Model identification method, communication device, network device, apparatus, and storage medium

Abstract

A model identification method, a communication device, a network device, an apparatus, and a storage medium. The method comprises: according to first information sent by a network device, sending first model identification request information to the network device, wherein the first model identification request information is used for requesting identification of a target model.

Description

Model recognition method, communication equipment, network equipment, device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese patent application number 202311014460.5, filed on August 11, 2023, entitled “Model Identification Method, Communication Equipment, Network Equipment, Device and Storage Medium,” which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates to the field of communication technology, and in particular to a model recognition method, communication equipment, network equipment, apparatus, and storage medium. Background Art

[0004] With the advancement of artificial intelligence (AI) and machine learning (ML), AI / ML models are being used to improve communication system performance. AI / ML models can be unilateral, meaning they are deployed only on one side, such as the network or user equipment (UE), or bilateral, meaning they are deployed on both the network and the UE, requiring collaboration between both sides for complete inference.

[0005] The unilateral model deployed on the UE side, or the UE-side portion of the bilateral model, may be trained and generated by the UE manufacturer, chip manufacturer, or third-party service provider and is unknown to the network side. In order to enable collaboration between the UE and the network on the AI / ML model, so that the network can manage the UE's model or assist the UE in managing its own model, the UE or third-party server needs to send relevant information about the AI / ML model to the network side.

[0006] However, there is currently no solution for the network to manage model identification on the UE or third-party server. If the UE or third-party server continuously initiates model identification on the network side, it may cause the complexity of the network side to increase infinitely.

[0007] Summary of the Invention

[0008] In response to the above-mentioned problems existing in the related technologies, embodiments of the present disclosure provide a model recognition method, a communication device, a network device, an apparatus, and a storage medium.

[0009] In a first aspect, an embodiment of the present disclosure provides a model recognition method, which is applied to a communication device, and includes: sending first model recognition request information to the network device based on first information sent by the network device; wherein the first model recognition request information is used to request recognition of a target model.

[0010] In some embodiments, the target model is: a first model set; or a second model set, wherein the second model set is a model in the first model set that is not recognized by the network device; or a third model set, wherein the third model set is a model in the first model set that is permitted by the network device for model recognition; or a fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device for model recognition.

[0011] In some embodiments, the sending of the first model identification request information to the network device includes:

[0012] Sending the first model recognition request information to the network device according to the information of the recognized model sent by the network device, where the first model recognition request information is used to request recognition of the second model set; or

[0013] sending the first model recognition request information to the network device according to the model recognition permission information sent by the network device, where the first model recognition request information is used to request recognition of the third model set; or

[0014] The first model recognition request information is sent to the network device according to the information of the model recognized by the network device and the model recognition permission information, where the first model recognition request information is used to request recognition of the fourth model set.

[0015] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0016] a set of identified models of the network device;

[0017] A list of identifications of models that have been identified by the network device;

[0018] The maximum value of the identification of the model recognized by the network device;

[0019] the number of models recognized by the network device;

[0020] a combination of an identification area of ​​a model identified by the network device and an identification maximum value in the identification area, wherein different identification areas are used to classify the model identified by the network device;

[0021] The identification area of ​​the model recognized by the network device and the number of models in the identification area.

[0022] In some embodiments, the model identifies permission information including at least one of the following:

[0023] First indication information of the network device allowing model recognition;

[0024] second indication information of the number of models permitted by the network device for model recognition;

[0025] third indication information of a model identifier permitted by the network device to perform model identification;

[0026] fourth indication information of an identification area permitted by the network device to perform model recognition;

[0027] The network device identifies an area where model recognition is permitted and fifth indication information of the number of models in the identified area where model recognition is permitted.

[0028] In some embodiments, the model recognition permission information and / or information of the model recognized by the network device is included in the first information.

[0029] In some embodiments, further comprising:

[0030] Second model identification request information is sent to the network device, where the second model identification request information is used to request model identification.

[0031] In some embodiments, the method further includes: sending a third model identification request message to the network device, wherein the third model identification request message is used to request identification of the first model set, and the target model is a subset of the first model set.

[0032] In some embodiments, the method further includes: receiving confirmation information sent by the network device; and determining the model in the target model recognized by the network device based on the confirmation information.

[0033] In some embodiments, the confirmation information is indicated by a bitmap.

[0034] In some embodiments, the method further includes: based on the confirmation information, stopping the recognition of the model in the target model that is not recognized by the network device until a preset condition is met.

[0035] In some embodiments, the preset conditions include: after a first time period, the first time period is predefined by the protocol or configured on the network side; or, when the first information is received via unicast, the next first information sent by the network device after the first information is received; or, when the first information is received via broadcast, the Lth first information sent by the network device after the first information is received, where L is an integer greater than or equal to 1.

[0036] In some embodiments, the method further includes: determining at least one of the following based on the confirmation information:

[0037] Updated information of the model identified by the network device;

[0038] Updated model recognition licensing information;

[0039] Instruction information requesting model recognition before the Mth broadcast period after receiving the confirmation information;

[0040] It is prohibited to request the instruction information of model identification before the Nth broadcast period after the confirmation information is received;

[0041] Wherein, M and N are integers greater than or equal to 1.

[0042] In a second aspect, an embodiment of the present disclosure also provides a model recognition method, applied to a network device, comprising: sending first information to a communication device; receiving first model recognition request information sent by the communication device based on the first information; wherein the first model recognition request information is used to request recognition of a target model.

[0043] In some embodiments, the target model is: a first model set; or a second model set, wherein the second model set is a model in the first model set that is not recognized by the network device; or a third model set, wherein the third model set is a model in the first model set that is permitted by the network device for model recognition; or a fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device for model recognition.

[0044] In some embodiments, the receiving first model recognition request information sent by the communication device based on the first information includes:

[0045] Sending information about the model identified by the network device to the communication device, and receiving first model identification request information sent by the communication device based on the information about the model identified by the network device, where the first model identification request information is used to request identification of the second model set; or

[0046] sending model recognition permission information to the communication device, and receiving the first model recognition request information sent by the communication device based on the model recognition permission information, where the first model recognition request information is used to request recognition of the third model set; or

[0047] Send information about the model identified by the network device and model identification permission information to the communication device, and receive the first model identification request information sent by the communication device based on the information about the model identified by the network device and the model identification permission information, wherein the first model identification request information is used to request identification of the fourth model set.

[0048] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0049] a set of identified models of the network device;

[0050] A list of identifications of models that have been identified by the network device;

[0051] The maximum value of the identification of the model recognized by the network device;

[0052] the number of models recognized by the network device;

[0053] a combination of an identification area of ​​a model identified by the network device and an identification maximum value in the identification area, wherein different identification areas are used to classify the model identified by the network device;

[0054] The identification area of ​​the model recognized by the network device and the number of models in the identification area.

[0055] In some embodiments, the model identifies permission information including at least one of the following:

[0056] First indication information of the network device allowing model recognition;

[0057] second indication information of the number of models permitted by the network device for model recognition;

[0058] third indication information of a model identifier permitted by the network device to perform model identification;

[0059] fourth indication information of an identification area permitted by the network device to perform model recognition;

[0060] The network device identifies an area where model recognition is permitted and fifth indication information of the number of models in the identified area where model recognition is permitted.

[0061] In some embodiments, the model recognition permission information and / or information of the model recognized by the network device is included in the first information.

[0062] In some embodiments, the method further includes: receiving second model recognition request information sent by the communication device, where the second model recognition request information is used to request model recognition.

[0063] In some embodiments, the method further includes: receiving third model recognition request information sent by the communication device, wherein the third model recognition request information is used to request recognition of the first model set, and the target model is a subset of the first model set.

[0064] In some embodiments, the method further includes: sending confirmation information to the communication device, where the confirmation information is used to indicate the model in the target model recognized by the network device.

[0065] In some embodiments, the confirmation information is indicated by a bitmap.

[0066] In some embodiments, the method further includes: after sending the confirmation information, stopping identifying models in the target model that are not identified by the network device until a preset condition is met.

[0067] In some embodiments, the preset conditions include: after a first time period has passed, the first time period is predefined by the protocol or configured by the network side; or, when the first information is sent via unicast, after sending the first information, the next first information is sent to the communication device; or, when the first information is sent via broadcast, after sending the first information, the Lth first information is sent to the communication device.

[0068] In some embodiments, the confirmation information is used to indicate at least one of the following:

[0069] Updated information of the model identified by the network device;

[0070] Updated model recognition licensing information;

[0071] Instruction information requesting model recognition before the Mth broadcast period after the confirmation information;

[0072] prohibiting the instruction information requesting model identification before the Nth broadcast period after the confirmation information;

[0073] Wherein, M and N are integers greater than or equal to 1.

[0074] In a third aspect, an embodiment of the present disclosure further provides a communication device, comprising a memory, a transceiver, and a processor; the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and execute the model recognition method provided in the first aspect as described above.

[0075] In a fourth aspect, an embodiment of the present disclosure further provides a communication device, comprising a memory, a transceiver, and a processor; the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and execute the model recognition method provided in the second aspect as described above.

[0076] In the fifth aspect, an embodiment of the present disclosure also provides a model recognition device, including: a first receiving unit, used to receive query information sent by a network device, and send first model recognition request information to the network device; or, a second receiving unit, used to receive broadcast information sent by a network device, and send first model recognition request information to the network device; wherein, the first model recognition request information is used to request the recognition of a target model.

[0077] In the sixth aspect, an embodiment of the present disclosure also provides a model identification device, including: a first sending unit, used to send inquiry information to a communication device, and receive first model identification request information sent by the communication device; or, a second sending unit, used to send broadcast information to a communication device, and receive first model identification request information sent by the communication device; wherein, the first model identification request information is used to request identification of a target model.

[0078] In a seventh aspect, an embodiment of the present disclosure further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the model recognition method provided in the first aspect or the second aspect as described above.

[0079] In an eighth aspect, an embodiment of the present disclosure further provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the model recognition method provided in the first aspect or the second aspect as described above.

[0080] In a ninth aspect, an embodiment of the present disclosure further provides a chip product, wherein a computer program is stored in the chip product, and the computer program is used to enable the chip product to execute the model recognition method provided in the first aspect or the second aspect as described above.

[0081] The model recognition method, communication equipment, network equipment, apparatus and storage medium provided by the embodiments of the present disclosure are such that the communication equipment sends the first model recognition request information for requesting recognition of the target model to the network equipment only after receiving the first information sent by the network equipment, thereby avoiding the high complexity caused by a large number of communication equipment initiating model recognition to the network equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0083] FIG1 is a schematic diagram of an application scenario of a model recognition method provided by an embodiment of the present disclosure;

[0084] FIG2 is a flow chart of a model recognition method according to an embodiment of the present disclosure;

[0085] FIG3 is a second flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0086] FIG4 is a third flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0087] FIG5 is a fourth flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0088] FIG6 is a fifth flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0089] FIG7 is a sixth flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0090] FIG8 is a seventh flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0091] FIG9 is an eighth flow chart of the model recognition method provided by an embodiment of the present disclosure;

[0092] FIG10 is a schematic structural diagram of a communication device provided in an embodiment of the present disclosure;

[0093] FIG11 is a schematic diagram of the structure of a network device provided in an embodiment of the present disclosure;

[0094] FIG12 is a schematic diagram of a structure of a model recognition device according to an embodiment of the present disclosure;

[0095] FIG13 is a second structural diagram of the model recognition device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0096] With the development of AI and ML, AI / ML models are being used to improve communication system performance. Related technologies have also explored how these models work. AI / ML models can be unilateral, meaning they are deployed on only one side, such as the network or the user end (UE), or bilateral, meaning they are deployed on both the network and the user end, requiring collaboration between the two sides for complete inference.

[0097] The unilateral model deployed on the UE side, or the part of the bilateral model that belongs to the UE side, may be trained and generated by the UE manufacturer, chip manufacturer or third-party service provider, and is unknown to the network side. In order to enable the UE side and the network side to collaborate on the AI / ML model, so that the network side can perform life cycle management (LCM) of the UE model, or allow the network side to assist the UE in managing its own model, the UE or third-party (Over The Top, OTT) server (Server) needs to send relevant information about the AI / ML model to the network side so that the network side can identify which models or models with which functions are supported by the UE or OTT Server. The related steps are called Model Identification, sometimes also called Model Registration.

