the first embedder.

[0357] Although the fifth semantic vector and the third semantic vector may not be exactly the same due to the randomness of the first embedding model, the fifth semantic vector and the third semantic vector indicate a strong semantic correlation.

[0358] Optionally, such as Figure 20 As shown, the central device can compare the correlation between the fifth semantic vector and the third semantic vector with a first threshold. If the correlation between the fifth semantic vector and the semantic vector of each registered functional modality is lower than the first threshold, the central device can determine that the first control message is an unregistered message; otherwise, the central device can determine that the first control message is a registered message. The central device can reject unregistered messages.

[0359] One of its advantages is that the central equipment can multicast or unicast the information payload to user equipment that has registered the relevant functional modes, thereby saving power consumption of user equipment.

[0360] like Figure 21 As shown, the central device can encode and transmit the parameter list of the first open vocabulary control message during the first transmission opportunity, and encode and transmit the fifth semantic vector during the second transmission opportunity.

[0361] In other words, the central device can encode and transmit open-voc control messages in two transmission opportunities.

[0362] The central device allocates a segment of radio resources for control messages. The first portion of the radio resources is reserved for standardizing control messages. The second portion of the radio resources is allocated to open vocabulary control messages, which include at least a first open vocabulary control message.

[0363] The central device can form a first information payload, which includes a parameter list of a first open vocabulary control message, the start position of a second transmission opportunity, a first length of a fifth semantic vector, a first MCS encoding the fifth semantic vector, and (optionally) a first user equipment identifier. The central device encodes the first information payload using a second MCS. The central device allocates a first transmission opportunity in a second portion of the radio resources to transmit the first information payload.

[0364] The central device can form a second information payload including a fifth semantic vector. The central device encodes the second information payload using a first MCS. The central device allocates a second transmission opportunity with a starting position and a first length in the second part of the radio resources to transmit the second information payload.

[0365] like Figure 22 As shown, the first user equipment receives a first transmission opportunity (i.e., receives certain information about the first transmission opportunity). The first user equipment uses a second MCS to decode the first information payload. Optionally, if the user equipment identifier is transmitted in the first information payload, and the first user equipment finds that the decoded user equipment identifier does not match, the first user equipment may stop decoding the second information payload.

[0366] like Figure 23 As shown, the first user equipment decodes the parameter list of the first open vocabulary control message, the starting position of the second transmission opportunity, the first length of the fifth semantic vector, and the first MCS. Based on this information, the first user equipment receives the second transmission opportunity and uses the first MCS to decode the fifth semantic vector.

[0367] The first user equipment calculates the relevance between the fifth semantic and all its candidate semantics (including at least the first semantic vector). The first user equipment can select the first semantic as the most relevant semantic to the fifth semantic. Then, the first user equipment can use the parameters decoded by the first user equipment in the first transmission opportunity to invoke the first API call function. Finally, the first user equipment executes the first functional mode with the correct parameters.

[0368] In the top-level architecture, the central device sends a first control message in natural language to the first user device that performs the first functional mode.

[0369] In addition to the examples above, the following are some further descriptions of this disclosure.

[0370] For some low-power IoT user devices that cannot run any transformation-based embedders, the first user device can request the central device to transmit a third semantic vector, which is then stored in the first user device's memory.

[0371] If the central device consistently generates at least two consecutive open-vocabulary control messages for the user equipment, it indicates that two functional modalities can be combined into one functional modality. The central device and the user equipment can negotiate to generate a third functional modality with a third functional API. The third API function sequentially calls the two functional APIs. As runtime increases, new functional modalities are created that encapsulate multiple older functional modalities in a certain order, thereby improving efficiency.

[0372] It should be noted that for V2X scenarios, DCI can be replaced with SCI, and DCI field packets can be replaced with SCI field packets.

[0373] It should be noted that in this disclosure, "controlling message" and "control signaling" have the same meaning and can be used interchangeably.

[0374] It should be noted that in this disclosure, "message" can mean "information" or carry "information". In some aspects of this disclosure, a computer program comprising instructions is provided. When the instructions are executed by a processor, the processor can implement the methods of this disclosure.

[0375] The following describes embodiments of products related to wireless communication methods.

[0376] Figure 24A schematic diagram of a first device according to one or more exemplary embodiments of the present disclosure is shown. This first device can be applied to the aforementioned central device, or a chip installed in or applied to the central device, or any other device, module, circuit, or unit capable of implementing the steps of the central device in the above method embodiments. Figure 24 As shown, the first device 2400 may include:

[0377] The processing module 2401 is configured to: generate control messages in natural language form using LM; obtain semantic information of the control messages based on the control messages; and form an information payload, wherein the information payload includes the semantic information of the control messages.

[0378] The sending module 2402 is used to send the information payload.

[0379] In one possible implementation, the LM can be an LLM.

[0380] In one possible implementation, the first device further includes an acquisition module 2403 for: acquiring registration information of a functional modality, wherein the registration information of the functional modality includes a description of the functional modality in natural language form.

[0381] In one possible implementation, the registration information for the functional modality also includes a list of parameters for the functional modality.

[0382] In one possible implementation, the processing module 2401 is also used to register functional modes with the LM.

[0383] In one possible implementation, the processing module 2401 is also used to record the registration information of the functional modality.

[0384] In one possible implementation, the processing module 2401 is further configured to record information indicating the user equipment ID of the user equipment, wherein registration information of the functional mode is received from the user equipment.

