Communication method and communication apparatus

Abstract

The present application provides a communication method and a communication apparatus, which are applied to the field of wireless communication. In the technical solution provided in the present application, a receiving end may perform training in a coordinated manner on an AI sequence and an AI detection model, and, after training of the AI sequence is completed, indicate an AI sequence generation manner to a transmitting end, so that the transmitting end can generate an AI sequence, and the receiving end does not need to transmit all AI sequences generated by means of training, thereby reducing signaling overheads. Since training is performed in a coordinated manner on the AI sequence sent by the transmitting end and the AI detection model of the receiving end, the detection performance of the receiving end with respect to the AI sequence can be improved.

Description

Communication method and communication apparatus

[0001] The present application claims priority to the Chinese patent application No. 202411110828.2, filed on August 13, 2024, and entitled "Communication method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of wireless communication, and in particular to a communication method and a communication apparatus. BACKGROUND

[0003] In the field of communication, a reference signal can be generated based on a reference sequence, so that the two parties of communication can agree on the transmitted signal, so that the receiving end can detect the received signal based on the agreed signal after receiving the signal transmitted by the sending end, to achieve the purposes such as access, synchronization, demodulation, measurement, estimation, etc.

[0004] However, the method has the problem of low detection performance. SUMMARY

[0005] The present application provides a communication method and a communication apparatus, which are applied to the field of wireless communication. The technical scheme provided by the present application can indicate the terminal to generate an artificial intelligence (AI) sequence autonomously, so as to improve the detection performance while reducing the signaling overhead.

[0006] In a first aspect, the embodiments of the present application provide a communication method, which can be applied to the sending end of an AI sequence. Taking the sending end as a terminal for example, the method can be applied to the terminal side, such as a terminal or a communication module in the terminal, or a circuit or chip responsible for the communication function in the terminal (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem module). Taking the method applied to the terminal for example, the method comprises: receiving first information, the first information being used to indicate a vector, the vector satisfying a first relationship with an identifier of an artificial intelligence (AI) sequence, the vector being used as an input of an AI model, the AI model being used to generate the AI sequence; and transmitting a first AI sequence, the first AI sequence being generated based on the first information.

[0007] In the technical solution, the network device can indicate the input of the AI model, such as a vector, to the terminal. The terminal can input the vector into the AI model to generate an AI sequence, and send the generated AI sequence to the network device. The AI model can be located in the terminal, or the terminal can implement calling of the AI model. The first AI sequence can be understood as the AI sequence determined by the terminal to send. The AI model can be predefined by a protocol.

[0008] In the technical solution, the AI sequence on the terminal side and the AI detection model on the network device side can be trained by the network device. Therefore, when the terminal sends the AI sequence to the network device for the purpose of, for example, access, synchronization, demodulation, measurement, estimation, and the like, the detection accuracy of the AI sequence sent by the terminal by the network device is high. In addition, by indicating the input of the AI model to the terminal, the terminal can be instructed to autonomously generate an AI sequence based on the AI model, so that the network device does not need to send all the AI sequences generated by training to the terminal, thereby reducing signaling overhead. It should be understood that the output of the AI model can include part or all of the AI sequence set generated by the network device through training.

[0009] With reference to the first aspect, in some implementations of the first aspect, the first information is used to indicate a vector, and the first information is used to indicate the first relationship.

[0010] In this implementation, the vector can be indicated by indicating the first relationship between the vector and the identifier of the AI sequence, so that the terminal can map the identifier of the first AI sequence to the first vector based on the first relationship, and input the first vector into the AI model to generate the first AI sequence.

[0011] With reference to the first aspect, in some implementations of the first aspect, the first information includes at least one of the following: a first formula that is satisfied between the identifier of the AI sequence and the vector, a parameter in the first formula, a length of the vector, or a processing manner of the vector.

[0012] As an example, the first relationship can be a mapping manner with a parameter. For example, the identifier of the AI sequence and the vector can satisfy a first formula, and the first formula can include a parameter. Optionally, the network device can indicate the first formula and the parameter in the first formula at the same time to improve communication efficiency. Optionally, the first formula can be predefined by a protocol or a standard, and the parameter in the first formula can be indicated by the network device to improve the use flexibility of the first formula.

[0013] As an example, the first relationship can be a mapping manner without a parameter. For example, the identifier of the AI sequence and the vector can satisfy a multi-ary conversion. The specific conversion mechanism can be predefined by a protocol or configured by the network device, which is not limited herein.

[0014] Optionally, the network device can indicate the length of the vector to the terminal, so that the vector input into the AI model is uniform in length, improving the performance of the AI model. The length of the vector can also be referred to as the dimension of the vector.

[0015] Optionally, the network device can also indicate the processing manner of the vector to the terminal, such as whether to perform normalization processing, to improve the performance of the AI model. In some embodiments, the network device can also indicate the interval of the normalization to the terminal.

[0016] In combination with the first aspect, in some implementations of the first aspect, the first information is used to indicate a vector, including: the first information is used to indicate a vector set in which the vector is located, a plurality of vectors in the vector set correspond to a plurality of AI sequences one by one, and a first relationship is satisfied between each vector in the plurality of vectors and the identification of the corresponding AI sequence, and the plurality of AI sequences belong to a subset of a sequence set in which the AI sequences are located.

[0017] In this implementation, the network device can indicate the vector by indicating the vector set. Wherein, the vectors in the vector set correspond to the sequences in the AI sequence set generated by the network device one by one. For example, when the first vector in the vector set corresponds to the first AI sequence in the AI sequence set, the first relationship can be satisfied between the first vector and the identification of the first AI sequence. It should be understood that each vector in the vector set can be used as input of the first AI model.

[0018] In this implementation, the network device can directly send the mapped vector set to the terminal without indicating the first relationship. Since the data amount of the vector set can be less than the data amount of the AI sequence set, compared with transmitting the AI sequence set, transmitting the vector set can achieve the purpose of reducing signaling overhead.

[0019] In combination with the first aspect, in some implementations of the first aspect, the first information includes at least one of the following information: the plurality of vectors, or the processing manner of each vector in the plurality of vectors.

[0020] As an example, the form of the vector set can be represented as [M, k]. Wherein, M represents the number of vectors in the vector set, and k represents the length of each vector. The number of vectors in the vector set can be the same as the number of AI sequences in the AI sequence set.

[0021] Optionally, the length of the vector can be less than the length of the AI sequence, so that the data amount of the vector set is less than the data amount of the AI sequence set, and compared with transmitting the AI sequence set, transmitting the vector set can reduce transmission overhead.

[0022] Optionally, the network device can further indicate to the terminal a processing manner of each vector in the vector set, for example, whether to perform normalization processing on the vector, so as to improve the performance of the AI model. In some embodiments, the network device can further indicate to the terminal a normalization interval.

[0023] With reference to the first aspect, in some implementations of the first aspect, the method further includes receiving second information, the second information being used to indicate the AI model.

[0024] In this implementation, the network device can further indicate to the terminal the AI model.

[0025] Optionally, when the structure of the AI model is predefined by a protocol or a standard or defined offline by the network device and the terminal, the second information can only indicate the parameters of the AI model, or the second information can indicate the parameters of the AI model and an identifier of the structure of the AI model, so as to reduce the overhead and complexity of AI model configuration.

[0026] Optionally, when the structure and the parameters of the AI model are predefined by a protocol or a standard or defined offline by the network device and the terminal, the second information can only indicate an identifier of the AI model.

[0027] Optionally, when the structure and / or the parameters of the AI model are configured by the network device, the second information can indicate the structure and / or the parameters of the AI model, so as to improve the flexibility of AI model configuration.

[0028] Optionally, the structure of the AI model can be a model structure supported in Z4 mode of model transfer in a fixed model structure.

[0029] In some embodiments, the AI model can be trained by the network device.

[0030] With reference to the first aspect, in some implementations of the first aspect, the method further includes sending third information, the third information being used to indicate at least one of the following information: supported AI model information, supported first relationship, or a time length required for generating the AI sequence.

[0031] In this implementation, the terminal can report to the network device a capability of the terminal, for example, a capability of supporting generation of the AI sequence by the AI model. When the terminal supports generation of the AI sequence by the AI model, the terminal can report to the network device AI model information (such as model structure and / or model parameters) supported by the terminal and / or a first relationship supported by the terminal, so that the network device can know the capability of the terminal, thereby improving the communication performance.

[0032] In some embodiments, when the terminal supports the capability of generating an AI sequence through an AI model, the terminal can report to the network device a time length required for the terminal to generate the AI sequence, so that the network device can know the capability of the terminal, to improve the communication performance.

[0033] In combination with the first aspect, in some implementations of the first aspect, the method further includes: receiving sixth information, the sixth information being used to indicate an identity of the first AI sequence.

[0034] In this implementation, the network device can indicate the identity of the AI sequence to the terminal, so that the terminal can determine the vector input into the AI model based on the identity of the AI sequence indicated by the network device, and then generate the AI sequence corresponding to the identity. In this implementation, the network device indicates the identity of the AI sequence, which can reduce the interference between the AI sequences generated by the terminals, as compared with the terminal randomly selecting the identity of the AI sequence.

[0035] In combination with the first aspect, in some implementations of the first aspect, the method further includes: performing any one of the following operations in a first time period: transmitting a first sequence, or not transmitting a sequence; wherein a starting time of the first time period is a starting time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

[0036] In this implementation, considering that the process of generating the AI sequence occupies a certain time length, or in other words, there is a time delay in the process of generating the AI sequence, the behavior of the terminal in this time period can be agreed, so that the terminal can know what behavior can be adopted in this time period, to improve the communication performance.

[0037] In a second aspect, an embodiment of the present application provides a communication method, which can be applied to a sending end of an AI sequence. Taking the sending end as an example, the method can be applied to a terminal side, such as a terminal or a communication module in the terminal, or a circuit or chip responsible for a communication function in the terminal (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem module). Taking the method applied to the terminal as an example, the method comprises: receiving first information, wherein the first information is used to indicate a plurality of sub-sequence sets, and the plurality of sub-sequence sets satisfy a second relationship with an AI sequence set; and sending a first AI sequence, wherein the first AI sequence is generated based on the first information, and the first AI sequence is included in the AI sequence set; wherein the product of the number of sub-AI sequences included in each sub-sequence set in the plurality of sub-sequence sets is equal to the number of AI sequences included in the AI sequence set, and the sum of the number of sub-AI sequences included in each sub-sequence set is less than the number of AI sequences included in the AI sequence set.

[0038] In this technical solution, the network device can divide the AI sequence set into a plurality of sub-sequence sets according to the hierarchical mapping manner to be adopted after training the AI sequence set, and send the plurality of sub-sequence sets to the terminal. The network device can also directly train a plurality of sub-sequence sets according to the hierarchical mapping manner to be adopted during the training process of the AI sequence, and send the plurality of sub-sequence sets to the terminal. It should be noted that the hierarchical mapping manner to be adopted and the specific implementation manner of hierarchical mapping are not limited herein.

[0039] Taking the hierarchical mapping manner as a remainder mapping for example, assuming that the AI sequence set is represented as MxN, that is, the AI sequence set includes M AI sequences, and the length of each AI sequence is N, if the number of sub-sequence sets is 2, then the two sub-sequence sets can be represented as M1xN and M2xN respectively. Wherein, M1xM2=M, and M1+M2

[0040] Optionally, the fourth information can be predefined through a protocol.

[0041] In this technical solution, the terminal can determine the AI sequence set based on the plurality of sub-sequence sets and the second relationship, so as to randomly select an AI sequence from the AI sequence set and send the AI sequence to the network device. Since the total data amount of the sub-sequence sets is less than the data amount of the AI sequence set, the transmission overhead of the network device when sending the sub-sequence sets to the terminal is low.

[0042] With reference to the second aspect, in some implementations of the second aspect, the method further includes: receiving fourth information, the fourth information being used to indicate the second relationship.

[0043] In this implementation, the second relationship can be configured by the network device to the terminal. For example, the network device can determine the second relationship according to real-time network conditions, load, and the like, and send it to the terminal to improve communication performance.

[0044] With reference to the second aspect, in some implementations of the second aspect, the method further includes: receiving fifth information, the fifth information being used to indicate a third relationship, the third relationship being a relationship between an identifier of the AI sequence and a plurality of sub-identifiers, the plurality of sub-identifiers corresponding to the plurality of sub-sequence sets, each of the plurality of sub-identifiers being used to determine one sub-AI sequence in a corresponding sub-sequence set, the AI sequence being generated based on a plurality of sub-AI sequences determined based on the plurality of sub-identifiers.

