CN116137595A

CN116137595A - AI information transmission method and device

Info

Publication number: CN116137595A
Application number: CN202111357214.0A
Authority: CN
Inventors: 任千尧; 崇卫微; 纪子超; 孙鹏; 吴晓波
Original assignee: Vivo Mobile Communication Co Ltd
Current assignee: Vivo Mobile Communication Co Ltd
Priority date: 2021-11-16
Filing date: 2021-11-16
Publication date: 2023-05-19
Also published as: WO2023088269A1

Abstract

The embodiment of the application discloses a transmission method and equipment of AI information, belonging to the technical field of communication. The AI information transmission method of the embodiment of the application comprises the following steps: the first communication equipment and the second communication equipment transmit AI information; the first AI model representation used by the first communication device matches the second AI model representation used by the second communication device.

Description

AI information transmission method and device

Technical Field

The application belongs to the technical field of communication, and particularly relates to a transmission method and equipment of artificial intelligence (Artificial Intelligence, AI) information, wherein the equipment can comprise communication equipment such as an AI information transmission device, a terminal or network side equipment and the like.

Background

The application of AI technology to a communication system can significantly improve communication system performance. However, since the common AI model representation (such as AI framework) is more, the emphasis points of different AI model representations and even the supported development languages are different, and the description and the implementation of the functions of the AI model are different, so that AI information cannot be transferred between two or more communication devices using different AI model representations, and the performance of the communication system is affected.

Disclosure of Invention

The embodiment of the application provides a transmission method and equipment of AI information, which can solve the problem that the performance of a communication system is affected because AI information under different AI model expression modes cannot be understood among communication equipment.

In a first aspect, there is provided a transmission method of AI information, including: the first communication equipment and the second communication equipment transmit AI information; the first AI model representation mode used by the first communication device is matched with the second AI model representation mode used by the second communication device.

In a second aspect, there is provided a transmission apparatus of AI information, including: the transmission module is used for carrying out AI information transmission with the second communication equipment; the first AI model representation mode used by the device is matched with the second AI model representation mode used by the second communication equipment.

In a third aspect, there is provided a communication device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, which program or instruction when executed by the processor implements the method according to the first aspect.

In a fourth aspect, a communication device is provided, including a processor and a communication interface, where the communication interface is configured to perform AI information transmission with a second communication device; the first AI model representation mode used by the communication equipment is matched with the second AI model representation mode used by the second communication equipment.

In a fifth aspect, there is provided a readable storage medium having stored thereon a program or instructions which when executed by a processor implement the method according to the first aspect.

In a sixth aspect, there is provided a chip comprising a processor and a communication interface coupled to the processor for running a program or instructions to implement the method of the first aspect.

In a seventh aspect, a computer program/program product is provided, the computer program/program product being stored in a non-transitory storage medium, the computer program/program product being executed by at least one processor to implement the method according to the first aspect.

In the embodiment of the application, since the first AI model representation mode used by the first communication device is matched with the second AI model representation mode used by the second communication device, the first communication device and the second communication device keep consistent understanding of the AI information in the AI model representation mode, and the AI information can be transmitted between the first communication device and the second communication device, which is beneficial to improving the performance of the communication system.

Drawings

Fig. 1 is a schematic diagram of a wireless communication system according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a transmission method of AI information according to an embodiment of the application;

fig. 3 is a schematic structural diagram of a transmission apparatus of AI information according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a communication device according to an embodiment of the present application;

fig. 5 is a schematic structural view of a terminal according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a network-side device according to an embodiment of the present application.

Detailed Description

Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or otherwise described herein, and that the terms "first" and "second" are generally intended to be used in a generic sense and not to limit the number of objects, for example, the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/" generally means a relationship in which the associated object is an "or" before and after.

It is noted that the techniques described in embodiments of the present application are not limited to long term evolution (Long Term Evolution, LTE)/LTE evolution (LTE-Advanced, LTE-a) systems, but may also be used in other wireless communication systems, such as code division multiple access (Code Division Multiple Access, CDMA), time division multiple access (Time Division Multiple Access, TDMA), frequency division multiple access (Frequency Division Multiple Access, FDMA), orthogonal frequency division multiple access (Orthogonal Frequency Division Multiple Access, OFDMA), single carrier frequency division multiple access (Single carrier-Frequency Division Multiple Access, SC-FDMA), and other systems. The terms "system" and "network" in embodiments of the present application are often used interchangeably, and the techniques described may be used for both the above-mentioned systems and radio technologies, as well as other systems and radio technologies. The following description describes a New air interface (NR) system for purposes of example, and in much of the description that follows, NR terminology is used, these techniques are also applicable to applications other than NR system applications, such as generation 6 (6) ^th Generation, 6G) communication system.

Fig. 1 shows a schematic diagram of a wireless communication system to which embodiments of the present application are applicable. The wireless communication system includes a terminal 11 and a network device 12. The terminal 11 may also be called a terminal Device or a User Equipment (UE), and the terminal 11 may be a terminal-side Device such as a mobile phone, a tablet (Tablet Personal Computer), a Laptop (Laptop Computer) or a notebook (Personal Digital Assistant, PDA), a palm Computer, a netbook, an ultra-mobile personal Computer (ultra-mobile personal Computer, UMPC), a mobile internet Device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR)/Virtual Reality (VR) Device, a robot, a Wearable Device (VUE), a pedestrian terminal (PUE), a smart home (home Device with a wireless communication function, such as a refrigerator, a television, a washing machine, or furniture, etc.), and the Wearable Device includes: intelligent watches, intelligent bracelets, intelligent headphones, intelligent glasses, intelligent jewelry (intelligent bracelets, intelligent rings, intelligent necklaces, intelligent bracelets, intelligent footchains, etc.), intelligent bracelets, intelligent clothing, game machines, etc. Note that, the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may be a base station or a core network, wherein the base station may be called a node B, an evolved node B, an access point, a base transceiver station (Base Transceiver Station, BTS), a radio base station, a radio transceiver, a basic service set (Basic Service Set, BSS), an extended service set (Extended Service Set, ESS), a node B, an evolved node B (eNB), a next generation node B (gNB), a home node B, a home evolved node B, a WLAN access point, a WiFi node, a transmission and reception point (Transmitting Receiving Point, TRP), or some other suitable terminology in the field, and the base station is not limited to a specific technical vocabulary, and it should be noted that, in the embodiment of the present application, only the base station in the NR system is taken as an example, but the specific type of the base station is not limited.

The following describes in detail, with reference to the attached drawings, the AI information transmission method and apparatus provided by the embodiments of the present application through some embodiments and application scenarios thereof.

As shown in fig. 2, the embodiment of the present application provides a method 200 for transmitting AI information, which may be performed by a first communication device, in other words, by software or hardware installed in the first communication device, where the first communication device may be a network side device or a terminal, and the method includes the following steps.

S202: the first communication equipment and the second communication equipment transmit AI information; the first AI model representation used by the first communication device matches the second AI model representation used by the second communication device.