[0385] In one possible implementation, the processing module 2401 is further configured to obtain the semantic information of the functional modality through the embedder based on the description of the functional modality.

[0386] In one possible implementation, the processing module 2401 is also used to store semantic information of the functional modality.

[0387] In one possible implementation, the sending module 2402 is also used to send semantic information of the functional modality.

[0388] In one possible implementation, the processing module 2401 is further configured to determine the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities, wherein the semantic information of each of the at least one functional modalities is obtained based on the description of each of the at least one functional modalities.

[0389] In one possible implementation, the processing module 2401 is further configured to: determine that the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities is less than a threshold; and reject the control message.

[0390] In one possible implementation, the processing module 2401 is further configured to: determine the portion of the control message that does not contain any parameters, and obtain the semantic information of the control message through the embedder based on that portion.

[0391] In one possible implementation, the processing module 2401 is further configured to: form a first information payload, wherein the first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information; form a second information payload, wherein the second information payload includes the semantic information of the control message, and the second transmission opportunity is used to transmit the second information payload information.

[0392] In one possible implementation, the control message also includes a parameter list, and the first information payload also includes the parameter list of the control message.

[0393] In one possible implementation, the processing module 2401 is further configured to: encode the second information payload using a first encoding method, wherein the first information payload also includes information from the first encoding method.

[0394] In one possible implementation, the processing module 2401 is further configured to encode the first information payload using a second encoding method.

[0395] In one possible implementation, the first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

[0396] In one possible implementation, the processing module 2401 is further configured to: determine the semantic information most relevant to the semantic information of the control message from the semantic information of each of the at least one registered functional modes, based on the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modes; determine at least one user equipment ID or at least one group of user equipment IDs corresponding to the most relevant semantic information, wherein the first information payload further includes: at least one user equipment ID or at least one group of user equipment IDs; or the first information payload further includes information indicating at least one user equipment ID or information indicating at least one group of user equipment IDs.

[0397] In one possible implementation, the information indicating at least one user equipment ID includes a first code generated based on at least one user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or the information indicating at least one group of user equipment IDs includes a second code generated based on at least one group of user equipment IDs, wherein the second code includes a mask, a spreading code, or an interleaving code.

[0398] In one possible implementation, the processing module 2401 is further configured to: generate a first code based on at least one user equipment ID; or generate a second code based on at least one group of user equipment IDs.

[0399] In one possible implementation, the sending module 2402 is further configured to: send a first information payload during a first transmission opportunity and send a second information payload during a second transmission opportunity.

[0400] In one possible implementation, the first transmission opportunity is located in the control physical channel and the second transmission opportunity is located in the data physical channel; or both the first and second transmission opportunities are located in the control physical channel; or both the first and second transmission opportunities are located in the data physical channel.

[0401] In one possible implementation, the processing module 2401 is further configured to: register a functional mode to at least one LM by providing registration information of the functional mode to at least one LM, wherein the at least one LM includes LM.

[0402] In one possible implementation, the sending module 2402 is further configured to: send configuration information of at least one embedder, wherein the embedder belongs to at least one embedder.

[0403] In one possible implementation, the configuration information of at least one embedder is sent via a broadcast message, multicast message, or unicast message.

[0404] In one possible implementation, the configuration information of at least one embedder includes the architecture and parameters of each of the at least one embedder.

[0405] In one possible implementation, the configuration information of at least one embedder also includes the embedder ID of each embedder in at least one embedder.

[0406] In one possible implementation, the first information payload further includes: information indicating the embedder ID of the embedder used to obtain semantic information of the control message.

[0407] In one possible implementation, the information payload is sent via multicast or unicast messages.

[0408] In one possible implementation, the processing module 2401 is further configured to: in response to the LM generating at least two consecutive control messages more than a preset number of times; combine the two functional modes corresponding to the at least two consecutive control messages to generate a combined functional mode; the sending module 2402 is further configured to send configuration information of the combined functional mode.

[0409] In one possible implementation, the processing module 2401 is also used to register the combined functional modes with the LM.

[0410] In one possible implementation, there are multiple LMs, each of which includes the LM, wherein each of the multiple LMs has at least one embedder.

[0411] In one possible implementation, at least one functional modality is registered in one or more of the multiple LMs, but not in all of the multiple LMs.

[0412] In one possible implementation, the multiple LMs include at least one LM that is compatible with the LTE system.

[0413] In one possible implementation, the multiple LMs include at least one LM that is compatible with the 5G system.

[0414] In one possible implementation, the first LM of a plurality of LMs has a first embeddinger, the second LM of a plurality of LMs has a second embeddinger, and the first embeddinger and the second embeddinger are constructed based on vocabularies of different domains.

[0415] In one possible implementation, LM has a first embeddinger and a second embeddinger built based on vocabularies from different domains.

[0416] In one possible implementation, the processing module 2401 is also used to register the LM.

[0417] In one possible implementation, the processing module 2401 is also used to register at least one embedder of the LM.

[0418] Figure 25 A schematic diagram of a second device according to one or more exemplary embodiments of the present disclosure is shown. This second device can be applied to the aforementioned user equipment, or to a chip installed in or applied to the user equipment, or any other device, module, circuit, or unit capable of implementing the steps of the user equipment in the above method embodiments. Figure 25 As shown, the second device 2500 may include:

[0419] The acquisition module 2501 is used to acquire the information payload, wherein the information payload includes the semantic information of the control message;

[0420] The processing module 2502 is configured to: determine target semantic information from at least one semantic information according to the semantic information of the control message, wherein each semantic information in the at least one semantic information corresponds to a corresponding functional modality in at least one functional modality, and is obtained according to the description of the corresponding functional modality, the description of the corresponding functional modality being in natural language form; and execute the functional modality corresponding to the target semantic information.