[0098] Currently, New Radio (NR) does not support model recognition for AI / ML models on the UE side. Recent discussions have only explored model recognition without over-the-air signaling or via over-the-air signaling. There is no clear solution for how network devices should manage model recognition.

[0099] Failure to manage model recognition for UEs or OTT servers may lead to the following problems:

[0100] ① Complexity. Network devices have limited capabilities for processing or managing UE or OTT server models. If the UE or OTT server continuously initiates model recognition requests from the network device, the complexity of the network device may increase infinitely.

[0101] ② Redundant identification. When a UE or OTT Server initiates model identification to a network device, it usually means that the UE or OTT Server needs to send model-related meta information, model description information, or model functionality information to the network device so that the network device can determine the function of the AI / ML model, or the input and output of the model, etc. The amount of metadata, model description information, or model functionality information may be large. In addition, if multiple UEs or OTT Servers support the same model, but all initiate identification of the model to the network device, the same information will be transmitted repeatedly, and the network device will perform redundant identification, wasting transmission resources.

[0102] In response to the above-mentioned problems existing in the related technologies, the embodiments of the present disclosure provide a model recognition method, communication equipment, network equipment, apparatus and storage medium. After receiving the first information sent by the network equipment, the communication equipment sends the first model recognition request information for requesting the recognition of the target model to the network equipment, thereby avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network equipment.

[0103] In the embodiments of the present disclosure, the term "and / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship. In the embodiments of the present disclosure, the term "plurality" refers to two or more, and other quantifiers are similar.

[0104] The technical solutions provided by the embodiments of the present disclosure can be applicable to a variety of systems, especially 5G systems, 5G Advanced systems, 6G systems and their evolution systems. For example, applicable systems can be Global System of Mobile Communication (GSM) systems, Code Division Multiple Access (CDMA) systems, Wideband Code Division Multiple Access (WCDMA) general packet radio service (GPRS) systems, Long Term Evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, Long Term Evolution Advanced (LTE-A) systems, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) systems, 5G New Radio (NR) systems, etc. These various systems include terminal devices and network devices. The system may also include core network parts, such as the Evolved Packet System (EPS), 5G System (5GS), etc.

[0105] The terminal device involved in the embodiments of the present disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing device connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called User Equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a radio access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit (Subscriber Unit), a subscriber station (Subscriber Station), a mobile station (Mobile Station), a mobile station (Mobile), a remote station (Remote Station), an access point (Access Point), a remote terminal device (Remote Terminal), an access terminal device (Access Terminal), a user terminal device (User Terminal), a user agent (User Agent), or a user device (User Device), but is not limited in the embodiments of the present disclosure.

[0106] The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in an access network that communicates with a wireless terminal device through one or more sectors on an air interface, or may be called another name. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be a network device (Base Transceiver Station, BTS) in the Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), a network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), an evolved network device (Evolutional Node B, eNB or e-NodeB) in the Long Term Evolution (LTE) system, a 5G base station (gNB) in the 5G network architecture (Next Generation System), a home evolved Node B (HeNB), a relay node, a home base station (Femto), a pico base station (Pico), etc., and is not limited in the embodiments of the present disclosure. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be geographically separated.

[0107] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0108] The model recognition method provided in this disclosure is applicable to systems requiring AI / ML model recognition. One application scenario is a 5G NR system, including network equipment and terminal devices. Figure 1 is a schematic diagram of an application scenario for the model recognition method provided in an embodiment of this disclosure. As shown in Figure 1 , multiple UEs, including UE1 and UE2, apply for wireless network connection services; the gNB provides wireless services to the UEs. Data is exchanged and transmitted between the gNB and UE1 and UE2 via wireless communication. Furthermore, an OTT server and the gNB are connected via a wired connection and exchange information, or the OTT server exchanges information with the gNB via the UEs.

[0109] In the embodiments of the present disclosure, entity A initiates (or performs) model identification to entity B (for example, a UE initiates model identification to a network device), or in other words, entity B identifies entity A's model. This means that entity A sends relevant information about entity A's model to entity B, such as model description information, model meta information, model function information, etc., so that entity B and entity A have a consistent understanding of the model, including but not limited to understanding the model's function, applicable scenarios, required configuration, expected performance, model input, and model output. Entity A does not necessarily send the model itself to entity B.

[0110] FIG2 is a flow chart of a model recognition method provided by an embodiment of the present disclosure. As shown in FIG2 , the method is performed by a communication device, including but not limited to a UE or an OTT server or other entity that wants to initiate model recognition to a network device. The following embodiments are described using a UE as an example. The method includes at least the following steps:

[0111] Step 201: Send first model recognition request information to the network device according to the first information sent by the network device.

[0112] The first model recognition request information is used to request recognition of a target model.

[0113] Specifically, after receiving the first information sent by the network device, the UE can send the first model identification request information for requesting identification of the target model to the network device. The first information is used to notify the UE that it can initiate model identification to the network device.

[0114] Optionally, the first information is unicast information, such as query information. Optionally, the query information is used to inquire whether the UE needs to perform model identification.

[0115] Optionally, the first information is broadcast information. Optionally, the broadcast information includes relevant information for broadcasting permission for model identification. For example, the network device broadcasts information that allows model identification, and the UE can request the network device to perform model identification. For example, if the UE broadcasts information that does not allow model identification, the UE cannot request the network device to perform model identification. The broadcast information is, for example, system information block (SIB) information, such as SIB1, SIB2, etc. All UEs in the cell covered by the network device can receive the broadcast information.

[0116] Compared with unicast information, broadcast information saves the signaling indication overhead of unicast information at the expense of the payload in the broadcast information.

[0117] The target model can be the full set of models that the UE wants to perform model recognition on, or a subset of the full set of models that the UE wants to perform model recognition on. The target model refers to a specific AI / ML model or a designated AI / ML model. The full set of models that the UE wants to perform model recognition on can be all models that the UE can support.

[0118] In the model recognition method provided by the embodiment of the present disclosure, the communication device sends the first model recognition request information for requesting the recognition of the target model to the network device only after receiving the first information sent by the network device, thereby avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device.

[0119] In some embodiments, the target model is one of the following:

[0120] ① First model set. The first model set is the complete set of AI / ML models that the UE wants to identify. Optionally, after receiving the query information or broadcast information sent by the network device, the UE can directly initiate model identification of the complete set of models that it wants to identify.

[0121] ② Second model set. The second model set is the models in the first model set that the network device has not yet identified. Optionally, the UE can only initiate identification of models that the network device has not yet identified. For models that the network device has already identified, the UE does not need to repeatedly initiate model identification with the network device.

[0122] ③ Third model set. The third model set is the models in the first model set that are permitted by the network device for model recognition. Optionally, the UE can only initiate recognition of models that the network device allows to be recognized. For models that the network device does not allow to be recognized, the UE cannot initiate model recognition to the network device.

[0123] ④ Fourth model set. The fourth model set is the models in the first model set that the network device has not yet recognized and that the network device has permitted model recognition. Optionally, the UE can only initiate recognition of models that the network device has not yet recognized and that the network device has permitted recognition. The UE cannot initiate model recognition with the network device for models that the network device has already recognized and / or models that the network device has not permitted recognition.

[0124] In the model recognition method provided by the embodiments of the present disclosure, the communication device does not initiate model recognition for a model that has already been recognized by the network device, and / or does not initiate model recognition for a model that the network device does not allow model recognition to be performed. This avoids the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoids the redundant recognition problem of the network device.

[0125] In some embodiments, in step 2011 and step 2012: sending the first model identification request information to the network device includes one of the following:

[0126] ① Receiving information about the identified model sent by the network device, and sending a first model identification request message to the network device based on the information about the identified model. If the UE receives information about the identified model sent by the network device, the target model is the second model set, i.e., the UE requests identification of the second model set in the first model identification request message.

[0127] Optionally, the UE receives information about the model recognized by the network device, and initiates model recognition of one or more models that are not in the set of models recognized by the network device.

[0128] ② Receive model identification permission information sent by the network device, and send a first model identification request message to the network device based on the model identification permission information. If the UE receives the model identification permission information sent by the network device, the target model is the third model set, that is, the UE requested identification of the second model set in the first model identification request message.

[0129] The model recognition permission information includes relevant information that the network device allows model recognition or relevant information that the network device does not allow model recognition. Optionally, the UE receives the model recognition permission information sent by the network device and initiates model recognition of one or more models that the network device allows model recognition. Optionally, the model that the network device allows model recognition for may be a model that the network device has not recognized.

[0130] ③ Upon receiving the identified model information and model identification permission information sent by the network device, the UE sends a first model identification request message to the network device based on the identified model information and the model identification permission information. If the UE receives both the identified model information and the model identification permission information sent by the network device, the target model is the fourth model set, i.e., the UE requests identification of the fourth model set in the first model identification request message.

[0131] Optionally, the UE receives the information about the recognized models and the model recognition permission information sent by the network device, and initiates model recognition of one or more models that the network device has not recognized and that the network device has permitted to perform model recognition. Optionally, if the model recognition permission information indicates relevant information that model recognition is not allowed or the number of models allowed to be recognized is 0, the UE often does not receive the information about the models recognized by the network device.

[0132] Optionally, the UE only receives the model recognition permission information and does not receive the information of the model recognized by the network device, which can effectively protect the privacy of the network device.

[0133] In the model recognition method provided by the embodiments of the present disclosure, the communication device does not initiate model recognition for the model already recognized by the network device, and / or does not initiate model recognition for the model that the network device does not allow to be recognized, based on the information of the recognized model and / or model recognition permission information sent by the network device. This avoids the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoids the redundant recognition problem of the network device.

[0134] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0135] ① The set of models recognized by the network device. The information about the models recognized by the network device directly indicates one or more models recognized by the network device, specifically as a set. There may be one or more sets, and different sets may correspond to different model categories, such as different model functions or different model size ranges.

[0136] ② A list of identifications of models recognized by the network device. The information on the models recognized by the network device directly indicates one or more models that the network device has recognized. Specifically, this can be indicated in the form of a list of identifications of one or more models. The identification can also be an index number, serial number, or other method that can distinguish different models. There may be one or more lists, and different lists can correspond to different model categories, such as different model functions or different model size ranges.

[0137] For example, a list: List = {model ID #1, model ID #2 ...}, represents the full set of models recognized by the network device. For example: multiple lists: List #1 = {model ID #1_1, Model ID #1_2 ...}, List #2 = {model ID #2_1, model ID #2_2 ...}, where List #1 represents the list of models used for Channel State Information (CSI) compressed feedback, and List #2 represents the list of models used for Beam Management (BM).

[0138] ③The maximum value of the identification of the model recognized by the network device (for example, max model ID). If the identification of the model recognized by the network device is continuously increasing according to a certain rule, such as model 0, model 1, model 2, or model A, model B, model C. The increasing rule can be, for example, increasing in the order of recognition, or increasing in the order of model version update, etc. In the information of the model recognized by the network device, the maximum value of the identification of the model recognized by the network device is indicated. Based on the maximum value of the identification of the model recognized by the network device, such as "2" or "C", the UE can determine that any model with a model identification less than or equal to the maximum value of the identification has been recognized by the network device, then the UE only needs to initiate the identification of the model with a model identification greater than the maximum value to the network device.

[0139] ④ The number of models recognized by the network device. Similarly, if the identification of the models recognized by the network device is continuously increased according to certain rules, such as the order of identification, the order of model version update, etc., the number of models recognized by the network device is indicated in the information of the models recognized by the network device. Based on the number of models recognized by the network device, the UE can determine the identification set and / or the maximum identification value of the models recognized by the network device, and only needs to initiate the identification of the model whose identification is not in the identification set and / or is greater than the maximum identification value to the network device.

[0140] ⑤ A combination of the identification area of ​​the model identified by the network device and the maximum value of the identification in the identification area, and different identification areas are used to classify the models identified by the network device. Different identification areas can correspond to different model categories, such as different model functions or different model size ranges. If the identification of the model identified by the network device in an identification area is continuously increasing over time, the information of the model identified by the network device indicates the combination of the identification area identified by the network device and the maximum value of the identification in the identification area. There may be one or more area identifications.

