Information transmitting and receiving method and device

Abstract

The embodiment of the invention provides an information transmitting and receiving method and device. The method comprises the following steps: a network device sends a quantization parameter of a to-be-reported object to a terminal device; and receiving the object quantized by the terminal device according to the quantization parameter.

Description

Information sending and receiving method and device Technical Field

[0001] The embodiments of the present application relate to the field of communication technologies. Background Art

[0002] As low-frequency spectrum resources become scarce, millimeter-wave (mmWave) bands offer greater bandwidth, making them a crucial frequency band for 5G NR (New Radio) systems. Due to their shorter wavelengths, mmWaves exhibit different propagation characteristics than traditional low-frequency bands, such as higher propagation loss and poor reflection and diffraction performance. Therefore, larger antenna arrays are typically employed to form shaped beams with greater gain, overcome propagation loss, and ensure system coverage. The 5G NR standard incorporates a series of beam management solutions, including beam scanning, beam measurement, beam reporting, and beam indication. However, a large number of transmit and receive beams significantly increases system load and latency.

[0003] With the development of artificial intelligence (AI) technology, applying it to the physical layer of wireless communications to address the difficulties of traditional methods has become a current technical trend. For beam management, using AI models to predict the optimal spatial beam pair based on a small number of beam measurements can significantly reduce system load and latency.

[0004] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0005] Summary of the Invention

[0006] Assume a communication system has M beams on the transmitter side and N beams on the receiver side. Existing standards require measuring M*N beams. When M and N are large, measuring M*N beams results in significant system load and latency. Using models (e.g., AI models) to predict the optimal beam pair based on a small number of beam measurements can significantly reduce the system load and latency caused by beam measurements.

[0007] In existing beam measurement reporting, measurement results must be quantized before being reported. The existing standard uses two quantization methods: absolute quantization and differential quantization. Absolute quantization directly quantizes the measured value, for example, using a fixed 7-bit quantization range of -140 to -44 dBm with a quantization step of 1 dB. Differential quantization uses the largest measurement value in the reporting entity as a reference, calculating the difference between the reported measurement value and the reference, quantizing this difference with 4 bits and a quantization step of 2 dB. However, the inventors discovered that the quantization parameters for both quantization methods in the existing standard are fixed, making this quantization method inflexible.

[0008] To address at least one of the above problems, embodiments of the present application provide a method and apparatus for sending and receiving information.

[0009] According to one aspect of an embodiment of the present application, there is provided an information transceiver device, which is applied to a network device, and the device includes:

[0010] a first sending unit, configured to send the quantized parameter of the object to be reported to the terminal device;

[0011] A first receiving unit receives the object quantized by the terminal device according to the quantization parameter.

[0012] According to another aspect of an embodiment of the present application, there is provided an information transceiver device, applied to a terminal device, the device comprising:

[0013] a second receiving unit, configured to receive the quantitative parameters of the object to be reported sent by the network device;

[0014] a first processing unit, which quantifies the object to be reported according to the quantification parameter;

[0015] A second sending unit sends the quantized object to the network device.

[0016] According to another aspect of an embodiment of the present application, there is provided an information transceiver device, applied to a terminal device, the device comprising:

[0017] a second processing unit, which quantifies the to-be-reported object according to a quantification parameter predefined for the AI ​​model usage stage, the AI ​​model, or the type of the to-be-reported object; wherein the quantification parameters of the to-be-reported object corresponding to different types of to-be-reported objects and / or different AI model usage stages and / or different AI models are the same or different;

[0018] A third sending unit sends the quantized object to the network device.

[0019] According to another aspect of an embodiment of the present application, a communication system is provided, including a terminal device and / or a network device, wherein the terminal device includes the information transceiver device of the aforementioned other aspect, and the network device includes the information transceiver device of the aforementioned one aspect.

[0020] One of the beneficial effects of the embodiments of the present application is that the network device configures the quantitative parameters of the object to be reported for the terminal device, so that the terminal device can quantize the object to be reported according to the quantitative parameters. This quantification method is more flexible, which can ensure the performance of the AI ​​model and reduce the load of the uplink.

[0021] One of the beneficial effects of the embodiments of the present application is that the terminal device can quantize the objects to be reported according to predefined quantization parameters. The quantization parameters of the objects to be reported corresponding to different types of objects to be reported and / or different AI model usage stages and / or different AI models are the same or different. This quantization method is more flexible, which can ensure the performance of the AI ​​model and reduce the load of the uplink.

[0022] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0023] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0024] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0026] FIG1 is a schematic diagram of a communication system of the present application;

[0027] FIG2 is a schematic diagram of a transmit beam and a receive beam in a communication system according to an embodiment of the present application;

[0028] FIG3 is a schematic diagram of an information sending and receiving method according to an embodiment of the present application;

[0029] FIG4 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0030] FIG5 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0031] FIG6 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0032] FIG7 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0033] FIG8 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0034] FIG9 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0035] FIG10 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0036] FIG11 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application;

[0037] FIG12 is a schematic diagram of an information transceiver device according to an embodiment of the present application;

[0038] FIG13 is a schematic diagram of an information transceiver device according to an embodiment of the present application;

[0039] FIG14 is a schematic diagram of an information transceiver device according to an embodiment of the present application;

[0040] FIG15 is a schematic diagram of a network device according to an embodiment of the present application;

[0041] FIG16 is a schematic diagram of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0043] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0044] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0045] In the embodiments of the present application, the term "communication network" or "wireless communication network" may refer to a network that complies with any of the following communication standards, such as Long Term Evolution (LTE), enhanced Long Term Evolution (LTE-A, LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0046] Furthermore, communication between devices in the communication system may be carried out according to communication protocols of any stage, for example, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), future 6G, etc., and / or other communication protocols currently known or to be developed in the future.

[0047] In the embodiments of the present application, the term "network device" refers to, for example, a device in a communication system that connects a terminal device to the communication network and provides services to the terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0048] Base stations may include, but are not limited to, NodeBs (NBs), evolved NodeBs (eNodeBs or eNBs), and 5G base stations (gNBs), among others. They may also include remote radio heads (RRHs), remote radio units (RRUs), relays, or low-power nodes (e.g., femeto, pico, etc.). The term "base station" may include some or all of their functions, and each base station may provide communication coverage for a specific geographic area. The term "cell" may refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0049] In the embodiments of the present application, the term "user equipment" (UE) or "terminal equipment" (TE) refers to, for example, a device that accesses a communication network through a network device and receives network services. A terminal device can be fixed or mobile and may also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and so on.

[0050] Among them, terminal devices may include but are not limited to the following devices: cellular phones, personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, machine-type communication devices, laptop computers, cordless phones, smart phones, smart watches, digital cameras, etc.

[0051] For another example, in scenarios such as the Internet of Things (IoT), the terminal device can also be a machine or device for monitoring or measurement, including but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device-to-device (D2D) terminal, machine-to-machine (M2M) terminal, and so on.

[0052] In addition, the term "network side" or "network device side" refers to one side of the network, which can be a base station or one or more network devices as described above. The term "user side" or "terminal side" or "terminal device side" refers to the user or terminal side, which can be a UE or one or more terminal devices as described above. Unless otherwise specified herein, "device" can refer to either network equipment or terminal equipment.

[0053] In the following description, the terms "uplink control signal" and "uplink control information (UCI)" or "physical uplink control channel (PUCCH)" are interchangeable, and the terms "uplink data signal" and "uplink data information" or "physical uplink shared channel (PUSCH)" are interchangeable to avoid confusion.

[0054] The terms "downlink control signal" and "downlink control information (DCI)" or "physical downlink control channel (PDCCH)" are interchangeable, and the terms "downlink data signal" and "downlink data information" or "physical downlink shared channel (PDSCH)" are interchangeable.

[0055] In addition, sending or receiving PUSCH can be understood as sending or receiving uplink data carried by PUSCH, sending or receiving PUCCH can be understood as sending or receiving uplink information carried by PUCCH, and sending or receiving PRACH can be understood as sending or receiving preamble carried by PRACH; uplink signals can include uplink data signals and / or uplink control signals, etc., and can also be referred to as uplink transmission (UL transmission) or uplink information or uplink channels. Sending uplink transmission on uplink resources can be understood as sending the uplink transmission using the uplink resources. Similarly, downlink data / signals / channels / information can be understood accordingly.

[0056] In the embodiments of the present application, the high-layer signaling may be, for example, radio resource control (RRC) signaling; for example, an RRC message, including, for example, an MIB, system information, or a dedicated RRC message; or an RRC information element (RRC IE). The high-layer signaling may also be, for example, MAC (Medium Access Control) signaling; or a MAC control element (MAC CE). However, the present application is not limited thereto.