[0421] In one possible implementation, the processing module 2502 is further configured to: encapsulate each of the at least one functional modalities into a calling function, wherein the calling function of the corresponding functional modality includes a description of the corresponding functional modality, or the calling function of the corresponding functional modality includes a parameter list of the corresponding functional modality and a description of the corresponding functional modality.

[0422] In one possible implementation, the calling function includes an application programming interface (API) calling function.

[0423] In one possible implementation, the second device further includes a sending module 2503, which is configured to: send registration information for each of at least one functional mode, wherein the registration information for each functional mode includes a description of the corresponding functional mode, or the registration information for each functional mode includes a parameter list and a description of the corresponding functional mode.

[0424] In one possible implementation, the acquisition module 2501 is configured to: acquire a first information payload during a first transmission opportunity, wherein the first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information of the control message; and acquire a second information payload during a second transmission opportunity based on the start position information of the second transmission opportunity and the length information of the semantic information of the control message, wherein the second information payload includes the semantic information of the control message. The processing module 2502 is further configured to: decode the first information payload to acquire the start position information of the second transmission opportunity and the length information of the semantic information of the control message; and decode the second information payload to acquire the semantic information of the control message.

[0425] In one possible implementation, the first information payload also includes a list of parameters for the control message.

[0426] In one possible implementation, the first information payload also includes information from the first encoding method, and the second information payload is decoded using the first encoding method.

[0427] In one possible implementation, a second encoding method is used to decode the first information payload.

[0428] In one possible implementation, the first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

[0429] In one possible implementation, the first information payload may further include: information indicating a user equipment identifier (ID) or information indicating a group of user equipment IDs.

[0430] In one possible implementation, the acquisition module 2501 is configured to: acquire a first code generated based on information indicating a user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or acquire a second code generated based on information indicating a group of user equipment IDs, wherein the second code includes a mask, a spreading code, or an interleaving code.

[0431] In one possible implementation, the processing module 2502 is configured to: stop decoding the second information payload in response to determining that the user equipment ID or group user equipment ID does not match the user equipment ID or group user equipment ID of the user equipment.

[0432] In one possible implementation, the acquisition module 2501 is used to acquire configuration information of at least one embedder.

[0433] In one possible implementation, the semantic information of the control message is obtained through a first embedding in at least one embedding, and at least one piece of semantic information of at least one functional modality is obtained through the first embedding.

[0434] In one possible implementation, the configuration information of at least one embedder includes the embedder ID of each of the at least one embedder.

[0435] In one possible implementation, the information payload includes information indicating the embedder ID of the first embedder.

[0436] In one possible implementation, information indicating the embedder ID of the first embedder is carried in the first information payload.

[0437] In one possible implementation, the processing module 2502 is configured to: acquire one or more pieces of semantic information through at least one embeddinger according to the description of each of the at least one functional modalities, wherein for each of the at least one functional modalities, each of the at least one embeddinger is used to acquire the corresponding semantic information; and store one or more pieces of semantic information.

[0438] In one possible implementation, the processing module 2502 is configured to: obtain at least one semantic information of at least one functional modality from one or more stored semantic information based on information indicating the embedder ID of the first embedder.

[0439] In one possible implementation, the processing module 2502 is configured to: obtain at least one semantic information of at least one functional modality through a first embedder, based on the description of each functional modality in at least one functional modality.

[0440] In one possible implementation, the acquisition module 2501 is configured to: receive at least one piece of semantic information for at least one functional modality.

[0441] In one possible implementation, the processing module 2502 is configured to: determine, from at least one piece of semantic information, the semantic information most relevant to the semantic information of the control message as the target semantic information.

[0442] In one possible implementation, there are more than one functional modality, and the acquisition module 2501 is also used to acquire configuration information of the combined functional modality, wherein the combined functional modality is composed of at least two functional modalities from the more than one functional modality; the processing module 2502 is also used to encapsulate the combined functional modality into a first calling function.

[0443] In one possible implementation, the configuration information for the combined functional modalities includes the calling order, whereby the first calling function calls the calling functions corresponding to at least two functional modalities in the calling order.

[0444] Those skilled in the art should understand that the descriptions of the above modules in the embodiments of this disclosure can be interpreted as descriptions of the data processing methods in the embodiments of this disclosure.

[0445] This disclosure provides a third apparatus including processing circuitry for performing any of the above-described communication methods executed by a central device. It should be understood that the third apparatus is capable of performing the steps executed by the central device in the above method embodiments, which will not be elaborated further here.

[0446] This disclosure provides a fourth apparatus, including processing circuitry for performing any of the above-described communication methods executed by a user equipment. It should be understood that the fourth apparatus is capable of performing the steps executed by the user equipment in the above method embodiments, which will not be elaborated further here.

[0447] This disclosure provides a communication system including at least one first device and / or at least one third device, as well as at least one second device and / or at least one fourth device.

[0448] This disclosure provides a communication system including at least one first processing circuit and at least one second processing circuit. The first processing circuit is used to execute the steps performed by a central device in any of the above-described communication methods, and the second processing circuit is used to execute the steps performed by a user device in any of the above-described communication methods.