The AI information referred to in various embodiments of the present application may include AI models (or AI networks), parameters, structures, etc., including, for example, neural network models, decision tree models, support vector machine models, bayesian classifier models, etc. The following embodiments will be described by taking an AI model as an example, and it should be understood that the AI information is not limited to the AI model.

The AI model representation modes mentioned in the embodiments of the present application, such as the first AI model representation mode, the second AI model representation mode, and the like, may specifically be AI frameworks, where the AI frameworks include TensorFlow, pyTorch, keras, MXNet, caffe2, and the like, and each AI framework uses its own method to describe the AI model, so as to complete the operations of building, training, and deducing the AI model.

Optionally, the transmission of AI information by the first communication device and the second communication device includes at least one of:

1) The first communication device receives AI information from the second communication device. For example, the terminal receives the AI model from the network side device, that is, the network side device may send the trained AI model to the terminal; for another example, the first terminal receives the AI model from the second terminal, i.e., the second terminal may send the trained AI model to the first terminal.

2) The first communication device transmits AI information to the second communication device. For example, the network side device sends the AI model to the terminal, i.e., the network side device may send the trained AI model to the terminal; for another example, the second terminal may send the AI model to the first terminal, i.e., the second terminal may send the trained AI model to the first terminal.

Optionally, matching the first AI model representation used by the first communication device with the second AI model representation used by the second communication device includes: the first AI model representation mode used by the first communication device is the same as the second AI model representation mode used by the second communication device; alternatively, the version supported by the first AI model representation and the version supported by the second AI model representation are progressive to each other. The first AI model representation mentioned here is the same as the second AI model representation, and may be the same in type (e.g., both are tensorflows), the same in version and other information, the same in file save format, and so on. The mutual progression mentioned here is that, for example, the version supported by the first AI model representation is a TensorFlow, the version supported by the second AI model representation is a Keras, which is a version of the package based on the TensorFlow.

According to the AI information transmission method, as the first AI model representation mode used by the first communication device is matched with the second AI model representation mode used by the second communication device, the first communication device and the second communication device keep consistent understanding of the AI information in the AI model representation mode, and the AI information can be transmitted between the first communication device and the second communication device, so that the communication system performance is improved.

The AI information transmission method provided in this embodiment of the present application may ensure that a plurality of communication devices (or called AI nodes) use a matched (e.g., identical) AI framework to transmit AI information, where the AI information includes an AI model, parameters, a structure, and so on, by using some methods, for example, a network side device configuration or a mode agreed in advance by a protocol. The communication device may be a base station, a terminal, a certain computing node of a core network, a functional node, or the like, as long as it is a node that performs training or estimation using an AI function. Alternatively, the above-mentioned several communication devices may be two AI nodes, or may be multiple AI nodes, or more than three AI nodes, where one AI node uses multiple different AI frameworks to interact with one AI framework of another AI node respectively.

On the basis of embodiment 200, before the first communication device and the second communication device perform AI information transmission, the method further includes the steps of: the first communication device receives first indication information, wherein the first indication information is used for indicating a plurality of AI model representation modes supported by the second communication device, and the AI model representation modes comprise the second AI model representation mode; the first communication device sends first feedback information, where the first feedback information is used to instruct the first communication device to select an AI model representation from the multiple AI model representations, and the selected AI model representation includes the first AI model representation.

Optionally, the method further comprises: the first communication device receives third indication information, where the third indication information is used to indicate the first communication device to receive or send the AI information.

In this embodiment, for example, the first communication device is a terminal, the second communication device is a network-side device, and the network-side and the terminal-side communicate AI information using AI frameworks that match each other.

Specifically, the network side may issue an AI framework selection range (may be implemented by the first indication information), and the terminal selects and reports a selection result (may be implemented by the first feedback information).

In this embodiment, the network side may train the same AI model using different AI frameworks, and broadcast the AI frameworks used to the served terminals, where each terminal receives the same content; the terminal selects an AI frame suitable for the terminal according to the terminal condition, and feeds back the selected AI frame and additional information; the additional information includes, for example: the terminal selects the version, variety and other information of the AI framework; if the terminal does not find a suitable AI frame, the terminal feeds back unselected information. In this way, the network side uses the matched AI framework and the terminal to transfer the AI model according to the information reported by each terminal, for example, the network side sends the AI model to the terminal. Optionally, the subsequent network side may further instruct the terminal (may be implemented by the third instruction information) whether the AI model transfer relationship may be established, and the time-frequency resource location of AI model transfer, and so on.

On the basis of embodiment 200, before the first communication device and the second communication device perform AI information transmission, the method further includes: the first communication device sends second indication information, wherein the second indication information is used for indicating AI model representation modes supported by the first communication device, and the AI model representation modes supported by the first communication device comprise the first AI model representation modes; the second indication information is further used for the second communication device to select an AI model representation from AI model representations supported by the first communication device, where the selected AI model representation includes the second AI model representation.

In this embodiment, for example, the first communication device is a terminal, the second communication device is a network-side device, and the network-side and the terminal-side communicate AI information using AI frameworks that match each other. In this embodiment, the terminal may report the AI framework capability (may be implemented by the second indication information), and the network side selects the AI framework to be used and indicates the AI framework to the terminal.

Specifically, the network side may instruct the terminal to report the supported AI framework capability; the terminal reports the supported AI frame capacity to indicate the AI frames and the additional information (which can be realized by the second indication information) which can be supported by the terminal; the network side selects whether to establish the transfer relation of the AI model with the terminal according to the capability of the terminal. In one example, the network side uses a matched AI framework for subsequent AI model training. Optionally, the network side informs the terminal of the content of the AI framework used, which may be specifically implemented through the third indication information. The embodiment can be completed when the terminal accesses the cell, or the network side indicates the terminal to complete through signaling.

The foregoing embodiments describe that the first communication device and the second communication device use the matched AI model representation to perform AI information transmission, and when the first communication device establishes a connection with the second communication device, the first communication device and the second communication device may determine the matched AI model representation. In the subsequent process, the first communication device and the second communication device can calibrate the AI model representation mode again; alternatively, the AI model representation may be recalibrated after a change in cell, environment, etc. The calibration or switching process of the AI model representations will be described in several embodiments.

On the basis of embodiment 200, the method further comprises: the first communication device sends first request information, where the first request information is used to request switching of the first AI model representation. For example, the terminal sends first request information to the network side for requesting to switch AI frameworks.

Optionally, the first request information includes at least one of: 1) The AI model representation supported by the first communication device; 2) The first communication device selects an AI model representation from a plurality of AI model representations supported by the second communication device; 3) And switching the moment of the first AI model representation mode.

After the first communication device transmits the first request information, the method further includes: the first communication device receives fourth indication information, and the first communication device performs one of the following according to the fourth indication information: 1) No further AI information is transmitted with the second communication device, e.g., fourth indication information indicates no further AI information is transmitted; 2) Transmitting AI information with the second communication device based on the AI model representation after the switching, for example, fourth indication information indicates which AI model representation method to switch to; 3) And transmitting AI information between the first communication device and the second communication device based on the original AI model representation mode, for example, the fourth indication information indicates that the AI representation method is not switched.