[0057] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0058] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation using a terminal device and a network device as an example. As shown in FIG1 , a communication system 100 may include a network device 101 and terminal devices 102 and 103. For simplicity, FIG1 illustrates only two terminal devices and one network device as an example, but the embodiments of the present application are not limited thereto.

[0059] In the embodiment of the present application, existing services or future services can be transmitted between the network device 101 and the terminal devices 102 and 103. For example, these services may include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0060] The terminal device 102 may send data to the network device 101, for example, using an authorized or unauthorized transmission mode. The network device 101 may receive data sent by one or more terminal devices 102 and provide feedback to the terminal device 102, such as ACK / NACK information. The terminal device 102 may confirm the end of the transmission process, or may continue with new data transmission, or may retransmit the data based on the feedback information.

[0061] It is worth noting that FIG1 shows that both terminal devices 102 and 103 are within the coverage range of network device 101, but the present application is not limited thereto. Both terminal devices 102 and 103 may not be within the coverage range of network device 101, or one terminal device 102 may be within the coverage range of network device 101 while the other terminal device 103 is outside the coverage range of network device 101.

[0062] An AI model (or ML model) includes, but is not limited to, an input layer (input), multiple convolutional layers, a concatenation layer (concat), a fully connected layer (FC), and a quantizer. The processing results of multiple convolutional layers are merged in the concatenation layer. The specific structure of the AI ​​model can be found in existing technologies and will not be detailed here.

[0063] FIG2 is a schematic diagram of transmit and receive beams in a communication system according to various embodiments of the present application. As shown in FIG2 , in a communication system 100, taking a downlink channel as an example, a network device 101 may have M1 downlink transmit beams DL TX, and a terminal device 102 may have N1 downlink receive beams DL RX.

[0064] In an embodiment of the present application, as shown in FIG2 , a model 201 for predicting beam measurement results can be deployed in a network device 101 or a terminal device 102. Model 201 can predict the measurement results of M1*N1 beams based on the measurement results of some beams. Model 201 can be, for example, an AI model.

[0065] In addition, for the uplink channel, the network device 101 may have N2 uplink receive beams (not shown in FIG. 2 ), and the terminal device 102 may have M2 uplink transmit beams UL TX (not shown in FIG. 2 ).

[0066] The inventors found that in traditional beam measurement reporting, the terminal device needs to report the measurement results of its beam to the network device. Table 1 below is a schematic diagram of the existing beam measurement reporting information format.

[0067] Table 1

[0068] As shown in Table 1, the reported information includes the measurement result RSRP (Reference Signal Receiving Power) values ​​#1, #2, #3, #4, and the synchronization signal block resource indicator (SSB resource indicator, SSB RI) or channel state information reference signal resource indicator (CSI-RS resource indicator, CSI) #1, #2, #3, #4 associated with the measurement result RSRP. In other words, the terminal device only reports the largest 1 to 4 results of its measured RSRP to the network device. However, in the beam prediction solution based on AI / ML models, including the use of AI models for reasoning, training (data collection), and model monitoring, for example, when using AI models for training, the terminal device may need to report the measurement / prediction results of all beams to the network device. At this time, the dynamic range of the results to be quantized is relatively large. Therefore, the use of traditional quantization schemes will cause the performance of beam prediction to degrade. The current standard does not define quantization parameters for AI models at different stages.

[0069] In response to the above problems, embodiments of the present application provide a method and device for sending and receiving information, which are described below with reference to the accompanying drawings and embodiments.

[0070] Embodiments of the first aspect

[0071] An embodiment of the present application provides a method for sending and receiving information, which is described from the perspective of a network device.

[0072] FIG3 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG3 , the method includes:

[0073] 301, the network device sends the quantitative parameters of the object to be reported to the terminal device;

[0074] 302. The network device receives the object quantized by the terminal device according to the quantization parameter.

[0075] It is worth noting that FIG3 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG3 above.

[0076] In some embodiments, the object to be reported in 301 is the object to be reported sent by the terminal device to the network device during the entire process of beam prediction based on the AI ​​model. The AI ​​model can be deployed on the network device side or on the terminal device side. The AI ​​model can include a training phase (data collection phase), an inference phase, and a performance monitoring phase. The following will first explain the above-mentioned different AI deployment locations and phases, as well as the objects to be reported involved.

[0077] In some embodiments (I), the AI ​​model is deployed on the network device side. During the AI ​​model training (data collection) phase (completed by the network device, training includes online training or offline training or updating), the terminal device needs to collect the measurement results of all beams (or beam pairs) and needs to report all measurement results to the network device. The network device uses all measurement results as label data for AI model training and inputs them into the AI ​​model for training. Therefore, in this scenario, the object to be reported sent by the terminal device is the measurement results of all beams (or beam pairs), such as the L1-RSRP (Reference Signal Receiving Power) value or the L1-SINR (Signal to Interference plus Noise Ratio) value.

[0078] In some embodiments (two), the AI ​​model is deployed on the network device side. In the AI ​​model reasoning (prediction) stage (completed by the network device), the terminal device needs to report the measurement results of some beams (or beam pairs) (for example, several measurement results with larger measurement values, etc., the embodiments of the present application are not limited to this), and needs to report these measurement results to the network device. The network device uses the partial measurement results as input data of the AI ​​model, inputs them into the AI ​​model for reasoning, and obtains prediction results, including the prediction results of each beam (or beam pair) and the corresponding measurement prediction value. Therefore, in this scenario, the object to be reported sent by the terminal device is the measurement result of some beams (or beam pairs), such as L1-RSRP (Reference Signal Receiving Power) value or L1-SINR (Signal to Interference plus Noise Ratio) value.

[0079] In some embodiments (three), the AI ​​model is deployed on the network device side, and the input of the AI ​​model is the measurement results of some beams (pairs). The output of the AI ​​model may include each beam (or beam pair) and the corresponding measurement prediction value. There may be errors between the predicted value and the actual measurement result. The error can be used to evaluate the performance of the AI ​​model. Therefore, in the AI ​​model performance monitoring stage (completed by the network device), the prediction error of the beam measurement result (for example, the difference between the predicted value and the measured value) and other performance metrics related to the measured value L1-RSRP or L1-SINR can be used as performance metrics in the AI ​​model performance monitoring stage. For the calculation method of the prediction error, reference can be made to the relevant technology, and the embodiments of the present application are not limited to this. Therefore, in this scenario, the object to be reported sent by the terminal device is the measurement results corresponding to some beams (or beam pairs) or all beams (or beam pairs). The measurement results are used to calculate the performance metric on the network device side in combination with the prediction results (obtained on the network side) for performance monitoring.

[0080] In some embodiments (four), the AI ​​model is deployed on the terminal device side, but the AI ​​model training phase is completed on the network device side. Therefore, the object to be reported by the terminal device in the AI ​​model training phase is the same as the corresponding phase when the AI ​​model is deployed on the network device side, and will not be repeated here.

[0081] In some embodiments (five), the AI ​​model is deployed on the terminal device side, but the AI ​​model performance monitoring phase is completed on the network device side. Therefore, in the AI ​​model performance monitoring phase, the object to be reported by the terminal device is the same as the corresponding phase when the AI ​​model is deployed on the network device side, and will not be repeated here. In addition, the object to be reported can also include a predicted value (obtained on the terminal side), and the network device can calculate the prediction error of the beam measurement result (for example, the difference between the predicted value and the measured value) as a performance metric in the AI ​​model performance monitoring phase.

[0082] In some embodiments (six), the AI ​​model is deployed on the terminal device side. During the AI ​​model inference phase, the terminal device measures and obtains the measurement results of some beams (or beam pairs), and inputs them into the AI ​​model for inference to obtain prediction results, including the prediction results for each beam (or beam pair) and the corresponding measurement prediction values. Therefore, in this scenario, the object to be reported sent by the terminal device is the measurement prediction value of some beams (or beam pairs), such as one or more optimal prediction values.

[0083] In some embodiments (seven), the AI ​​model is deployed on the terminal device side, but when the AI ​​model performance monitoring phase is on the terminal device side, the terminal device needs to determine the performance metric value (e.g., prediction error) based on the predicted value and measured value obtained in the inference phase, and report the performance metric value to the network device. The network device can determine whether to switch the AI ​​model, activate the AI ​​model, or deactivate the AI ​​model based on the performance metric value. Therefore, in this scenario, the object to be reported sent by the terminal device is the AI ​​model performance metric.