[0045] In this implementation, the sub-identifier can be understood as an identifier of a sub-AI sequence in a sub-sequence set. The terminal can map the identifier of the AI sequence to the plurality of sub-identifiers based on the third relationship, and determine the corresponding sub-AI sequence from the corresponding sub-sequence set based on the plurality of sub-identifiers, thereby determining the AI sequence. Wherein, the AI sequence can be a product of the plurality of sub-AI sequences.

[0046] With reference to the second aspect, in some implementations of the second aspect, the method further includes: receiving sixth information, the sixth information being used to indicate the identifier of the first AI sequence.

[0047] In this implementation, the network device can indicate the identifier of the AI sequence to the terminal, so that the terminal can determine the vector input into the AI model based on the identifier of the AI sequence indicated by the network device, and further generate the AI sequence corresponding to the identifier. In this implementation, the network device indicates the identifier of the AI sequence, which can reduce the interference between the AI sequences generated by the terminals, as compared to the terminal randomly selecting the identifier of the AI sequence.

[0048] With reference to the second aspect, in some implementations of the second aspect, the method further includes: performing any one of the following operations in a first time period: sending the first sequence, or not sending the sequence; wherein a starting time of the first time period is a starting time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

[0049] In this implementation, considering that the process of generating the AI sequence occupies a certain time length, or in other words, there is a time delay in the process of generating the AI sequence, the behavior of the terminal in this period of time can be agreed, so that the terminal can know what behavior can be adopted in this period of time, to improve the communication performance.

[0050] In a third aspect, an embodiment of the present application provides a communication method, which can be applied to a detection end or a receiving end of an AI sequence. Taking a receiving end as a network device for example, the method can be applied to a network side, such as an access network device of the network side, a module (such as a circuit, a chip or a chip system, etc.) in the access network device, or a logic node, a logic module or software capable of realizing all or part of the function of the access network device. Taking the method applied to a network device (such as an access network device) for example, the method comprises: sending first information, the first information being used to indicate a vector, the vector satisfying a first relationship with an identifier of an AI sequence, the vector being used as an input of an AI model, the AI model being used to generate the AI sequence; and receiving a first AI sequence, the first AI sequence being generated based on the first information.

[0051] In the technical solution, the network device can indicate an input of the AI model, such as a vector, to the terminal, the terminal can input the vector into the AI model, thereby generating an AI sequence, and send the generated AI sequence to the network device. The AI model can be located in the terminal, or in other words, the terminal can realize the calling of the AI model. The first AI sequence can be understood as an AI sequence determined to be sent by the terminal. The AI model can be predefined by a protocol.

[0052] In the technical solution, the AI sequence on the terminal side and the AI detection model on the network device side can be trained by the network device in pairs, so that when the terminal sends the AI sequence to the network device for the purpose of, for example, access, synchronization, demodulation, measurement, estimation, etc., the detection accuracy of the AI sequence sent by the terminal by the network device is high. In addition, by indicating the input of the AI model to the terminal, the terminal can be instructed to generate an AI sequence based on the AI model, which can reduce the signaling overhead of the network device without sending all the AI sequences generated by training to the terminal. It should be understood that the output of the AI model can include part or all of the AI sequence set generated by the network device through training.

[0053] In combination with the third aspect, in some implementation forms of the third aspect, the first information is used to indicate the vector, comprising: the first information is used to indicate the first relationship.

[0054] In the implementation form, the vector can be indicated by indicating the first relationship between the vector and the identifier of the AI sequence, so that the terminal can map the identifier of the first AI sequence to the first vector based on the first relationship, and input the first vector into the AI model to generate the first AI sequence.

[0055] In some embodiments of the third aspect, the first information comprises at least one of: a first formula satisfied between the identifier of the AI sequence and the vector, a parameter in the first formula, a length of the vector, or a processing manner of the vector.

[0056] As an example, the first relationship can be a mapping manner with a parameter. For example, a first formula can be satisfied between the identifier of the AI sequence and the vector, and the first formula can comprise a parameter. Optionally, the network device can indicate the first formula and the parameter in the first formula simultaneously to improve communication efficiency. Optionally, the first formula can be predefined by a protocol or a standard, and the parameter in the first formula can be indicated by the network device to improve flexibility of use of the first formula.

[0057] As an example, the first relationship can be a mapping manner without a parameter. For example, a multi-ary conversion can be satisfied between the identifier of the AI sequence and the vector. The conversion mechanism can be predefined by a protocol or configured by the network device, which is not limited herein.

[0058] Optionally, the network device can indicate the length k of the vector to the terminal, so that the vector input into the AI model is uniform in length and the performance of the AI model is improved.

[0059] Optionally, the network device can also indicate the processing manner of the vector to the terminal, for example, whether to perform normalization processing, to improve the performance of the AI model. In some embodiments, the network device can also indicate the interval of normalization to the terminal.

[0060] In some embodiments of the third aspect, the first information is used to indicate the vector, comprising: the first information is used to indicate a vector set in which the vector is located, a plurality of vectors in the vector set correspond to a plurality of AI sequences one by one, and a first relationship is satisfied between each vector in the plurality of vectors and an identifier of a corresponding AI sequence, and the plurality of AI sequences belong to a subset of a sequence set in which the AI sequence is located.

[0061] In this implementation, the network device can indicate the vector by indicating the vector set. Each vector in the vector set corresponds to a sequence in the AI sequence set generated by the network device one by one. For example, when a first vector in the vector set corresponds to a first AI sequence in the AI sequence set, the first relationship can be satisfied between the first vector and the identifier of the first AI sequence. It should be understood that each vector in the vector set can be used as input of the first AI model.

[0062] In this implementation, the network device can directly send the mapped vector set to the terminal without indicating the first relationship. Since the data amount of the vector set can be less than that of the AI sequence set, transmitting the vector set can achieve the purpose of reducing signaling overhead compared with transmitting the AI sequence set.

[0063] In some implementations of the third aspect, the first information includes at least one of the following: the plurality of vectors, or a processing manner of each vector in the plurality of vectors.

[0064] For example, the form of the vector set can be represented as [M, k], where M represents the number of vectors in the vector set, and k represents the length of each vector. The number of vectors in the vector set can be the same as the number of AI sequences in the AI sequence set.

[0065] Optionally, the length of the vector can be less than the length of the AI sequence, so that the data amount of the vector set is less than that of the AI sequence set, and transmitting the vector set can reduce transmission overhead compared with transmitting the AI sequence set.

[0066] Optionally, the network device can also indicate to the terminal a processing manner of each vector in the vector set, for example, whether to perform normalization processing on the vector, so as to improve the performance of the AI model. In some embodiments, the network device can also indicate to the terminal a normalization interval.

[0067] In some implementations of the third aspect, the method further includes: sending second information, where the second information is used to indicate the AI model.

[0068] In this implementation, the network device can also indicate to the terminal the AI model.

[0069] Optionally, when the structure of the AI model is predefined by a protocol or a standard, or defined offline by the network device and the terminal, the second information can only indicate the parameters of the AI model, or the second information can indicate the parameters of the AI model and an identifier of the structure of the AI model, so as to reduce the overhead and complexity of AI model configuration.

[0070] Optionally, when the structure and the parameters of the AI model are predefined by a protocol or a standard, or defined offline by the network device and the terminal, the second information can only indicate an identifier of the AI model.

[0071] Optionally, when the structure and / or the parameters of the AI model are configured by the network device, the second information can indicate the structure and / or the parameters of the AI model, so as to improve the flexibility of AI model configuration.

[0072] Optionally, the structure of the AI model can be a model structure supported in a Z4 mode of a fixed model structure in model transfer.

[0073] In some embodiments, the AI model can be trained by the network device.

[0074] In combination with the third aspect, in some implementations of the third aspect, the method further includes: receiving third information, the third information being used to indicate at least one of the following: supported AI model information, supported first relationship, or time length required for generating the AI sequence.

[0075] In this implementation, the terminal can report its capability to the network device, for example, whether it supports the capability of generating an AI sequence through an AI model. When the terminal supports the capability of generating an AI sequence through an AI model, the terminal can report to the network device the AI model information (such as model structure and / or model parameter) supported by the terminal and / or the first relationship supported by the terminal, so that the network device can know the capability of the terminal and improve the communication performance.

[0076] In some embodiments, when the terminal supports the capability of generating an AI sequence through an AI model, the terminal can report to the network device the time length required for the terminal to generate an AI sequence, so that the network device can know the capability of the terminal and improve the communication performance.

[0077] In combination with the third aspect, in some implementations of the third aspect, the method further includes: sending sixth information, the sixth information being used to indicate an identity of the first AI sequence.

[0078] In this implementation, the network device can indicate to the terminal the identity of the AI sequence, so that the terminal can determine the vector input into the AI model based on the identity of the AI sequence indicated by the network device, and then generate the AI sequence corresponding to the identity. In this implementation, the network device indicates the identity of the AI sequence, which can reduce the interference between AI sequences generated by terminals, as compared with the terminal randomly selecting the identity of the AI sequence.

[0079] In combination with the third aspect, in some implementations of the third aspect, the method further includes: performing any one of the following in a first time period: receiving a first sequence, or not receiving a sequence; wherein a starting time of the first time period is a starting time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

[0080] In this implementation, considering that the AI sequence generation process occupies a certain time length, or in other words, there is a time delay in the AI sequence generation process, the behavior of the network device in this time period can be agreed, so that the network device can know what behavior can be adopted in this time period to improve the communication performance.

[0081] In a fourth aspect, an embodiment of the present application provides a communication method, which can be applied to a detection end or a receiving end of an AI sequence. Taking the receiving end as a network device for example, the method can be applied to the network side, such as an access network device of the network side, a module (such as a circuit, a chip or a chip system, etc.) in the access network device, or a logic node, a logic module or software capable of realizing all or part of the functions of the access network device. Taking the method applied to the network device (such as the access network device) for example, the method comprises: sending first information, wherein the first information is used to indicate a plurality of sub-sequence sets, and the plurality of sub-sequence sets satisfy a second relationship with an AI sequence set; receiving a first AI sequence, wherein the first AI sequence is generated based on the first information, and the first AI sequence is contained in the AI sequence set; wherein the product of the number of sub-AI sequences contained in each sub-sequence set in the plurality of sub-sequence sets is equal to the number of AI sequences contained in the sequence set, and the sum of the number of sub-AI sequences contained in each sub-sequence set is less than the number of AI sequences contained in the AI sequence set.

[0082] In this technical solution, after the network device trains the AI sequence set, the network device can divide the AI sequence set into a plurality of sub-sequence sets according to the hierarchical mapping mode to be adopted, and send the sub-sequence sets to the terminal. The network device can also directly train a plurality of sub-sequence sets according to the hierarchical mapping mode to be adopted during the training process of the AI sequence, and send the sub-sequence sets to the terminal. It should be noted that the hierarchical mapping mode to be adopted and the specific implementation mode of hierarchical mapping are not limited herein.

[0083] Taking the hierarchical mapping mode as the commercial surplus mapping for example, assuming that the AI sequence set is represented as MxN, that is, the AI sequence set includes M AI sequences, and the length of each AI sequence is N, if the number of sub-sequence sets is 2, then the two sub-sequence sets can be represented as M1xN and M2xN. Wherein, M1xM2=M, and M1+M2<M, so that the total data amount of the sub-sequence sets can be less than the data amount of the AI sequence set, to reduce the transmission overhead. Wherein, M, N, M1, M2 are positive integers.

[0084] Optionally, the fourth information can be predefined through a protocol.

[0085] In the technical solution, the terminal can determine the AI sequence set based on the multiple sub-sequence sets and the second relationship, so that the terminal can randomly select an AI sequence from the AI sequence set and send the AI sequence to the network device. Since the total data amount of the sub-sequence set is less than the data amount of the AI sequence set, when the network device sends the sub-sequence set to the terminal, the transmission overhead is low.

[0086] With reference to the fourth aspect, in some implementations of the fourth aspect, the method further includes: sending fourth information, the fourth information being used to indicate the second relationship.

[0087] In the implementation, the second relationship can be configured by the network device to the terminal. For example, the network device can determine the second relationship according to real-time network conditions, load, and the like, and send the second relationship to the terminal to improve communication performance.

[0088] With reference to the fourth aspect, in some implementations of the fourth aspect, the method further includes: sending fifth information, the fifth information being used to indicate a third relationship, the third relationship being a relationship between an identifier of the AI sequence and multiple sub-identifiers, the multiple sub-identifiers corresponding to the multiple sub-sequence sets, each of the multiple sub-identifiers being used to determine one sub-AI sequence in a corresponding sub-sequence set, the AI sequence being generated based on multiple sub-AI sequences determined based on the multiple sub-identifiers.