In this embodiment, for example, the first communication device is a terminal, the second communication device is a network-side device, and the terminal may apply for switching the AI model representation. For example, the terminal applies for a new AI framework according to its own situation, for example, a high-precision framework (TensorFlow, etc.) is used when the power is high, and a low-precision framework (caffe, etc.) is switched when the power is low, so that the flexibility of communication is improved. In this way, the network side selects one of the following according to the AI framework newly requested by the terminal: a) Discarding the AI connection; b) Using a new AI framework connection; c) The original AI framework connection is maintained. In this example, the terminal may directly send its updated AI framework capability to the network side, so that the network side decides on a new AI framework; or the terminal selects one from the selectable AI frames issued by the network side, notifies the network, and indicates the terminal selection result by the network.

On the basis of embodiment 200, the method further comprises: the first communication device receives fifth indication information, where the fifth indication information is used to instruct the first communication device to switch the first AI model representation.

Optionally, the fifth indication information includes at least one of: 1) The second communication device selects an AI model representation mode from AI model representation modes supported by the first communication device; 2) And the second communication equipment supports a plurality of AI model representation modes.

Optionally, the method further comprises: AI information is no longer transmitted between the first communication device and the second communication device if at least one of: 1) The first communication device only supports one AI model representation; 2) The AI model representation supported by the first communication device does not have the AI model representation to which the second communication device expects to switch; 3) The first communication device does not transmit feedback information of the fifth indication information.

In this embodiment, for example, the first communication device is a terminal, the second communication device is a network-side device, and the network-side instructs the terminal to switch the AI-model representation (may be implemented by the fifth instruction information). For example, the network side decides to change the AI framework matched with the terminal according to the use condition, which comprises one of the following steps: a) The network side selects a new AI frame from the AI frame capacity reported by the terminal and indicates the terminal; b) The network side sends a new optional AI frame to the terminal for selection; c) If the terminal can only support one AI frame, or if no AI frame which the terminal wants to switch is in the AI frames supported by the terminal, or the terminal feeds back unselected information, the network side indicates whether the terminal is disconnected.

On the basis of embodiment 200, the method further comprises: the first communication device (such as a base station before terminal switching) sends the AI model representation mode used or supported by the second communication device (such as a terminal) to a third communication device (such as a target base station after terminal switching); the second communication device is further configured to perform AI information transmission with the third communication device.

In this embodiment, for example, the first communication device is a network-side device, the second communication device is a terminal, and when a cell handover occurs in the terminal, AI model representation information of the terminal is interacted between cells. For example, the old cell transfers information such as the AI network condition and AI matching framework of the terminal to the new cell through the data channel between cells.

On the basis of embodiment 200, the method further comprises: the first communication device (such as a target base station after terminal switching) receives sixth indication information from the third communication device (such as a base station before terminal switching); the first communication device determines at least one of the following according to the sixth indication information: whether AI information is transmitted between the first communication device and the second communication device; and the AI model representation mode used for transmitting AI information between the first communication equipment and the second communication equipment.

In this embodiment, for example, the first communication device is a network-side device, the second communication device is a terminal, and when a cell handover occurs in the terminal, AI model representation information of the terminal is interacted between cells. For example, the new cell decides whether to continue to establish AI model delivery with the terminal according to its own capability, and whether the user is required to adjust the AI framework; if the adjustment is needed, the new cell sends signaling to the terminal for adjustment.

Optionally, the method provided by the above two embodiments further includes: the first communication device receives seventh indication information from a fourth communication device (such as a core network device); and the first communication equipment adjusts the used AI model representation mode according to the seventh indication information.

In this embodiment, the core network device may also adjust cell information, for example, the core network device may re-issue the required AI information to the new cell according to the cell handover situation; the new cell and the terminal reestablish the link of AI information transfer, and a new AI framework is used; the terminal retrains the AI model using the new AI framework and parameters.

On the basis of embodiment 200, in the case where the third communication device to be connected to the first communication device for communication does not support the use of the AI functionality, the method further includes one of: 1) The first communication device does not establish communication connection with the third communication device and is still connected with the second communication device; 2) The first communication device establishes communication connection with the third communication device, and AI information is not transmitted between the first communication device and the third communication device; 3) The first communication device establishes communication connection with the third communication device, and the first communication device stops using the AI function.

In this embodiment, for example, the first communication device is a terminal, the second communication device is a network-side device, the new cell to which the terminal is to be connected does not support the use of the AI function, and the terminal may perform one of the following: 1) The cell is not handed over. 2) And switching the cell, and not transmitting AI information. The terminal side independently used AI model can continue to operate, for example, channel estimation based on terminal AI, etc.; the terminal and the network side are required to simultaneously use the function stop of the AI model, and the conventional method is switched. Such as AI-based channel state information (Channel State Information, CSI) feedback, etc. 3) And switching cells, cutting off all AI connections, stopping using the AI function, and completely recovering the traditional method by the terminal.

The above description is given taking the example that the first communication device is a terminal and the second communication device is a network side device, in fact, both the first communication device and the second communication device may be terminals, and specific implementation processes are not described by way of example.

On the basis of embodiment 200, before the first communication device and the second communication device perform AI information transmission, the method further includes: the first communication device sends second request information when determining that the AI model representation mode supported by the first communication device is matched with the AI model representation mode supported by the second communication device, wherein the second request information is used for requesting the first communication device and the second communication device to transmit AI information by using the matched AI model representation mode; the first communication device receives second feedback information, wherein the second feedback information is used for indicating the first communication device and the second communication device to transmit the AI information by using the matched AI model representation mode.

Optionally, before the first communication device and the second communication device perform AI information transmission, the method further includes at least one of: 1) The first communication device acquires an AI model representation mode supported by the second communication device; 2) The first communication device sends the AI model representation mode supported by the first communication device to the second communication device.

This embodiment, for example, the first communication device and the second communication device are two parallel nodes, such as terminals, and the first communication device and the second communication device may use the same AI framework.

In this embodiment, for example, each AI node sends an AI framework that can be supported by itself to all the participating AI nodes, for example, when AI node a wants to establish a data connection with AI node B as required, it first distinguishes whether the AI node a and AI node B have the same AI framework capability, if so, sends a request to AI node B, and after AI node B receives, feeds back information about whether the AI framework can be used by AI node a.

On the basis of embodiment 200, before the first communication device and the second communication device perform AI information transmission, the method further includes: the first communication device sends third request information to a fifth communication device, wherein the third request information is used for requesting the first communication device and the second communication device to transmit AI information by using a matched AI model representation mode; the first communication device receives eighth indication information from the fifth communication device, wherein the eighth indication information indicates that the first communication device and the second communication device transmit AI information by using a matched AI model representation.