[0449] This disclosure provides a computer-readable medium storing computer-executable instructions that, when executed by a processor, cause the processor to perform any of the communication methods described above.

[0450] This disclosure provides a computer program product including computer-executable instructions that, when executed by a processor, cause the processor to perform any of the above-described communication methods.

[0451] Although the embodiments of this disclosure describe methods and processes by way of steps performed in a certain order, one or more steps in the methods and processes may be omitted or modified as appropriate. Where appropriate, one or more steps may be performed in an order other than that described.

[0452] In some aspects of this disclosure, a non-transitory computer-readable medium is provided that stores instructions that, when executed by a processor, enable the processor to implement the methods of this disclosure.

[0453] In some aspects of this disclosure, an apparatus / chipset system is provided, including components for implementing methods implemented by the sensing devices of this disclosure.

[0454] In some aspects of this disclosure, an apparatus / chipset system is provided, including components for implementing the methods implemented by the central device of this disclosure.

[0455] In some aspects of this disclosure, an apparatus / chipset system is provided, including components for implementing methods implemented by the GPT device of this disclosure.

[0456] In some aspects of this disclosure, a system is provided that includes at least two of the means in the sensing device of this disclosure, the means in the central device of this disclosure, and the means in the GPT device of this disclosure.

[0457] In some aspects of this disclosure, an apparatus / chipset system is provided, including at least one processor that executes instructions stored in a computer-readable medium to implement a method implemented by a sensing device of this disclosure.

[0458] In some aspects of this disclosure, an apparatus / chipset system is provided, including at least one processor that executes instructions stored in a computer-readable medium to implement a method implemented by the central device of this disclosure.

[0459] In some aspects of this disclosure, an apparatus / chipset system is provided, including at least one processor that executes instructions stored in a computer-readable medium to implement a method implemented by the GPT device of this disclosure.

[0460] This disclosure includes various embodiments, not only method embodiments but also other embodiments, such as apparatus embodiments and embodiments related to non-transitory computer-readable storage media. Embodiments may be incorporated individually or in combination with the features disclosed herein.

[0461] Although this disclosure references illustrative embodiments, it is not intended to be construed in a limiting sense. Those skilled in the art will recognize, upon referring to this description, various modifications and combinations of the illustrative embodiments, as well as other embodiments of this disclosure.

[0462] Additionally or alternatively, features disclosed herein in the context of any particular embodiment may be implemented in other embodiments. For example, method embodiments may be implemented in apparatus, system, and / or computer program product embodiments. Furthermore, although embodiments are described primarily in the context of methods and apparatus, other implementations are contemplated as instructions stored in non-transitory computer-readable media, etc. Such media may store programs or instructions to perform any of the methods consistent with this disclosure.

Claims

1. A control method, characterized in that, include: Use the Language Model (LM) to generate control messages in natural language form; Obtain the semantic information of the control message based on the control message; An information payload is formed, wherein the information payload includes the semantic information of the control message; Send the aforementioned information payload.

2. The method according to claim 1, characterized in that, Also includes: Obtain registration information of a functional modality, wherein the registration information of the functional modality includes a description of the functional modality, the description being in natural language form.

3. The method according to claim 2, characterized in that, The registration information of the functional modality also includes a parameter list of the functional modality.

4. The method according to claim 2 or 3, characterized in that, Also includes: Register the functional mode with the LM.

5. The method according to claim 4, characterized in that, Also includes: Record the registration information of the functional modality.

6. The method according to claim 5, characterized in that, Also includes: Record information indicating the user equipment identifier ID of the user equipment, wherein the registration information of the functional mode is received from the user equipment.

7. The method according to any one of claims 2 to 6, characterized in that, Also includes: Based on the description of the functional modality, the semantic information of the functional modality is obtained through an embedder.

8. The method according to claim 7, characterized in that, Also includes: The semantic information of the functional modality is stored.

9. The method according to claim 7 or 8, characterized in that, Also includes: Send the semantic information of the functional modality.

10. The method according to any one of claims 7 to 9, characterized in that, Prior to forming the information payload, the method further includes: Determine the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities, wherein the semantic information of each of the at least one functional modalities is obtained based on the description of each of the at least one functional modalities.

11. The method according to claim 10, characterized in that, Also includes: The correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities is determined to be below a threshold. The control message is rejected.

12. The method according to any one of claims 1 to 11, characterized in that, The step of obtaining the semantic information of the control message based on the control message includes: Identify the portion of the control message that does not contain any parameters; According to the aforementioned portion, the semantic information of the control message is obtained through the embedder.

13. The method according to claim 12, characterized in that, The formation of the information payload includes: A first information payload is formed, wherein the first information payload includes the starting position information of the second transmission opportunity and the length information of the semantic information; A second information payload is formed, wherein the second information payload includes the semantic information of the control message, and the second transmission opportunity is used to transmit the second information payload.

14. The method according to claim 13, characterized in that, The control message also includes a parameter list, and the first information payload also includes the parameter list of the control message.

15. The method according to claim 13, characterized in that, Also includes: The second information payload is encoded using the first encoding method. The first information payload also includes information from the first encoding method.

16. The method according to claim 15, characterized in that, Also includes: The first information payload is encoded using a second encoding method.