[0141] For example, the max model ID in ID area #1 is 3, and the max model ID in ID area #2 is 5. The UE will not initiate model identification for models with IDs less than or equal to 3 in ID area #1, and will not initiate model identification for models with IDs less than or equal to 5 in ID area #2.

[0142] It should be noted that replacing the identification area with an identification set, identification list, etc. is also applicable. Different identification areas, identification sets, identification lists, etc. are mainly used to classify models. There are many bases for classifying models, such as model function, model size range, etc. This is not limited in the embodiments of the present disclosure.

[0143] The UE can determine the identification areas identified by the network device and the models in each identification area based on a combination of the identification areas identified by the network device and the maximum identification value in the identification areas, and no longer initiates model identification of these models.

[0144] ⑥ The identification area of ​​the model recognized by the network device and the number of models in the identification area. If the identification of the model recognized by the network device in an identification area is continuously increasing according to certain rules, such as increasing over time, the order of recognition, or the order of model version update, the identification area recognized by the network device and the number of models in the identification area are indicated in the information of the model recognized by the network device. The UE can then determine the identification area of ​​the model recognized by the network device, as well as the identification set and / or identification maximum value of the model in the identification area.

[0145] Optionally, if the UE sends a request message to the network device requesting identification of one or more models before receiving information about models already identified by the network device, the information about models already identified by the network device received by the UE may only include relevant information about models already identified by the network device within the identification area where these models are located. For example, if the models for which the UE requests model identification all belong to ID area #1, the information about models already identified by the network device received by the UE may only include the combination of the maximum value of the identifier or the number of models in ID area #1, and does not include relevant information about ID area #2.

[0146] In the model recognition method provided by the embodiment of the present disclosure, the communication device only initiates model recognition for models that have not been recognized by the network device based on the information of the recognized model sent by the network device, thereby avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoiding the redundant recognition problem of the network device.

[0147] In some embodiments, the model identifies permission information including at least one of the following:

[0148] ① First indication information that the network device permits model recognition. The first indication information can be a general indication, indicating that model recognition is permitted or not permitted. Optionally, it indicates that all models that the UE wants to recognize can be recognized, or it indicates that all models that the UE wants to recognize cannot be recognized.

[0149] ② Second indication information regarding the number of models permitted for model recognition by the network device. The model recognition permission information may indicate the number of models permitted for model recognition. For example, the network device may further permit the recognition of three models. When the number of models permitted for model recognition by the network device is 0, it indicates that the network device does not permit model recognition. The number of models permitted for model recognition may also be multiple, with different numbers of models corresponding to different model categories, indicating how many models of different categories are permitted for model recognition.

[0150] ③ The third indication information of the model identification that the network device permits to perform model recognition. Of the full set of models that the UE wants to recognize, often only a part may be allowed to be recognized by the network device. If the UE first sends a request for model recognition of certain models, the model recognition permission information fed back by the network device can accurately indicate the models that are allowed to perform model recognition, such as indicating the identification of the models that are allowed to perform model recognition. For example, the terminal requests to perform recognition of models 1, 2, 3, and 4, and in the model recognition permission information, only the recognition of models 3 and 4 is allowed. There are other ways for the model recognition permission information to indicate the models that are allowed to perform model recognition, such as indicating the category of models that are allowed to perform model recognition (including model functions, model size range, etc.).

[0151] ④ Fourth indication information of the identification area where the network device is permitted to perform model recognition. The model recognition permission information may indicate the identification area where model recognition is permitted or the identification area where model recognition is not permitted.

[0152] ⑤ Fifth indication information indicating the identification areas for which the network device is permitted to perform model recognition and the number of models permitted within the identification areas. Model permission information can indicate the identification areas for which model recognition is permitted or not permitted, as well as the number of models. For example, the network device may permit the recognition of two models in ID area #1, three models in ID area #2, and zero models in ID area #3.

[0153] In the model recognition method provided by the embodiment of the present disclosure, the communication device only initiates model recognition for models that the network device allows to be recognized based on the model recognition permission information sent by the network device, thereby avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoiding the redundant recognition problem of the network device.

[0154] In some embodiments, information about the model identified by the network device is included in the first information. The first information may be, for example, a unicast query message or a broadcast message. Alternatively, the UE receives information about the model identified by the network device through information other than the first information. For example, after receiving the query message or the broadcast message, the UE sends a model identification request to the network device, and then receives feedback from the network device regarding the model identified by the network device.

[0155] In some embodiments, the model identification permission information is included in the first information. The first information may be, for example, a unicast query message or a broadcast message. Alternatively, the UE receives the model identification permission information via information other than the first information. For example, after receiving the query message or the broadcast message, the UE sends a model identification request to the network device and then receives the model identification permission information in feedback from the network device.

[0156] In some embodiments, before receiving the first unicast information sent by the network device, the communication device further includes:

[0157] Second model identification request information is sent to the network device, where the second model identification request information is used to request model identification.

[0158] Specifically, the unicast first information (e.g., query information) can be actively sent by the network device or actively triggered by the UE. The UE sends a second model identification request message to the network device, requesting model identification. At this time, triggered by the second model identification request message, the UE receives the query information sent by the network device.

[0159] In the model recognition method provided by the embodiment of the present disclosure, the communication device actively triggers the network device to send a unicast first message through the second model recognition request information to perform a subsequent model recognition process. In addition to avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device and the redundant recognition problem of the network device, it also improves the flexibility of the timing of the communication device initiating model recognition.

[0160] In some embodiments, before receiving the model recognition permission information sent by the network device, the method further includes:

[0161] A third model identification request message is sent to the network device, where the third model identification request message is used to request identification of the first model set, and the target model is a subset of the first model set.

[0162] Specifically, the UE may first send a third model identification request message to the network device for requesting identification of the first model set, notifying the network device of the full set of models it wants to identify, so that the network device can determine the model identification permission information that allows or does not allow the UE to perform model identification and indicate it to the UE.

[0163] Optionally, the model identification permission information is included in the unicast query information. The UE first sends the third model identification request information to the network device. The network device indicates whether to allow or not to perform model identification through the model identification permission information in the query information.

[0164] In the model recognition method provided by the embodiment of the present disclosure, the communication device first sends the third model recognition request information to the network device, and the network device then feeds back the model recognition permission information, which can effectively avoid the redundant recognition problem of the network device.

[0165] In some embodiments, it further includes:

[0166] Receive confirmation information sent by the network device;

[0167] Based on the confirmation information, a model recognized by the network device in the target model is determined.

[0168] Specifically, the UE sends a first model identification request message to the network device to request identification of the target model, and may then receive confirmation information fed back by the network device, and determine the model identified by the network device in the target model according to the confirmation information.

[0169] Optionally, if the UE does not receive the confirmation information, it is considered that all the target models are recognized by the network device, or it is considered that all the target models are not recognized by the network device.

[0170] Due to factors such as network device management capabilities, complexity, and implementation, network devices may not necessarily recognize and use the model identified by the UE. Therefore, the network device can selectively complete the identification of some models and feed the identified models back to the UE. In other words, the model identified by the network device in the confirmation information is a subset of the target model.

[0171] Optionally, the confirmation information is indicated by a bitmap. Each target model corresponds to a bit in the bitmap, for example, the bitmap bits may correspond in order of model ID from small to large or from large to small. For example, a bitmap bit value of 1 indicates that the model is recognized, and a value of 0 indicates that the model is not recognized; or, a value of 0 indicates that the model is recognized, and a value of 1 indicates that the model is not recognized. Taking the value of 1 indicating that the model is recognized as an example, the target models include model 1, model 2, model 3 and model 4, and bitmap = "1011", it means that model 1, model 3 and model 4 are recognized by the network device, and model 2 is not recognized by the network device.

[0172] Optionally, the confirmation information may be an overall indication information, for example, that all target models are recognized by the network device, or that all target models are not recognized by the network device.

[0173] Optionally, the confirmation information may be an identification list or an identification set, which includes an identification list or an identification set in the target model that is recognized by the network device or is not recognized by the network device.

[0174] Optionally, the confirmation information may include a combination of the identification area and identifications of models within the identification area that are recognized or not recognized by the network device.

[0175] The model recognition method provided by the embodiment of the present disclosure is that the communication device confirms the information of the model recognized by the network device in the model initiated by the communication device through the confirmation information fed back by the network device, thereby realizing the management of the model on the communication device side by the network device and having higher flexibility.

[0176] In some embodiments, further comprising:

[0177] Based on the confirmation information, the recognition of the target model that is not recognized by the network device is stopped until a preset condition is met.

[0178] Specifically, if there is no restriction on the UE repeatedly initiating recognition of models that the network device does not want to recognize in the target model, it will waste resources. Therefore, after receiving the confirmation information, the UE will no longer initiate model recognition for the models that the network device does not recognize in the target model until the preset conditions are met.

[0179] Optionally, the preset conditions include:

[0180] ① A first time period has passed. The first time period is predefined by the protocol or configured on the network side. The first time period refers to a specific time period, a designated time period, etc. It can be predefined by the protocol or indicated or configured by the network device. Optionally, the first time period is associated with the time when the network device initiates the query. Optionally, the first time period is associated with the broadcast period during which the network device sends broadcast information.

[0181] ② The first message is unicast information, and is the next first message sent after receiving the first message sent by the network device in step 201. For example, based on the confirmation information, the UE stops identifying the target model that is not recognized by the network device until it receives the query information sent by the network device again.

[0182] ③ The first information is broadcast information. This is the Lth first information broadcast after the first information sent by the network device in step 201 is received, where L is an integer greater than or equal to 1. For example, based on the confirmation information, the UE stops identifying target models that are not recognized by the network device until the next broadcast period. The broadcast period is often fixed, so the value of L can be predefined by the protocol or configured / indicated by the network device, allowing for a certain degree of flexibility.

[0183] Alternatively, if the network device sends unicast inquiry information at a certain period, the broadcast information in ③ can be replaced with the unicast inquiry information, which can also be achieved.

[0184] The model recognition method provided by the embodiment of the present disclosure is that after the communication device initiates the recognition of the target model to the network device, the recognition of the models in the target model that are not recognized by the network device is stopped according to the confirmation information fed back by the network device until the preset conditions are met, thereby avoiding the communication device from continuously initiating the recognition of models that the network device does not want to recognize, avoiding waste of resources, and further avoiding and reducing the high complexity caused by a large number of communication devices initiating model recognition to the network device and the redundant recognition problem of the network device.

[0185] In some embodiments, it further includes:

[0186] Based on the confirmed information, determine at least one of the following:

[0187] ① Updated information about models recognized by the network device. After the UE initiates target model recognition, the network device may recognize all or part of the target model. The network device can then update the set of recognized models and provide feedback to the UE. For example, the confirmation message can include updated information about models recognized by the network device.

[0188] ② Updated model recognition permission information. After the UE initiates target model recognition, the network device may recognize all or part of the target model. At this time, the number of model recognitions or the identification area allowed by the network device may have changed. Therefore, the network device can feedback the updated model recognition permission information to the UE. For example, the confirmation information can include the updated model recognition permission information.

[0189] ③ Instruction information requesting model recognition before the Mth broadcast period after receiving the confirmation information, where M is an integer greater than or equal to 1.

[0190] ④ It is prohibited to request the instruction information for model identification before the Nth broadcast period after receiving the confirmation information, where N is an integer greater than or equal to 1.

[0191] For ③ and ④, since the broadcast information is sent periodically, multiple UEs may initiate a large number of model identifications in a similar time, and the sum of the number of models exceeds the maximum number of models allowed to be identified by the network equipment. Model identification of some UEs may fail. Therefore, the confirmation information may include relevant information on the failure of model identification, as well as indication information on whether model identification can be requested before the specified number of broadcast cycles after receiving the confirmation information.

[0192] When the confirmation information directly includes the updated model identification permission information, if the number of models allowed to be identified indicated in the updated model identification permission information is greater than 0, the UE can make a model identification request based on the updated model identification permission information without waiting for the update time of the subsequent broadcast cycle.

[0193] Optionally, if the network device sends unicast inquiry information at a certain period, the broadcast information in ③ and ④ can be replaced with unicast inquiry information, which can also be achieved.