[0084] In the above scenarios (1) and (4), the terminal device not only needs to report measurement results with larger data, but also needs to report measurement results with smaller data. That is to say, the terminal device needs a larger dynamic range to quantify the measurement results, and the reported results are also relatively large. In the above scenario (2), the terminal device only needs to report the measurement results of some beams (or beam pairs), and the dynamic range of the reported measurement values ​​is similar to or smaller than that in the training phase. In the above scenario (3), if the terminal device only needs to report some measurement results, the dynamic range of the reported values ​​is similar to that of the traditional beam report. If the terminal device needs to report all measurement results, the dynamic range of the reported measurement values ​​is similar to that of the training phase. In the above scenario (6), the terminal device only reports some predicted values ​​to the network device, and the dynamic range of the reported predicted values ​​is similar to that of the traditional beam report. In the above scenario (5), the terminal device needs to report the measurement results corresponding to some beams (or beam pairs) and all beams (or beam pairs), and can also report some predicted values. Therefore, the dynamic range of the reported values ​​is similar to that of scenario (3). In the above scenario (seven), the terminal device reports performance metrics, which are different from the quantitative accuracy or data dynamic range of the measured and predicted values.

[0085] Through the above examples, it can be seen that since the data volume, dynamic range, quantization accuracy requirements, etc. of different AI model usage stages, or different types of objects to be reported, are different, quantization parameters can be configured for different AI model usage stages, or different types of objects to be reported, thereby avoiding performance degradation and reducing uplink load. Among them, the quantization parameters of different types of objects to be reported are the same or different, and the quantization parameters of objects to be reported corresponding to different AI model usage stages are the same or different. Among them, the network device can configure corresponding quantization parameters for each AI model usage stage (or each type of object to be reported), or only configure corresponding quantization parameters for some AI model usage stages (or some types of objects to be reported), and other AI model usage stages that are not configured with quantization parameters (or other types of objects to be reported that are not configured with quantization parameters) can reuse the quantization parameters configured for this part of the AI ​​model usage stage (or some types of objects to be reported), or use predefined quantization parameters, and the embodiments of the present application are not limited to this. Alternatively, for example, other AI model usage stages (or some types of objects to be reported) that are not configured with quantization parameters can reuse the quantization parameters configured for the most recently configured quantization parameters.

[0086] The following describes how to configure the quantization parameters.

[0087] In some embodiments, the object to be reported uses fixed-point data, and the network device can configure quantization parameters for the fixed-point nature of the object to be reported. The quantization parameters include at least one of the number of quantization bits, the dynamic range of the value to be quantized, and the quantization step size. The number of quantization bits refers to the number of bits used to represent the data to be quantized. The dynamic range of quantization includes the maximum and minimum values ​​of the quantized data, expressed in dBm (L1-RSRP) or dB (L1-SINR), and the quantization step size (in dB).

[0088] For example, in scenario (six), for the AI ​​model inference stage, the quantization parameters configured by the network equipment include: the dynamic range of the value to be quantized is -140dBm to -40dBm, the number of quantization bits is 7 bits, and the quantization step is 1dB.

[0089] For example, in scenarios (1) and (4), for the AI ​​model training phase, the quantization parameters configured for the network equipment include: a dynamic range of -172dBm to -40dBm, 7 quantization bits, and a 1dB quantization step. Alternatively, to achieve higher quantization accuracy, the quantization bit count can be 8 bits, with a 0.5dB quantization step.

[0090] In some embodiments, the quantization types include differential quantization and absolute quantization, wherein the quantization parameters of the to-be-reported object corresponding to different quantization types are the same or different.

[0091] For example, for absolute quantization, the object of quantization is each object to be reported, and the quantization parameters of absolute quantization may include the number of quantization bits, dynamic range, and quantization step size. For differential quantization, the object of quantization is the difference between the object to be reported in a reporting entity and the maximum reported value in the entity. The quantization parameters of differential quantization include the quantization bit value and the quantization step size. It should be noted that the maximum reported value in differential quantization is quantized using absolute quantization. The parameters of absolute quantization may be the aforementioned quantization parameters of absolute quantization configured for absolute quantization, or predefined quantization parameters of absolute quantization. The embodiments of the present application are not limited to this.

[0092] In some embodiments, when the quantization type is differential quantization, the terminal device can group the objects to be reported (for example, in the AI ​​model training stage, if the terminal device needs to report the measured values ​​or predicted values ​​of all beams (pairs), the measured values ​​or predicted values ​​can be grouped), and each group of objects to be reported corresponds to one reporting entity. In a grouped reporting entity, the maximum reported value is quantized using absolute quantization (using the aforementioned absolute quantization quantization parameters configured for absolute quantization, or predefined absolute quantization quantization parameters), and other objects to be reported are quantized using differential quantization (using differential quantization quantization parameters) after calculating the difference with the maximum reported data in the reporting entity of the group. Therefore, in order to support this grouped differential quantization method, the quantization parameter can also include the number N of objects to be reported contained in a reporting entity, and the aforementioned grouping is performed according to the number N and the number M of objects to be reported, and differential quantization as described above is performed for each group.

[0093] In some embodiments, the aforementioned quantization type may be explicitly indicated in the quantization parameter, that is, the quantization parameter may include the quantization type, but the embodiments of the present application are not limited to this. For example, the quantization type corresponding to each type of object to be reported may also be predefined or determined according to a preset rule or implicitly. For example, 1 bit may be used to indicate the quantization type. When the value of 1 bit is 0, the quantization type is indicated as absolute quantization. When the value of 1 bit is 1, the quantization type is indicated as differential quantization, and vice versa. Alternatively, the quantization type may be predefined or implicitly indicated for different AI model usage stages or types of objects to be reported. For example, in the AI ​​model training stage, due to the large amount of data, in order to reduce the uplink load, differential quantization may be predefined or implicitly determined. In the AI ​​model inference stage, in order to improve the prediction accuracy, absolute quantization may be predefined or implicitly determined. The embodiments of the present application are not limited to this.

[0094] The following describes how to determine the AI ​​model usage phase or the type of object to be reported for which the quantitative parameters are configured.

[0095] In some embodiments, it can be explicitly indicated that the quantization parameter is configured for which AI model usage stage or type of object to be reported. For example, the network device also sends the object type indication information to be reported and / or AI model usage stage indication information corresponding to the quantization parameter to the terminal device. The above indication information can be included in the quantization parameter and sent, or the quantization parameter can be included in the indication information and sent, or the quantization parameter and the indication information can be carried and sent separately by the same information domain / information element. Thus, when the terminal device receives the above indication information and quantization parameter, it can determine for which AI model usage stage or type of object to be reported the quantization parameter is configured. For example, the AI ​​model usage stage indication information is represented by 2 bits. When the value of the 2 bits is 00, it indicates that the configured quantization parameters are configured for the AI ​​model training stage. When the value of the 2 bits is 01, it indicates that the configured quantization parameters are configured for the AI ​​model inference stage. When the value of the 2 bits is 10, it indicates that the configured quantization parameters are configured for the AI ​​model performance monitoring stage. The embodiments of the present application are not limited to this. For example, the type indication information of the object to be reported is represented by 2 bits. When the value of the 2 bits is 00, it indicates that the object to be reported is a beam measurement result. When the value of the 2 bits is 01, it indicates that the object to be reported is a beam prediction result. When the value of the 2 bits is 10, it indicates that the object to be reported is a performance measurement value. Examples are not given one by one here.

[0096] In some embodiments, the quantization parameter can be sent according to the timing (for example, at which stage of the AI ​​model it is sent) to determine for which AI model usage stage or type of object to be reported the quantization parameter is configured. For example, the network device can send an AI model usage stage trigger signaling to the terminal device. The quantization parameter and the trigger signaling can be sent separately, or the quantization parameter can be included in the trigger signaling and sent. This application is not limited to this. After receiving the trigger signaling, the terminal device triggers the corresponding AI usage stage and quantizes the object to be reported according to the quantization parameter, that is, the terminal device can determine that the received quantization parameter is used in the AI ​​model usage stage triggered by the trigger signaling.

[0097] For example, the above-mentioned trigger signaling can be an enable signal for the AI ​​model usage phase. For example, the enable signal is 2-bit information. When the bit value of the enable signal is 00, it indicates that the process of enabling (triggering) the AI ​​model training phase is enabled. When the bit value of the enable signal is 01, it indicates that the process of enabling (triggering) the AI ​​model reasoning phase is enabled. When the bit value of the enable signal is 10, it indicates that the process of enabling (triggering) the AI ​​model performance monitoring phase is enabled. This is only an example for explanation, and this application is not limited to this.