[0089] In the implementation, the sub-identifier can be understood as an identifier of the sub-AI sequence in the sub-sequence set. The terminal can map the identifier of the AI sequence to the multiple sub-identifiers based on the third relationship, and determine the corresponding sub-AI sequence from the corresponding sub-sequence set based on the multiple sub-identifiers, so as to determine the AI sequence. The AI sequence can be a product of the multiple sub-AI sequences.

[0090] With reference to the fourth aspect, in some implementations of the fourth aspect, the method further includes: sending sixth information, the sixth information being used to indicate the identifier of the first AI sequence.

[0091] In the implementation, the network device can indicate the identifier of the AI sequence to the terminal, so that the terminal can determine the vector input into the AI model based on the identifier of the AI sequence indicated by the network device, and then generate the AI sequence corresponding to the identifier. In the implementation, the network device indicates the identifier of the AI sequence, which can reduce interference between AI sequences generated by the terminals, as compared to the terminal randomly selecting the identifier of the AI sequence.

[0092] In a fourth aspect, in some implementations of the fourth aspect, the method further includes: performing any one of the following in a first time period: receiving the first sequence, or not receiving a sequence; wherein a start time of the first time period is a start time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

[0093] In this implementation, considering that the AI sequence generation process occupies a certain time length, or in other words, there is a time delay in the AI sequence generation process, the behavior of the network device in this period of time can be agreed, so that the network device can know what behavior can be adopted in this period of time, to improve the communication performance.

[0094] In a fifth aspect, the present application provides a communication apparatus, which has the function of implementing the first aspect, for example, the communication apparatus includes a module or unit or means corresponding to the operation of the first aspect, which can be implemented by software, or by hardware, or by a combination of software and hardware.

[0095] For example, the apparatus can include a receiving module and a sending module. The receiving module is configured to receive first information, the first information being used to indicate a vector, the vector satisfying a first relationship with an identifier of an AI sequence, the vector being used as an input of an AI model, the AI model being used to generate the AI sequence; and the sending module is configured to send a first AI sequence, the first AI sequence being generated based on the first information.

[0096] In combination with the fifth aspect, in some implementations of the fifth aspect, the first information is used to indicate a vector, including that the first information is used to indicate the first relationship.

[0097] In combination with the fifth aspect, in some implementations of the fifth aspect, the first information includes at least one of the following: a first formula satisfied between the identifier of the AI sequence and the vector, a parameter in the first formula, a length of the vector, or a processing manner of the vector.

[0098] In combination with the fifth aspect, in some implementations of the fifth aspect, the first information is used to indicate a vector, including that the first information is used to indicate a vector set in which the vector is located, a plurality of vectors in the vector set corresponding to a plurality of AI sequences in a one-to-one manner, each of the plurality of vectors satisfying the first relationship with an identifier of a corresponding AI sequence, and the plurality of AI sequences belonging to a subset of a sequence set in which the AI sequence is located.

[0099] In some embodiments of the fifth aspect, the first information comprises at least one of: the plurality of vectors, or a processing manner of each vector in the plurality of vectors.

[0100] In some embodiments of the fifth aspect, the receiving module is further configured to receive second information, the second information being used to indicate the AI model.

[0101] In some embodiments of the fifth aspect, the sending module is further configured to send third information, the third information being used to indicate at least one of: supported AI model information, a supported first relationship, or a time length required for generating the AI sequence.

[0102] In some embodiments of the fifth aspect, the receiving module is further configured to receive sixth information, the sixth information being used to indicate an identity of the first AI sequence.

[0103] In some embodiments of the fifth aspect, the apparatus can further include a processing module. The processing module is configured to control the apparatus to perform any one of the following operations in a first time period: sending a first sequence, or not sending a sequence; wherein a start time of the first time period is a start time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

[0104] In the sixth aspect, the present application provides a communication apparatus having a function of implementing the second aspect, for example, the communication apparatus includes a module or unit or means corresponding to the operations of the second aspect, which can be implemented by software, or by hardware, or by a combination of software and hardware.

[0105] For example, the apparatus can include a receiving module and a sending module. The receiving module is configured to receive first information, the first information being used to indicate a plurality of sub-sequence sets, the plurality of sub-sequence sets satisfying a second relationship with a set of AI sequences; and the sending module is configured to send a first AI sequence, the first AI sequence being generated based on the first information, the first AI sequence being included in the set of AI sequences; wherein a product of a number of sub-AI sequences included in each sub-sequence set in the plurality of sub-sequence sets is equal to a number of AI sequences included in the set of AI sequences, and a sum of the number of sub-AI sequences included in each sub-sequence set is less than the number of AI sequences included in the set of AI sequences.

[0106] In some embodiments of the sixth aspect, the receiving module is further configured to receive fourth information, the fourth information being used to indicate the second relationship.

[0107] In some implementations of the sixth aspect, in conjunction with the sixth aspect, the receiving module is further configured to receive fifth information, where the fifth information is used to indicate a third relationship between an identity of the AI sequence and a plurality of sub-identities, the plurality of sub-identities correspond to the plurality of sub-sequence sets, each of the plurality of sub-identities is used to determine one sub-AI sequence in a corresponding sub-sequence set, and the AI sequence is generated based on a plurality of sub-AI sequences determined based on the plurality of sub-identities.

[0108] In some implementations of the sixth aspect, in conjunction with the sixth aspect, the receiving module is further configured to receive sixth information, where the sixth information is used to indicate the identity of the first AI sequence.

[0109] In some implementations of the sixth aspect, in conjunction with the sixth aspect, the apparatus can further include a processing module. The processing module is configured to control the apparatus to perform any one of the following operations in a first time period: send a first sequence, or not send a sequence, where a start time of the first time period is a start time of generating the AI sequence, and a length of the first time period is a length of time required for generating the AI sequence.

[0110] In the seventh aspect, the present application provides a communication apparatus, which has the function of implementing the third aspect, for example, the communication apparatus includes a module or unit or means corresponding to the operations related to the third aspect, which can be implemented by software, or by hardware, or by a combination of software and hardware.

[0111] For example, the apparatus can include a sending module and a receiving module. The sending module is configured to send first information, where the first information is used to indicate a vector, the vector and an identity of an AI sequence satisfy a first relationship, the vector is used as an input of an AI model, and the AI model is used to generate the AI sequence. The receiving module is configured to receive a first AI sequence, where the first AI sequence is generated based on the first information.

[0112] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the first information used to indicate the vector includes that the first information is used to indicate the first relationship.

[0113] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the first information includes at least one of the following information: a first formula satisfied between the identity of the AI sequence and the vector, a parameter in the first formula, a length of the vector, or a processing manner of the vector.

[0114] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the first information is used to indicate a vector, including: the first information is used to indicate a vector set in which the vector is located, a plurality of vectors in the vector set correspond to a plurality of AI sequences one by one, and each vector in the plurality of vectors and the identifier of the corresponding AI sequence satisfy the first relationship, and the plurality of AI sequences belong to a subset of a sequence set in which the AI sequences are located.

[0115] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the first information includes at least one of the following information: the plurality of vectors, or a processing manner of each vector in the plurality of vectors.

[0116] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the receiving module is further configured to receive third information, the third information being used to indicate at least one of the following information: supported AI model information, supported first relationship, or time length required for generating the AI sequence.

[0117] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the receiving module is further configured to receive third information, the third information being used to indicate at least one of the following information: supported AI model information, supported first relationship, or time length required for generating the AI sequence.

[0118] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the receiving module is further configured to receive third information, the third information being used to indicate at least one of the following information: supported AI model information, supported first relationship, or time length required for generating the AI sequence.

[0119] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the apparatus can further include a processing module. The processing module is configured to control the apparatus to perform any one of the following operations in a first time period: receive a first sequence, or not receive a sequence; wherein the starting time of the first time period is the starting time of generating the AI sequence, and the time length of the first time period is the time length required for generating the AI sequence.

[0120] In the eighth aspect, the present application provides a communication apparatus having the function of realizing the fourth aspect, for example, the communication apparatus includes a module or unit or means corresponding to the operation related to the fourth aspect, which can be realized by software, or by hardware, or by a combination of software and hardware.

[0121] For example, the apparatus can include a sending module and a receiving module. The sending module is configured to send first information, the first information being used to indicate a plurality of sub-sequence sets, the plurality of sub-sequence sets satisfying a second relationship with an AI sequence set; and the receiving module is configured to receive a first AI sequence, the first AI sequence being generated based on the first information, the first AI sequence being included in the AI sequence set; wherein a product of a number of sub-AI sequences included in each of the plurality of sub-sequence sets is equal to a number of AI sequences included in the sequence set, and a sum of the number of sub-AI sequences included in each of the plurality of sub-sequence sets is less than the number of AI sequences included in the AI sequence set.

[0122] With reference to the eighth aspect, in some implementations of the eighth aspect, the sending module is further configured to send fourth information, the fourth information being used to indicate the second relationship.

[0123] With reference to the eighth aspect, in some implementations of the eighth aspect, the sending module is further configured to send fifth information, the fifth information being used to indicate a third relationship, the third relationship being a relationship between an identity of the AI sequence and a plurality of sub-identities, the plurality of sub-identities corresponding to the plurality of sub-sequence sets, each of the plurality of sub-identities being used to determine one sub-AI sequence in a corresponding sub-sequence set, the AI sequence being generated based on a plurality of sub-AI sequences determined based on the plurality of sub-identities.

[0124] With reference to the eighth aspect, in some implementations of the eighth aspect, the sending module is further configured to send sixth information, the sixth information being used to indicate the identity of the first AI sequence.

[0125] With reference to the eighth aspect, in some implementations of the eighth aspect, the apparatus can further include a processing module. The processing module is configured to control the apparatus to perform any one of the following operations in a first time period: receiving a first sequence, or not receiving a sequence; wherein a starting time of the first time period is a starting time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

[0126] In a ninth aspect, the present application provides a communication apparatus, which includes an interface circuit and one or more processors. The one or more processors are coupled with a memory. The memory is used to store part or all of the necessary computer programs or instructions for implementing the functions related to the above-mentioned first aspect. The one or more processors can execute the computer programs or instructions, when the computer programs or instructions are executed, so as to make the communication apparatus implement the method in any possible design or implementation manner in the above-mentioned first aspect. The interface circuit is used to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other apparatuses or components.

[0127] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0128] In a possible design, the communication apparatus can further include the memory.

[0129] The communication apparatus can be a terminal, or a communication module in the terminal, or a chip responsible for a communication function in the terminal, such as a modem chip (also referred to as a baseband chip), or an SoC or SIP chip including a modem module.

[0130] In a possible design, the communication apparatus can further include the memory.

[0131] The communication apparatus can be a terminal, or a communication module in the terminal, or a chip responsible for a communication function in the terminal, such as a modem chip (also referred to as a baseband chip), or an SoC or SIP chip including a modem module.

[0132] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0133] In a possible design, the communication apparatus can further include the memory.

[0134] The communication apparatus can be a terminal, or a communication module in the terminal, or a chip responsible for a communication function in the terminal, such as a modem chip (also referred to as a baseband chip), or an SoC or SIP chip including a modem module.

[0135] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0136] In a possible design, the communication apparatus can further include the memory.

[0137] The communication apparatus can be a network device (e.g., a base station), or a module (e.g., a circuit, a chip or a chip system, etc.) in the network device, or a logic node, a logic module or software capable of implementing all or part of the functions of the network device.

[0138] In a twelfth aspect, the present application provides a communication apparatus, which comprises an interface circuit and one or more processors. The one or more processors are coupled with a memory. The memory is configured to store part or all of the computer programs or instructions necessary for implementing the functions related to the fourth aspect. The one or more processors can execute the computer programs or instructions, which, when executed, cause the communication apparatus to implement the method in any possible design or implementation manner of the fourth aspect. The interface circuit is configured to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other apparatuses or components.

[0139] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0140] In a possible design, the communication apparatus can further comprise the memory.

[0141] The communication apparatus can be a network device (e.g., a base station), or a module (e.g., a circuit, a chip or a chip system, etc.) in the network device, or a logic node, a logic module or software capable of implementing all or part of the functions of the network device.