[0194] The model identification information provided by the embodiment of the present disclosure enables the communication device to determine the timing of initiating new model identification based on the relevant information of the updated model identification contained in the confirmation information, thereby avoiding and reducing the high complexity caused by a large number of communication devices initiating model identification to the network device and the redundant identification problem of the network device.

[0195] FIG3 is a third flow chart of a model identification method provided by an embodiment of the present disclosure. As shown in FIG3 , the method is performed by a network (NW) device, such as a base station, and includes at least the following steps:

[0196] Step 301: Send first information to a communication device.

[0197] Step 302: Receive first model recognition request information sent by the communication device based on the first information.

[0198] The first model recognition request information is used to request recognition of a target model.

[0199] Specifically, the communication device includes but is not limited to a UE or an OTT Server or other entities that want to initiate model recognition to a network device. The following embodiments are described using the UE as an example.

[0200] After the network device sends the first information to the UE, the UE can send the first model identification request information for requesting identification of the target model. Optionally, the first information is unicast information or broadcast information, and the unicast information is, for example, query information.

[0201] Optionally, the inquiry information is used to inquire whether the UE needs to perform model identification.

[0202] Optionally, the broadcast information is used to broadcast information related to permission for model identification. For example, the network device broadcasts information allowing model identification before the UE can request the network device to perform model identification. For example, if the UE broadcasts information not allowing model identification, the UE cannot request the network device to perform model identification. The broadcast information, for example, SIB information, such as SIB1, SIB2, etc., can be received by all UEs in the cell covered by the network device.

[0203] Compared with unicast query information, broadcast information saves the signaling indication overhead of unicast query information at the expense of the payload in the broadcast information.

[0204] The target model can be the full set of models that the UE wants to perform model identification on, or a subset of the full set of models that the UE wants to perform model identification on. The target model refers to a specific AI / ML model or a designated AI / ML model.

[0205] In the model recognition method provided by the embodiment of the present disclosure, the communication device can send the first model recognition request information for requesting the recognition of the target model only after the network device sends the first information to the communication device. The network device flexibly negotiates the timing of model recognition with the communication device, avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device.

[0206] In some embodiments, the target model is one of the following:

[0207] ① First model set. The first model set is the complete set of AI / ML models that the UE wants to identify. Optionally, after the network device sends a query message or broadcasts information to the UE, the UE can directly initiate model identification for the complete set of models it wants to identify.

[0208] ② Second model set. The second model set is the models in the first model set that the network device has not yet identified. Optionally, the UE can only initiate identification of models that the network device has not yet identified. For models that the network device has already identified, the UE does not need to repeatedly initiate model identification with the network device.

[0209] ③ Third model set. The third model set is the models in the first model set that are permitted by the network device for model recognition. Optionally, the UE can only initiate recognition of models that the network device allows to be recognized. For models that the network device does not allow to be recognized, the UE cannot initiate model recognition to the network device.

[0210] ④ Fourth model set. The fourth model set is the models in the first model set that the network device has not yet recognized and that the network device has permitted model recognition. Optionally, the UE can only initiate recognition of models that the network device has not yet recognized and that the network device has permitted recognition. The UE cannot initiate model recognition with the network device for models that the network device has already recognized and / or models that the network device has not permitted recognition.

[0211] In the model recognition method provided by the embodiments of the present disclosure, the communication device does not initiate model recognition for a model that has already been recognized by the network device, and / or does not initiate model recognition for a model that the network device does not allow model recognition to be performed. This avoids the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoids the redundant recognition problem of the network device.

[0212] In some embodiments, receiving first model recognition request information sent by a communication device based on the first information includes:

[0213] ① Send information about models identified by the network device to the communication device, and receive first model identification request information sent by the communication device, where the first model identification request information is used to request identification of the second model set. The network device also sends information about the identified model to the UE. If the UE receives information about the identified model sent by the network device, the target model is the second model set, i.e., the UE requests identification of the second model set in the first model identification request information, i.e., initiating model identification of one or more models not in the set of models identified by the network device.

[0214] ② Sending model identification permission information to the communication device and receiving first model identification request information sent by the communication device, where the first model identification request information is used to request identification of the third model set. The network device also sends model identification permission information to the UE. If the UE receives the model identification permission information sent by the network device, the target model is the third model set, i.e., the UE requested identification of the second model set in the first model identification request information, i.e., the initiating network device identifies the model allowed for model identification.

[0215] The model recognition permission information includes relevant information that the network device is allowed to perform model recognition or relevant information that the network device is not allowed to perform model recognition. Optionally, the model that the network device is allowed to perform model recognition may be a model that the network device has not recognized.

[0216] ③ Send information about models that have been identified by the network device and model identification permission information to the communication device, and receive the first model identification request information sent by the communication device, where the first model identification request information is used to request identification of the fourth model set. The network device can send information about identified models and model identification permission information to the UE. If the UE receives both the information about identified models and the model identification permission information sent by the network device, the target model is the fourth model set, that is, the UE requests identification of the fourth model set in the first model identification request information, that is, initiates model identification of one or more models that have not been identified by the network device and are permitted by the network device to perform model identification. Optionally, if the model identification permission information indicates relevant information that does not allow model identification or the number of models allowed to be identified is 0, the UE will often not receive information about models that have been identified by the network device.

[0217] Optionally, the network device only sends model recognition permission information and does not send information about the model that the network device has recognized, which can effectively protect the privacy of the network device.

[0218] In the model recognition method provided by the embodiments of the present disclosure, a network device notifies a communication device of information about a model that the network device has recognized and / or model recognition permission information, so that the communication device does not initiate model recognition for a model that the network device has recognized, and / or does not initiate model recognition for a model that the network device does not allow model recognition to be performed. This avoids the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoids the problem of redundant recognition of the network device.

[0219] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0220] ① The set of models recognized by the network device. In the information about the models recognized by the network device, the network device directly indicates one or more models it has recognized, specifically as a set. There may be one or more sets, and different sets may correspond to different model categories, such as different model functions or different model size ranges.

[0221] ② A list of identifications of models recognized by the network device. In the information about models recognized by the network device, the network device directly indicates one or more models it has recognized. Specifically, this can be indicated in the form of a list of identifications of one or more models. Identification can also be an index number, serial number, or other method that can distinguish different models. There may be one or more lists, and different lists can correspond to different model categories, such as different model functions or different model size ranges.

[0222] For example, a list: List = {model ID #1, model ID #2 ...}, represents the full set of models recognized by the network device. For example: multiple lists: List #1 = {model ID #1_1, Model ID #1_2 ...}, List #2 = {model ID #2_1, model ID #2_2 ...}, where List #1 represents the list of models used for CSI compression feedback and List #2 represents the list of models used for BM.

[0223] ③ The maximum value of the identification of the model recognized by the network device (for example, max model ID). If the identification of the model recognized by the network device is continuously increasing according to a certain rule, such as model 0, model 1, model 2, or model A, model B, model C. The increasing rule can be increasing in the order of recognition, or increasing in the order of model version update, etc. In the information of the model recognized by the network device, the maximum value of the identification of the model recognized by the network device is indicated. So that the UE can determine, based on the maximum value of the identification of the model recognized by the network device, such as "2" or "C", that any model with a model identification less than or equal to the maximum value of the identification has been recognized by the network device, then the UE only needs to initiate the identification of the model with a model identification greater than the maximum value to the network device.

[0224] ④ The number of models recognized by the network device. Similarly, if the identifiers of the models recognized by the network device are continuously incremented according to certain rules (such as the order of recognition, the order of model version update, etc.), the number of models recognized by the network device is indicated in the information of the models recognized by the network device. This allows the UE to determine the identifier set and / or the maximum identifier value of the models recognized by the network device based on the number of models recognized by the network device. It only needs to initiate the identification of models whose model identifiers are not in the identifier set and / or are greater than the maximum identifier value to the network device.

[0225] ⑤ A combination of the identification area of ​​the model identified by the network device and the maximum value of the identification in the identification area, and different identification areas are used to classify the models identified by the network device. Different identification areas may correspond to different model categories, such as different model functions or different model size ranges. If within an identification area, the identification of the model identified by the network device increases continuously over time, the information of the model identified by the network device indicates the combination of the identification area identified by the network device and the maximum value of the identification in the identification area, so that the UE can determine the identification area identified by the network device and the models in each identification area based on the combination of the identification area identified by the network device and the maximum value of the identification in the identification area, and no longer initiate model identification of these models.

[0226] There may be one or more area identifiers. For example, if the max model ID in ID area #1 is 3 and the max model ID in ID area #2 is 5, the UE will not initiate model identification for models with IDs less than or equal to 3 in ID area #1, and will not initiate model identification for models with IDs less than or equal to 5 in ID area #2.

[0227] It should be noted that replacing the identification area with an identification set, identification list, etc. is also applicable. Different identification areas, identification sets, identification lists, etc. are mainly used to classify models. There are many bases for classifying models, such as model function, model size range, etc. This is not limited in the embodiments of the present disclosure.

[0228] ⑥ The identification area of ​​the model recognized by the network device and the number of models in the identification area. If the identification of the model recognized by the network device in an identification area is continuously increased according to certain rules (for example, over time, the order of identification, the order of model version update, etc.), the identification area recognized by the network device and the number of models in the identification area are indicated in the information of the model recognized by the network device, so that the UE can determine the identification area of ​​the model recognized by the network device, as well as the identification set and / or identification maximum value of the model in the identification area.

[0229] Optionally, if the network device has received a request message from the UE requesting identification of one or more models before sending the information about the identified models, the information about the models identified by the network device fed back may only include relevant information about the models identified by the network device within the identification area where these models are located. For example, if the models for which the UE requests model identification all belong to ID area #1, the information about the identified models fed back by the network device will only include the combination of the maximum identifier value or the number of models in ID area #1, and will not include relevant information about ID area #2.

[0230] In the model recognition method provided by the embodiment of the present disclosure, the network device sends information about the recognized model to the communication device, so that the UE only initiates model recognition for the model that has not been recognized by the network device, avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoiding the redundant recognition problem of the network device.

[0231] In some embodiments, the model identifies permission information including at least one of the following:

[0232] ① First indication information that the network device permits model recognition. The first indication information can be a general indication, indicating that model recognition is permitted or not permitted. Optionally, it indicates that all models that the UE wants to recognize can be recognized, or it indicates that all models that the UE wants to recognize cannot be recognized.

[0233] ② Second indication information regarding the number of models permitted for model recognition by the network device. The model recognition permission information may indicate the number of models permitted for model recognition. For example, the network device may further permit the recognition of three models. When the number of models permitted for model recognition by the network device is 0, it indicates that the network device does not permit model recognition. The number of models permitted for model recognition may also be multiple, with different numbers of models corresponding to different model categories, indicating how many models of different categories are permitted for model recognition.

[0234] ③ The third indication information of the model identification that the network device permits to perform model recognition. Of the full set of models that the UE wants to recognize, often only a part may be allowed to be recognized by the network device. If the network device receives a request from the UE to perform model recognition of certain models before sending the model recognition permission information indication, the model recognition permission information fed back by the network device can accurately indicate the models that are allowed to perform model recognition, such as indicating the identification of the models that are allowed to perform model recognition. For example, the terminal requests to perform recognition of models 1, 2, 3, and 4, and in the model recognition permission information, only recognition of models 3 and 4 is allowed. There are other ways for the model recognition permission information to indicate the models that are allowed to perform model recognition, such as indicating the categories of models that are allowed to perform model recognition (including model functions, model size ranges, etc.).

[0235] ④ Fourth indication information of the identification area where the network device is permitted to perform model recognition. The model recognition permission information may indicate the identification area where model recognition is permitted or the identification area where model recognition is not permitted.

[0236] ⑤ Fifth indication information indicating the identification areas for which the network device is permitted to perform model recognition and the number of models permitted within the identification areas. Model permission information can indicate the identification areas for which model recognition is permitted or not permitted, as well as the number of models. For example, the network device may permit the recognition of two models in ID area #1, three models in ID area #2, and zero models in ID area #3.

[0237] In the model recognition method provided by the embodiment of the present disclosure, a network device sends model recognition permission information to a communication device so that the communication device only initiates model recognition for models that the network device allows model recognition to be performed, thereby avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device, and also avoiding the redundant recognition problem of the network device.