[0098] For example, the above-mentioned trigger signaling can be the aforementioned object type indication information to be reported and / or AI model usage phase indication information. In other words, the indication information can be used as trigger signaling to trigger the corresponding AI model usage phase. For example, when the terminal device receives a 2-bit AI model usage phase indication information with a value of 00, the AI ​​model training phase process is triggered.

[0099] For example, the above-mentioned trigger signaling may be reference signal configuration information and / or measurement report configuration information corresponding to the AI ​​model usage phase, implicitly triggering the process of the AI ​​model usage phase. For example, the reference signal configured by the reference signal configuration information is a measurement reference signal configured for the AI ​​model training phase. When the terminal device receives the reference signal configuration information, it triggers the process of the AI ​​model training phase, or the reference signal configured by the reference signal configuration information is a measurement reference signal configured for the AI ​​model inference phase. When the terminal device receives the reference signal configuration information, it triggers the process of the AI ​​model inference phase. Examples are not given one by one here.

[0100] In some embodiments, the trigger signaling may be sent periodically or aperiodically, and the embodiments of the present application are not limited thereto.

[0101] In some embodiments, the quantization parameter and / or trigger signaling can be sent simultaneously, for example, the quantization parameter can be included in the trigger signaling and sent, or the quantization parameter and trigger signaling can be sent separately, for example, the quantization parameter is sent after the trigger signaling is sent. This application is not limited to this. The quantization parameter and / or trigger signaling can be carried by RRC signaling or MAC CE signaling or DCI signaling; for example, the quantization parameter can be a new information field or information element in RRC signaling or MAC CE signaling or DCI signaling, and the trigger signaling can be a new information field or information element in RRC signaling or MAC CE signaling or DCI signaling. This embodiment of the application is not limited to this.

[0102] In some embodiments, the network device may first receive an AI model usage phase request sent by the terminal device. After receiving the request, the network device sends the trigger signaling in response to the request. For example, for the aforementioned scenario (six), when the AI ​​model enters the inference phase, the terminal device may first send an AI model inference request to the network device. The network device sends a trigger signaling in response to the request to trigger the AI ​​model inference phase process. The above only uses scenario (six) as an example for illustration, and the embodiments of the present application are not limited to this scenario. The AI ​​model usage phase request can be sent periodically or non-periodically, and the embodiments of the present application are not limited to this.

[0103] In some embodiments, the terminal device obtains the object to be reported through measurement, prediction or calculation, and after receiving the trigger signaling and quantization parameters, uses the quantization parameters to quantize the object to be reported, and sends the quantized object to the network device. The quantized object is carried by UCI or MAC CE. How the terminal device quantizes and when to report, and how to report will be explained in the embodiment of the second aspect described later.

[0104] In addition, in the above embodiments, the network device configures corresponding quantization parameters for the type of the object to be reported or the AI ​​model usage stage as an example for illustration, but the embodiments of the present application are not limited to this. For example, the network device can also configure corresponding quantization parameters for different AI models. For example, when multiple AI models are deployed on the network device side or the terminal device side, corresponding quantization parameters can be configured for each AI model. For example, for AI model 1, quantization parameter 1 is configured, for AI model 2, quantization parameter 2 is configured, for AI model 3, quantization parameter 3 is configured, and quantization parameters 1, 2, and 3 are the same or different; or, for AI model 1, quantization parameter 1 is configured, and for AI model 2, quantization parameter 1 is reused, etc. The embodiments of the present application are not limited to this and will not be repeated here.

[0105] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0106] Therefore, the network device configures the quantitative parameters of the object to be reported for the terminal device, so that the terminal device can quantify the object to be reported according to the quantitative parameters. This quantification method is more flexible, which can ensure the performance of the AI ​​model and reduce the load of the uplink.

[0107] Embodiments of the second aspect

[0108] An embodiment of the present application provides a method for sending and receiving information, which is explained from the terminal device side, and the contents that are the same as the embodiment of the first aspect are not repeated.

[0109] FIG4 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG4 , the method includes:

[0110] 401. The terminal device receives the quantitative parameters of the object to be reported sent by the network device;

[0111] 402. The terminal device quantifies the reporting object according to the quantization parameter.

[0112] 403. The terminal device sends the quantized object to the network device.

[0113] It is worth noting that FIG4 above is merely a schematic illustration of an embodiment of the present application, and the present application is not limited thereto. For example, the execution order of the various operations may be appropriately adjusted, and other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above description, and are not limited to the description of FIG4 above.

[0114] In some embodiments, the implementation of 401 may correspond to 301 , and the repeated parts will not be repeated.

[0115] In some embodiments, the method may further include receiving an AI model usage phase trigger signaling sent by a network device. In step 402, upon receiving the quantization parameter and the trigger signaling, the terminal device quantizes the object to be reported. The implementation of the trigger signaling and the quantization parameter is as described above and will not be further elaborated here.

[0116] It should be noted that, as mentioned above, the network device can configure corresponding quantization parameters for each AI model usage phase. For example, the quantization parameter can be sent together with the trigger signaling or separately. The terminal device quantizes the reporting object according to the trigger signaling 1 (corresponding to the AI ​​model usage phase A) and the quantization parameter 1 (corresponding to the AI ​​model usage phase A). The terminal device quantizes the reporting object according to the trigger signaling 2 (corresponding to the AI ​​model usage phase B) and the quantization parameter 2 (corresponding to the AI ​​model usage phase B). However, the embodiment of the present application is not limited to this. The network device can configure quantization parameters for some AI model usage phases. For example, only the quantization parameter 1 is configured for the AI ​​model usage phase A. When the terminal device receives the trigger signaling 1 that triggers the AI ​​model usage phase A, the reporting object is quantized according to the configured quantization parameter 1. Since the network device does not configure the corresponding quantization parameter for the AI ​​model usage phase B, when the terminal device receives the trigger signaling 2 that triggers the AI ​​model usage phase B, it can reuse the received quantization parameter 1 or reuse the most recently received quantization parameter to quantize the reporting object. Examples are not given one by one here.

[0117] In some embodiments, the method may further include: the terminal device sends an AI model usage phase request to the network device, and receives a trigger signaling sent by the network device in response to the request. For example, for the aforementioned scenario (six), when the AI ​​model enters the inference phase, the terminal device may first send an AI model inference request to the network device, and then receive a trigger signaling to trigger the AI ​​model inference phase process. The implementation method of the AI ​​model usage phase request is as described above and will not be repeated here.

[0118] The following is a detailed description of scenarios (1) to (7) in the embodiment of the first aspect.

[0119] For example, for scenarios (1) and (4), the network device sends a trigger signaling to the terminal device to trigger the AI ​​model training phase, and sends the quantization parameters configured for the AI ​​model training phase (or for the measurement value) to the terminal device (the quantization parameters and trigger signaling, as mentioned above, can be sent simultaneously or separately). After receiving the trigger signaling, the terminal device triggers the AI ​​model training phase. After obtaining all beam measurement results, all measured beam measurement results are quantized according to the quantization parameters, and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0120] For example, for scenario (2), the network device sends a trigger signaling to the terminal device to trigger the AI ​​model inference phase, and sends the quantization parameters configured for the AI ​​model inference phase (or for the measurement value) to the terminal device (the quantization parameters and trigger signaling, as mentioned above, can be sent simultaneously or separately). After receiving the trigger signaling, the terminal device triggers the AI ​​model inference phase. After measuring the measurement results of some beams, the measurement results of some beams are quantized according to the quantization parameters, and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0121] For example, for scenario (three), the network device sends a trigger signaling to the terminal device to trigger the process of the AI ​​model performance monitoring phase, and sends the quantization parameters configured for the AI ​​model performance monitoring phase (or for the measurement value) to the terminal device (the quantization parameters and trigger signaling, as mentioned above, can be sent simultaneously or separately). After receiving the trigger signaling, the terminal device triggers the process of the AI ​​model performance monitoring phase. After measuring the measurement results corresponding to some beams (pairs) or all beams (or beam pairs), the measurement results are quantized according to the quantization parameters, and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0122] For example, for scenario (five), the network device sends a trigger signaling to the terminal device to trigger the process of the AI ​​model performance monitoring phase, and sends the quantization parameters configured for the AI ​​model performance monitoring phase (or for the measurement value and prediction value) to the terminal device (the quantization parameters and trigger signaling, as mentioned above, can be sent simultaneously or separately). After receiving the trigger signaling, the terminal device triggers the process of the AI ​​model performance monitoring phase, measures and obtains the measurement results corresponding to some beams (pairs) or all beams (or beam pairs), and uses the AI ​​model to obtain the prediction results. According to the quantization parameters, the measured measurement results and prediction results are quantized, and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0123] For example, for scenario (seven), the network device sends a trigger signaling to the terminal device to trigger the process of the AI ​​model performance monitoring phase, and sends the quantization parameters configured for the AI ​​model performance monitoring phase (or for the performance measurement value) to the terminal device (the quantization parameters and trigger signaling, as mentioned above, can be sent simultaneously or separately). After receiving the trigger signaling, the terminal device triggers the process of the AI ​​model performance monitoring phase, measures the measurement results of some beams, and uses the AI ​​model to obtain the prediction results. The performance measurement value is calculated based on the measurement results and the prediction results, and the calculated performance measurement value is quantized according to the quantization parameter. The quantization result is used as the measurement report result and reported to the network device through UCI or MAC CE.