Optionally, the fifth communication device stores the AI model representation supported by the first communication device and the AI model representation supported by the second communication device; or the third request information includes an AI model representation supported by the first communication device, and the sixth communication device is further configured to obtain, when receiving the third request information, the AI model representation supported by the second communication device; or the third request information includes an AI model representation supported by the first communication device, and the fifth communication device is further configured to send the AI model representation supported by the first communication device to the second communication device, and determine, based on a report result of the second communication device, that the second communication device supports and the first communication device uses the matched AI model representation to transmit AI information.

In this embodiment, the first communication device and the second communication device are two parallel nodes, such as a terminal, and the fifth communication device may be a third party node, where the third party node assists the first communication device and the second communication device in using a matched AI framework. The third party node may be a special terminal, a base station, a core network device, etc.

In one example, a third party node requires all participating AI nodes to send self-supporting AI frameworks. The AI node A sends a request for establishing connection with the AI node B to a third party node, wherein the content comprises at least one of the following components: the identification of the AI node which requests connection, the AI frame which the AI node A can support, and the AI frame which the AI node A wants to use; the third party node decides whether the AI node A and the AI node B establish AI connection according to the AI framework capacity and the actual situation of the AI node A and the AI node B; the third party node transmits indication information to the AI node a and the AI node B.

In another example, the third party node is not aware of the AI framework capabilities of other AI nodes. The AI node A sends a request for establishing connection with the AI node B to a third party node, wherein the content comprises at least one of the following components: the identification of the AI node which requests connection, the AI frame which the AI node A can support, and the AI frame which the AI node A wants to use; the third party node requests the reporting capability of the AI node B and makes a decision based on the reporting capability; or the third party node sends information to B, and the B decides and reports the result; the third party node sends information to a.

In order to describe the AI information transmission method provided in the embodiments of the present application in detail, several specific embodiments will be described below.

Example 1

This embodiment mainly describes CSI feedback process based on AI model (or AI network).

In this embodiment, the terminal and the network perform CSI feedback by using a combined AI network, that is, the terminal converts the channel information into CSI feedback information of several bits (bits) through the AI network and reports the CSI feedback information to the base station, and the base station receives the CSI feedback information of the terminal and recovers the channel information through the AI network at the base station side.

The CSI feedback here focuses on precoding matrix indicator (Pre-coding Matrix Indicator, PMI) information, which may be a calculated precoding matrix or a channel itself.

Because the network of the base station and the terminal need to perform joint training, different cell channel conditions are different, and new network parameters may also need to be needed, when a user accesses the network, the base station needs to send the network parameters used by the user to the user, and for this reason, the base station and the user need to first establish a matched AI framework (abbreviated as framework).

When a user accesses a cell, the cell transmits supportable frame information to the user, specifically, the frame information can be broadcasted through a physical random access channel (Physical Random Access Channel, PRACH), or the frame information can be transmitted to the user through a data channel after the user accesses the cell, and for all the users, the cell transmits the same frame information. After receiving the frame information, the terminal selects whether a frame suitable for the terminal is available according to the self-capability.

If the terminal finds that all frameworks supported by the cell cannot be supported by the terminal or the terminal does not support the AI function, the terminal feeds back a message to the base station indicating that the appropriate framework is not selected.

If the terminal finds and fits the own frame, the terminal feeds back the selected frame and whether there is additional frame information, such as version of the frame, special operation set, etc.

And the base station determines whether to establish AI information transfer with the terminal according to the content fed back by the user, and if the AI information transfer cannot be established, the base station uses a non-AI codebook to perform CSI feedback.

If the appropriate AI framework exists, the base station uses the corresponding AI framework to send the trained network to the terminal, and ensures that the terminal can load the data structure. The specific AI model may transmit only the network part of the terminal or may transmit the base station and the joint network of the terminal together.

In another way, when the user accesses the cell, instead of sending the frame information from the cell, the user reports the frame information which can be supported by the user, and the network side selects an appropriate frame according to the frame information supported by the user and sends an AI model of CSI feedback under the corresponding frame, or the base station finds that a uniform AI frame cannot be established, and then selects to use non-AI codebook feedback.

Specifically, the specific signaling interaction process may be that when the user accesses the cell, the user interacts with each cell, and when other conditions are the same, the user preferentially selects the cell which can be matched with the AI framework, or after the user accesses the cell, the user determines the framework information with the accessed cell.

Example two

This embodiment mainly describes the AI network-based channel measurement procedure.

In the process of measuring the downlink channel by the UE, the UE may use the AI network to perform channel measurement, including channel estimation such as channel state information Reference Signal (Channel State Information-Reference Signal, CSI-RS), demodulation Reference Signal (Demodulation Reference Signal, DMRS), and radio resource management (Radio Resource Management, RRM) measurement. Also, due to the channel differences of different cells, when a user switches cells, it is often necessary to switch the network used because the network of the old cell cannot support the channel change under the new cell. Where the new cell needs to be frame matched with the user.

When a user switches cells, a data channel is established between the new cell and the old cell, the old cell sends the current user use AI frame information to the new cell, if the new cell does not support the AI frame, the new cell notifies the UE to resume the non-AI method to perform channel measurement, the notification can be downlink control information (Downlink Control Information, DCI), a media access control unit (Media Access Control Control Element, MAC CE) directly enables a terminal to modify the method, or a radio resource control (Radio Resource Control, RRC) configuration delay is effective.

The new cell may also resend the supported frame information to the user, or ask the user to report the supported frame information, and re-match, and the specific method is similar to the first embodiment.

If a new cell can support such a framework, the new cell may send the network structure and parameters of the new channel measurements directly using the corresponding framework without informing the user. If this framework supported by the new cell differs from the framework used by the user by version information, the user may be informed if the feedback is compatible with other versions.

Optionally, if the old cell has the frame capability of the user, when the new cell does not support the frame of the user, the old cell can be informed of the frame capability of the user to be sent, or the old cell can directly send the capability of the user to the new cell, so that the user capability can be directly obtained without reporting the capability of the user, and the new frame is selected.

Example III

This embodiment mainly describes a base station assisted positioning procedure based on AI network.

The AI positioning at the terminal side processes the positioning signal through the AI network to determine the position of the user, and the training and the inference of the network can be synchronously performed, namely, the training can be continuously performed. And the AI positioning at the network side can send the user after training the information at the network side through the AI network, thereby assisting the user in positioning.

The positioning accuracy and the movement speed have a great relationship, if the positioning is at the terminal side, a user moving at a low speed can use a simple network and even a simple frame to train, so that the calculated amount and the power consumption are reduced, and a user at a high speed needs a complex network, and a more powerful frame to train and improve the positioning accuracy. Thus, both the AI network and the AI framework may change as the speed of movement of the user changes.

For example, when the user is in low-speed motion, in order to save calculation amount and power consumption, the Caffe2 framework is used for training and deducing the positioning network, and as the speed of the user increases, the user can apply for training and deducing by using a finer framework, for example, the TensorFlow2 is used for deducing and training, so that the training speed and the deducing accuracy are improved.