[0238] In some embodiments, information about the model identified by the network device is included in the first message. The first message is unicast or broadcast. Alternatively, the network device transmits information about the model identified by the network device via a message other than the first message. For example, after transmitting a query message or a broadcast message, the network device receives a model identification request from the UE and then provides feedback about the model identified by the network device.

[0239] In some embodiments, the model identification permission information is included in the first message. Alternatively, the network device sends the model identification permission information via a message other than the first message. For example, after sending a query message or a broadcast message, the network device receives a model identification request sent by the UE and then feeds back the model identification permission information.

[0240] In some embodiments, before sending the unicast first information to the communication device, the method further includes:

[0241] Second model identification request information sent by the communication device is received, where the second model identification request information is used to request model identification.

[0242] Specifically, the unicast first information can be actively sent by the network device or actively triggered by the UE. The network device receives the second model identification request information sent by the UE, which requests model identification. At this time, triggered by the second model identification request information, the network device sends the query information.

[0243] In the model recognition method provided by the embodiment of the present disclosure, the network device triggers the sending of first information based on the second model recognition request information sent by the communication device to perform a subsequent model recognition process. In addition to avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device and the redundant recognition problem of the network device, it also improves the flexibility of the timing of the communication device initiating model recognition.

[0244] In some embodiments, before sending the model recognition permission information to the communication device, the method further includes:

[0245] A third model identification request message sent by the communication device is received, where the third model identification request message is used to request identification of the first model set, and the target model is a subset of the first model set.

[0246] Specifically, the network device first receives the third model recognition request information sent by the UE for requesting recognition of the first model set, determines the full set of models that the UE wants to recognize, and then feeds back model recognition permission information to the UE, which allows or does not allow the UE to perform model recognition.

[0247] Optionally, the model identification permission information is included in the query information. The network device receives the third model identification request information sent by the UE, and then the network device indicates whether to allow or not to perform model identification through the model identification permission information in the query information.

[0248] In the model recognition method provided by the embodiment of the present disclosure, the network device feeds back the model recognition permission information only after receiving the third model recognition request information sent by the communication device, which can effectively avoid the redundant recognition problem of the network device.

[0249] In some embodiments, further comprising:

[0250] A confirmation message is sent to the communication device, where the confirmation message is used to indicate the model in the target model recognized by the network device.

[0251] Specifically, after a network device receives the first model identification request message from a UE requesting identification of a target model, due to factors such as the network device's management capabilities, complexity, and implementation, the network device may not necessarily identify and use the model for which the UE initiated model identification. Therefore, the network device may selectively identify or use the model for which the UE initiated model identification, and feedback the identified model to the UE via a confirmation message. The model identified by the network device in the confirmation message is a subset of the target model.

[0252] Optionally, if the network device does not feed back the confirmation information, the UE defaults that all target models are recognized by the network device, or that all target models are not recognized by the network device.

[0253] Optionally, the confirmation information is indicated by a bitmap. Each target model corresponds to a bit in the bitmap, for example, the bitmap bits may correspond in order of model ID from small to large or from large to small. For example, a bitmap bit value of 1 indicates that the model is recognized, and a value of 0 indicates that the model is not recognized; or, a value of 0 indicates that the model is recognized, and a value of 1 indicates that the model is not recognized. Taking the value of 1 indicating that the model is recognized as an example, the target models include model 1, model 2, model 3 and model 4, and bitmap = "1011", it means that model 1, model 3 and model 4 are recognized by the network device, and model 2 is not recognized by the network device.

[0254] Optionally, the confirmation information may be an overall indication information, for example, that all target models are recognized by the network device, or that all target models are not recognized by the network device.

[0255] Optionally, the confirmation information may be an identification list or an identification set, which includes an identification list or an identification set in the target model that is recognized by the network device or is not recognized by the network device.

[0256] Optionally, the confirmation information may include a combination of the identification area and identifications of models within the identification area that are recognized or not recognized by the network device.

[0257] The model recognition method provided by the embodiment of the present disclosure is that the network device feeds back confirmation information to the communication device, and the communication device initiates the model recognition of the model information recognized by the network device, thereby realizing the network device's management of the model on the communication device side, with higher flexibility.

[0258] In some embodiments, it further includes:

[0259] After sending the confirmation information, the recognition of the models in the target model that are not recognized by the network device is stopped until a preset condition is met.

[0260] Specifically, for models in the target model that are not recognized by the network device, the UE may repeatedly initiate model recognition. After sending the confirmation information, the network device may not recognize the models in the target model that the network device has not recognized until the preset conditions are met.

[0261] Optionally, the preset conditions include:

[0262] ① A first time period has passed. The first time period is predefined by the protocol or configured on the network side. The first time period refers to a specific time period, a designated time period, etc. It can be predefined by the protocol or indicated or configured by the network device. Optionally, the first time period is associated with the time when the network device initiates the query. Optionally, the first time period is associated with the broadcast period during which the network device sends broadcast information.

[0263] ② The first information is unicast information, and the next first information is sent to the UE after the first information sent in step 301. For example, the network device may not start identifying the target model that has not been identified by the network device until the query information is sent again.

[0264] ③ The first information is broadcast information. After the first information sent in step 301, the first information is broadcast to the UE for the Lth time, where L is an integer greater than or equal to 1. For example, the network device may not begin identifying models in the target model that have not yet been recognized by the network device until the next broadcast period. The broadcast period is often fixed, so the value of L can be predefined by the protocol or configured / indicated by the network device, providing a certain degree of flexibility.

[0265] Alternatively, if the network device sends unicast inquiry information at a certain period, the broadcast information in ③ can be replaced with the inquiry information, which can also be achieved.

[0266] The model recognition method provided by the embodiment of the present disclosure is that the network device may not recognize the model in the target model that has not been recognized by the network device until the preset conditions are met, thereby avoiding the waste of resources caused by the communication device continuously initiating the recognition of models that the network device does not want to recognize, and further avoiding and reducing the high complexity caused by a large number of communication devices initiating model recognition to the network device and the redundant recognition problem of the network device.

[0267] In some embodiments, the confirmation information is used to indicate at least one of the following:

[0268] ① Updated information about models recognized by the network device. After the UE initiates target model recognition, the network device may recognize all or part of the target model. The network device can then update the set of recognized models and provide feedback to the UE. For example, the confirmation message can include updated information about models recognized by the network device.

[0269] ② Updated model recognition permission information. After the UE initiates target model recognition, the network device may recognize all or part of the target model. At this time, the number of model recognitions or the identification area allowed by the network device may have changed. Therefore, the network device can feedback the updated model recognition permission information to the UE. For example, the confirmation information can include the updated model recognition permission information.

[0270] ③ Instruction information requesting model identification before the Mth broadcast period after the confirmation information, where M is an integer greater than or equal to 1.

[0271] ④ It is prohibited to request the instruction information for model identification before the Nth broadcast period after the confirmation information, where N is an integer greater than or equal to 1.

[0272] For ③ and ④, since the broadcast information is sent periodically, multiple UEs may initiate a large number of model identifications in a similar time, and the sum of the number of models exceeds the maximum number of models allowed to be identified by the network equipment. Model identification of some UEs may fail. Therefore, the confirmation information may include relevant information on the failure of model identification, as well as indication information indicating whether the UE can request model identification before a specified number of broadcast cycles after receiving the confirmation information.

[0273] When the confirmation information directly includes the updated model identification permission information, if the number of models allowed to be identified indicated in the updated model identification permission information is greater than 0, the UE can make a model identification request based on the updated model identification permission information without waiting for the update time of the subsequent broadcast cycle.

[0274] Optionally, if the network device sends inquiry information at a certain period, the broadcast information in ③ and ④ can be replaced with the inquiry information, which can also be achieved.

[0275] The model recognition information provided by the embodiment of the present disclosure is used by the network device to notify the communication device of the relevant information of the updated model recognition so that the communication device can initiate new model recognition, thereby avoiding the high complexity caused by a large number of communication devices initiating model recognition to the network device and the redundant recognition problem of the network device.

[0276] The technical solutions of the embodiments of the present disclosure are further described below through several specific examples, where NW represents a network device.

[0277] Example 1: The NW sends a query message, which indicates information about the model that the NW has recognized.

[0278] FIG4 is a third flow chart of the model identification method provided by an embodiment of the present disclosure. As shown in FIG4 , the method includes at least the following steps:

[0279] Step 1: The NW sends a query message to the UE, asking whether the UE needs to perform model recognition.

[0280] Optionally, the query information includes information about models that have been recognized by the current network device, or a set of models that have been recognized by the current network device, so that the UE can determine which models have been recognized by the network device without initiating recognition again.

[0281] Optionally, information about the models recognized by the network device is indicated by a list of IDs of the models currently recognized by the network device. Optionally, there is a single ID list, for example, List = {model ID #1, model ID #2 ...}, indicating the full set of recognized models. Optionally, there are multiple ID lists, for example, List #1 = {model ID #11, Model ID #1_2 ...}, List #2 = {model ID #21, model ID #2_2 ...}.

[0282] Optionally, the maximum value among the model IDs currently recognized by the network device indicates the information of the model recognized by the network device. Assuming that the models are recognized continuously, the model ID increases according to the recognition time. Optionally, the maximum value is one, such as max model ID, which indicates the maximum value of the model ID among the recognized models, and any model with a model ID less than or equal to max model ID has been recognized by the network device. Optionally, the maximum value is multiple, that is, multiple maximum values ​​in each of the multiple ID areas, such as max model ID#1 in ID area #1, max model ID#2 in ID area #2, etc., which respectively indicate that any model with a model ID less than the max model ID in each ID area has been recognized by the network device.

[0283] Optionally, other indication methods are used to enable the UE to clearly understand the information of the model that has been identified by the network device.

[0284] Step 2: UE performs model recognition on NW.

[0285] The UE can identify one or more AI / ML models. The UE can only initiate identification of models that the network device has not yet identified. If the network device has already identified a model, the UE does not need to initiate model identification for the model that the network device has already identified.

[0286] Step 3: Optionally, the NW feeds back confirmation information to the UE.

[0287] In the absence of step 3, the UE assumes that all models identified in step 2 are recognized by the network device. However, due to network device management capabilities, complexity, or implementation factors, the network device may not necessarily want to recognize and use a model identified by the UE. Therefore, the network device can selectively complete the identification of some models and feedback the identified models to the UE. The models identified by the network device should be a subset of the models identified by the UE.

[0288] Optionally, the network device feeds back the confirmation information in a specific manner of a list, ie, a "list of model IDs identified by the network device in the models for which the UE initiates model identification".

[0289] Optionally, the confirmation information fed back by the network device may be in the form of a bitmap. For example, "0" indicates unrecognized and "1" indicates recognized. Then, bitmap = "1011" indicates that the first, third, and fourth models are recognized, but the second model is not recognized.

[0290] Optionally, the network device may also feed back indication information of “all models are recognized” or “all models are not recognized”.

[0291] Optionally, other methods that can correctly reflect the model identified by the network device among the models initiated by the UE.

[0292] In addition, the handling of models that are not permitted by the model recognition permission information sent by the network device must also be considered. If no restrictions are imposed, the UE may repeatedly initiate the recognition of models that the network device does not want to recognize, resulting in a waste of resources. Therefore, the UE will no longer initiate model recognition for models that are not confirmed by the feedback information from the network device, and may only initiate model recognition again after the following conditions are met:

[0293] ① After a specific time period. The specific time period can be a predefined time period, or a time period that can be configured / indicated by the network device.

[0294] ②After the network device initiates the next model recognition inquiry / permission.

[0295] The network device actively controls the timing of UE model recognition, avoiding the high complexity caused by large numbers of UEs performing model recognition. When actively querying the UE, the network device also indicates the model it has already recognized, so the UE does not perform model recognition on the model it has already recognized, thus avoiding the problem of redundant recognition. Furthermore, the network device can selectively recognize the model initiated by the UE, providing greater flexibility.

[0296] Example 2: The NW sends an inquiry message, and after receiving the model identification request fed back by the UE, it feeds back model identification permission information.

[0297] FIG5 is a fourth flow chart of the model identification method provided by an embodiment of the present disclosure. As shown in FIG5 , the method includes at least the following steps:

[0298] Step 1: The NW sends a query message to the UE, asking whether the UE needs to perform model recognition.