17. The method according to claim 16, characterized in that, The first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

18. The method according to claim 13, characterized in that, Also includes: Based on the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities, the semantic information most relevant to the semantic information of the control message is determined from the semantic information of each of the at least one registered functional modalities. Determine at least one user equipment ID or at least one group of user equipment IDs corresponding to the most relevant semantic information, wherein, The first information payload further includes the at least one user equipment ID, or the at least one group of user equipment IDs; or the first information payload further includes information indicating the at least one user equipment ID, or information indicating the at least one group of user equipment IDs.

19. The method according to claim 18, characterized in that, The information indicating the at least one user equipment ID includes a first code generated based on the at least one user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or The information indicating the at least one group user equipment ID includes a second code generated based on the at least one group user equipment ID, wherein the second code includes a mask, a spreading code, or an interleaving code.

20. The method according to claim 19, characterized in that, Also includes: The first code is generated based on the at least one user equipment ID; or The second code is generated based on the at least one group of user equipment IDs.

21. The method according to claim 13, characterized in that, The payload for transmitting the information includes: The first information payload is transmitted during the first transmission opportunity. The second information payload is transmitted during the second transmission opportunity.

22. The method according to claim 21, characterized in that, The first transmission opportunity is located in the control physical channel, and the second transmission opportunity is located in the data physical channel; or Both the first transmission opportunity and the second transmission opportunity are located in the control physical channel; or Both the first and second transmission opportunities are located in the data physical channel.

23. The method according to claim 4, characterized in that, Registering the functional modality with the LM includes: The functional modality is registered to at least one LM by providing the registration information of the functional modality to the at least one LM, wherein the at least one LM includes the LM.

24. The method according to claim 7, characterized in that, Also includes: Send configuration information for at least one embedder, wherein the embedder belongs to the at least one embedder.

25. The method according to claim 24, characterized in that, The configuration information of the at least one embedder is sent via broadcast message, multicast message, or unicast message.

26. The method according to claim 24 or 25, characterized in that, The configuration information of the at least one embedder includes the architecture and parameters of each of the at least one embedder.

27. The method according to claim 26, characterized in that, The configuration information of the at least one embedder also includes the embedder ID of each of the at least one embedder.

28. The method according to claim 27, characterized in that, The first information payload further includes: information indicating an embedder ID of an embedder used to acquire the semantic information of the control message.

29. The method according to any one of claims 1 to 28, characterized in that, The information payload is sent via multicast or unicast messages.

30. The method according to any one of claims 1 to 29, characterized in that, Also includes: In response to the LM generating at least two consecutive control messages more than a preset number of times, the two functional modes corresponding to the two consecutive control messages are combined to generate a combined functional mode; Send the configuration information for the combined functional mode.

31. The method according to claim 30, characterized in that, Also includes: Register the combined functional mode with the LM.

32. The method according to any one of claims 1 to 31, characterized in that, There are multiple LMs, the multiple LMs including the LM, wherein each of the multiple LMs has at least one embedder.

33. The method according to claim 32, characterized in that, The at least one functional mode is registered in one or more of the plurality of LMs, but not in all of the plurality of LMs.

34. The method according to claim 33, characterized in that, The plurality of LMs includes at least one LM that is compatible with the LTE system.

35. The method according to claim 32, characterized in that, The plurality of LMs includes at least one LM that is compatible with 5G systems.

36. The method according to claim 32, characterized in that, The first LM of the plurality of LMs has a first embeddinger, the second LM of the plurality of LMs has a second embeddinger, and the first embeddinger and the second embeddinger are constructed based on vocabularies from different domains.

37. The method according to claim 1, characterized in that, The LM has a first embeddinger and a second embeddinger built based on vocabularies from different domains.

38. The method according to claim 1, characterized in that, Also includes: Register the LM.

39. The method according to claim 38, characterized in that, Also includes: Register at least one embedder of the LM.

40. A control method, characterized in that, include: Acquire information payload, wherein the information payload includes semantic information of control messages; Based on the semantic information of the control message, target semantic information is determined from at least one piece of semantic information, wherein each piece of semantic information corresponds to a corresponding functional modality in at least one functional modality, and is obtained based on the description of the corresponding functional modality, the description of the corresponding functional modality being in natural language form; Execute the functional modality corresponding to the target semantic information.

41. The method according to claim 40, characterized in that, Also includes: Each of the at least one functional modalities is encapsulated as a calling function, wherein the calling function of the corresponding functional modality includes the description of the corresponding functional modality, or the calling function of the corresponding functional modality includes a parameter list of the corresponding functional modality and the description of the corresponding functional modality.

42. The method according to claim 41, characterized in that, The calling functions include application programming interface (API) calling functions.

43. The method according to claim 40, characterized in that, Also includes: Send registration information for each of the at least one functional modalities, wherein the registration information for each functional modality includes the description of the corresponding functional modality, or the registration information for each functional modality includes a parameter list and the description of the corresponding functional modality.

44. The method according to claim 40, characterized in that, The information payload acquired includes: During the first transmission opportunity, a first information payload is acquired, wherein the first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information of the control message; The first information payload is decoded to obtain the starting position information of the second transmission opportunity and the length information of the semantic information of the control message; Based on the starting position information of the second transmission opportunity and the length information of the semantic information of the control message, a second information payload is acquired during the second transmission opportunity, wherein the second information payload includes the semantic information of the control message; The second information payload is decoded to obtain the semantic information of the control message.

45. The method according to claim 44, characterized in that, The first information payload also includes: a parameter list for the control message.

46. ​​The method according to claim 44 or 45, characterized in that, The first information payload also includes information about the first encoding method, and the second information payload is decoded using the first encoding method.