First, if the user does not support other frameworks, the user chooses to continue using the existing framework or to use a non-AI method for channel prediction. If the user can support other frames and has a switching requirement, the user sends a switching request to the base station, wherein the frame and the information which are required to be switched are carried, and the base station judges whether the user can support the frame and whether the user can switch according to the frame information which is required to be switched, and indicates whether the user performs switching.

Or the user only sends a switching request, the base station determines whether the frame can be switched according to the service condition, indicates the user result, synchronously issues the frame information which can be switched if the frame information can be switched, and the user selects the frame which is wanted to be switched or enables the user to report the frame information which is wanted to be switched and can be supported, and then the base station selects the frame.

After determining the new frame, the terminal continues training under the new frame, and the network continues generating auxiliary information under the new frame and transmitting the auxiliary information to the terminal.

Example IV

This embodiment mainly introduces AI network interactions between terminals.

Considering that some AI functions only require the terminal to use AI networks, and do not need to perform joint training with the network side, for example, channel prediction, positioning and the like at the terminal side, the AI networks are affected by channel environments, and along with the movement of the terminal, the AI networks need to be continuously trained and updated. When the terminal B enters the area of the terminal a, the terminal a can transmit the trained network to the terminal B, and the terminal B trains based on the network of the terminal a.

Between any two associated nodes, the training complexity can be reduced by transferring the already trained network, and even the network trained by other nodes can be directly used.

Two terminals using the AI network can perform information interaction, for example, terminal a sends an AI framework matching request to terminal B through a side link (SideLink) channel, the AI framework matching request includes framework information that can be supported by the terminal B, and the terminal B determines whether the terminal B can be matched with the terminal B according to the framework that is being used by the terminal B, and then sends matching information to the terminal B.

Or the terminal A sends a request to the network side, and the network side judges whether the two terminals can perform frame matching according to the frame capability of the terminal A and the frame capability matched before the terminal B and informs the terminal A to use the same frame as the terminal B. After frame matching, terminal B may transmit network parameters directly to terminal a.

It should be noted that, in the AI information transmission method provided in the embodiment of the present application, the execution body may be an AI information transmission device, or a control module for executing the AI information transmission method in the AI information transmission device. In the embodiment of the present application, a method for transmitting AI information by using a transmitting device for AI information is taken as an example, and the transmitting device for AI information provided in the embodiment of the present application is described.

Fig. 3 is a schematic structural diagram of an AI information transmission apparatus according to an embodiment of the present application, which may correspond to the first communication device in other embodiments. As shown in fig. 3, the apparatus 300 includes the following modules.

A transmission module 302, configured to perform AI information transmission with the second communication device; the first AI model representation mode used by the device is matched with the second AI model representation mode used by the second communication equipment.

Optionally, the apparatus 300 further comprises a processing module, such as a processor or the like.

According to the AI information transmission device provided by the embodiment of the application, as the first AI model representation mode used by the AI information transmission device is matched with the second AI model representation mode used by the second communication equipment, the AI information transmission device and the second communication equipment keep consistent understanding of the AI information in the AI model representation mode, and the AI information transmission can be carried out between the AI information transmission device and the second communication equipment, so that the communication system performance is improved.

Optionally, as an embodiment, the first AI model representation used by the apparatus is the same as the second AI model representation used by the second communication device; alternatively, the version supported by the first AI model representation and the version supported by the second AI model representation are progressive to each other.

Optionally, as an embodiment, the transmission module 302 is configured to at least one of: receiving AI information from the second communication device; and sending AI information to the second communication equipment.

Optionally, as an embodiment, the transmission module 302 is further configured to: receiving first indication information, wherein the first indication information is used for indicating a plurality of AI model representation modes supported by the second communication equipment, and the AI model representation modes comprise the second AI model representation mode; and sending first feedback information, wherein the first feedback information is used for indicating an AI model representation mode selected by the device from the AI model representations, and the selected AI model representation mode comprises the first AI model representation mode.

Optionally, as an embodiment, the transmission module 302 is further configured to: transmitting second indication information, wherein the second indication information is used for indicating an AI model representation mode supported by the device, and the AI model representation mode supported by the device comprises the first AI model representation mode; the second indication information is further used for the second communication device to select an AI model representation from AI model representations supported by the apparatus, where the selected AI model representation includes the second AI model representation.

Optionally, as an embodiment, the transmission module 302 is further configured to: and receiving third indication information, wherein the third indication information is used for indicating the device to receive or send the AI information.

Optionally, as an embodiment, the transmission module 302 is further configured to: and sending first request information, wherein the first request information is used for requesting to switch the first AI model representation mode.

Optionally, as an embodiment, the first request information includes at least one of: the AI model representation mode supported by the device; the apparatus selects an AI model representation from a plurality of AI model representations supported by the second communication device; and switching the moment of the first AI model representation mode.

Optionally, as an embodiment, the transmission module 302 is further configured to: receiving fourth indication information, and executing one of the following according to the fourth indication information: AI information is no longer transmitted with the second communication device; the AI information is transmitted between the second communication equipment based on the AI model representation mode after switching; and transmitting AI information with the second communication equipment based on the original AI model representation mode.

Optionally, as an embodiment, the transmission module 302 is further configured to: fifth indication information is received, wherein the fifth indication information is used for indicating the device to switch the first AI model representation mode.

Optionally, as an embodiment, the fifth indication information includes at least one of: the second communication device selects an AI model representation mode from AI model representation modes supported by the device; and the second communication equipment supports a plurality of AI model representation modes.

Optionally, as an embodiment, the transmission module 302 is further configured to: AI information is no longer transmitted with the second communication device if at least one of: the device supports only one AI model representation; the AI model representation supported by the device does not have the AI model representation to which the second communication device expects to switch; the apparatus does not transmit feedback information of the fifth indication information.

Optionally, as an embodiment, the transmission module 302 is further configured to: sending the AI model representation mode used or supported by the second communication device to a third communication device; the second communication device is further configured to perform AI information transmission with the third communication device; or, receiving sixth indication information from the third communication device, and determining at least one of the following according to the sixth indication information: whether AI information is transmitted between the apparatus and the second communication device; and the AI model representation mode used for transmitting AI information between the device and the second communication equipment.

Optionally, as an embodiment, the transmission module 302 is further configured to: receiving seventh indication information from fourth communication equipment; and adjusting the used AI model representation mode according to the seventh indication information.

Optionally, as an embodiment, in a case where the AI functionality is not supported by the third communication device to be communicatively connected to the apparatus, the transmission module 302 is further configured to: the communication connection is not established with the third communication equipment, and the third communication equipment is still connected with the second communication equipment; establishing communication connection with the third communication equipment, wherein AI information is not transmitted between the third communication equipment and the communication equipment; and establishing communication connection with the third communication equipment, and stopping using the AI function.