[0299] The query information is only used to trigger or prompt the UE to send a model identification request.

[0300] Step 2: The UE sends a model identification request message to the NW.

[0301] The model identification request information indicates the model that the UE wants to perform model identification on, for example, carries an ID list of the models that the UE wants to perform model identification on.

[0302] Optionally, there are one or more ID lists. Different ID lists represent different model functions or model range sizes, etc.

[0303] Step 3: The NW feeds back model identification permission information to the UE.

[0304] The model identification permission information indicates which models, among the models requested by the UE in step 2, are permitted for model identification. Optionally, the model identification permission information notified by the network device is a general indication, indicating that all models the UE wishes to identify are permitted, or that none are permitted. Optionally, the model identification permission information notified by the network device indicates a list of model IDs permitted for identification, which may include one or more models.

[0305] Step 4: UE performs model recognition on NW.

[0306] The UE can only perform model identification on the models allowed to be identified in step 3.

[0307] Step 5: The NW sends confirmation information back to the UE. The specific implementation is the same as in Example 1.

[0308] Compared with Example 1, the network device does not send the models that have been identified in the network device to the UE, which can protect the privacy of the network device; and the number of bits and resources required to indicate the ID list of the models that the UE requests to be identified in the model identification request in step 2 is less (compared to directly transmitting the model's metadata or model description information), which is more flexible than the UE directly initiating the identification of all models, and can effectively avoid resource waste.

[0309] Example 3: The UE receives the query information sent by the network device and directly initiates the identification of one or more models.

[0310] FIG6 is a fifth flow chart of the model identification method provided by an embodiment of the present disclosure. As shown in FIG6 , the method includes at least the following steps:

[0311] Step 1: The NW sends a query message to the UE, asking whether the UE needs to perform model recognition.

[0312] The query information is only used to trigger or prompt the UE to send a model identification request.

[0313] Step 2: UE performs model recognition on NW.

[0314] Different from Example 1 and Example 2, the UE is not aware of the information of the models that have been identified by the network device, and has not received the model identification permission information, and directly initiates the identification of the full set of models that it wants to identify.

[0315] Step 3: The NW sends confirmation information back to the UE. The specific implementation is the same as in Example 1.

[0316] Compared to Example 1, the network device does not send the UE the models it has already identified, thus protecting the network device's privacy. Compared to Example 2, the interaction between the UE and the network device is significantly reduced, and the time required for model identification is shortened, resulting in lower latency. However, because the UE directly initiates full model identification, redundant identification and waste of transmission resources are unavoidable.

[0317] Example 4: NW broadcast model identification permission.

[0318] FIG7 is a sixth flow chart of the model identification method provided by an embodiment of the present disclosure. As shown in FIG7 , the method includes at least the following steps:

[0319] For part (a) in FIG. 7 , except step 1, the entire process can refer to Example 3.

[0320] Step 1. The NW broadcasts model identification permission information. All UEs in the cell covered by the network device can receive the broadcast information. Optionally, the model identification permission information is carried in the SIB and broadcast. Optionally, the model identification permission information is an indication of "whether model identification is allowed". Only when the indication is "model identification is allowed", can the UE initiate model identification. Optionally, the model identification permission information is a quantity indication of "how many models are allowed to be identified". Only when the indication "the number of models allowed to be identified" is greater than 0, can the UE initiate model identification.

[0321] For part (b) in FIG. 7 , except step 1, the whole process can refer to Example 2.

[0322] Step 1. The NW broadcasts model identification permission information. All UEs in the cell covered by the network device can receive the broadcast information. Optionally, the model identification permission information is carried in the SIB and broadcast. Optionally, the model identification permission information is an indication of "whether model identification is allowed". Only when the indication is "model identification is allowed", can the UE initiate model identification. Optionally, the model identification permission information is a quantity indication of "how many models are allowed to be identified". Only when the indication "the number of models allowed to be identified" is greater than 0, can the UE initiate model identification.

[0323] In Figure 7, since the model identification permission is sent through SIB broadcast, which often has a certain period, the update of the model identification permission information is also periodic. Therefore, the UE's model identification behavior has the following characteristics:

[0324] When the UE wants to perform model recognition or send a model recognition request at time t, it needs to determine whether the recognition can be performed based on the model recognition permission information broadcast before time t and closest to time t.

[0325] Because multiple UEs may initiate model identification within a similar time period, the total number of models that the UEs want to identify may exceed the number of models that the network device allows to identify. Therefore, model identification for some UEs may fail. Therefore, the network device can include "model identification failure" information in the feedback confirmation information, as well as:

[0326] ① Whether the indication of model identification can be initiated before the next SIB broadcast transmission cycle.

[0327] ② Directly carry the updated model identification permission information so that the UE can determine whether to initiate model identification or send a model identification request based on the updated model identification permission information without waiting for the update time of the next SIB broadcast cycle.

[0328] Compared with Example 2 and Example 3, the model identification permission information contained in the unicast query information is replaced by the broadcast model identification permission information, and the physical downlink control channel (PDCCH) and physical downlink shared channel (PDSCH) indication overhead of the unicast query are saved at the expense of the load in the SIB, which is suitable for occasions where PDCCH / PDSCH capacity is limited.

[0329] Example 5: The NW broadcasts information about the model that the NW has identified.

[0330] Figure 8 is a seventh flow diagram of a model identification method provided by an embodiment of the present disclosure. As shown in Figure 8 , the entire flow of this method, except for step 1, can be referred to as Example 1. In step 1, the network device broadcasts information about the model it has identified. Optionally, the information about the model identified by the network device is carried in a SIB and broadcast. This broadcast information replaces the unicast query message, which carries the information about the model identified by the network device.

[0331] Compared with Example 1, the information of the model identified by the network device is carried through broadcast information rather than unicast query information, saving the PDCCH and PDSCH indication overhead of unicast query at the expense of the payload in the SIB, which is suitable for occasions with limited PDCCH / PDSCH capacity.

[0332] Example 6: The NW broadcasts the information of the model recognized by the NW and / or the model recognition permission information.

[0333] FIG9 is a flowchart of the eighth embodiment of the model identification method provided by the present disclosure. As shown in FIG9 , the method includes at least the following steps:

[0334] Part (a) of FIG9 shows the process when the model recognition permission information broadcast by the network device is “model recognition is not allowed”, and part (b) of FIG9 shows the process when the model recognition permission information broadcast by the network device is “model recognition is allowed”.

[0335] Step 1. The NW broadcasts model identification permission information. All UEs in the cells covered by the network device can receive the broadcast information. Optionally, the model identification permission information is carried in the SIB and broadcast. Optionally, the model identification permission information is an indication of "whether model identification is allowed". Only when the indication is "model identification is allowed" can the UE initiate model identification. Optionally, when the model identification permission information is "model identification is allowed", the number of models allowed for model identification can also be indicated.

[0336] Optionally, in the case of “allowing model identification”, the network device also broadcasts information of the model that has been identified by the network device.

[0337] Step 2: (Only when "model identification is allowed") the UE performs model identification on the NW. The UE only performs model identification on models that are allowed and not identified by the network device.

[0338] Step 3: (Only when "model identification is allowed") the NW feeds back confirmation information to the UE. For specific implementation, please refer to Example 1 and Example 2.

[0339] Based on Example 4 and Example 5, further improvements have been made. When the network device does not allow model recognition, the recognized model is not broadcast, saving indication overhead; when the network device allows model recognition, the recognized model is indicated to avoid redundant recognition.

[0340] Example 7: Based on Examples 1, 2, and 3, add Step 0 before Step 1: The UE sends a model identification request message to the NW to request model identification. Only after Step 0 is completed can the NW execute Step 1: The NW sends a query message to the UE.

[0341] In step 0, the model identification request information is only used to request model identification and does not include other indication information. The model identification request information can be carried via physical layer signaling (e.g., physical random access channel (PRACH) or physical uplink control channel (PUCCH)), or via higher layer signaling (e.g., an information element carrying a model identification request).

[0342] Optionally, after the UE sends the model identification request information to the network device, the UE can perform subsequent model identification only after receiving the query information fed back by the network device.

[0343] Compared with Example 1, the timing of the UE initiating model identification is more flexible. The UE can actively try to trigger it instead of passively waiting for the network device to initiate the query. The network device's active query is often periodic and the cycle is often long.

[0344] FIG10 is a schematic diagram of the structure of a communication device provided in an embodiment of the present disclosure. As shown in FIG10 , the terminal includes a memory 1001, a transceiver 1002, and a processor 1003, wherein:

[0345] The memory 1001 is used to store computer programs; the transceiver 1002 is used to send and receive data under the control of the processor 1003.

[0346] Specifically, the transceiver 1002 is configured to receive and send data under the control of the processor 1003 .

[0347] In FIG10 , the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1003 and memory represented by memory 1001. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1002 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. For different user devices, the user interface 1004 may also be an interface capable of connecting to required external or internal devices, including but not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0348] The processor 1003 is responsible for managing the bus architecture and general processing, and the memory 1001 can store data used by the processor 1003 when performing operations.

[0349] Optionally, the processor 1003 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0350] The processor calls the computer program stored in the memory to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0351] The processor 1003 is configured to read the computer program in the memory 1001 and perform the following operations: receiving first information sent by a network device, and sending first model recognition request information to the network device; wherein the first model recognition request information is used to request recognition of a target model.

[0352] In some embodiments, the target model is: a first model set; or a second model set, wherein the second model set is a model in the first model set that is not recognized by the network device; or a third model set, wherein the third model set is a model in the first model set that is permitted by the network device for model recognition; or a fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device for model recognition.

[0353] In some embodiments, the sending of the first model identification request information to the network device includes:

[0354] Sending the first model recognition request information to the network device according to the information of the recognized model sent by the network device, where the first model recognition request information is used to request recognition of the second model set; or

[0355] sending the first model recognition request information to the network device according to the model recognition permission information sent by the network device, where the first model recognition request information is used to request recognition of the third model set; or

[0356] The first model recognition request information is sent to the network device according to the information of the model recognized by the network device and the model recognition permission information, where the first model recognition request information is used to request recognition of the fourth model set.

[0357] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0358] a set of identified models of the network device;

[0359] A list of identifications of models that have been identified by the network device;

[0360] The maximum value of the identification of the model recognized by the network device;

[0361] the number of models recognized by the network device;

[0362] a combination of an identification area of ​​a model identified by the network device and an identification maximum value in the identification area, wherein different identification areas are used to classify the model identified by the network device;

[0363] The identification area of ​​the model recognized by the network device and the number of models in the identification area.

[0364] In some embodiments, the model identifies permission information including at least one of the following:

[0365] First indication information of the network device allowing model recognition;

[0366] second indication information of the number of models permitted by the network device for model recognition;

[0367] third indication information of a model identifier permitted by the network device to perform model identification;

[0368] fourth indication information of an identification area permitted by the network device to perform model recognition;

[0369] The network device identifies an area where model recognition is permitted and fifth indication information of the number of models in the identified area where model recognition is permitted.

[0370] In some embodiments, the model recognition permission information and / or information of the model recognized by the network device is included in the first information.

[0371] In some embodiments, the processor 1003 is configured to read the computer program in the memory 1001 and further perform the following operations: sending second model recognition request information to the network device, where the second model recognition request information is used to request model recognition.

[0372] In some embodiments, the processor 1003 is used to read the computer program in the memory 1001 and further perform the following operations: sending a third model identification request message to the network device, wherein the third model identification request message is used to request identification of the first model set, and the target model is a subset of the first model set.

[0373] In some embodiments, the processor 1003 is configured to read the computer program in the memory 1001 and further perform the following operations: receiving confirmation information sent by the network device;

[0374] Based on the confirmation information, a model in the target model recognized by the network device is determined.

[0375] In some embodiments, the confirmation information is indicated by a bitmap.

[0376] In some embodiments, the processor 1003 is configured to read the computer program in the memory 1001 and further perform the following operations: based on the confirmation information, stopping the recognition of the model in the target model that is not recognized by the network device until a preset condition is met.