[0142] In a thirteenth aspect, the present application provides a communication system, which comprises the apparatus in the fifth aspect or the ninth aspect, and comprises the apparatus in the seventh aspect or the eleventh aspect; or the communication system comprises the apparatus in the sixth aspect or the tenth aspect, and comprises the apparatus in the eighth aspect or the twelfth aspect.

[0143] In a fourteenth aspect, the present application provides a chip system, which comprises at least one processor configured to implement the functions related to any of the first aspect to the fourth aspect and any possible implementation manner of any of the aspects. For example, the processor is configured to send, receive or process the data and / or information related to the methods. In a possible implementation manner, the chip system further comprises a memory configured to store program instructions and data, and the memory is located in or outside the processor. The chip system can be composed of a chip, or can comprise a chip and other discrete devices.

[0144] In a fifteenth aspect, the present application provides a computer readable storage medium, which stores computer readable instructions. When the computer readable instructions are read and executed by a computer, the computer is caused to perform the method in any of the first aspect to the fourth aspect and any possible implementation manner of any of the aspects.

[0145] In a sixteenth aspect, the present application provides a computer program product, which, when executed by a computer, causes the computer to perform the method in any one of the first aspect to the fourth aspect and any possible implementation thereof.

[0146] The technical effects achieved by any one of the fifth aspect to the sixteenth aspect and any possible implementation thereof can refer to the technical effects achieved by any one of the first aspect to the fourth aspect and any possible implementation thereof, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0147] FIG. 1 is a schematic illustration of a communication system to which embodiments of the present application are applicable;

[0148] FIG. 2 is a schematic flowchart of a communication method according to an embodiment of the present application;

[0149] FIG. 3 is a schematic flowchart of a communication method according to another embodiment of the present application;

[0150] FIG. 3a is a schematic illustration of a first AI model training according to an embodiment of the present application;

[0151] FIG. 3b is a schematic flowchart of a first AI sequence generation according to an embodiment of the present application;

[0152] FIG. 4 is a schematic flowchart of a communication method according to yet another embodiment of the present application;

[0153] FIG. 5 is a schematic flowchart of a communication method according to another embodiment of the present application;

[0154] FIG. 6 is a schematic flowchart of a communication method according to yet another embodiment of the present application;

[0155] FIG. 7 is a schematic illustration of a determination of a first AI sequence according to an embodiment of the present application;

[0156] FIG. 8 is a schematic structural diagram of a communication apparatus according to an embodiment of the present application;

[0157] FIG. 9 is a schematic structural diagram of a communication apparatus according to another embodiment of the present application. DETAILED DESCRIPTION

[0158] In a communication system, a reference signal can be generated based on a predefined reference sequence, so that the two parties of communication can agree on the transmitted signal, so that the receiving end can detect the received signal based on the agreed signal after receiving the signal transmitted by the sending end, so as to achieve the purposes such as access, synchronization, demodulation, measurement, estimation, etc. For example, the reference signal can include but is not limited to: a preamble sequence for random access, a synchronization signal sequence for synchronization, a channel state information-reference signal (CSIRS) sequence for channel measurement, a sounding reference signal (SRS) sequence, a demodulation reference signal (DMRS) sequence for data demodulation. In future communication systems, there can also be a perception reference signal sequence for perception, etc.

[0159] Taking random access as an example, the terminal and the network device (such as a base station) can agree on a preamble sequence. The terminal can select a preamble sequence from the agreed preamble sequence set and send the selected preamble sequence in a specific random access opportunity (such as a random access slot) to initiate a random access request. Correspondingly, the network device can receive the uplink signal in the specific random access slot and perform correlation detection on the received uplink signal based on the agreed preamble sequence set to determine the correlation value of the received uplink signal and each preamble sequence in the preamble sequence set, thereby obtaining a correlation value sequence. The correlation value sequence is used to represent the matching degree of the received uplink signal and each preamble sequence, and the higher the correlation value, the higher the matching degree. After determining the peak value in the correlation value sequence, the network device can determine the relationship between the peak value and the preset detection threshold. If the peak value is greater than or equal to the detection threshold, it indicates that there is a preamble sequence sent by the terminal in the received uplink signal, and the network device can provide access service for the terminal. If there are multiple peak values in the correlation value sequence, it indicates that multiple terminals have sent preamble sequences.

[0160] When multiple terminals send preamble sequences, the uplink signal received by the network device is a superposition of multiple preamble sequences. However, since the currently commonly used preamble sequence is generated based on a ZC (Zadoff-Chu) sequence, there is a certain similarity between multiple ZC sequences, which causes interference between multiple preamble sequences, thereby causing the detection performance of the network device on multiple preamble sequences to be low. In addition, the network device detects the received uplink signal based on a detection threshold, but the optimal detection threshold is difficult to determine, thereby causing the detection accuracy to be low. Therefore, in the multi-user random access scenario, the detection performance of the network device on the received uplink signal is low, and the communication performance is poor.

[0161] Therefore, the present application proposes that an artificial intelligence (AI) technology can be used to improve the detection performance of the network device, thereby improving the communication performance of the communication system. For example, a two-end AI model can be used, and the AI model on the terminal side and the network device side are regarded as a whole to complete an AI function. The two-end AI model can include an AI sequence on the terminal side and a matching AI detection model on the network device side. Since the AI sequence on the terminal side and the AI detection model on the network device side are jointly trained, the interference between multiple AI sequences can be reduced in the terminal large-scale concurrent access scenario, and the detection performance of the network device based on the matching AI detection model for detecting the AI sequence is also improved accordingly. The AI sequence can be understood as a sequence determined based on an AI manner. The AI detection model can also be referred to as an AI detection network.

[0162] In the communication system, the two-end AI model can be trained by a type 1 (type 1) training manner. The type 1 training manner means that one node in the network device or the terminal trains the entire two-end AI model, and sends the trained opposite-end AI model to the opposite end. For example, the network device can train the AI sequence and the matching AI detection model, and send the trained AI sequence to the terminal. The terminal subsequently uses the AI sequence as a reference signal for transmission, and the network device uses the corresponding AI detection model for detection. It should be noted that in the training process of the AI sequence and the AI detection model, the AI sequence is actually part of the entire two-end AI model, and under the usual training manner, the AI sequence is trained as a part of the parameter of the whole model, rather than a black-box model.

[0163] However, after the AI sequence training is completed, how the network device sends the AI sequence generated by the training to the terminal becomes a technical problem to be solved. One possible implementation manner is that the network device can directly send the AI sequence generated by the training to the terminal. For example, in a random access scenario, the AI sequence can be sent through a broadcast message, such as sending the AI sequence to all terminals in the cell through a system information block (SIB). However, the data amount of the AI sequence generated by the training is large, which can exceed the data amount range that can be carried by the broadcast message, thereby causing the AI sequence to be difficult to be correctly transmitted, thereby affecting the implementation of the entire AI function; when the data amount of the AI sequence generated by the training is large, the transmission power consumption of the AI sequence is also large.

[0164] Therefore, the present application provides a communication method and a communication apparatus. In the technical solution provided by the present application, the network device can send indication information to the terminal to indicate the generation manner of the AI sequence, so that the terminal can autonomously generate the AI sequence, thereby reducing the transmission resources and power consumption of the network device and the terminal, and improving the communication performance of the system.

[0165] It should be understood that the technical solution provided by the present application can be applied to a double-end communication scenario in which a sending end sends a signal and a receiving end detects the signal sent by the sending end. For example, it can be used in the transmission and detection of a preamble sequence in a random access scenario, and can also be used in the transmission and detection of a synchronization signal sequence, a CSI RS sequence, an SRS sequence, a DMRS sequence, and the like, and the present application does not limit this. For example, the network device can train an AI DMRS sequence and a corresponding AI channel estimation model, and send the generation manner of the AI DMRS sequence to the terminal, so that the terminal can autonomously generate the AI DMRS sequence and send the generated AI DMRS sequence to the network device, and the network device detects the AI DMRS sequence sent by the terminal using the AI channel estimation model corresponding to the AI DMRS sequence to perform corresponding channel estimation. The technical solution provided by the present application can be applied to the transmission of uplink and downlink signals, and can also be applied to the transmission of sidelink signals, and the present application does not limit this.

[0166] The technical solutions provided in the present application can be applied to various communication systems, including but not limited to: a narrow band-internet of things (NB-IoT) system, a long term evolution (LTE) system, an LTE advanced (LTE-A) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), a fourth generation (4G) mobile communication system, a 5th generation (5G) mobile communication system, a new radio (NR) communication system, and a future communication system, and the present application does not make a specific limitation in this regard.

[0167] FIG. 1 is a schematic illustration of a communication system to which embodiments of the present application are applicable. As shown in FIG. 1, the communication system 100 can include a radio access network (RAN) 110 and a core network (CN) 120. The RAN 110 can include at least one RAN node (e.g., 130a and 130b in FIG. 1, collectively referred to as 130) and at least one terminal (e.g., 140a-140j in FIG. 1, collectively referred to as 140). The RAN 110 can further include other RAN nodes, such as a wireless relay device and / or a wireless backhaul device (not shown in FIG. 1), etc. The terminal 140 can be connected to the RAN node 130 in a wireless manner. The RAN node 130 can be connected to the core network 120 in a wireless or wired manner. The core network device in the core network 120 and the RAN node 130 in the RAN 110 can be different physical devices, respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the radio access network. In some embodiments, the communication system 100 can also include an Internet 150.

[0168] The RAN 110 can be a 3rd generation partnership project (3GPP) related cellular system, such as a 4G, 5G mobile communication system, or a future-oriented evolution system. The RAN 110 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a WiFi system. The RAN 110 can also be a communication system in which two or more of the above systems are integrated.

[0169] The RAN nodes 130, which can also be referred to as access network devices, RAN entities, or access nodes, etc., form part of the communication system and are responsible for enabling wireless access to the communication system for the terminals. The RAN nodes 130 in the communication system 100 can be the same type of nodes or different types of nodes. In some scenarios, the roles of the RAN nodes 130 and the terminals 140 are relative, e.g., the network element 140i in Figure 1 can be a helicopter or a drone, which can be configured to move as a mobile base station, to the terminal 140j accessing the RAN 110 through the network element 140i, the network element 140i is a base station; but to the base station 130a, the network element 140i is a terminal. The RAN nodes 110 and the terminals 140 are sometimes referred to as communication apparatuses, e.g., the network elements 130a and 130b in Figure 1 can be understood as communication apparatuses with base station functionality, and the network elements 140a-140j can be understood as communication apparatuses with terminal functionality

[0170] In a possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission and receiving point (TRP), a gNB, a base station in a future mobile communication system, etc. The RAN node can be a macro base station (such as 130a in FIG. 1), a micro base station or an indoor station (such as 130b in FIG. 1), a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, an access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). All or part of the functions of the RAN node in this application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform such as a cloud platform. The RAN node can also be provided with a communication module, circuit or chip for performing corresponding communication functions, and program instructions for performing corresponding communication functions. The RAN node in this application can also be a logical node, a logical module or software that can implement all or part of the functions of the RAN node. In this embodiment, the RAN node can also be referred to as a network device, for example. In this application, the network device is the original expression for the access network device (such as a base station). In this embodiment, the network device can include a baseband processor. The device for implementing AI functions of the network device can be a network device AI application accelerator, such as a neural processing unit (NPU) or a graphics processing unit (GPU).

[0171] In another possible scenario, a terminal is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, included in a remote radio unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0172] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0173] A terminal can be a device or module with corresponding communication functions and can access the above communication system. The terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely used in various scenarios, such as device-to-device (D2D), vehicle to everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, transport vehicle with wireless communication function, communication module, etc. Embodiments of the present application do not limit the device form of the terminal. The terminal usually has a communication module, circuit or chip for performing corresponding communication functions. The terminal can also be configured with program instructions for performing corresponding communication functions. In the embodiments, the terminal can include a baseband processor. The device for implementing AI functions of the terminal can be a terminal AI application accelerator, such as NPU and GPU.

[0174] In order to facilitate understanding of the method provided by the embodiments of the present application, the following points are first explained:

[0175] First, in the embodiments of the present application, "sending information" can be understood as a device sending information to another device, or it can also be understood as a logical module in a device sending information to another logical module. For example, "the network device sending information" can be understood as the network device sending information to another device (such as a terminal), or it can be understood as a logical module 1 in the network device sending information to a logical module 2 in the network device.

[0176] Second, in the embodiments of the present application, "receiving information" can be understood as a device receiving information from another device, or it can also be understood as a logical module in a device receiving information from another logical module. For example, "the terminal receiving information" can be understood as the terminal receiving information from another device (such as a network device), or it can be understood as a logical module 1 in the terminal receiving information from a logical module 2 in the terminal.