[0124] For example, for scenario (six), the terminal device can first send an AI model usage (model inference) stage request to the network device. In response to the request, the network device sends a trigger signaling to the terminal device to trigger the AI ​​model inference stage process, and sends the terminal device the quantization parameters configured for the AI ​​model inference stage (or for the predicted value) (the quantization parameters and trigger signaling, as mentioned above, can be sent simultaneously or separately). After receiving the trigger signaling, the terminal device triggers the AI ​​model inference stage process. After measuring the measurement results of some beams and using the AI ​​model to obtain the prediction results, the beam prediction results are quantized according to the quantization parameters, and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0125] In the above example, the network device configures corresponding quantization parameters for each AI model usage phase, and the quantization parameters can be sent together with or separately from the corresponding trigger signaling for triggering the AI ​​model usage phase. However, the embodiments of the present application are not limited to this. The network device can configure quantization parameters for some AI model usage phases, and the terminal device can reuse other configured quantization parameters or the most recently received quantization parameters to quantize the objects to be reported corresponding to the AI ​​model usage phase that is not configured with quantization parameters. Examples will not be given one by one here.

[0126] Therefore, the network device configures the quantitative parameters of the object to be reported for the terminal device, so that the terminal device can quantify the object to be reported according to the quantitative parameters. This quantification method is more flexible, which can ensure the performance of the AI ​​model and reduce the load of the uplink.

[0127] In the above example, the network device configures corresponding quantization parameters for each or part of the AI ​​model usage phase, but the embodiment of the present application is not limited to this. The network device may not configure corresponding quantization parameters for any AI model usage phase. The terminal device uses quantization parameters predefined for the AI ​​model usage phase or for the type of object to be reported for quantization. The following is an explanation with reference to the embodiment of Figure 5.

[0128] FIG5 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG5 , the method includes:

[0129] 501. The terminal device quantifies the to-be-reported object according to a quantification parameter predefined for the AI ​​model usage stage, the AI ​​model, or the type of the to-be-reported object; wherein the quantification parameters of the to-be-reported object corresponding to different types of to-be-reported objects and / or different AI model usage stages and / or different types of AI models are the same or different;

[0130] 502. The terminal device sends the quantized object to the network device.

[0131] In some embodiments, the difference from the aforementioned embodiment is that the quantization parameters of the objects to be reported corresponding to various types of objects to be reported and / or AI model usage phases and / or AI models are predefined and not configured by the network device. The specific content of the predefined quantization parameters is similar to the configured quantization parameters. For example, the predefined quantization parameters include: at least one of the number of quantization bits, the dynamic range of the value to be quantized, and the quantization step size. The number of quantization bits refers to how many bits are used to represent the data to be quantized. The dynamic range of quantization includes the maximum and minimum values ​​of the quantized data, in dBm (L1-RSRP) or dB (L1-SINR), and the quantization step size (in dB).

[0132] In some embodiments, the quantization types include differential quantization and absolute quantization, wherein the predefined quantization parameters of the object to be reported corresponding to different quantization types are the same or different.

[0133] For example, for absolute quantization, the quantized object is each object to be reported, and the predefined absolute quantization parameters may include the number of quantization bits, dynamic range, and quantization step size. For differential quantization, the quantized object is the difference between the object to be reported in a reporting entity and the maximum reported value in the entity. The predefined differential quantization parameters include the quantization bit value and quantization step size. It should be noted that the maximum reported value in differential quantization is quantized using absolute quantization, and the absolute quantization parameters are predefined.

[0134] In some embodiments, when the quantization type is differential quantization, the predefined quantization parameters may also include the number N of objects to be reported contained in a reporting entity. According to the number N and the number M of objects to be reported, the aforementioned grouping is performed, and differential quantization as described above is performed for each group.

[0135] The above-mentioned when to use absolute quantization and when to use differential quantization can also be predefined or defaulted. The embodiments of the present application are not limited to this. For example, absolute quantization is predefined for the AI ​​model inference stage, and differential quantization is predefined for the AI ​​model training stage, etc., and examples are not given one by one here.

[0136] That is, a set of quantization parameters can be predefined for the AI ​​model inference phase, a set of quantization parameters can be predefined for the AI ​​model training phase, and a set of quantization parameters can be predefined for the AI ​​model performance monitoring phase. The above sets of quantization parameters can be the same or different.

[0137] In some embodiments, the method may further include receiving AI model usage phase trigger signaling sent by a network device. In step 501, upon receiving the trigger signaling, the terminal device quantizes the to-be-reported object according to a predefined quantization parameter corresponding to the AI ​​model usage phase triggered by the trigger signaling. The implementation of the trigger signaling and the quantization parameter are as described above and will not be further elaborated here.

[0138] In some embodiments, the method may further include: the terminal device sends an AI model usage phase request to the network device, and receives a trigger signaling sent by the network device in response to the request. For example, for the aforementioned scenario (six), when the AI ​​model enters the inference phase, the terminal device may first send an AI model inference request to the network device, and then receive a trigger signaling to trigger the AI ​​model inference phase process. The above only takes scenario (six) as an example, and the embodiments of this application are not limited to this scenario. The implementation method of the AI ​​model usage phase request is as described above and will not be repeated here.

[0139] The following is a detailed description of scenarios (1) to (7) in the embodiment of the first aspect.

[0140] For example, for scenarios (1) and (4), the network device sends a trigger signaling to the terminal device to trigger the AI ​​model training phase. After receiving the trigger signaling, the terminal device triggers the AI ​​model training phase. After obtaining all beam measurement results, all measured beam measurement results are quantized according to the quantization parameters predefined for the AI ​​model training phase (or for the measurement value), and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0141] For example, for scenario (2), the network device sends a trigger signaling to the terminal device to trigger the AI ​​model inference phase. After receiving the trigger signaling, the terminal device triggers the AI ​​model inference phase. After obtaining the measurement results of some beams, the terminal device quantizes the measurement results of some beams according to the quantization parameters predefined for the AI ​​model inference phase (or for the measurement value), and reports the quantization results as measurement report results to the network device through UCI or MAC CE.

[0142] For example, for scenario (three), the network device sends a trigger signaling to the terminal device to trigger the process of the AI ​​model performance monitoring phase. After receiving the trigger signaling, the terminal device triggers the process of the AI ​​model performance monitoring phase. After measuring the measurement results of some beams (or beam pairs) or all beams (or beam pairs), the measurement results are quantized according to the quantization parameters predefined for the AI ​​model performance monitoring phase (or for the measurement value), and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0143] For example, for scenario (five), the network device sends a trigger signaling to the terminal device to trigger the process of the AI ​​model performance monitoring phase. After receiving the trigger signaling, the terminal device triggers the process of the AI ​​model performance monitoring phase, measures and obtains the measurement results of some beams (or beam pairs) or all beams (or beam pairs), and uses the AI ​​model to obtain the prediction results. According to the quantization parameters predefined for the AI ​​model performance monitoring phase (or for the measurement value and the prediction value), the measured measurement results and prediction results are quantized, and the quantization results are used as the measurement report results and reported to the network device through UCI or MAC CE.

[0144] For example, for scenario (seven), the network device sends a trigger signaling to the terminal device to trigger the process of the AI ​​model performance monitoring phase. After receiving the trigger signaling, the terminal device triggers the process of the AI ​​model performance monitoring phase, measures the measurement results of some beams, and uses the AI ​​model to obtain the prediction results. The performance metric value is calculated based on the measurement results and the prediction results. According to the quantization parameters predefined for the AI ​​model performance monitoring phase (or for the performance metric value), the calculated performance metric value is quantized, and the quantization result is used as the measurement report result and reported to the network device through UCI or MAC CE.