47. The method according to claim 46, characterized in that, The first information payload is decoded using a second encoding method.

48. The method according to claim 47, characterized in that, The first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

49. The method according to any one of claims 44 to 48, characterized in that, The first information payload also includes: information indicating a user equipment identifier ID or information indicating a group user equipment ID.

50. The method according to any one of claims 44 to 47, characterized in that, Also includes: Obtain a first code generated based on information indicating the user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or Obtain a second code generated based on the information of the instruction group user equipment ID, wherein the second code includes a mask, a spreading code, or an interleaving code.

51. The method according to claim 49 or 50, characterized in that, Also includes: In response to determining that the user equipment ID or the group user equipment ID does not match the user equipment ID or the group user equipment ID of the user equipment, the decoding of the second information payload is stopped.

52. The method according to any one of claims 44 to 51, characterized in that, Also includes: Obtain configuration information for at least one embedder.

53. The method according to claim 52, characterized in that, The semantic information of the control message is obtained through a first embedding device in the at least one embedding device, and the at least one piece of semantic information of the at least one functional modality is obtained through the first embedding device.

54. The method according to claim 53, characterized in that, The configuration information of the at least one embedder includes the embedder ID of each of the at least one embedder.

55. The method according to claim 54, characterized in that, The information payload includes information indicating the embedder ID of the first embedder.

56. The method according to claim 55, characterized in that, The information indicating the embedder ID of the first embedder is carried in the first information payload.

57. The method according to claim 54 or 55, characterized in that, Also includes: Based on the description of each of the at least one functional modalities, one or more pieces of semantic information are obtained through the at least one embeddinger, wherein for each of the at least one functional modalities, each of the at least one embeddingers is used to obtain the corresponding semantic information; Store one or more pieces of semantic information.

58. The method according to claim 57, characterized in that, Also includes: Based on the information indicating the embedder ID of the first embedder, the at least one semantic information of the at least one functional modality is obtained from the stored one or more semantic information.

59. The method according to claim 55 or 56, characterized in that, After obtaining the information payload, the method further includes: Based on the description of each of the at least one functional modalities, the at least one piece of semantic information of the at least one functional modality is obtained through the first embeddinger.

60. The method according to any one of claims 40 to 51, characterized in that, Also includes: Receive at least one piece of semantic information from the at least one functional modality.

61. The method according to any one of claims 40 to 60, characterized in that, Determining the target semantic information includes: From the at least one semantic information, determine the semantic information most relevant to the semantic information of the control message as the target semantic information.

62. The method according to any one of claims 40 to 61, characterized in that, If there is more than one functional mode, the method further includes: Obtain configuration information for a combined functional mode, wherein the combined functional mode is composed of at least two functional modes from the one or more functional modes; The combined functional modality is encapsulated as a first calling function.

63. The method according to claim 62, characterized in that, The configuration information of the combined functional modal includes the calling order, wherein the first calling function calls the calling functions corresponding to the at least two functional modalities in accordance with the calling order.

64. A first device, characterized in that, include: Processing module, used for: Use the Language Model (LM) to generate control messages in natural language form; Obtain the semantic information of the control message based on the control message; An information payload is formed, wherein the information payload includes the semantic information of the control message; The sending module is used to send the information payload.

65. The first apparatus according to claim 64, characterized in that, The first device further includes an acquisition module, configured to: acquire registration information of a functional modality, wherein the registration information of the functional modality includes a description of the functional modality, the description being in natural language form.

66. The first apparatus according to claim 65, characterized in that, The registration information of the functional modality also includes a parameter list of the functional modality.

67. The first apparatus according to claim 65 or 66, characterized in that, The processing module is also used for: Register the functional mode with the LM.

68. The first apparatus according to claim 67, characterized in that, The processing module is also used for: Record the registration information of the functional modality.

69. The first apparatus according to claim 68, characterized in that, The processing module is also used for: Record information indicating the user equipment identifier ID of the user equipment, wherein the registration information of the functional mode is received from the user equipment.

70. The first device according to any one of claims 65 to 69, characterized in that, The processing module is also used for: Based on the description of the functional modality, the semantic information of the functional modality is obtained through an embedder.

71. The first apparatus according to claim 70, characterized in that, The processing module is also used for: The semantic information of the functional modality is stored.

72. The first apparatus according to claim 70 or 71, characterized in that, The processing module is also used for: Send the semantic information of the functional modality.

73. The first device according to any one of claims 70 to 72, characterized in that, The processing module is also used for: Determine the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities, wherein the semantic information of each of the at least one functional modalities is obtained based on the description of each of the at least one functional modalities.

74. The first apparatus according to claim 73, characterized in that, The processing module is also used for: The correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities is determined to be below a threshold. The control message is rejected.

75. The first device according to any one of claims 64 to 74, characterized in that, The processing module is also used for: Identify the portion of the control message that does not contain any parameters; According to the aforementioned portion, the semantic information of the control message is obtained through the embedder.

76. The first apparatus according to claim 75, characterized in that, The processing module is also used for: A first information payload is formed, wherein the first information payload includes the starting position information of the second transmission opportunity and the length information of the semantic information; A second information payload is formed, wherein the second information payload includes the semantic information of the control message, and the second transmission opportunity is used to transmit the second information payload information.

77. The first apparatus according to claim 76, characterized in that, The control message also includes a parameter list, and the first information payload also includes the parameter list of the control message.