[0377] In some embodiments, the preset conditions include: after a first time period, the first time period is predefined by the protocol or configured on the network side; or, when the first information is received via unicast, the next first information sent by the network device after the first information is received; or, when the first information is received via broadcast, the Lth first information sent by the network device after the first information is received, where L is an integer greater than or equal to 1.

[0378] In some embodiments, the processor 1003 is configured to read the computer program in the memory 1001 and further perform the following operations: based on the confirmation information, determine at least one of the following:

[0379] Updated information of the model identified by the network device;

[0380] Updated model recognition licensing information;

[0381] Instruction information requesting model recognition before the Mth broadcast period after receiving the confirmation information;

[0382] It is prohibited to request the instruction information for model identification before the Nth broadcast period after the confirmation information is received;

[0383] Wherein, M and N are integers greater than or equal to 1.

[0384] It should be noted here that the above-mentioned communication device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment with the communication device as the execution body, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0385] Figure 11 is a structural diagram of a network device provided in an embodiment of the present disclosure. As shown in Figure 11, the network device includes a memory 1101, a transceiver 1102, and a processor 1103, wherein: the memory 1101 is used to store computer programs; the transceiver 1102 is used to send and receive data under the control of the processor 1103.

[0386] Specifically, the transceiver 1102 is configured to receive and send data under the control of the processor 1103 .

[0387] In FIG11 , the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1103 and memory represented by memory 1101. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1102 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, or the like. The processor 1103 is responsible for managing the bus architecture and general processing, and the memory 1101 may store data used by the processor 1103 when performing operations.

[0388] The processor 1103 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0389] The processor 1103 is configured to read the computer program in the memory 1101 and perform the following operations:

[0390] Sending first information to a communication device, and receiving first model recognition request information sent by the communication device based on the first information; wherein the first model recognition request information is used to request recognition of a target model.

[0391] In some embodiments, the target model is: a first model set; or a second model set, wherein the second model set is a model in the first model set that is not recognized by the network device; or a third model set, wherein the third model set is a model in the first model set that is permitted by the network device for model recognition; or a fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device for model recognition.

[0392] In some embodiments, the receiving first model recognition request information sent by the communication device based on the first information includes:

[0393] Sending information about the model identified by the network device to the communication device, and receiving first model identification request information sent by the communication device based on the information about the model identified by the network device, where the first model identification request information is used to request identification of the second model set; or

[0394] sending model recognition permission information to the communication device, and receiving the first model recognition request information sent by the communication device based on the model recognition permission information, where the first model recognition request information is used to request recognition of the third model set; or

[0395] Send information about the model identified by the network device and model identification permission information to the communication device, and receive the first model identification request information sent by the communication device based on the information about the model identified by the network device and the model identification permission information, wherein the first model identification request information is used to request identification of the fourth model set.

[0396] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0397] a set of identified models of the network device;

[0398] A list of identifications of models that have been identified by the network device;

[0399] The maximum value of the identification of the model recognized by the network device;

[0400] the number of models recognized by the network device;

[0401] a combination of an identification area of ​​a model identified by the network device and an identification maximum value in the identification area, wherein different identification areas are used to classify the model identified by the network device;

[0402] The identification area of ​​the model recognized by the network device and the number of models in the identification area.

[0403] In some embodiments, the model identifies permission information including at least one of the following:

[0404] First indication information of the network device allowing model recognition;

[0405] second indication information of the number of models permitted by the network device for model recognition;

[0406] third indication information of a model identifier permitted by the network device to perform model identification;

[0407] fourth indication information of an identification area permitted by the network device to perform model recognition;

[0408] The network device identifies an area where model recognition is permitted and fifth indication information of the number of models in the identified area where model recognition is permitted.

[0409] In some embodiments, the model recognition permission information and / or information of the model recognized by the network device is included in the first information.

[0410] In some embodiments, the processor 1103 is configured to read the computer program in the memory 1101 and further perform the following operations: receiving second model recognition request information sent by the communication device, where the second model recognition request information is used to request model recognition.

[0411] In some embodiments, the processor 1103 is used to read the computer program in the memory 1101 and further perform the following operations: receiving a third model recognition request message sent by the communication device, the third model recognition request message being used to request recognition of the first model set, the target model being a subset of the first model set.

[0412] In some embodiments, the processor 1103 is configured to read the computer program in the memory 1101 and further perform the following operations: sending confirmation information to the communication device, where the confirmation information is used to indicate the model in the target model recognized by the network device.

[0413] In some embodiments, the confirmation information is indicated by a bitmap.

[0414] In some embodiments, the processor 1103 is configured to read the computer program in the memory 1101 and further perform the following operations: after sending the confirmation information, stop identifying models in the target model that are not identified by the network device until a preset condition is met.

[0415] In some embodiments, the preset conditions include: after a first time period has passed, the first time period is predefined by the protocol or configured by the network side; or, when the first information is sent via unicast, after sending the first information, the next first information is sent to the communication device; or, when the first information is sent via broadcast, after sending the first information, the Lth first information is sent to the communication device.

[0416] In some embodiments, the confirmation information is used to indicate at least one of the following:

[0417] Updated information of the model identified by the network device;

[0418] Updated model recognition licensing information;

[0419] Instruction information requesting model recognition before the Mth broadcast period after the confirmation information;

[0420] prohibiting the instruction information requesting model identification before the Nth broadcast period after the confirmation information;

[0421] Wherein, M and N are integers greater than or equal to 1.

[0422] It should be noted here that the above-mentioned network device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment with the network device as the execution body, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0423] FIG12 is a schematic diagram of a structure of a model recognition device provided by an embodiment of the present disclosure. As shown in FIG12 , the device at least includes:

[0424] The first sending unit 1201 is configured to send first model recognition request information to the network device according to the query information sent by the network device;

[0425] The first model recognition request information is used to request recognition of a target model.

[0426] In some embodiments, the target model is: a first model set; or a second model set, wherein the second model set is a model in the first model set that is not recognized by the network device; or a third model set, wherein the third model set is a model in the first model set that is permitted by the network device for model recognition; or a fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device for model recognition.

[0427] In some embodiments, the first sending unit 1201 is specifically configured to:

[0428] Sending the first model recognition request information to the network device according to the information of the recognized model sent by the network device, where the first model recognition request information is used to request recognition of the second model set; or

[0429] sending the first model recognition request information to the network device according to the model recognition permission information sent by the network device, where the first model recognition request information is used to request recognition of the third model set; or

[0430] The first model recognition request information is sent to the network device according to the information of the model recognized by the network device and the model recognition permission information, where the first model recognition request information is used to request recognition of the fourth model set.

[0431] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0432] a set of identified models of the network device;

[0433] A list of identifications of models that have been identified by the network device;

[0434] The maximum value of the identification of the model recognized by the network device;

[0435] the number of models recognized by the network device;

[0436] a combination of an identification area of ​​a model identified by the network device and an identification maximum value in the identification area, wherein different identification areas are used to classify the model identified by the network device;

[0437] The identification area of ​​the model recognized by the network device and the number of models in the identification area.

[0438] In some embodiments, the model identifies permission information including at least one of the following:

[0439] First indication information of the network device allowing model recognition;

[0440] second indication information of the number of models permitted by the network device for model recognition;

[0441] third indication information of a model identifier permitted by the network device to perform model identification;

[0442] fourth indication information of an identification area permitted by the network device to perform model recognition;

[0443] The network device identifies an area where model recognition is permitted and fifth indication information of the number of models in the identified area where model recognition is permitted.

[0444] In some embodiments, the model recognition permission information and / or information of the model recognized by the network device is included in the first information.

[0445] In some embodiments, the method further includes: a first sending unit configured to send second model identification request information to the network device, wherein the second model identification request information is used to request model identification.

[0446] In some embodiments, it further includes: a second sending unit, used to send third model identification request information to the network device, the third model identification request information is used to request identification of the first model set, and the target model is a subset of the first model set.

[0447] In some embodiments, the method further includes: a third receiving unit for receiving confirmation information sent by the network device; and a first determining unit for determining the model in the target model recognized by the network device based on the confirmation information.

[0448] In some embodiments, the confirmation information is indicated by a bitmap.

[0449] In some embodiments, the method further includes: a stopping unit configured to stop identifying the target model that is not identified by the network device based on the confirmation information until a preset condition is met.

[0450] In some embodiments, the preset conditions include: after a first time period, the first time period is predefined by the protocol or configured on the network side; or, when the first information is received via unicast, the next first information sent by the network device after the first information is received; or, when the first information is received via broadcast, the Lth first information sent by the network device after the first information is received, where L is an integer greater than or equal to 1.

[0451] In some embodiments, the method further includes: a second determining unit configured to determine at least one of the following based on the confirmation information:

[0452] Updated information of the model identified by the network device;

[0453] Updated model recognition licensing information;

[0454] Instruction information requesting model recognition before the Mth broadcast period after receiving the confirmation information;

[0455] It is prohibited to request the instruction information for model identification before the Nth broadcast period after the confirmation information is received;

[0456] Wherein, M and N are integers greater than or equal to 1.

[0457] FIG13 is a second structural diagram of a model recognition device provided by an embodiment of the present disclosure. As shown in FIG13 , the device at least includes:

[0458] A first sending unit 1301 is configured to send first information to a communication device;

[0459] A first receiving unit 1302 is configured to receive first model identification request information sent by the communication device based on the first information;

[0460] The first model recognition request information is used to request recognition of a target model.

[0461] In some embodiments, the target model is: a first model set; or a second model set, wherein the second model set is a model in the first model set that is not recognized by the network device; or a third model set, wherein the third model set is a model in the first model set that is permitted by the network device for model recognition; or a fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device for model recognition.

[0462] In some embodiments, the first receiving unit 1302 is specifically configured to:

[0463] Sending information about the model identified by the network device to the communication device, and receiving first model identification request information sent by the communication device based on the information about the model identified by the network device, where the first model identification request information is used to request identification of the second model set; or

[0464] sending model recognition permission information to the communication device, and receiving the first model recognition request information sent by the communication device based on the model recognition permission information, where the first model recognition request information is used to request recognition of the third model set; or

[0465] Send information about the model identified by the network device and model identification permission information to the communication device, and receive the first model identification request information sent by the communication device based on the information about the model identified by the network device and the model identification permission information, wherein the first model identification request information is used to request identification of the fourth model set.

[0466] In some embodiments, the information of the model identified by the network device includes at least one of the following:

[0467] a set of identified models of the network device;

[0468] A list of identifications of models that have been identified by the network device;

[0469] The maximum value of the identification of the model recognized by the network device;

[0470] the number of models recognized by the network device;

[0471] a combination of an identification area of ​​a model identified by the network device and an identification maximum value in the identification area, wherein different identification areas are used to classify the model identified by the network device;

[0472] The identification area of ​​the model recognized by the network device and the number of models in the identification area.

[0473] In some embodiments, the model identifies permission information including at least one of the following:

[0474] First indication information of the network device allowing model recognition;

[0475] second indication information of the number of models permitted by the network device for model recognition;

[0476] third indication information of a model identifier permitted by the network device to perform model identification;

[0477] fourth indication information of an identification area permitted by the network device to perform model recognition;

[0478] The network device identifies an area where model recognition is permitted and fifth indication information of the number of models in the identified area where model recognition is permitted.

[0479] In some embodiments, the model recognition permission information and / or information of the model recognized by the network device is included in the first information.

[0480] In some embodiments, the system further includes: a first receiving unit configured to receive second model recognition request information sent by the communication device, where the second model recognition request information is used to request model recognition.

[0481] In some embodiments, it further includes: a second receiving unit, used to receive third model recognition request information sent by the communication device, the third model recognition request information is used to request recognition of the first model set, and the target model is a subset of the first model set.

[0482] In some embodiments, the method further includes: a third sending unit, configured to send confirmation information to the communication device, wherein the confirmation information is used to indicate the model in the target model recognized by the network device.

[0483] In some embodiments, the confirmation information is indicated by a bitmap.

[0484] In some embodiments, the method further includes: an identification unit configured to stop identifying models in the target model that are not identified by the network device after sending the confirmation information until a preset condition is met.

[0485] In some embodiments, the preset conditions include: after a first time period has passed, the first time period is predefined by the protocol or configured by the network side; or, when the first information is sent via unicast, after sending the first information, the next first information is sent to the communication device; or, when the first information is sent via broadcast, after sending the first information, the Lth first information is sent to the communication device.