[0177] Thirdly, in the embodiments of the present application, "sending information to a device (e.g., a terminal)" or related illustrations in the drawings can be understood as that the destination of the information is the terminal. It can include directly or indirectly sending information to the terminal. "Receiving information from a device (e.g., a terminal)" or "receiving information from a device (e.g., a terminal)" or "receiving information sent by a device (e.g., a terminal)", or related illustrations in the drawings can be understood as that the source of the information is the terminal, which can include directly or indirectly receiving information from the terminal. The information can be processed between the source and the destination of the information, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be similarly understood, and will not be repeated here.

[0178] The communication method and the communication apparatus provided by the embodiments of the present application will be described below in conjunction with FIG. 2 to FIG. 9. It can be understood that the network device and the terminal are taken as an example to illustrate the execution subject of the interaction in the present application, but the present application does not limit the execution subject of the interaction. For example, the method executed by the network device in the present application can also be implemented by a module (such as a circuit, a chip or a chip system, etc.) in the network device, or a logical node, a logical module or software capable of realizing all or part of the function of the access network device; the method executed by the terminal in the present application can also be implemented by a communication module in the terminal or a circuit or a chip (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem module, or a SIP chip) responsible for the communication function in the terminal.

[0179] FIG. 2 is a schematic flow chart of a communication method according to an embodiment of the present application. As shown in FIG. 2, the method can include S201 and S202.

[0180] S201, the network device sends first information, the first information is used to indicate a vector, the vector satisfies a first relationship with the identity of the AI sequence, the vector is used as an input of a first AI model, and the first AI model is used to generate the AI sequence. Correspondingly, the terminal receives the first information.

[0181] In the embodiments, the terminal can generate the AI sequence based on the first AI model. The first AI model can be located in the terminal, or the first AI model can not be located in the terminal, and the terminal can realize the calling of the first AI model, which is not limited here. Optionally, the first AI model can be predefined by a protocol, and the terminal can realize the acquisition of the first AI model through the protocol. For example, the structure and / or parameters of the first AI model can be defined by the protocol, and the terminal determines the first AI model according to the model structure and / or parameters defined by the protocol.

[0182] In this embodiment, the network device can indicate the input of the first AI model to the terminal, so that the terminal can generate an AI sequence based on the first AI model and the input of the first AI model. For example, the network device can send first information to the terminal, and the first information is used to indicate the input of the first AI model. The specific form of the input of the first AI model is not limited in the present application. For example, the input of the first AI model can be in the form of a vector, a matrix, etc. In the present embodiment, the vector is taken as the input of the first AI model.

[0183] In this embodiment, the vector indicated by the first information can be used as the input of the first AI model. The vector and the identifier of the AI sequence satisfy a first relationship, so that the first AI model can generate the AI sequence corresponding to the identifier based on the vector. That is, the vector input into the first AI model can be different, and the AI sequence generated by the first AI model can be different. The identifier of the AI sequence can be an integer, which is used to distinguish different AI sequences.

[0184] In this embodiment, the terminal can input the vector indicated by the first information into the first AI model to generate the AI sequence after receiving the first information. For example, when the first information indicates the first vector, and the first vector and the identifier of the first AI sequence satisfy the first relationship, the terminal can generate the first AI sequence after inputting the first vector into the first AI model. The first AI sequence can be understood as the AI sequence determined to be sent by the terminal. Correspondingly, the network device can receive the first AI sequence and detect the first AI sequence after receiving the first AI sequence. For example, the network device can detect the received signal containing the first AI sequence to determine whether the terminal has sent the first AI sequence.

[0185] In this embodiment, the terminal can send the AI sequence to the network device after generating the AI sequence. Correspondingly, the network device can receive and detect the AI sequence to provide services for the terminal. For example, when the AI sequence is a random access sequence, the network device can provide access services for the terminal after receiving and detecting the AI sequence.

[0186] In this embodiment, the terminal can generate the required AI sequence based on the vector indicated by the network device and the first AI model. In this embodiment, the network device can only indicate the input of the AI model, without sending all the AI sequences generated by training to the terminal, so as to reduce the signaling overhead. Moreover, the data amount of the vector is smaller than that of the AI sequence generated by training, the broadcast message can carry the vector, and the transmission reliability of the vector is higher.

[0187] In this embodiment, the terminal can generate the required AI sequence based on the vector indicated by the network device and the first AI model. In this embodiment, the network device can only indicate the input of the AI model, without sending all the AI sequences generated by training to the terminal, so as to reduce the signaling overhead. Moreover, the data amount of the vector is smaller than that of the AI sequence generated by training, the broadcast message can carry the vector, and the transmission reliability of the vector is higher.

[0188] In a possible implementation, the first information is used to indicate the vector, and the first information can indicate the vector by indicating the first relationship, or the first information can indicate the vector by indicating a vector set. The specific implementation of the two methods is described below in combination with FIG. 3 and FIG. 4.

[0189] FIG. 3 is a schematic flowchart of a communication method according to another embodiment of the present application. In the method shown in FIG. 3, the first information can indicate the vector by indicating the first relationship. As shown in FIG. 3, the method can include S301 to S305.

[0190] S301, the terminal sends third information, and the third information is used to indicate whether the capability of generating an AI sequence by an AI model is supported. Correspondingly, the network device receives the third information.

[0191] In this embodiment, the terminal can report the capability of the terminal to the network device, for example, whether the capability of generating an AI sequence by an AI model is supported. Correspondingly, the network device can receive the capability reported by the terminal. For convenience of description, the capability of generating an AI sequence by an AI model can be referred to as a first capability.

[0192] As an example, when the AI sequence is a preamble sequence, or in other words, the AI sequence is used for random access, the terminal has not accessed the network. Therefore, it can be defaulted that the terminal supports the first capability. In some embodiments, when the terminal supports the first capability, it can be considered that the terminal has at least one default first relationship, or in other words, the terminal has at least one supported first relationship by default.

[0193] As an example, when the AI sequence is a sequence for DMRS, CSIRS, SRS, etc., when the terminal supports the first capability, the terminal can report at least one of the following information to the network device: AI model information supported, or a supported first relationship. The AI model information can include an AI model structure and / or an AI model parameter. The terminal can report the AI model information supported and / or the supported first relationship to the network device through the third information, or report through other information, which is not limited herein.

[0194] In some embodiments, when the terminal supports the first capability, the terminal can report a time length required for the terminal to generate an AI sequence, or in other words, a time length required for the terminal to infer an AI sequence based on an AI model, to the network device. The terminal can report the time length required for the terminal to generate an AI sequence to the network device through the third information, or report through other information, which is not limited herein.

[0195] It should be noted that S301 is an optional step, which can be executed or not executed.

[0196] S302, the network device sends first information, the first information is used to indicate a first relationship between a vector and an identification of an AI sequence, the vector is used as an input of a first AI model, and the first AI model is used to generate the AI sequence. Correspondingly, the terminal receives the first information.

[0197] In this embodiment, the network device can send the first information to the terminal, and the first information can be used to indicate the first relationship between the vector and the identification of the AI sequence. Correspondingly, the terminal can receive the first information. The terminal can determine the vector input to the first AI model based on the identification of the AI sequence and the first relationship, so as to generate the AI sequence. In some embodiments, the first relationship can be used to indicate a fixed pre-coding preprocessing operation before the AI sequence is recovered or generated by using the first AI model. The fixed pre-coding can be understood as the identification of the AI sequence, and the preprocessing operation refers to mapping the identification of the AI sequence to the vector. The first relationship indicated by the first information can be a first relationship supported by the terminal.

[0198] In an implementable manner, the first relationship can be a mapping manner with parameters, for example, the identification of the AI sequence and the vector can satisfy a first formula, and the first formula contains parameters. In this implementation manner, the first information can include the first formula.

[0199] As an example, the identification of the AI sequence and the vector can satisfy a global hash mapping formula, such as: q = ((a*x+b)mod p)mod m. Wherein, q is an element in the vector, x is the identification of the AI sequence, a is a random integer, b is a random non-zero integer, m is the size of the hash table, or in other words, m is the value range after the hash mapping is completed, and p is a random prime number greater than m. The element of the vector can be understood as an individual numerical value or object constituting the vector. It should be understood that the vector contains at least one element.

[0200] Optionally, the first formula can be predefined by a protocol, and the parameters a, b, p, m, etc. in the first formula can be indicated by the network device to improve the use flexibility of the formula. The terminal can determine the vector input to the first AI model based on the first formula and the identification of the AI sequence. Optionally, the first formula and the parameters in the first formula can be configured by the network device.

[0201] In an implementable manner, the first relationship can be a parameter-free mapping manner. As an example, the identification of the AI sequence and the vector can satisfy a multi-ary conversion. For example, the identification of the AI sequence and the vector can satisfy a binary conversion, and the terminal can perform binary conversion on the identification of the AI sequence, and take the binary number formed by the conversion as the vector. Each bit in the binary number can be taken as an element in the vector, and the value of the element is 0 or 1. The specific conversion mechanism can be predefined by the protocol or configured by the network device, which is not limited here.

[0202] Optionally, the network device can indicate the dimension k of the vector to the terminal, so that the vector input into the AI model is uniform in dimension, and the performance of the AI model is improved. k is a positive integer. As an example, when the vector is a one-dimensional vector, the dimension of the vector can be understood as the number of elements contained in the vector. After the terminal determines the vector based on the first relationship, if the dimension of the vector is less than k, the terminal can expand the vector to a vector with a dimension of k; if the dimension of the vector is greater than k, the terminal can reduce the vector to a vector with a dimension of k. In some embodiments, the dimension of the vector can also be referred to as the bit number or length of the vector, which is not limited here. The network device can indicate the dimension of the vector to the terminal through the first information, or can indicate it through other information, which is not limited here.

[0203] In an implementable manner, if the identification of the AI sequence and the vector satisfy the first formula, the terminal can use the first formula k times to determine a vector with a dimension of k. Wherein, each use of the first formula is used to determine an element in the vector, or the v-th use of the first formula is used to determine the v-th element in the vector, v is a positive integer less than or equal to k.

[0204] Optionally, the network device can also indicate the processing manner of the vector to the terminal, for example, whether to perform normalization processing on the vector, so as to improve the performance of the AI model. In some embodiments, the network device can also indicate the interval of the normalization to the terminal. The network device can indicate the processing manner of the vector to the terminal through the first information, or can indicate it through other information, which is not limited here.

[0205] Optionally, the first information can be carried by a radio resource control (RRC) message, a SIB message, or a non-access stratum (NAS) message, which is not limited here.

[0206] S303, the network device sends second information, and the second information is used to indicate the first AI model. Correspondingly, the terminal receives the second information.

[0207] In this embodiment, the network device can send the second information to the terminal, and the second information is used to indicate the first AI model. Correspondingly, the terminal can receive the second information. Optionally, the first AI model indicated by the second information can be an AI model supported by the terminal.

[0208] Optionally, when the structure of the first AI model is predefined by a protocol or a standard, or defined offline by the network device and the terminal, the second information can only indicate the parameters of the first AI model, or the second information can indicate the parameters of the first AI model and the identifier of the structure of the first AI model, so as to reduce the overhead and complexity of the configuration of the first AI model.

[0209] Optionally, when the structure and the parameters of the first AI model are predefined by a protocol or a standard, or defined offline by the network device and the terminal, the second information can only indicate the identifier of the first AI model.

[0210] Optionally, when the structure and / or the parameters of the first AI model are configured by the network device, the second information can be used to indicate the structure and / or the parameters of the first AI model, so as to improve the flexibility of the configuration of the first AI model.

[0211] Optionally, the structure of the first AI model can be a model structure supported in a Z4 mode of a model transfer (model transfer) in a fixed model structure.

[0212] Optionally, the terminal or the terminal manufacturer can perform optimization processing on the first AI model, so as to avoid the case that the terminal cannot directly use the first AI model.

[0213] As an example, the second information can be transmitted through an air interface message, such as an RRC message, or a SIB message, or a NAS message. The air interface message can be a message or data on a control plane.

[0214] As an example, the second information can be transmitted through a non-air interface message, such as a service data packet, or an application layer data. The non-air interface message can be a message or data on a user plane.

[0215] As an example, the first AI model can be a deep neural network (DNN) model. The DNN model is more suitable for a Z4 model transfer mode in a fixed model structure, so as to simplify the transmission process of the model information, and reduce power consumption and overhead.