[0145] For example, for scenario (six), the terminal device can first send an AI model usage phase (model inference) request to the network device. In response to the request, the network device sends a trigger signaling to the terminal device to trigger the AI ​​model inference phase process. After receiving the trigger signaling, the terminal device triggers the AI ​​model inference phase process. After measuring the measurement results of some beams and using the AI ​​model to obtain the prediction results, the beam prediction results are quantized according to the quantization parameters predefined for the AI ​​model inference phase (or for the predicted value), and the quantization results are used as measurement report results and reported to the network device through UCI or MAC CE.

[0146] In addition, in the above embodiments, the corresponding quantization parameters are predefined for the type of the object to be reported or the usage stage of the AI ​​model as an example, but the embodiments of the present application are not limited to this. For example, corresponding quantization parameters can also be predefined for different AI models. For example, when multiple AI models are deployed on the network device side or the terminal device side, corresponding quantization parameters can be predefined for each AI model. For example, for AI model 1, quantization parameter 1 is predefined, for AI model 2, quantization parameter 2 is predefined, and for AI model 3, quantization parameter 3 is predefined; quantization parameters 1, 2, and 3 are the same or different. The embodiments of the present application are not limited to this and will not be repeated here.

[0147] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0148] Therefore, the terminal device can quantize the objects to be reported according to predefined quantization parameters. The quantization parameters of objects to be reported corresponding to different types of objects to be reported and / or different AI model usage stages and / or different AI models are the same or different. This quantization method is more flexible, which can ensure the performance of the AI ​​model and reduce the load of the uplink.

[0149] FIG6 is a schematic diagram of an information sending and receiving method according to an embodiment of the present application (scenarios 1 to 5). As shown in FIG6 , the AI ​​model is deployed on the network device side or the terminal device side, but the AI ​​model training phase and the AI ​​model performance monitoring phase are completed on the network device side. The method includes:

[0150] 601, the network device sends the aforementioned trigger signaling to the terminal device;

[0151] 602, the network device sends the quantization parameter to the terminal device;

[0152] 603, the terminal device triggers the corresponding AI model usage phase according to the trigger signaling;

[0153] 604, the terminal device performs beam measurement;

[0154] 605 , quantizing the measurement value according to the configured quantization parameters corresponding to the AI ​​model usage phase in 603 ;

[0155] 606. The terminal device reports the quantized measurement value.

[0156] In this embodiment, the quantization parameter in 602 may be included in the trigger signaling or sent separately from the trigger signaling. When the AI ​​model is deployed on the terminal device side, but the AI ​​model performance monitoring phase is completed on the network device side, in 604, the beam measurement value needs to be input into the AI ​​model to obtain a predicted value. In 605, the predicted value needs to be quantized according to the configured quantization parameter, and in 606, the quantized predicted value is also reported to the network device.

[0157] FIG7 is a schematic diagram of an information sending and receiving method according to an embodiment of the present application (scenarios 1 to 5). As shown in FIG7 , the AI ​​model is deployed on the network device side or the terminal device side, but the AI ​​model training phase and the AI ​​model performance monitoring phase are completed on the network device side. The method includes:

[0158] 701, the network device sends the aforementioned trigger signaling to the terminal device;

[0159] 702, the terminal device triggers the corresponding AI model usage phase according to the trigger signaling;

[0160] 703, the terminal device performs beam measurement;

[0161] 704 , quantizing the measurement value according to a predefined quantization parameter corresponding to the AI ​​model usage phase in 702 ;

[0162] 705. The terminal device reports the quantized measurement value.

[0163] When the AI ​​model is deployed on the terminal device side, but the AI ​​model performance monitoring phase is completed on the network device side, in 703, the beam measurement value needs to be input into the AI ​​model to obtain a predicted value. In 704, the predicted value needs to be quantized according to a predefined quantization parameter, and the quantized predicted value is also reported to the network device in 705.

[0164] FIG8 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG8 , the AI ​​model is deployed on the terminal device side. The method includes:

[0165] 801, the terminal device sends an AI model usage phase request to the network device;

[0166] 802. The network device sends the aforementioned trigger signaling to the terminal device.

[0167] 803, the network device sends the quantization parameter to the terminal device;

[0168] 804, the terminal device triggers the corresponding AI model usage phase according to the trigger signaling;

[0169] 805, the terminal device performs beam measurement and inputs the beam measurement value into the AI ​​model to obtain a predicted value;

[0170] 806 , quantizing the predicted value according to the configured quantization parameters corresponding to the AI ​​model usage phase in 803 ;

[0171] 807, the terminal device reports the quantized prediction value.

[0172] In this embodiment, the quantization parameter in 803 may be included in the trigger signaling and sent, or sent separately from the trigger signaling.

[0173] FIG9 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application. As shown in FIG9 , the AI ​​model is deployed on the terminal device side. The method includes:

[0174] 901, the terminal device sends an AI model usage phase request to the network device;

[0175] 902. The network device sends the aforementioned trigger signaling to the terminal device.

[0176] 903, the terminal device triggers the corresponding AI model usage phase according to the trigger signaling;

[0177] 904. The terminal device performs beam measurement and inputs the beam measurement value into the AI ​​model to obtain a predicted value.

[0178] 905, quantizing the predicted value according to a predefined quantization parameter corresponding to the AI ​​model usage stage in 803;

[0179] 906. The terminal device reports the quantized prediction value.

[0180] The above Figures 8 and 9 illustrate the quantification of the predicted value as an example, but the embodiments of the present application are not limited to this. The quantified object and the object to be reported can also include measurement values ​​or performance measurement values, which are not exemplified one by one here.

[0181] FIG10 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application (Scenario 7). As shown in FIG10 , the AI ​​model is deployed on the terminal device side, and the AI ​​model performance monitoring phase is completed on the terminal device side. The method includes:

[0182] 1001, the network device sends the aforementioned trigger signaling to the terminal device;

[0183] 1002. The network device sends a quantization parameter to the terminal device.

[0184] 1003, the terminal device triggers the corresponding AI model usage phase according to the trigger signaling;

[0185] 1004. The terminal device performs beam measurement, inputs the beam measurement value into the AI ​​model to obtain a predicted value, and calculates a performance metric based on the measured value and the predicted value.

[0186] 1005, quantizing the performance metric according to the configured quantization parameters corresponding to the AI ​​model usage phase in 1002;

[0187] 1006. The terminal device reports the quantized performance measurement value.

[0188] In this embodiment, the quantization parameter in 1002 may be included in the trigger signaling and sent, or sent separately from the trigger signaling.

[0189] FIG11 is a schematic diagram of a method for sending and receiving information according to an embodiment of the present application (Scenario 7). As shown in FIG11 , the AI ​​model is deployed on the terminal device side, and the AI ​​model performance monitoring phase is completed on the terminal device side. The method includes:

[0190] 1101, the network device sends the aforementioned trigger signaling to the terminal device;

[0191] 1102, the terminal device triggers the corresponding AI model usage phase according to the trigger signaling;

[0192] 1103. The terminal device performs beam measurement, inputs the beam measurement value into the AI ​​model to obtain a predicted value, and calculates a performance metric based on the measured value and the predicted value.

[0193] 1104, quantizing the performance metric according to predefined quantization parameters corresponding to the AI ​​model usage phase in 1002;

[0194] 1105. The terminal device reports the quantized performance measurement value.

[0195] The beam to be measured can be configured through reference signal information. For details, please refer to the existing technology and will not be described here.

[0196] Embodiments of the third aspect

[0197] The embodiment of the present application provides an information transceiver device, which may be, for example, a terminal device, or one or more components or assemblies configured in the terminal device, and the contents that are the same as those in the embodiment of the second aspect are not repeated here.

[0198] FIG12 is a schematic diagram of an information transceiver device according to an embodiment of the present application. As shown in FIG12 , the information transceiver device 1200 includes:

[0199] A second receiving unit 1201 receives a quantized parameter of an object to be reported sent by a network device;

[0200] A first processing unit 1202 quantifies the object to be reported according to the quantization parameter;

[0201] The second sending unit 1203 sends the quantized object to the network device.

[0202] In some embodiments, the implementation of the second receiving unit 1201, the first processing unit 1202 and the second sending unit 1203 corresponds to 401-403 and will not be repeated here.

[0203] FIG13 is a schematic diagram of an information transceiver device according to an embodiment of the present application. As shown in FIG13 , the information transceiver device 1300 includes:

[0204] A second processing unit 1301 quantifies the to-be-reported object according to a quantification parameter predefined for the AI ​​model usage stage, the AI ​​model, or the type of the to-be-reported object; wherein the quantification parameters for the to-be-reported objects corresponding to different types of to-be-reported objects and / or different AI model usage stages and / or different AI models are the same or different;

[0205] The third sending unit 1302 sends the quantized object to the network device.