Optionally, as an embodiment, the transmission module 302 is further configured to: sending second request information when determining that the AI model representation supported by the device matches the AI model representation supported by the second communication device, where the second request information is used to request the device and the second communication device to transmit AI information using the matched AI model representation; and receiving second feedback information, wherein the second feedback information is used for indicating the device and the second communication equipment to transmit the AI information by using the matched AI model representation mode.

Optionally, as an embodiment, the transmission module 302 is further configured to at least one of: acquiring an AI model representation mode supported by the second communication equipment; and sending the AI model representation mode supported by the device to the second communication equipment.

Optionally, as an embodiment, the transmission module 302 is further configured to: transmitting third request information to fifth communication equipment, wherein the third request information is used for requesting the equipment to transmit AI information by using a matched AI model representation mode; and receiving eighth indication information from the fifth communication device, wherein the eighth indication information indicates the device and the second communication device to transmit the AI information by using the matched AI model representation mode.

Optionally, as an embodiment, the fifth communication device stores the AI model representation supported by the apparatus and the AI model representation supported by the second communication device; or the third request information includes an AI model representation supported by the device, and the sixth communication device is further configured to obtain, when receiving the third request information, the AI model representation supported by the second communication device; or the third request information includes an AI model representation supported by the device, and the fifth communication device is further configured to send the AI model representation supported by the device to the second communication device, and determine, based on a report result of the second communication device, that the second communication device supports and the device uses a matched AI model representation to transmit AI information.

The apparatus 300 according to the embodiment of the present application may refer to the flow of the method 200 corresponding to the embodiment of the present application, and each unit/module in the apparatus 300 and the other operations and/or functions described above are respectively for implementing the corresponding flow in the method 200, and may achieve the same or equivalent technical effects, which are not described herein for brevity.

The AI information transmission device in this embodiment of the present application may be a device, a device with an operating system, or an electronic apparatus, or may be a component, an integrated circuit, or a chip in a terminal. The apparatus or electronic device may be a mobile terminal or a non-mobile terminal. By way of example, mobile terminals may include, but are not limited to, the types of terminals 11 listed above, and non-mobile terminals may be servers, network attached storage (Network Attached Storage, NAS), personal computers (personal computer, PCs), televisions (TVs), teller machines, self-service machines, etc., and embodiments of the present application are not limited in detail.

The AI information transmission device provided in this embodiment of the present application can implement each process implemented by the method embodiment of fig. 2, and achieve the same technical effects, so that repetition is avoided, and no further description is provided herein.

Optionally, as shown in fig. 4, the embodiment of the present application further provides a communication device 400, including a processor 401, a memory 402, and a program or an instruction stored in the memory 402 and capable of running on the processor 401, where, for example, the communication device 400 is a terminal, the program or the instruction is executed by the processor 401 to implement each process of the above-mentioned AI information transmission method embodiment, and achieve the same technical effects. When the communication device 400 is a network side device, the program or the instruction, when executed by the processor 401, implements the processes of the above-mentioned AI information transmission method embodiment, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.

The embodiment of the application also provides a terminal, which comprises a processor and a communication interface, wherein the communication interface is used for carrying out AI information transmission with the second communication equipment; the first AI model representation mode used by the terminal is matched with the second AI model representation mode used by the second communication equipment. The terminal embodiment corresponds to the terminal-side method embodiment, and each implementation process and implementation manner of the method embodiment are applicable to the terminal embodiment and can achieve the same technical effects. Specifically, fig. 5 is a schematic hardware structure of a terminal for implementing an embodiment of the present application.

The terminal 500 includes, but is not limited to: at least some of the components of the radio frequency unit 501, the network module 502, the audio output unit 503, the input unit 504, the sensor 505, the display unit 506, the user input unit 507, the interface unit 508, the memory 509, and the processor 510.

Those skilled in the art will appreciate that the terminal 500 may further include a power source (e.g., a battery) for powering the various components, and the power source may be logically coupled to the processor 510 via a power management system so as to perform functions such as managing charging, discharging, and power consumption via the power management system. The terminal structure shown in fig. 5 does not constitute a limitation of the terminal, and the terminal may include more or less components than shown, or may combine certain components, or may be arranged in different components, which will not be described in detail herein.

It should be appreciated that in embodiments of the present application, the input unit 504 may include a graphics processor (Graphics Processing Unit, GPU) 5041 and a microphone 5042, with the graphics processor 5041 processing image data of still pictures or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The display unit 506 may include a display panel 5061, and the display panel 5061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 507 includes a touch panel 5071 and other input devices 5072. Touch panel 5071, also referred to as a touch screen. Touch panel 5071 may include two parts, a touch detection device and a touch controller. Other input devices 5072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.

In this embodiment, after receiving downlink data from a network side device, the radio frequency unit 501 processes the downlink data with the processor 510; in addition, the uplink data is sent to the network side equipment. Typically, the radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.

The memory 509 may be used to store software programs or instructions as well as various data. The memory 509 may mainly include a storage program or instruction area and a storage data area, wherein the storage program or instruction area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. In addition, the Memory 509 may include a high-speed random access Memory, and may further include a non-transitory Memory, wherein the non-transitory Memory may be a Read Only Memory (ROM), a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable EPROM (EEPROM), or a flash Memory. Such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device.

Processor 510 may include one or more processing units; alternatively, the processor 510 may integrate an application processor that primarily processes operating systems, user interfaces, and applications or instructions, etc., with a modem processor that primarily processes wireless communications, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor 510.

The radio frequency unit 501 may be configured to perform AI information transmission with the second communication device; the first AI model representation mode used by the terminal is matched with the second AI model representation mode used by the second communication equipment.

According to the terminal provided by the embodiment of the application, as the first AI model representation mode used by the terminal is matched with the second AI model representation mode used by the second communication equipment, the terminal and the second communication equipment keep consistent understanding of the AI information in the AI model representation mode, and the AI information can be transmitted between the terminal and the second communication equipment, so that the communication system performance is improved.

The terminal 500 provided in this embodiment of the present application may further implement each process of the above embodiment of the AI information transmission method, and may achieve the same technical effects, so that repetition is avoided and no further description is given here.

The embodiment of the application also provides network side equipment, which comprises a processor and a communication interface, wherein the communication interface is used for carrying out AI information transmission with the second communication equipment; the first AI model representation mode used by the network side equipment is matched with the second AI model representation mode used by the second communication equipment. The network side device embodiment corresponds to the network side device method embodiment, and each implementation process and implementation manner of the method embodiment can be applied to the network side device embodiment, and the same technical effects can be achieved.

Specifically, the embodiment of the application also provides network side equipment. As shown in fig. 6, the network side device 600 includes: an antenna 61, a radio frequency device 62, a baseband device 63. The antenna 61 is connected to a radio frequency device 62. In the uplink direction, the radio frequency device 62 receives information via the antenna 61, and transmits the received information to the baseband device 63 for processing. In the downlink direction, the baseband device 63 processes information to be transmitted, and transmits the processed information to the radio frequency device 62, and the radio frequency device 62 processes the received information and transmits the processed information through the antenna 61.