[0216] Optionally, the network device can also indicate to the terminal a processing manner of the AI sequence output by the first AI model. The processing manner of the AI sequence output by the first AI model can include inverse normalization processing or quantization processing. In some embodiments, the network device can also indicate to the terminal an inverse normalization processing interval or a quantization interval, so that the terminal can perform inverse normalization processing or quantization processing according to the maximum value or the minimum value of the interval indicated by the network device, to improve the detection performance of the AI sequence.

[0217] In some embodiments, the first AI model can be trained by the network device. When the network device trains the AI sequence and the corresponding AI detection model, the first AI model can be included in the training process of this part of the AI sequence. As an example, the first AI model can be a deep hash embedding (DHE) model, which can also be referred to as an AI compression model.

[0218] FIG. 3a is a schematic illustration of training of a first AI model according to an embodiment of the present application. FIG. 3a includes two parts, the first part is the training of the first AI model, and the second part is the training of the AI sequence and the AI detection model.

[0219] In one possible implementation, the AI sequence and the AI detection model can be trained first, and the training of the first AI model can be based on the trained AI sequence. For convenience of description and differentiation, the trained AI sequence is referred to as an initial AI sequence. Before the training of the first AI model, the network device needs to determine a first relationship between a sequence identifier and a vector, and determine an initial AI model as the first AI model. The network device can randomly select one or more identifiers from the identifiers of the initial AI sequence, map the selected identifiers to vectors in sequence based on the first relationship, and input the vectors to the first AI model in sequence, thereby generating one or more AI sequences. The network device can determine the performance (such as inference accuracy, or accuracy of generating the initial AI sequence) of the first AI model based on the initial AI sequence corresponding to the selected identifier and the AI sequence generated by the first AI model, and if the performance of the first AI model does not reach a target performance, the structure and / or parameters of the first AI model can be adjusted, and the training process can be performed again until the performance of the first AI model reaches the target performance. As shown in FIG. 3, identifier 1 and identifier 2 are identifiers of the initial AI sequence, the network device can map identifier 1 to vector 1 based on the first relationship, and input vector 1 to the first AI model to generate AI sequence 1; map identifier 2 to vector 2 based on the first relationship, and input vector 2 to the first AI model to generate AI sequence 2. The network device can determine the performance of the first AI model based on the initial AI sequence corresponding to identifier 1 and AI sequence 1 generated by the first AI model, and based on the initial AI sequence corresponding to identifier 2 and AI sequence 2 generated by the first AI model.

[0220] After the first AI model is trained, the AI detection model that has been trained can be trained again based on the AI sequence output by the first AI model to improve the detection performance of the AI detection model. As shown in FIG. 3, the AI sequence 1 can be transmitted through channel 1, the AI sequence 2 can be transmitted through channel 2, and the transmitted signals can be input into the AI detection model after superimposing noise thereon. At this time, the signal received by the AI detection model contains the AI sequence 1 and the AI sequence 2, and the AI detection model can detect the AI sequence 1 and the AI sequence 2 from the received signal. Assuming that the AI detection model detects the sequence Q1 and the sequence Q2 from the received signal, the network device can determine the detection loss of the AI detection model based on the sequence Q1 and the sequence Q2 detected by the AI detection model and the AI sequence 1 and the AI sequence 2, and further determine the detection performance of the AI detection model. If the detection loss of the AI detection model does not reach the target detection loss, the AI detection model can be adjusted, and the detection process can be performed again until the detection loss of the AI detection model reaches the target detection loss. For example, the detection loss of the AI detection model can be determined based on a cross-entropy loss function.

[0221] Optionally, after the first AI model is trained, the loss of the AI sequence output by the first AI model can also be verified. For example, the loss of the AI sequence output by the first AI model can be determined based on a blur function to reduce the interference between the AI sequences output by the first AI model, and further improve the detection performance of the AI sequence. If the loss of the AI sequence output by the first AI model does not reach the target sequence loss, the above steps can be repeatedly performed until the AI sequence loss of the first AI model reaches the target training loss, the performance of the first AI model reaches the target performance, and the detection loss of the AI detection model reaches the target detection loss.

[0222] After the first AI model is trained, the AI sequence generated by the training can be implicitly contained in the first AI model, and the network device no longer has an explicit AI sequence. It should be understood that after the first AI model is trained, the vector generated based on the first relationship mapping input into the first AI model can generate the AI sequence corresponding to the identifier.

[0223] In this embodiment, the network device can send the sixth information to the terminal, and the sixth information is used to indicate the identifier of the first AI sequence.

[0224] In this embodiment, the network device can send the sixth information to the terminal, and the sixth information is used to indicate the identifier of the first AI sequence.

[0225] In an implementable manner, the sixth information can include a quantity M of AI sequences generated by the network device through training. The terminal can determine an identification range of the AI sequences based on the sixth information, so as to determine the identification of the first AI sequence. For example, the terminal can randomly select an identification from the identification range of the AI sequences as the identification of the first AI sequence, improving the selection flexibility of the identification of the first AI sequence. In some embodiments, the network device can indicate at least one of the following information to the terminal: a length N of each AI sequence generated through training, or a channel number L of each AI sequence generated through training. The length N of each AI sequence and the channel number L of each AI sequence can be indicated by the sixth information, or can be indicated by other information, which is not limited herein. In this example, the size of the set of AI sequences generated through training is M*N*L. Each value of the AI sequence can be a complex number, a real number, a floating point number, or a fixed point number, which is not limited herein. M, N, and L are positive integers.

[0226] In an implementable manner, the sixth information can include the identification of the first AI sequence. The terminal can directly determine the identification of the first sequence based on the sixth information, improving the communication efficiency of the system.

[0227] It should be noted that S304 is an optional step, which can be executed or not executed. For example, the identification range of the AI sequence can be predefined by a protocol.

[0228] In this embodiment, the execution sequence of S301 to S304 is not specifically limited.

[0229] S305, the terminal sends the first AI sequence. Correspondingly, the network device receives the first AI sequence.

[0230] In this embodiment, after obtaining the identification of the first AI sequence, the terminal can map the identification of the first AI sequence to a first vector based on a first relationship, input the first vector into a first AI model, so as to generate the first AI sequence, as shown in the method of FIG. 3b. As shown in FIG. 3b, the first vector can be represented as [x1, x2, …, xk]. The terminal can send the generated first AI sequence to the network device. Correspondingly, the network device can receive and detect the first AI sequence, and provide corresponding network service for the terminal. In some embodiments, after the terminal maps the identification of the first AI sequence to the first vector based on the first relationship, the first vector can be normalized, and then the normalized first vector is input into the first AI model to generate the first AI sequence.

[0231] In some embodiments, considering that the AI sequence generation process occupies a certain time length, or there is a time delay in the AI sequence generation process, when the AI sequence indicates the transmission mode of the network device, the terminal can perform any one of the following operations in the first time period: transmit the first sequence or not transmit the sequence. The starting time of the first time period can be the starting time of generating the AI sequence, or can be the time when the terminal selects / determines the first AI sequence identifier. The time length of the first time period is the time length required for generating the AI sequence. Correspondingly, the network device can receive the first sequence in the first time period, or not receive the sequence. In this embodiment, by agreeing that the network device does not expect the terminal to transmit the corresponding sequence in the first time period, or in other words, by agreeing that the network device does not expect the terminal to transmit any sequence in the first time period, the behavior of the terminal and the network device in this period of time is regulated, so that the terminal and the network device can know what behavior can be adopted in this period of time, to improve the communication performance. When the AI sequence is a DMRS sequence, the terminal can ignore the corresponding uplink scheduling or use a default legacy DMRS sequence in the first time period.

[0232] In this embodiment, the network device can send the terminal an indication of the first relationship, and the terminal can map the identifier of the AI sequence to a vector based on the first relationship and input it into the first AI model to generate the first AI sequence. In this embodiment, the AI model is used to generate the corresponding AI sequence, which can save the air interface transmission overhead and reduce the power consumption of the network device and the terminal compared to transmitting the AI sequence generated by training. In addition, the AI model generates the AI sequence, and the detection accuracy of the network device for the AI sequence is also high, and the detection performance is not greatly lost.

[0233] FIG. 4 is a schematic flowchart of a communication method according to another embodiment of the present application. In the method shown in FIG. 4, the first information can indicate the vector by indicating the vector set. As shown in FIG. 4, the method can include S401-S405.

[0234] S401, the terminal sends third information, and the third information is used to indicate whether the terminal supports the capability of generating the AI sequence by the AI model. Correspondingly, the network device receives the third information.

[0235] In this embodiment, the specific implementation of S401 can refer to S301, which will not be described here.

[0236] Compared with S301, in this embodiment, when the terminal supports the first capability, the terminal can also report the vector set supported by the terminal to the network device. The terminal can report the vector set supported by the terminal to the network device through the third information, or report it through other information, which is not limited here.

[0237] S402, the network device sends first information, the first information is used to indicate a vector set, a plurality of vectors in the vector set correspond to a plurality of AI sequences in an AI sequence set one by one, and a first relationship is met between each vector in the plurality of vectors and the identifier of the corresponding AI sequence. Correspondingly, the terminal receives the first information.

[0238] In this embodiment, the network device can determine a first relationship, and map the identifier of each AI sequence generated by training based on the first relationship, thereby generating a vector set, and indicating the generated vector set to the terminal through the first information. The vectors in the vector set correspond to the AI sequences in the AI sequence set one by one. For example, when the first vector in the vector set corresponds to the first AI sequence in the AI sequence set, the first relationship is met between the first vector and the identifier of the first AI sequence. Correspondingly, the terminal can receive the first information. It should be understood that each vector in the vector set can be used as input of the first AI model. The AI sequence set can include part or all of the AI sequences generated by training.

[0239] In an implementable manner, the form of the vector set can be represented as [M, k]. Wherein, M represents the number of vectors in the vector set; k represents the dimension of each vector. It should be understood that the number of vectors in the vector set is the same as the number of AI sequences in the AI sequence set.

[0240] Optionally, k can be less than the length N of the AI sequence, so that the data amount of the vector set is less than the data amount of the AI sequence set, thereby making the transmission overhead of the vector set lower.

[0241] Optionally, the network device can also indicate to the terminal the processing mode of each vector in the plurality of vectors, such as whether to perform normalization processing on the vector, so as to improve the performance of the AI model. In some embodiments, the network device can also indicate to the terminal the interval of normalization. Wherein, the network device can indicate the processing mode of the vector to the terminal through the first information, or through other information, which is not limited here.

[0242] Optionally, the first information can be carried through an RRC message, an SIB message, or a NAS message, which is not limited here.

[0243] S403, the network device sends second information, the second information is used to indicate the first AI model. Correspondingly, the terminal receives the second information.

[0244] In this embodiment, the specific implementation of S403 can refer to S303, which will not be described here.

[0245] S404, the network device sends sixth information, the sixth information is used to indicate the identifier of the first AI sequence. Correspondingly, the terminal receives the sixth information.

[0246] In this embodiment, the specific implementation of S404 can refer to S304, which is not described here again.

[0247] In this embodiment, S404 is an optional step, which can be executed or not executed. For example, the identification range of the AI sequence can be determined based on the number of vectors in the vector set.

[0248] S405, the terminal sends the first AI sequence. Correspondingly, the network device receives the first AI sequence.

[0249] In this embodiment, after obtaining the identification of the first AI sequence, the terminal can select a first vector with the same identification as the first AI sequence from the vector set, and input the first vector into the first AI model, so as to generate the first AI sequence and send it to the network device. Correspondingly, the network device can receive and detect the first AI sequence, and provide corresponding network service for the terminal. The identification of the first AI sequence can be the same as the identification of the first vector in the vector set.

[0250] In some embodiments, the terminal can directly select a vector from the vector set at random, and input the selected vector into the first AI model to generate the AI sequence.

[0251] In some embodiments, after determining the vector input into the first AI model, the terminal can perform normalization processing on the vector, and then input the vector after normalization processing into the first AI model to generate the AI sequence.

[0252] In this embodiment, the behavior of the terminal and the network device in the first time period can also be agreed to improve the communication performance. For details, please refer to the related description in S305, which is not described here again.

[0253] In this embodiment, the network device can directly send the mapped vector set to the terminal without indicating the first relationship, thereby reducing the standardization difficulty. At the same time, the data amount of the vector set can be less than that of the AI sequence set, so compared with transmitting the AI sequence set, transmitting the vector set can achieve the purpose of reducing the transmission overhead. Compared with the method in FIG. 3, in this embodiment, the terminal can achieve the purpose of generating the first AI sequence through the first AI model without explicitly obtaining the first relationship.