[0206] In some embodiments, the implementation of the second processing unit 1301 and the third sending unit 1302 corresponds to 501-502 and will not be repeated here.

[0207] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0208] It is worth noting that the above description only describes the components or modules related to the present application, but the present application is not limited thereto. The information transceiver devices 1200 and 1300 may also include other components or modules. For the specific contents of these components or modules, reference may be made to the relevant art.

[0209] In addition, for the sake of simplicity, Figures 12 and 13 only illustrate the connection relationships or signal paths between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connections can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; this application is not limited to this.

[0210] Embodiments of the fourth aspect

[0211] The embodiment of the present application provides an information transceiver device, which may be, for example, a network device, or one or more components or assemblies configured in the network device, and the same contents as those in the embodiment of the first aspect will not be repeated.

[0212] FIG14 is a schematic diagram of an information transceiver device according to an embodiment of the present application. As shown in FIG14 , the information transceiver device 1400 includes:

[0213] A first sending unit 1401 sends a quantized parameter of an object to be reported to a terminal device;

[0214] The first receiving unit 1402 receives the object quantized by the terminal device according to the quantization parameter.

[0215] In some embodiments, the implementation of the first sending unit 1401 and the first receiving unit 1402 corresponds to 301 - 302 and will not be repeated here.

[0216] The above embodiments are merely exemplary of the present invention, but the present invention is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used alone, or one or more of the above embodiments may be combined.

[0217] It is worth noting that the above description only describes the components or modules related to the present application, but the present application is not limited thereto. The information transceiver 1400 may also include other components or modules. For the specific contents of these components or modules, reference may be made to the relevant art.

[0218] In addition, for the sake of simplicity, FIG14 only illustrates the connection relationship or signal direction between various components or modules. However, it should be clear to those skilled in the art that various related technologies such as bus connection can be used. The above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0219] Embodiments of the fifth aspect

[0220] An embodiment of the present application also provides a communication system, and reference may be made to FIG1 . The contents that are the same as those in the first to fourth aspects of the embodiments will not be repeated.

[0221] In some embodiments, the communication system 100 may include at least: a network device 101 and / or a terminal device 102, the network device sends quantization parameters of the object to be reported to the terminal device; the network device receives the object quantized by the terminal device according to the quantization parameters.

[0222] In some embodiments, a communication system 100 may include at least: a network device 101 and / or a terminal device 102, wherein the terminal device quantizes an object to be reported based on a quantization parameter predefined for an AI model usage phase, an AI model, or a type of object to be reported; wherein the quantization parameters for objects to be reported corresponding to different types of objects to be reported and / or different AI model usage phases and / or different AI models are the same or different; and the quantized object is sent to the network device. The network device receives the quantized object sent by the terminal device.

[0223] In some embodiments, the implementation of the above-mentioned quantitative parameters and objects to be reported can refer to the embodiments of the first aspect and the second aspect, and will not be repeated here.

[0224] An embodiment of the present application further provides a network device, which may be, for example, a base station, but the present application is not limited thereto and may also be other network devices.

[0225] Figure 15 is a schematic diagram illustrating the structure of a network device according to an embodiment of the present application. As shown in Figure 15 , network device 1500 may include a processor 1510 (e.g., a central processing unit (CPU)) and a memory 1520; memory 1520 is coupled to processor 1510. Memory 1520 may store various data and may also store an information processing program 1530, which is executed under the control of processor 1510.

[0226] For example, the processor 1510 may be configured to execute a program to implement the information sending and receiving method as described in the embodiment of the first aspect.

[0227] In addition, as shown in FIG15 , network device 1500 may further include: a transceiver 1540 and an antenna 1550, etc.; wherein, the functions of the above components are similar to those in the prior art and are not described in detail here. It is worth noting that network device 1500 does not necessarily include all the components shown in FIG15 ; in addition, network device 1500 may also include components not shown in FIG15 , and reference may be made to the prior art for details.

[0228] The embodiment of the present application also provides a terminal device, but the present application is not limited thereto and may also be other devices.

[0229] Figure 16 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in Figure 16 , terminal device 1600 may include a processor 1616 and a memory 1620. Memory 1620 stores data and programs and is coupled to processor 1616. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication or other functions.

[0230] For example, the processor 1616 may be configured to execute a program to implement the information sending and receiving method as described in the embodiment of the second aspect.

[0231] As shown in Figure 16 , the terminal device 1600 may further include: a communication module 1630, an input unit 1640, a display 1650, and a power supply 1660. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that the terminal device 1600 does not necessarily include all of the components shown in Figure 16 , and these components are not essential. Furthermore, the terminal device 1600 may also include components not shown in Figure 16 , for which reference may be made to the prior art.

[0232] An embodiment of the present application also provides a computer program, wherein when the program is executed in a terminal device, the program enables the terminal device to execute the information sending and receiving method described in the embodiment of the second aspect.

[0233] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the information sending and receiving method described in the embodiment of the second aspect.

[0234] An embodiment of the present application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the information sending and receiving method described in the embodiment of the first aspect.

[0235] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the information sending and receiving method described in the embodiment of the first aspect.

[0236] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0237] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0238] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0239] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0240] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0241] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0242] 1. A method for sending and receiving information, applied to a network device, characterized in that the method comprises:

[0243] The network device sends the quantified parameters of the object to be reported to the terminal device;

[0244] The network device receives the object quantized by the terminal device according to the quantization parameter.

[0245] 2. The method according to Note 1, wherein the quantitative parameters of different types of objects to be reported are the same or different.

[0246] 3. The method according to Note 1 or 2, wherein the quantitative parameters of the objects to be reported corresponding to different AI model usage stages and / or different AI models are the same or different.

[0247] 4. The method described in Note 2, wherein the types of objects to be reported include: beam measurement results, beam prediction results, and AI model performance measurement results.

[0248] 5. According to the method described in Note 3, the AI ​​model usage stage includes: AI model reasoning stage, AI model training stage, and AI model performance monitoring stage.

[0249] 6. The method according to any one of Notes 1 to 5, wherein the quantization parameter includes at least one of the number of quantization bits, the dynamic range of the value to be quantized, and the quantization step size.

[0250] 7. The method according to Note 6, wherein the quantization parameter further includes a quantization type, and the quantization type includes differential quantization and absolute quantization.

[0251] 8. According to the method described in Note 7, the quantitative parameters of the object to be reported corresponding to different quantification types are the same or different.

[0252] 9. The method according to Note 7, wherein, when the quantization type is differential quantization, the quantization parameter also includes the number of objects to be reported contained in a reporting entity.

[0253] 10. The method according to any one of Notes 1 to 9, further comprising:

[0254] The network device sends to the terminal device the indication information of the type of object to be reported and / or the indication information of the AI ​​model usage stage corresponding to the quantization parameter.

[0255] 11. The method according to any one of Notes 1 to 10, further comprising:

[0256] The network device sends an AI model usage phase trigger signaling to the terminal device.

[0257] 12. The method according to Note 11, wherein the trigger signaling includes indication information of the type of object to be reported and / or indication information of the AI ​​model usage phase corresponding to the quantization parameter, or reference signal configuration information and / or measurement reporting configuration information corresponding to the AI ​​model usage phase.

[0258] 13. The method according to Supplementary Note 11, further comprising:

[0259] The network device receives the AI ​​model usage phase request sent by the terminal device, and the network device sends an AI model usage phase trigger signaling to the terminal device in response to the request.

[0260] 14. The method according to Note 11 or 13, wherein the quantization parameter is carried in the trigger signaling.

[0261] 15. The method according to any one of Notes 11 to 14, wherein the trigger signaling is sent periodically or aperiodically.

[0262] 16. A method according to any one of Notes 1 to 15, wherein the quantization parameter and / or the trigger signaling is carried by RRC signaling or MAC CE signaling or DCI signaling; and the quantized object is carried by UCI or MAC CE.

[0263] 17. A method for sending and receiving information, applied to a terminal device, characterized in that the method comprises:

[0264] The terminal device receives the quantitative parameters of the object to be reported sent by the network device;

[0265] The terminal device quantifies the object to be reported according to the quantification parameter;

[0266] The terminal device sends the quantized object to the network device.

[0267] 18. The method according to Note 17, wherein the quantitative parameters of different types of objects to be reported are the same or different.

[0268] 19. The method according to Note 17 or 18, wherein the quantitative parameters of the objects to be reported corresponding to different AI model usage stages and / or different AI models are the same or different.

[0269] 20. The method described in Note 17, wherein the types of objects to be reported include: beam measurement results, beam prediction results, and AI model performance measurement results.