78. The first apparatus according to claim 76, characterized in that, The processing module is also used for: The second information payload is encoded using a first encoding method, wherein, The first information payload also includes information from the first encoding method.

79. The first apparatus according to claim 78, characterized in that, The processing module is also used for: The first information payload is encoded using a second encoding method.

80. The first apparatus according to claim 79, characterized in that, The first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

81. The first apparatus according to claim 76, characterized in that, The processing module is also used for: Based on the correlation between the semantic information of the control message and the semantic information of each of the at least one registered functional modalities, the semantic information most relevant to the semantic information of the control message is determined from the semantic information of each of the at least one registered functional modalities. Determine at least one user equipment ID or at least one group of user equipment IDs corresponding to the most relevant semantic information, wherein, The first information payload further includes the at least one user equipment ID, or the at least one group of user equipment IDs; or the first information payload further includes information indicating the at least one user equipment ID, or information indicating the at least one group of user equipment IDs.

82. The first apparatus according to claim 81, characterized in that, The information indicating the at least one user equipment ID includes a first code generated based on the at least one user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or The information indicating the at least one group user equipment ID includes a second code generated based on the at least one group user equipment ID, wherein the second code includes a mask, a spreading code, or an interleaving code.

83. The first apparatus according to claim 82, characterized in that, The processing module is also used for: The first code is generated based on the at least one user equipment ID; or The second code is generated based on the at least one group of user equipment IDs.

84. The first apparatus according to claim 76, characterized in that, The sending module is also used for: The first information payload is transmitted during the first transmission opportunity. The second information payload is transmitted during the second transmission opportunity.

85. The first apparatus according to claim 84, characterized in that, The first transmission opportunity is located in the control physical channel, and the second transmission opportunity is located in the data physical channel; or Both the first transmission opportunity and the second transmission opportunity are located in the control physical channel; or Both the first and second transmission opportunities are located in the data physical channel.

86. The first apparatus according to claim 67, characterized in that, The processing module is also used for: The functional modality is registered to at least one LM by providing the registration information of the functional modality to the at least one LM, wherein the at least one LM includes the LM.

87. The first apparatus according to claim 70, characterized in that, The sending module is also used for: Send configuration information for at least one embedder, wherein the embedder belongs to the at least one embedder.

88. The first apparatus according to claim 87, characterized in that, The configuration information of the at least one embedder is sent via broadcast message, multicast message, or unicast message.

89. The first apparatus according to claim 87 or 88, characterized in that, The configuration information of the at least one embedder includes the architecture and parameters of each of the at least one embedder.

90. The first apparatus according to claim 89, characterized in that, The configuration information of the at least one embedder also includes the embedder ID of each of the at least one embedder.

91. The first apparatus according to claim 90, characterized in that, The first information payload further includes: information indicating an embedder ID of an embedder used to acquire the semantic information of the control message.

92. The first device according to any one of claims 64 to 91, characterized in that, The information payload is sent via multicast or unicast messages.

93. The first device according to any one of claims 64 to 92, characterized in that, The processing module is also used for: In response to the LM generating at least two consecutive control messages more than a preset number of times, the two functional modes corresponding to the two consecutive control messages are combined to generate a combined functional mode; The sending module is also used to send the configuration information of the combined functional mode.

94. The first apparatus according to claim 93, characterized in that, The processing module is also used for: Register the combined functional mode with the LM.

95. The first device according to any one of claims 64 to 94, characterized in that, There are multiple LMs, the multiple LMs including the LM, wherein each of the multiple LMs has at least one embedder.

96. The first apparatus according to claim 95, characterized in that, The at least one functional mode is registered in one or more of the plurality of LMs, but not in all of the plurality of LMs.

97. The first apparatus according to claim 96, characterized in that, The plurality of LMs includes at least one LM that is compatible with the LTE system.

98. The first apparatus according to claim 95, characterized in that, The plurality of LMs includes at least one LM that is compatible with 5G systems.

99. The first apparatus according to claim 95, characterized in that, The first LM of the plurality of LMs has a first embeddinger, the second LM of the plurality of LMs has a second embeddinger, and the first embeddinger and the second embeddinger are constructed based on vocabularies from different domains.

100. The first apparatus according to claim 64, characterized in that, The LM has a first embeddinger and a second embeddinger built based on vocabularies from different domains.

101. The first apparatus according to claim 64, characterized in that, The processing module is also used for: Register the LM.

102. The first apparatus according to claim 101, characterized in that, The processing module is also used for: Register at least one embedder of the LM.

103. A second device, characterized in that, include: An acquisition module is used to acquire an information payload, wherein the information payload includes semantic information of a control message; Processing module, used for: Based on the semantic information of the control message, target semantic information is determined from at least one piece of semantic information, wherein each piece of semantic information corresponds to a corresponding functional modality in at least one functional modality, and is obtained based on the description of the corresponding functional modality, the description of the corresponding functional modality being in natural language form; Execute the functional modality corresponding to the target semantic information.

104. The second apparatus according to claim 103, characterized in that, The processing module is also used for: Each of the at least one functional modalities is encapsulated as a calling function, wherein the calling function of the corresponding functional modality includes the description of the corresponding functional modality, or the calling function of the corresponding functional modality includes a parameter list of the corresponding functional modality and the description of the corresponding functional modality.

105. The second apparatus according to claim 104, characterized in that, The calling functions include application programming interface (API) calling functions.