[0254] In a possible implementation, the terminal can not generate the AI sequence by using the AI model, but can determine the AI sequence by using a hierarchical mapping manner. For example, the network device can perform hierarchical mapping on the AI sequence set to obtain a plurality of sub-sequence sets, and send the plurality of sub-sequence sets to the terminal. The terminal can determine the to-be-sent AI sequence based on the plurality of sub-sequence sets and the identifier of the to-be-sent AI sequence. Since the total data amount of the plurality of sub-sequence sets is less than the data amount of the AI sequence set, the transmission overhead can be reduced. The method is described below with reference to FIG. 5 and FIG. 6.

[0255] FIG. 5 is a schematic flowchart of a communication method according to another embodiment of the present application. In the method shown in FIG. 5, the network device can perform hierarchical mapping on the AI sequence set to obtain a plurality of sub-sequence sets, so that the terminal can determine the to-be-sent first AI sequence based on the plurality of sub-sequence sets. As shown in FIG. 5, the method can include S501 to S504.

[0256] S501, the network device sends first information, the first information being used to indicate the plurality of sub-sequence sets, and the plurality of sub-sequence sets satisfying a second relationship with the AI sequence set. Correspondingly, the terminal receives the first information.

[0257] As an example, after the network device generates the AI sequence set by training, the network device can determine T sub-sequence sets smaller than the AI sequence set according to a hierarchical mapping manner to be used, and send the T sub-sequence sets to the terminal. T is a positive integer. The hierarchical mapping manner used and the specific implementation of the hierarchical mapping are not limited in the embodiments of the present application. For example, the hierarchical mapping manner can be a quotient-remainder mapping.

[0258] As an example, the network device can directly train the T sub-sequence sets in combination with the hierarchical mapping manner in the training process of the AI sequence and the AI detection model.

[0259] Taking the quotient-remainder mapping as an example, assuming that the AI sequence set is represented as M×N, that is, the AI sequence set includes M AI sequences, and the length of each AI sequence is N, if T is 2, the two sub-sequence sets can be represented as M1×N and M2×N respectively. M1×M2=M, and M1+M2M, so that the data amount of the sub-sequence set is less than the data amount of the AI sequence set, and the transmission overhead is reduced. M1 and M2 are positive integers.

[0260] In the embodiment, the network device can indicate the T sub-sequence sets after hierarchical mapping to the terminal by using the first information. Correspondingly, the terminal can receive the first information. The T sub-sequence sets satisfy a second relationship with the AI sequence set. The second relationship can be determined based on the hierarchical mapping manner used.

[0261] Optionally, the first information can be carried by an RRC message, an SIB message, or a NAS message, or the T subsequence sets can be carried by an RRC message, an SIB message, or a NAS message.

[0262] S502, the network device sends fourth information, the fourth information being used for indicating the second relationship.

[0263] In this embodiment, the network device can send the fourth information to indicate the second relationship between the T subsequence sets and the AI sequence set. Correspondingly, the terminal can receive the fourth information. After determining the second relationship, the terminal can determine the AI sequence set based on the second relationship and the received T subsequence sets.

[0264] In some embodiments, considering that the second relationship can be determined based on a hierarchical mapping manner, the hierarchical mapping manner can be a manner agreed by the network device and the terminal, for example, predefined by a protocol or a standard, or defined by offline negotiation between the network device and the terminal. Therefore, S502 is an optional step.

[0265] S503, the network device sends sixth information, the sixth information being used for indicating the identity of the first AI sequence. Correspondingly, the terminal receives the sixth information.

[0266] In this embodiment, the specific implementation of S503 can refer to S304, which is not described here again.

[0267] Considering that M1 x M2 = M, the terminal can determine the identity range of the AI sequence based on the received T subsequence sets, and randomly select an identity from the identity range as the identity of the first AI sequence, so as to improve the selection flexibility of the identity of the first AI sequence. Therefore, S503 is an optional step, which can be executed or not executed.

[0268] S504, the terminal sends the first AI sequence, the first AI sequence being generated based on the first information, and the first AI sequence being included in the AI sequence set. Correspondingly, the network device receives the first AI sequence.

[0269] In this embodiment, after determining the identity of the first AI sequence and the AI sequence set, the terminal can determine the first AI sequence based on the identity of the first AI sequence and the AI sequence set, and send the first AI sequence to the network device. Correspondingly, the network device can receive and detect the first AI sequence, and provide corresponding network service for the terminal.

[0270] In an implementable manner, the terminal can determine the AI sequence set based on the plurality of subsequence sets and the second relationship, so as to randomly select an AI sequence from the AI sequence set and send the AI sequence to the network device.

[0271] In this embodiment, the network device can send a plurality of sub-sequence sets to the terminal, the plurality of sub-sequence sets satisfy a second relationship with the AI sequence set, and the terminal can determine the AI sequence set based on the plurality of sub-sequence sets, so as to determine the AI sequence to be sent. In this embodiment, the total data amount of the plurality of sub-sequence sets is less than the data amount of the AI sequence set, and therefore, compared with transmitting the AI sequence set, transmitting the plurality of sub-sequence sets can also reduce the air interface overhead.

[0272] In a possible implementation, when the network device indicates the plurality of sub-sequence sets to the terminal, the network device can also indicate a third relationship to the terminal, the third relationship being a relationship between the identifier of the AI sequence and the identifier of the sub-AI sequence in the sub-sequence set, so that the terminal can determine the AI sequence to be sent based on the plurality of sub-sequence sets and the third relationship.

[0273] FIG. 6 is a schematic flowchart of a communication method provided by another embodiment of the present application. As shown in FIG. 6, the method can include S601 to S604.

[0274] S601, the network device sends first information, the first information being used to indicate a plurality of sub-sequence sets, the plurality of sub-sequence sets satisfying a second relationship with an AI sequence set. Correspondingly, the terminal receives the first information.

[0275] In this embodiment, the specific implementation of S601 can refer to S501, which is not described herein again.

[0276] S602, the network device sends fifth information, the fifth information being used to indicate a third relationship, the third relationship being a relationship between the identifier of the AI sequence and a plurality of sub-identifiers, the plurality of sub-identifiers corresponding to the plurality of sub-sequence sets, and each sub-identifier in the plurality of sub-identifiers being used to determine one sub-AI sequence in the corresponding sub-sequence set. Correspondingly, the terminal receives the fifth information.

[0277] In this embodiment, the sub-identifier can be understood as the identifier of the sub-AI sequence in the sub-sequence set.

[0278] In this embodiment, on the basis of hierarchically mapping the AI sequence set into the plurality of sub-sequence sets, the identifier of the AI sequence can be hierarchically mapped into the plurality of sub-identifiers, each sub-identifier corresponding to one sub-AI sequence in one sub-sequence set.

[0279] As an example, the identity of the AI sequence can be hierarchically mapped into multiple sub-identities by a remainder mapping. For example, assuming T is 2, sub-sequence set 1 contains M1 sub-AI sequences, and sub-sequence set 2 contains M2 sub-AI sequences. Then the sub-identity 1 of the sub-AI sequence 1 in the sub-sequence set 1 can satisfy the following relationship with the identity of the AI sequence: f1(x) = x / / M1. Where / / represents integer division. The sub-identity 2 of the sub-AI sequence 2 in the sub-sequence set 2 can satisfy the following relationship with the identity of the AI sequence: f2(x) = x mod M1. Where mod represents the remainder. Where f1(x) is the sub-identity 1, x is the identity of the AI sequence, and f2(x) is the sub-identity 2.

[0280] Optionally, f1(x) and f2(x) can be predefined by standards, and parameters (such as x, M1) in f1(x) and f2(x) can be indicated by the network device to improve the flexibility of identity mapping.

[0281] Optionally, f1(x) and f2(x) can be an AI model. The AI model can be located in the terminal, or the terminal can implement the calling of the AI model.

[0282] Optionally, the fifth information can be carried by an RRC message, an SIB message, or a NAS message, or the third relationship can be carried by an RRC message, an SIB message, or a NAS message, which is not limited herein.

[0283] S603, the network device sends sixth information, and the sixth information is used to indicate the identity of the first AI sequence. Correspondingly, the terminal receives the sixth information.

[0284] In this embodiment, the specific implementation of S603 can refer to S503, which is not described herein again.

[0285] S604, the terminal sends the first AI sequence, the first AI sequence is generated based on the first information, and the first AI sequence is included in the AI sequence set. Correspondingly, the network device receives the first AI sequence.

[0286] In this embodiment, after determining the identity of the first AI sequence, the terminal can map the identity of the first AI sequence into multiple sub-identities based on the third relationship, and determine multiple sub-AI sequences in multiple sub-sequence sets based on the multiple sub-identities, so as to determine the first AI sequence. Wherein, the first AI sequence is the product of the multiple sub-AI sequences.

[0287] FIG. 7 is a schematic diagram illustrating a method for determining a first AI sequence according to an embodiment of the present application. As shown in FIG. 7, the identifier of the first AI sequence is x, and the terminal can map the identifier x of the first AI sequence to two sub-identifiers based on the third relationship, such as the sub-identifier f1(x) and the sub-identifier f2(x) shown in FIG. 7. The terminal can determine a sub-AI sequence Z1 in the sub-sequence set Y1 based on the sub-identifier f1(x), and determine a sub-AI sequence Z2 in the sub-sequence set Y based on the sub-identifier f2(x). After determining the sub-AI sequence Z1 and the sub-AI sequence Z2, the first AI sequence can be determined. For example, the first AI sequence and the sub-AI sequence Z1 and the sub-AI sequence Z2 satisfy the relationship: Z = Z1*Z2. Z is the first AI sequence. The terminal can send the first AI sequence to the network device, and the network device can detect the first AI sequence based on the AI detection model.

[0288] In this embodiment, the network device can indicate the plurality of sub-sequence sets after hierarchical mapping and the third relationship to the terminal, the terminal can determine a plurality of sub-identifiers based on the identifier of the AI sequence to be sent and the third relationship, and determine a plurality of sub-AI sequences based on the plurality of sub-identifiers and the plurality of sub-sequence sets, so as to determine the AI sequence to be sent. In this embodiment, the data amount of the plurality of sub-sequence sets sent by the network device is smaller than the data amount of the AI sequence set, so as to reduce the air interface overhead to a certain extent.

[0289] It should be noted that the information sent by the network device in the embodiments of the present application can be sent through the same message or sent separately through different messages, and the present application does not limit this.

[0290] FIG. 8 is a structural schematic diagram of a communication apparatus according to an embodiment of the present application. The apparatus 800 shown in FIG. 8 can be used to implement each step / operation performed by the terminal or the network device in the foregoing method embodiments. As shown in FIG. 8, the apparatus 800 can include a receiving module 810 and a sending module 820.

[0291] In an implementable manner, the apparatus 800 can implement each step or operation performed by the terminal in the methods shown in FIG. 2, FIG. 3, FIG. 4, FIG. 5 and FIG. 6.

[0292] For example, when the apparatus 800 is used to implement each step / operation performed by the terminal in the method shown in FIG. 2, the receiving module 810 can be used to implement the operation performed by the terminal in S201; and the sending module 820 can be used to implement the operation performed by the terminal in S202.

[0293] As an example, when the apparatus 800 is configured to implement the steps / operations performed by the terminal in the method shown in FIG. 3, the receiving module 810 can be configured to implement the operations performed by the terminal in S302, S303 and S304; and the sending module 820 can be configured to implement the operations performed by the terminal in S301 and S305.

[0294] As an example, when the apparatus 800 is configured to implement the steps / operations performed by the terminal in the method shown in FIG. 4, the receiving module 810 can be configured to implement the operations performed by the terminal in S402, S403 and S404; and the sending module 820 can be configured to implement the operations performed by the terminal in S401 and S405.

[0295] As an example, when the apparatus 800 is configured to implement the steps / operations performed by the terminal in the method shown in FIG. 5, the receiving module 810 can be configured to implement the operations performed by the terminal in S501, S502 and S503; and the sending module 820 can be configured to implement the operations performed by the terminal in S504.

[0296] As an example, when the apparatus 800 is configured to implement the steps / operations performed by the terminal in the method shown in FIG. 6, the receiving module 810 can be configured to implement the operations performed by the terminal in S601, S602 and S603; and the sending module 820 can be configured to implement the operations performed by the terminal in S604.

[0297] In this implementation manner, the apparatus 800 can further include a processing module 830. The processing module 830 is configured to control the apparatus 800 to perform any one of the following operations in the first time period: sending the first sequence, or not sending the sequence; wherein the starting moment of the first time period is the starting moment of generating the AI sequence, and the time length of the first time period is the time length required for generating the AI sequence.