[0270] 21. The method according to Note 19, wherein the AI ​​model usage stage includes: AI model reasoning stage, AI model training stage, and AI model performance monitoring stage.

[0271] 22. A method according to any one of Notes 17 to 21, wherein the quantization parameter includes at least one of: the number of quantization bits, the dynamic range of the value to be quantized, and the quantization step size.

[0272] 23. The method according to Note 22, wherein the quantization parameter further includes a quantization type, and the quantization type includes differential quantization and absolute quantization.

[0273] 24. According to the method described in Note 23, the quantitative parameters of the object to be reported corresponding to different quantification types are the same or different.

[0274] 25. The method according to Note 24, wherein, when the quantization type is differential quantization, the quantization parameter further includes the number of objects to be reported contained in a reporting entity.

[0275] 26. The method according to any one of Notes 17 to 25, further comprising:

[0276] The terminal device receives the to-be-reported object type indication information and / or AI model usage stage indication information corresponding to the quantization parameter sent by the network device.

[0277] 27. The method according to any one of Notes 17 to 26, further comprising:

[0278] The terminal device receives the AI ​​model usage phase trigger signaling sent by the network device, and quantizes the reporting object when receiving the quantization parameter and the trigger signaling.

[0279] 28. The method according to Note 27, wherein the trigger signaling includes indication information of the type of object to be reported and / or indication information of the AI ​​model usage phase corresponding to the quantization parameter, or reference signal configuration information and / or measurement reporting configuration information corresponding to the AI ​​model usage phase.

[0280] 29. The method according to Supplement 27 or 28, wherein the method further comprises:

[0281] The terminal device sends an AI model usage phase request to the network device, and receives an AI model usage phase trigger signaling sent by the network device in response to the request.

[0282] 30. A method according to any one of Notes 27 to 29, wherein the quantization parameter is carried in the trigger signaling.

[0283] 31. The method according to any one of Notes 27 to 29, wherein the trigger signaling is sent periodically or aperiodically.

[0284] 32. A method according to any one of Notes 17 to 31, wherein the quantization parameter and / or the trigger signaling is carried by RRC signaling or MAC CE signaling or DCI signaling; and the quantized object is carried by UCI or MAC CE.

[0285] 33. A method for sending and receiving information, applied to a terminal device, characterized in that the method comprises:

[0286] The terminal device quantifies the object to be reported according to a quantification parameter predefined for the AI ​​model usage stage, the AI ​​model, or the type of the object to be reported; wherein the quantification parameters of the objects to be reported corresponding to different types of objects to be reported and / or different AI model usage stages and / or different AI models are the same or different;

[0287] The terminal device sends the quantized object to the network device.

[0288] 34. The method described in Note 33, wherein the types of objects to be reported include: beam measurement results, beam prediction results, and AI model performance measurement results.

[0289] 35. The method according to Note 33, wherein the AI ​​model usage stage includes: AI model reasoning stage, AI model training stage, and AI model performance monitoring stage.

[0290] 36. The method according to Note 33, 34 or 35, wherein the predefined quantization parameter includes: at least one of the number of quantization bits, the dynamic range of the value to be quantized, and the quantization step size.

[0291] 37. The method according to Note 36, wherein the predefined quantization parameter further includes a quantization type, and the quantization type includes differential quantization and absolute quantization.

[0292] 38. According to the method described in Note 37, the quantitative parameters of the object to be reported corresponding to different quantification types are the same or different.

[0293] 39. The method according to Note 37, wherein, when the quantization type is differential quantization, the predefined quantization parameter also includes the number of objects to be reported contained in a reporting entity.

[0294] 40. The method according to any one of Notes 33 to 39, further comprising:

[0295] The terminal device receives an AI model usage phase trigger signaling sent by the network device;

[0296] And when the trigger signaling is received, the object to be reported is quantized according to the predefined quantization parameter corresponding to the AI ​​model usage phase triggered by the trigger signaling.

[0297] 41. According to the method described in Note 40, the trigger signaling includes indication information of the type of object to be reported and / or indication information of the AI ​​model usage phase corresponding to the quantization parameter, or reference signal configuration information and / or measurement reporting configuration information corresponding to the AI ​​model usage phase.

[0298] 42. The method according to Supplement 40, wherein the method further comprises:

[0299] The terminal device sends an AI model usage phase request to the network device, and receives an AI model usage phase trigger signaling sent by the network device in response to the request.

[0300] 43. The method according to any one of Notes 40 to 42, wherein the trigger signaling is sent periodically or aperiodically.

[0301] 44. A method according to any one of Notes 33 to 43, wherein the trigger signaling is carried by RRC signaling or MAC CE signaling or DCI signaling; and the quantized object is carried by UCI or MAC CE.

[0302] 45. A network device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the method as described in any one of Notes 1 to 16.

[0303] 46. ​​A terminal device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the method as described in any one of Notes 17 to 44.

[0304] 47. A communication system comprising the network device described in Note 45 and / or the terminal device described in Note 46.

Claims

1. An information transceiver device, applied to a network device, characterized in that: The device comprises: A first sending unit, which sends the quantized parameter of the object to be reported to the terminal device; A first receiving unit receives the object quantized by the terminal device according to the quantization parameter.

2. The device according to claim 1, wherein: The quantitative parameters of different types of objects to be reported are the same or different.

3. The device according to claim 1, wherein: The quantitative parameters of the objects to be reported corresponding to different AI model usage stages and / or different AI models are the same or different.

4. The device according to claim 2, wherein: The types of objects to be reported include: beam measurement results, beam prediction results, and AI model performance measurement results.

5. The device according to claim 3, wherein: The AI ​​model usage stages include: AI model reasoning stage, AI model training stage, and AI model performance monitoring stage.

6. The device according to claim 1, wherein: The quantization parameter includes at least one of: the number of quantization bits, the dynamic range of the value to be quantized, and the quantization step size.

7. The device according to claim 6, wherein: The quantization parameter also includes a quantization type, and the quantization type includes differential quantization and absolute quantization. 8 . The device according to claim 7 , wherein the quantization parameters of the objects to be reported corresponding to different quantization types are the same or different.

9. The device according to claim 7, wherein: When the quantization type is differential quantization, the quantization parameter also includes the number of objects to be reported contained in a reporting entity.

10. The device according to claim 1, wherein: The first sending unit is also used to send to the terminal device the indication information of the type of object to be reported and / or the indication information of the AI ​​model usage stage corresponding to the quantization parameter.

11. The device according to claim 1, wherein: The first sending unit is also used to send AI model usage phase trigger signaling to the terminal device.

12. The device according to claim 11, wherein The trigger signaling includes indication information of the type of object to be reported and / or indication information of the AI ​​model usage phase corresponding to the quantization parameter, or reference signal configuration information and / or measurement report configuration information corresponding to the AI ​​model usage phase.

13. The device according to claim 1, wherein: The first receiving unit is also used to receive an AI model usage phase request sent by the terminal device, and the first sending unit sends an AI model usage phase trigger signaling to the terminal device in response to the request.

14. The device according to claim 11 or 13, wherein: The quantization parameter is carried in the trigger signaling.

15. The device according to claim 11, wherein The trigger signaling is sent periodically or aperiodically.

16. The device according to claim 1 or 11 or 13, wherein: The quantization parameter and / or the trigger signaling are carried by RRC signaling or MAC CE signaling or DCI signaling; and the quantized object is carried by UCI or MAC CE.

17. An information transceiver device, applied to a terminal device, characterized in that: The device comprises: A second receiving unit, which receives the quantitative parameters of the object to be reported sent by the network device; A first processing unit, which quantifies the object to be reported according to the quantification parameter; A second sending unit sends the quantized object to the network device.

18. The device according to claim 17, wherein: The second receiving unit is also used to receive an AI model usage phase trigger signaling. When the second receiving unit receives the quantization parameter and the trigger signaling, the first processing unit quantizes the object to be reported.

19. An information transceiver device, applied to a terminal device, characterized in that: The device comprises: A second processing unit, which quantifies the object to be reported according to a quantification parameter predefined for the AI ​​model usage stage or for the AI ​​model or for the type of the object to be reported; wherein the quantification parameters of the objects to be reported corresponding to different types of objects to be reported and / or different AI model usage stages and / or different AI models are the same or different; A third sending unit sends the quantized object to the network device.

20. The device according to claim 19, wherein The device also includes: A third receiving unit, which is used to receive an AI model usage phase trigger signaling; And when the third receiving unit receives the trigger signaling, the second processing unit quantizes the object to be reported according to a predefined quantization parameter corresponding to the AI ​​model usage phase triggered by the trigger signaling.

Images