106. The second apparatus according to claim 103, characterized in that, The second device further includes a transmitting module, the transmitting module being used for: Send registration information for each of the at least one functional modalities, wherein the registration information for each functional modality includes the description of the corresponding functional modality, or the registration information for each functional modality includes a parameter list and the description of the corresponding functional modality.

107. The second apparatus according to claim 103, characterized in that, The acquisition module is used for: During the first transmission opportunity, a first information payload is acquired, wherein the first information payload includes the start position information of the second transmission opportunity and the length information of the semantic information of the control message; Based on the starting position information of the second transmission opportunity and the length information of the semantic information of the control message, a second information payload is acquired during the second transmission opportunity, wherein the second information payload includes the semantic information of the control message; The processing module is also used for: The first information payload is decoded to obtain the starting position information of the second transmission opportunity and the length information of the semantic information of the control message; The second information payload is decoded to obtain the semantic information of the control message.

108. The second apparatus according to claim 107, characterized in that, The first information payload also includes: a parameter list for the control message.

109. The second apparatus according to claim 107 or 108, characterized in that, The first information payload also includes information about the first encoding method, and the second information payload is decoded using the first encoding method.

110. The second apparatus according to claim 109, characterized in that, The first information payload is decoded using a second encoding method.

111. The second apparatus according to claim 110, characterized in that, The first encoding method includes a first modulation and coding scheme (MCS), and the second encoding method includes a second MCS.

112. The second device according to any one of claims 107 to 111, characterized in that, The first information payload also includes: information indicating a user equipment identifier ID or information indicating a group user equipment ID.

113. The second device according to any one of claims 107 to 110, characterized in that, The acquisition module is used for: Obtain a first code generated based on information indicating the user equipment ID, wherein the first code includes a mask, a spreading code, or an interleaving code; or Obtain a second code generated based on the information of the instruction group user equipment ID, wherein the second code includes a mask, a spreading code, or an interleaving code.

114. The second device according to claim 112 or 113, characterized in that, The processing module is used for: In response to determining that the user equipment ID or the group user equipment ID does not match the user equipment ID or the group user equipment ID of the user equipment, the decoding of the second information payload is stopped.

115. The second device according to any one of claims 107 to 114, characterized in that, The acquisition module is used for: Obtain configuration information for at least one embedder.

116. The second apparatus according to claim 115, characterized in that, The semantic information of the control message is obtained through a first embedding device in the at least one embedding device, and the at least one piece of semantic information of the at least one functional modality is obtained through the first embedding device.

117. The second apparatus according to claim 116, characterized in that, The configuration information of the at least one embedder includes the embedder ID of each of the at least one embedder.

118. The second apparatus according to claim 117, characterized in that, The information payload includes information indicating the embedder ID of the first embedder.

119. The second apparatus according to claim 118, characterized in that, The information indicating the embedder ID of the first embedder is carried in the first information payload.

120. The second device according to claim 118 or 117, characterized in that, The processing module is used for: Based on the description of each of the at least one functional modalities, one or more pieces of semantic information are obtained through the at least one embeddinger, wherein for each of the at least one functional modalities, each of the at least one embeddingers is used to obtain the corresponding semantic information; Store one or more pieces of semantic information.

121. The second apparatus according to claim 120, characterized in that, The processing module is used for: Based on the information indicating the embedder ID of the first embedder, the at least one semantic information of the at least one functional modality is obtained from the stored one or more semantic information.

122. The method according to claim 118 or 119, characterized in that, The processing module is used for: Based on the description of each of the at least one functional modalities, the at least one piece of semantic information of the at least one functional modality is obtained through the first embeddinger.

123. The second device according to any one of claims 103 to 114, characterized in that, The acquisition module is used for: Receive at least one piece of semantic information from the at least one functional modality.

124. The second device according to any one of claims 103 to 123, characterized in that, The processing module is used for: From the at least one semantic information, determine the semantic information most relevant to the semantic information of the control message as the target semantic information.

125. The second device according to any one of claims 103 to 124, characterized in that, If there is more than one functional mode, the acquisition module is further used for: Obtain configuration information for a combined functional mode, wherein the combined functional mode is composed of at least two functional modes from the one or more functional modes; The processing module is also used to encapsulate the combined functional modality into a first calling function.

126. The second apparatus according to claim 125, characterized in that, The configuration information of the combined functional modal includes the calling order, wherein the first calling function calls the calling functions corresponding to the at least two functional modalities in accordance with the calling order.

127. A third device, characterized in that, It includes a processing circuit for performing the control method according to any one of claims 1 to 39.

128. A fourth device, characterized in that, It includes processing circuitry for performing the control method according to any one of claims 40 to 63.

129. A communication system, characterized in that, include: The first device according to any one of claims 64 to 102 or the third device according to claim 127; The second device according to any one of claims 103 to 126 or the fourth device according to claim 128.

130. A communication system, characterized in that, include: A first processing circuit is configured to execute the control method according to any one of claims 1 to 39; The second processing circuit is used to execute the control method according to any one of claims 40 to 63.

131. A computer-readable storage medium storing computer-executable instructions, characterized in that, When the computer execution instructions are executed by the processor, the processor performs the control method according to any one of claims 1 to 39 or the control method according to any one of claims 40 to 63.

132. A computer program product comprising computer-executable instructions, characterized in that, When the computer execution instructions are executed by the processor, the processor performs the control method according to any one of claims 1 to 39 or the control method according to any one of claims 40 to 63.

Images