The above-described band processing means may be located in the baseband apparatus 63, and the method performed by the network-side device in the above embodiment may be implemented in the baseband apparatus 63, and the baseband apparatus 63 includes the processor 64 and the memory 65.

The baseband apparatus 63 may, for example, include at least one baseband board, on which a plurality of chips are disposed, as shown in fig. 6, where one chip, for example, a processor 64, is connected to the memory 65 to call a program in the memory 65 to perform the network side device operation shown in the above method embodiment.

The baseband apparatus 63 may also include a network interface 66 for interacting with the radio frequency apparatus 62, such as a common public radio interface (Common Public Radio Interface, CPRI).

Specifically, the network side device in the embodiment of the application further includes: instructions or programs stored in the memory 65 and executable on the processor 64, the processor 64 invokes the instructions or programs in the memory 65 to perform the methods performed by the modules shown in fig. 3 and achieve the same technical effects, and are not repeated here.

The embodiment of the present application further provides a readable storage medium, where the readable storage medium may be volatile or non-volatile, and the readable storage medium may be transient or non-transient, and a program or an instruction is stored on the readable storage medium, where the program or the instruction is executed by a processor to implement each process of the above-mentioned AI information transmission method embodiment, and the process may achieve the same technical effect, so that repetition is avoided and no further description is given here.

The processor may be a processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.

The embodiment of the application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled with the processor, and the processor is configured to run a program or an instruction, implement each process of the above AI information transmission method embodiment, and achieve the same technical effect, so that repetition is avoided, and no further description is provided herein.

It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, or the like.

The embodiments of the present application further provide a computer program product stored in a non-transitory storage medium, where the computer program product is executed by at least one processor to implement each process of the above-mentioned AI information transmission method embodiment, and the same technical effects can be achieved, so that repetition is avoided, and details are not repeated here.

The embodiment of the present application further provides a communication device configured to perform each process of the above embodiment of the AI information transmission method, and achieve the same technical effects, which is not repeated herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network side device, etc.) to perform the method described in the embodiments of the present application.

The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.

Claims

1. A transmission method of artificial intelligence AI information, comprising:

the first communication equipment and the second communication equipment transmit AI information;

the first AI model representation mode used by the first communication device is matched with the second AI model representation mode used by the second communication device.

2. The method of claim 1, wherein the matching of the first AI model representation used by the first communication device with the second AI model representation used by the second communication device comprises:

the first AI model representation mode used by the first communication device is the same as the second AI model representation mode used by the second communication device; or alternatively, the process may be performed,

the version supported by the first AI model representation and the version supported by the second AI model representation are progressive to each other.

3. The method according to claim 1 or 2, wherein the transmission of AI information by the first communication device with the second communication device comprises at least one of:

the first communication device receives AI information from the second communication device;

the first communication device transmits AI information to the second communication device.

4. The method of claim 1, wherein prior to the transmission of AI information by the first communication device with the second communication device, the method further comprises:

the first communication device receives first indication information, wherein the first indication information is used for indicating a plurality of AI model representation modes supported by the second communication device, and the AI model representation modes comprise the second AI model representation mode;

the first communication device sends first feedback information, where the first feedback information is used to instruct the first communication device to select an AI model representation from the multiple AI model representations, and the selected AI model representation includes the first AI model representation.

5. The method of claim 1, wherein prior to the transmission of AI information by the first communication device with the second communication device, the method further comprises:

the first communication device sends second indication information, wherein the second indication information is used for indicating AI model representation modes supported by the first communication device, and the AI model representation modes supported by the first communication device comprise the first AI model representation modes; the second indication information is further used for the second communication device to select an AI model representation from AI model representations supported by the first communication device, where the selected AI model representation includes the second AI model representation.

6. The method according to claim 4 or 5, characterized in that the method further comprises:

the first communication device receives third indication information, where the third indication information is used to indicate the first communication device to receive or send the AI information.

7. The method according to claim 1, wherein the method further comprises:

the first communication device sends first request information, where the first request information is used to request switching of the first AI model representation.

8. The method of claim 7, wherein the first request information comprises at least one of:

the AI model representation supported by the first communication device;

the first communication device selects an AI model representation from a plurality of AI model representations supported by the second communication device;

and switching the moment of the first AI model representation mode.

9. The method according to claim 7 or 8, wherein after the first communication device transmits the first request information, the method further comprises: the first communication device receives fourth indication information, and the first communication device performs one of the following according to the fourth indication information:

AI information is no longer transmitted with the second communication device;

the AI information is transmitted between the second communication equipment based on the AI model representation mode after switching;

and transmitting AI information with the second communication equipment based on the original AI model representation mode.

10. The method according to claim 1, wherein the method further comprises:

the first communication device receives fifth indication information, where the fifth indication information is used to instruct the first communication device to switch the first AI model representation.

11. The method of claim 10, wherein the fifth indication information comprises at least one of:

the second communication device selects an AI model representation mode from AI model representation modes supported by the first communication device;

and the second communication equipment supports a plurality of AI model representation modes.

12. The method according to claim 10 or 11, characterized in that the method further comprises: AI information is no longer transmitted between the first communication device and the second communication device if at least one of:

the first communication device only supports one AI model representation;

The AI model representation supported by the first communication device does not have the AI model representation to which the second communication device expects to switch;

the first communication device does not transmit feedback information of the fifth indication information.

13. The method according to claim 1, wherein the method further comprises:

the first communication device sends the AI model representation mode used or supported by the second communication device to a third communication device; the second communication device is further configured to perform AI information transmission with the third communication device; or alternatively, the process may be performed,

the first communication device receives sixth indication information from the third communication device; the first communication device determines at least one of the following according to the sixth indication information: whether AI information is transmitted between the first communication device and the second communication device; and the AI model representation mode used for transmitting AI information between the first communication equipment and the second communication equipment.

14. The method of claim 13, wherein the method further comprises:

the first communication device receives seventh indication information from the fourth communication device;

And the first communication equipment adjusts the used AI model representation mode according to the seventh indication information.

15. The method of claim 1, wherein in the event that a third communication device with which the first communication device is to establish a communication connection does not support the use of AI functionality, the method further comprises one of:

the first communication device does not establish communication connection with the third communication device and is still connected with the second communication device;

the first communication device establishes communication connection with the third communication device, and AI information is not transmitted between the first communication device and the third communication device;

the first communication device establishes communication connection with the third communication device, and the first communication device stops using the AI function.

16. The method of claim 1, wherein prior to the transmission of AI information by the first communication device with the second communication device, the method further comprises:

the first communication device sends second request information when determining that the AI model representation mode supported by the first communication device is matched with the AI model representation mode supported by the second communication device, wherein the second request information is used for requesting the first communication device and the second communication device to transmit AI information by using the matched AI model representation mode;

The first communication device receives second feedback information, wherein the second feedback information is used for indicating the first communication device and the second communication device to transmit the AI information by using the matched AI model representation mode.