[0298] In an implementable manner, the apparatus 800 can implement the steps or operations performed by the network device in the methods shown in FIG. 2, FIG. 3, FIG. 4, FIG. 5 and FIG. 6.

[0299] As an example, when the apparatus 800 is configured to implement the steps / operations performed by the network device in the method shown in FIG. 2, the receiving module 810 can be configured to implement the operations performed by the network device in S202; and the sending module 820 can be configured to implement the operations performed by the network device in S201.

[0300] As an example, when the apparatus 800 is configured to implement the steps / operations performed by the network device in the method shown in FIG. 3, the receiving module 810 can be configured to implement the operations performed by the network device in S301 and S305; and the sending module 820 can be configured to implement the operations performed by the network device in S302, S303 and S304.

[0301] As an example, when the apparatus 800 is configured to implement the various steps / operations performed by the network device in the method shown in FIG. 4, the receiving module 810 can be configured to implement the operations performed by the network device in S401 and S405; and the sending module 820 can be configured to implement the operations performed by the network device in S402, S403 and S404.

[0302] As an example, when the apparatus 800 is configured to implement the various steps / operations performed by the network device in the method shown in FIG. 5, the receiving module 810 can be configured to implement the operations performed by the network device in S504; and the sending module 820 can be configured to implement the operations performed by the network device in S501, S502 and S503.

[0303] As an example, when the apparatus 800 is configured to implement the various steps / operations performed by the network device in the method shown in FIG. 6, the receiving module 810 can be configured to implement the operations performed by the network device in S604; and the sending module 820 can be configured to implement the operations performed by the network device in S601, S602 and S603.

[0304] In this implementation, the apparatus 800 can further include a processing module 830. The processing module 830 is configured to control the apparatus 800 to perform any one of the following operations in the first time period: receiving the first sequence, or not receiving the sequence; wherein the starting moment of the first time period is the starting moment of generating the AI sequence, and the time length of the first time period is the time length required for generating the AI sequence.

[0305] FIG. 9 is a structural schematic diagram of a communication apparatus provided by another embodiment of the present application. The apparatus 900 shown in FIG. 9 can be configured to implement the method performed by the terminal or the network device in any one of the preceding embodiments.

[0306] As shown in FIG. 9, the apparatus 900 of the present embodiment includes a memory 910, a processor 920, a communication interface 930 and a bus 940. The memory 910, the processor 920 and the communication interface 930 are in communication connection with each other through the bus 940.

[0307] The memory 910 can be a read only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 910 can store a program, and when the program stored in the memory 910 is executed by the processor 920, the processor 920 is configured to perform the various steps in the method shown in FIG. 2, FIG. 3, FIG. 4, FIG. 5 or FIG. 6 performed by the terminal or the network device.

[0308] The processor 920 can be a general purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits used for executing programs, to implement the communication method shown in the method embodiments of the present application.

[0309] The processor 920 can also be an integrated circuit chip having a processing capability of signals. In the implementation process, each step of the communication method shown in the method embodiments of the present application can be completed by the integrated logic circuit of hardware in the processor 920 or the instructions in the form of software.

[0310] The processor 920 described above can also be 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. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0311] The steps of the method disclosed in the embodiments of the present application can be directly embodied as hardware code processing for execution, or executed by a combination of hardware and software modules in the code processing. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register, or other mature storage medium in the art. The storage medium is located in the storage 910, and the processor 920 reads the information in the storage 910, and combines the hardware to complete the functions required to be executed by the units included in the communication device of the present application. For example, each step / function performed by the terminal or network device in the method shown in FIG. 2, FIG. 3, FIG. 4, FIG. 5 or FIG. 6 can be executed.

[0312] Optionally, the storage 910 and the processor 920 can be integrated together.

[0313] The communication interface 930 can use, but not limited to, a transceiver such as a transceiver to realize the communication between the device 900 and other devices or devices.

[0314] The bus 940 can include a path for transmitting information between various components (for example, the storage 910, the processor 920, the communication interface 930) of the device 900.

[0315] Some embodiments of the present application further provide a computer program product, which, when run on a processor, can implement the method shown in the foregoing embodiments. Some embodiments of the present application further provide a computer-readable storage medium, which contains computer instructions, which, when run on a processor, can implement the method shown in the foregoing embodiments.

[0316] It should be noted that the modules or components shown in the foregoing embodiments can be one or more integrated circuits configured to implement the above method, for example, one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), etc. For another example, when a certain module above is implemented in the form of invoking program code by a processing element, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor capable of invoking program code, such as a controller. For another example, these modules can be integrated together to be implemented in the form of a system on a chip (SOC).

[0317] In the embodiments described above, all or part of the embodiments can be implemented by software, hardware, firmware, software elements, or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0318] The term "multiple" herein refers to two or more. The term "and / or" herein is only used to describe an associated relationship of associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " herein generally represents that the associated objects before and after are in an "or" relationship; in the formula, the character " / " represents that the associated objects before and after are in a "division" relationship. In addition, it should be understood that in the description of the present application, the terms "first", "second", etc. are only used to distinguish the purposes of description and cannot be understood as indicating or implying relative importance or indicating or implying order.

[0319] It should be understood that the term "exemplary" or "for example" and the like in the present document is used to indicate an example, illustration, or description. Any embodiment or design scheme described herein as "exemplary" or "for example" should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" and the like is intended to present the relevant concept in a specific manner.

[0320] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for differentiation for convenience of description, and are not used to limit the scope of the embodiments of the present application.

[0321] It can be understood that, in the embodiments of the present application, the size of the serial number of the above processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Claims

1. A communication method characterized by comprising: The method comprises: receiving first information, the first information being used to indicate a vector, the vector satisfying a first relationship with an identifier of an artificial intelligence (AI) sequence, the vector being used as an input of an AI model, the AI model being used to generate the AI sequence; sending a first AI sequence, the first AI sequence being generated based on the first information.

2. The method of claim 1, wherein, The first information used to indicate the vector comprises: The first information is used to indicate the first relationship.

3. The method of claim 2, wherein, The first information comprises at least one of the following: a first formula satisfied between the identifier of the AI sequence and the vector, a parameter in the first formula, a length of the vector, or a processing manner of the vector.

4. The method of claim 1, wherein, The first information used to indicate the vector comprises: The first information is used to indicate a vector set in which the vector is located, a plurality of vectors in the vector set corresponding to a plurality of AI sequences one by one, each of the plurality of vectors satisfying the first relationship with an identifier of a corresponding AI sequence, the plurality of AI sequences belonging to a subset of a sequence set in which the AI sequence is located.

5. The method of claim 4, wherein, The first information comprises at least one of the following: the plurality of vectors, or a processing manner of each of the plurality of vectors.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: receiving second information, the second information being used to indicate the AI model.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: sending third information, the third information being used to indicate at least one of the following: supported AI model information, a supported first relationship, or a time length required for generating the AI sequence.

8. A communication method characterized by comprising: The method comprises: receiving first information, the first information being used to indicate a plurality of sub-sequence sets, the plurality of sub-sequence sets satisfying a second relationship with an artificial intelligence (AI) sequence set; sending a first AI sequence, the first AI sequence being generated based on the first information, the first AI sequence being contained in the AI sequence set; wherein a product of a number of sub-AI sequences included in each of the plurality of sub-sequence sets is equal to a number of AI sequences included in the AI sequence set, and a sum of the number of sub-AI sequences included in each of the plurality of sub-sequence sets is less than the number of AI sequences included in the AI sequence set.

9. The method of claim 8, wherein, The method further comprises: receiving fourth information, the fourth information being used to indicate the second relationship.

10. The method according to claim 8 or 9, characterized in that, The method further comprises: receiving fifth information, the fifth information being used to indicate a third relationship, the third relationship being a relationship between an identifier of the AI sequence and a plurality of sub-identifiers, the plurality of sub-identifiers corresponding to the plurality of sub-sequence sets, each of the plurality of sub-identifiers being used to determine one sub-AI sequence in a corresponding sub-sequence set, the AI sequence being generated based on a plurality of sub-AI sequences determined based on the plurality of sub-identifiers.

11. The method according to any one of claims 1 to 10, characterized in that, The method further comprises: receiving sixth information, the sixth information being used to indicate an identifier of the first AI sequence.

12. The method according to any one of claims 1 to 11, characterized in that, The method further comprises: performing any one of the following in a first time period: sending a first sequence, or not sending a sequence; wherein a starting time of the first time period is a starting time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

13. A method of communication, comprising: The method comprises: sending first information, the first information being used to indicate a vector, the vector satisfying a first relationship with an identifier of an artificial intelligence (AI) sequence, the vector being used as an input of an AI model, the AI model being used to generate the AI sequence; receiving a first AI sequence, the first AI sequence being generated based on the first information.

14. The method of claim 13, wherein, The first information used to indicate the vector comprises: The first information is used to indicate the first relationship.

15. The method of claim 14, wherein, The first information comprises at least one of the following: a first formula satisfied between the identifier of the AI sequence and the vector, a parameter in the first formula, a length of the vector, or a processing manner of the vector.

16. The method of claim 13, wherein, The first information used to indicate the vector comprises: The first information is used to indicate a vector set in which the vector is located, a plurality of vectors in the vector set corresponding to a plurality of AI sequences one by one, each of the plurality of vectors satisfying the first relationship with an identifier of a corresponding AI sequence, the plurality of AI sequences belonging to a subset of a sequence set in which the AI sequence is located.

17. The method of claim 16, wherein, The first information comprises at least one of the following: the plurality of vectors, or a processing manner of each of the plurality of vectors.

18. The method according to any one of claims 13 to 17, characterized in that, The method further comprises: sending second information, the second information being used to indicate the AI model.

19. The method according to any one of claims 13 to 18, characterized in that, The method further comprises: receiving third information, the third information being used to indicate at least one of the following: supported AI model information, a supported first relationship, or a time length required for generating the AI sequence.

20. A method of communication, comprising: The method comprises: sending first information, the first information being used to indicate a plurality of sub-sequence sets, the plurality of sub-sequence sets satisfying a second relationship with an artificial intelligence (AI) sequence set; receiving a first AI sequence, the first AI sequence being generated based on the first information, the first AI sequence being contained in the AI sequence set; wherein a product of a number of sub-AI sequences contained in each of the plurality of sub-sequence sets is equal to a number of AI sequences contained in the sequence set, and a sum of the number of sub-AI sequences contained in each of the plurality of sub-sequence sets is less than the number of AI sequences contained in the AI sequence set.

21. The method of claim 20, wherein, The method further comprises: sending fourth information, the fourth information being used to indicate the second relationship.

22. The method of claim 20 or 21, wherein, The method further comprises: sending fifth information, the fifth information being used to indicate a third relationship, the third relationship being a relationship between an identifier of the AI sequence and a plurality of sub-identifiers, the plurality of sub-identifiers corresponding to the plurality of sub-sequence sets, each of the plurality of sub-identifiers being used to determine one sub-AI sequence in a corresponding sub-sequence set, the AI sequence being generated based on a plurality of sub-AI sequences determined based on the plurality of sub-identifiers.

23. The method of any one of claims 13-22, wherein, The method further comprises: sending sixth information, the sixth information being used to indicate an identifier of the first AI sequence.

24. The method of any one of claims 13-23, wherein, The method further comprises: performing any one of the following in a first time period: receiving a first sequence, or not receiving a sequence; wherein a starting time of the first time period is a starting time of generating the AI sequence, and a time length of the first time period is a time length required for generating the AI sequence.

25. A communications device, characterized by comprising various functional modules for implementing the method as claimed in any one of claims 1 to 12 or any one of claims 13 to 24.

26. A communications device, characterized by comprising: a processor coupled with a memory for storing a computer program which, when invoked by the processor, causes the apparatus to perform the method as claimed in any one of claims 1 to 12 or any one of claims 13 to 24.

27. A chip, characterized by comprising: a processor for invoking and executing a computer program in a memory, causing the chip to perform the method as claimed in any one of claims 1 to 12 or any one of claims 13 to 24.

28. A computer readable medium characterized by the computer readable medium stores instructions which, when executed, cause the method as claimed in any one of claims 1 to 12 or any one of claims 13 to 24 to be implemented.

29. A computer program product, characterised in that, comprising computer program code which, when run on a computer, causes the method as claimed in any one of claims 1 to 12 or any one of claims 13 to 24 to be implemented.

Images