17. The method of claim 16, wherein prior to the transmission of AI information by the first communication device with the second communication device, the method further comprises at least one of:

the first communication device acquires an AI model representation mode supported by the second communication device;

the first communication device sends the AI model representation mode supported by the first communication device to the second communication device.

18. The method of claim 1, wherein prior to the transmission of AI information by the first communication device with the second communication device, the method further comprises:

the first communication device sends third request information to a fifth communication device, wherein the third request information is used for requesting the first communication device and the second communication device to transmit AI information by using a matched AI model representation mode;

the first communication device receives eighth indication information from the fifth communication device, wherein the eighth indication information indicates that the first communication device and the second communication device transmit AI information by using a matched AI model representation.

19. The method of claim 18, wherein the step of providing the first information comprises,

the fifth communication device stores the AI model representation supported by the first communication device and the AI model representation supported by the second communication device; or alternatively, the process may be performed,

the third request information comprises an AI model representation supported by the first communication device, and the sixth communication device is further configured to obtain the AI model representation supported by the second communication device when the third request information is received; or alternatively, the process may be performed,

the third request information comprises an AI model representation supported by the first communication device, and the fifth communication device is further configured to send the AI model representation supported by the first communication device to the second communication device, and determine, based on a report result of the second communication device, that the second communication device supports and the first communication device uses the matched AI model representation to transmit AI information.

20. An AI information transmission apparatus, comprising:

the transmission module is used for carrying out AI information transmission with the second communication equipment;

the first AI model representation mode used by the device is matched with the second AI model representation mode used by the second communication equipment.

21. The apparatus of claim 20, wherein a first AI model representation used by the apparatus is the same as a second AI model representation used by the second communication device; alternatively, the version supported by the first AI model representation and the version supported by the second AI model representation are progressive to each other.

22. The apparatus of claim 20 or 21, wherein the transmission module is configured to at least one of:

receiving AI information from the second communication device;

and sending AI information to the second communication equipment.

23. The apparatus of claim 20, wherein the transmission module is further configured to:

receiving first indication information, wherein the first indication information is used for indicating a plurality of AI model representation modes supported by the second communication equipment, and the AI model representation modes comprise the second AI model representation mode;

and sending first feedback information, wherein the first feedback information is used for indicating an AI model representation mode selected by the device from the AI model representations, and the selected AI model representation mode comprises the first AI model representation mode.

24. The apparatus of claim 20, wherein the transmission module is further configured to:

transmitting second indication information, wherein the second indication information is used for indicating an AI model representation mode supported by the device, and the AI model representation mode supported by the device comprises the first AI model representation mode; the second indication information is further used for the second communication device to select an AI model representation from AI model representations supported by the apparatus, where the selected AI model representation includes the second AI model representation.

25. The apparatus of claim 23 or 24, wherein the transmission module is further configured to:

and receiving third indication information, wherein the third indication information is used for indicating the device to receive or send the AI information.

26. The apparatus of claim 20, wherein the transmission module is further configured to:

and sending first request information, wherein the first request information is used for requesting to switch the first AI model representation mode.

27. The apparatus of claim 26, wherein the first request information comprises at least one of:

the AI model representation mode supported by the device;

The apparatus selects an AI model representation from a plurality of AI model representations supported by the second communication device;

and switching the moment of the first AI model representation mode.

28. The apparatus of claim 26 or 27, wherein the transmission module is further configured to: receiving fourth indication information, and executing one of the following according to the fourth indication information:

AI information is no longer transmitted with the second communication device;

29. The apparatus of claim 20, wherein the transmission module is further configured to:

fifth indication information is received, wherein the fifth indication information is used for indicating the device to switch the first AI model representation mode.

30. The apparatus of claim 29, wherein the fifth indication information comprises at least one of:

the second communication device selects an AI model representation mode from AI model representation modes supported by the device;

31. The apparatus of claim 29 or 30, wherein the transmission module is further configured to: AI information is no longer transmitted with the second communication device if at least one of:

the device supports only one AI model representation;

the AI model representation supported by the device does not have the AI model representation to which the second communication device expects to switch;

the apparatus does not transmit feedback information of the fifth indication information.

32. The apparatus of claim 20, wherein the transmission module is further configured to:

sending the AI model representation mode used or supported by the second communication device to a third communication device; the second communication device is further configured to perform AI information transmission with the third communication device;

or alternatively, the process may be performed,

receiving sixth indication information from third communication equipment, and determining at least one of the following according to the sixth indication information: whether AI information is transmitted between the apparatus and the second communication device; and the AI model representation mode used for transmitting AI information between the device and the second communication equipment.

33. The apparatus of claim 32, wherein the transmission module is further configured to: receiving seventh indication information from fourth communication equipment; and adjusting the used AI model representation mode according to the seventh indication information.

34. The apparatus of claim 20, wherein the transmission module is further configured to, in the event that the AI function is not supported by a third communication device with which the apparatus is to establish a communication connection, one of:

the communication connection is not established with the third communication equipment, and the third communication equipment is still connected with the second communication equipment;

establishing communication connection with the third communication equipment, wherein AI information is not transmitted between the third communication equipment and the communication equipment;

and establishing communication connection with the third communication equipment, and stopping using the AI function.

35. The apparatus of claim 20, wherein the transmission module is further configured to:

sending second request information when determining that the AI model representation supported by the device matches the AI model representation supported by the second communication device, where the second request information is used to request the device and the second communication device to transmit AI information using the matched AI model representation;

and receiving second feedback information, wherein the second feedback information is used for indicating the device and the second communication equipment to transmit the AI information by using the matched AI model representation mode.

36. The apparatus of claim 35, wherein the transmission module is further configured to at least one of:

Acquiring an AI model representation mode supported by the second communication equipment;

and sending the AI model representation mode supported by the device to the second communication equipment.

37. The apparatus of claim 20, wherein the transmission module is further configured to:

transmitting third request information to fifth communication equipment, wherein the third request information is used for requesting the equipment to transmit AI information by using a matched AI model representation mode;

and receiving eighth indication information from the fifth communication device, wherein the eighth indication information indicates the device and the second communication device to transmit the AI information by using the matched AI model representation mode.

38. The apparatus of claim 37, wherein the device comprises a plurality of sensors,

the fifth communication device stores the AI model representation supported by the device and the AI model representation supported by the second communication device; or alternatively, the process may be performed,

the third request information comprises an AI model representation supported by the device, and the sixth communication device is further configured to obtain the AI model representation supported by the second communication device when the third request information is received; or alternatively, the process may be performed,

The third request information comprises an AI model representation supported by the device, and the fifth communication device is further configured to send the AI model representation supported by the device to the second communication device, and determine, based on a report result of the second communication device, that the second communication device supports and the device uses the matched AI model representation to transmit AI information.

39. A communication device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, which when executed by the processor, implements the AI-information transmission method of any of claims 1-19.

40. A readable storage medium, wherein a program or an instruction is stored on the readable storage medium, which when executed by a processor, implements the AI information transmission method of any one of claims 1 to 19.