[0486] In some embodiments, the confirmation information is used to indicate at least one of the following:

[0487] Updated information of the model identified by the network device;

[0488] Updated model recognition licensing information;

[0489] Instruction information requesting model recognition before the Mth broadcast period after the confirmation information;

[0490] prohibiting the instruction information requesting model identification before the Nth broadcast period after the confirmation information;

[0491] Wherein, M and N are integers greater than or equal to 1.

[0492] The methods and devices provided in the various embodiments of the present disclosure are based on the same application concept. Since the methods and devices solve problems based on similar principles, the implementation of the devices and methods can refer to each other, and the repeated parts will not be repeated.

[0493] It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0494] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0495] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0496] On the other hand, an embodiment of the present disclosure further provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, wherein the computer program is configured to cause a computer to execute the model recognition method provided in each of the above embodiments, including:

[0497] Sending first model recognition request information to the network device according to the first information sent by the network device; wherein the first model recognition request information is used to request recognition of the target model;

[0498] or,

[0499] Sending first information to a communication device; receiving first model recognition request information sent by the communication device based on the first information; wherein the first model recognition request information is used to request recognition of a target model.

[0500] The non-transitory readable storage medium can be any available medium or data storage device that can be accessed, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid-state drives (SSDs)), etc.

[0501] Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Thus, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage) containing computer-usable program code.

[0502] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0503] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0504] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0505] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. A model recognition method, applied to a communication device, comprising: Sending first model identification request information to the network device according to the first information sent by the network device; The first model recognition request information is used to request recognition of a target model.

2. The model recognition method according to claim 1, wherein: The target model is: A first model set; or, a second model set, where the second model set is a model in the first model set that is not recognized by the network device; or A third model set, wherein the third model set is a model in the first model set that is permitted by the network device to perform model recognition; or A fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device to perform model recognition.

3. The model recognition method according to claim 2, wherein: The sending the first model identification request information to the network device includes: According to the information of the identified model sent by the network device, sending the first model identification request information to the network device, where the first model identification request information is used to request identification of the second model set; or sending the first model recognition request information to the network device according to the model recognition permission information sent by the network device, wherein the first model recognition request information is used to request recognition of the third model set; or The first model recognition request information is sent to the network device according to the information of the model recognized by the network device and the model recognition permission information, wherein the first model recognition request information is used to request recognition of the fourth model set.

4. The model recognition method according to claim 3, wherein: The information of the model identified by the network device includes at least one of the following: a set of models that the network device has identified; A list of identifications of models that the network device has identified; The maximum value of the identification of the model identified by the network device; the number of models that the network device has identified; a combination of an identification area of ​​a model that has been identified by the network device and a maximum value of an identification in the identification area, wherein different identification areas are used to classify the model that has been identified by the network device; The identification area of ​​the model identified by the network device and the number of models in the identification area.

5. The model recognition method according to claim 3, wherein: The model identifies licensing information, including at least one of the following: First indication information that the network device permits model recognition; second indication information of the number of models permitted by the network device for model identification; third indication information of the model identification of the network device allowing the model identification; fourth indication information of the identification area where the network device is permitted to perform model recognition; The network device identifies the area where model recognition is permitted and fifth indication information of the number of models in the identification area where model recognition is permitted.

6. The model recognition method according to claim 3, wherein: The model recognition permission information and / or information of the model recognized by the network device are included in the first information.

7. The model recognition method according to any one of claims 1 to 6, wherein: Also includes: Sending second model identification request information to the network device, where the second model identification request information is used to request model identification.

8. The model recognition method according to claim 3, wherein: Also includes: A third model identification request message is sent to the network device, where the third model identification request message is used to request identification of a first model set, and the target model is a subset of the first model set.

9. The model recognition method according to any one of claims 1 to 8, wherein: Also includes: Receiving confirmation information sent by the network device; Based on the confirmation information, a model in the target model recognized by the network device is determined.

10. The model recognition method according to claim 9, wherein: The confirmation information is indicated by a bitmap.

11. The model recognition method according to claim 9, wherein: Also includes: Based on the confirmation information, the recognition of the model in the target model that is not recognized by the network device is stopped until a preset condition is met.

12. The model recognition method according to claim 11, wherein: The preset conditions include: After a first time period, the first time period is predefined by the protocol or configured by the network side; or, In the case where the first information is received in a unicast manner, receiving the next first information sent by the network device after the first information; or, In the case where the first information is received via broadcast, the Lth first information sent by the network device after the first information is received, where L is an integer greater than or equal to 1.

13. The model recognition method according to claim 9, wherein: Also includes: Based on the confirmation information, determine at least one of the following: Updated information of the model identified by the network device; Updated model identification licensing information; Instruction information for requesting model identification before the Mth broadcast period after receiving the confirmation information; It is prohibited to request the instruction information for model identification before the Nth broadcast period after receiving the confirmation information; Wherein, M and N are integers greater than or equal to 1.

14. A model recognition method, applied to a network device, comprising: Sending first information to a communication device; receiving first model identification request information sent by the communication device based on the first information; The first model recognition request information is used to request recognition of a target model.

15. The model recognition method according to claim 14, wherein: The target model is: A first model set; or, a second model set, where the second model set is a model in the first model set that is not recognized by the network device; or A third model set, wherein the third model set is a model in the first model set that is permitted by the network device to perform model recognition; or The fourth model set is the network device unrecognized in the first model set. The network device may identify a model that is recognized and permitted by the network device for model recognition.

16. The model recognition method according to claim 15, wherein: The receiving first model identification request information sent by the communication device based on the first information includes: Sending information about the model that has been identified by the network device to the communication device, and receiving the first model identification request information sent by the communication device based on the information about the model that has been identified by the network device, wherein the first model identification request information is used to request identification of the second model set; or, sending model recognition permission information to the communication device, and receiving the first model recognition request information sent by the communication device based on the model recognition permission information, wherein the first model recognition request information is used to request recognition of the third model set; or Send information about the model that has been identified by the network device and model identification permission information to the communication device, and receive the first model identification request information sent by the communication device based on the information about the model that has been identified by the network device and the model identification permission information, wherein the first model identification request information is used to request identification of the fourth model set.

17. The model recognition method according to claim 16, wherein: The information of the model identified by the network device includes at least one of the following: a set of models that the network device has identified; A list of identifications of models that the network device has identified; The maximum value of the identification of the model identified by the network device; the number of models that the network device has identified; a combination of an identification area of ​​a model that has been identified by the network device and a maximum value of an identification in the identification area, wherein different identification areas are used to classify the model that has been identified by the network device; The identification area of ​​the model identified by the network device and the number of models in the identification area.

18. The model recognition method according to claim 16, wherein: The model identifies licensing information, including at least one of the following: First indication information that the network device permits model recognition; second indication information of the number of models permitted by the network device for model identification; third indication information of the model identification of the network device allowing the model identification; fourth indication information of the identification area where the network device is permitted to perform model recognition; The network device identifies the area where model recognition is permitted and fifth indication information of the number of models in the identification area where model recognition is permitted.

19. The model recognition method according to claim 16, wherein: The model recognition permission information and / or information of the model recognized by the network device are included in the first information.

20. The model recognition method according to any one of claims 14 to 19, wherein: Also includes: Second model identification request information sent by the communication device is received, where the second model identification request information is used to request model identification.

21. The model recognition method according to claim 16, wherein: Also includes: A third model identification request message sent by the communication device is received, where the third model identification request message is used to request identification of a first model set, and the target model is a subset of the first model set.

22. The model recognition method according to any one of claims 14 to 21, wherein: Also includes: Confirmation information is sent to the communication device, where the confirmation information is used to indicate the model in the target model recognized by the network device.

23. The model recognition method according to claim 22, wherein: The confirmation information is indicated by a bitmap.

24. The model recognition method according to claim 22, wherein: Also includes: After sending the confirmation information, stop identifying the models in the target model that are not identified by the network device until a preset condition is met.

25. The model recognition method according to claim 24, wherein: The preset conditions include: After a first time period, the first time period is predefined by the protocol or configured by the network side; or, In the case where the first information is sent in a unicast manner, after sending the first information, sending the next first information to the communication device; or, In the case where the first information is sent by broadcasting, after the first information is sent, the Lth first information is sent to the communication device.

26. The model recognition method according to claim 22, wherein: The confirmation information is used to indicate at least one of the following: Updated information of the model identified by the network device; Updated model identification licensing information; Instruction information requesting model identification before the Mth broadcast period after the confirmation information; prohibiting the instruction information for requesting model identification before the Nth broadcast period after the confirmation information; Wherein, M and N are integers greater than or equal to 1.

27. A communication device comprising a memory, a transceiver, and a processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Sending first model identification request information to the network device according to the first information sent by the network device; in, The first model recognition request information is used to request recognition of a target model.

28. The communication device according to claim 27, wherein: The target model is: A first model set; or, a second model set, where the second model set is a model in the first model set that is not recognized by the network device; or A third model set, wherein the third model set is a model in the first model set that is permitted by the network device to perform model recognition; or A fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device to perform model recognition.

29. The communication device according to claim 28, wherein: The sending the first model identification request information to the network device includes: According to the information of the identified model sent by the network device, sending the first model identification request information to the network device, where the first model identification request information is used to request identification of the second model set; or According to the model recognition permission information sent by the network device, the first model recognition request information is sent to the network device, wherein the first model recognition request information is used to request the third Identification of a model ensemble; or, The first model recognition request information is sent to the network device according to the information of the model recognized by the network device and the model recognition permission information, wherein the first model recognition request information is used to request recognition of the fourth model set.

30. The communication device according to claim 29, wherein: The information of the model identified by the network device includes at least one of the following: a set of models that the network device has identified; A list of identifications of models that the network device has identified; The maximum value of the identification of the model identified by the network device; the number of models that the network device has identified; a combination of an identification area of ​​a model that has been identified by the network device and a maximum value of an identification in the identification area, wherein different identification areas are used to classify the model that has been identified by the network device; The identification area of ​​the model identified by the network device and the number of models in the identification area.

31. The communication device according to claim 29, wherein: The model identifies licensing information, including at least one of the following: First indication information that the network device permits model recognition; second indication information of the number of models permitted by the network device for model identification; third indication information of the model identification of the network device allowing the model identification; fourth indication information of the identification area where the network device is permitted to perform model recognition; The network device identifies the area where model recognition is permitted and fifth indication information of the number of models in the identification area where model recognition is permitted.

32. The communication device according to claim 29, wherein: The model recognition permission information and / or information of the model recognized by the network device are included in the first information.

33. The communication device according to any one of claims 27 to 32, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: Sending second model identification request information to the network device, where the second model identification request information is used to request model identification.

34. The communication device according to claim 29, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: A third model identification request message is sent to the network device, where the third model identification request message is used to request identification of a first model set, and the target model is a subset of the first model set.

35. The communication device according to any one of claims 27 to 34, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: Receiving confirmation information sent by the network device; Based on the confirmation information, a model in the target model recognized by the network device is determined.

36. The communication device according to claim 35, wherein: The confirmation information is indicated by a bitmap.

37. The communication device according to claim 35, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: Based on the confirmation information, the recognition of the model in the target model that is not recognized by the network device is stopped until a preset condition is met.

38. The communication device according to claim 37, wherein: The preset conditions include: After a first time period, the first time period is predefined by the protocol or configured by the network side; or, In the case where the first information is received in a unicast manner, receiving the next first information sent by the network device after the first information; or, In the case where the first information is received via broadcast, the Lth first information sent by the network device after the first information is received, where L is an integer greater than or equal to 1.

39. The communication device according to claim 35, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: Based on the confirmation information, determine at least one of the following: Updated information of the model identified by the network device; Updated model identification licensing information; Instruction information for requesting model identification before the Mth broadcast period after receiving the confirmation information; It is forbidden to request model recognition before the Nth broadcast cycle after receiving the confirmation information. Instructions; Wherein, M and N are integers greater than or equal to 1.

40. A network device comprising a memory, a transceiver, and a processor; Memory for storing computer programs; a transceiver, for transmitting and receiving data under the control of the processor; A processor is configured to read the computer program in the memory and perform the following operations: Sending first information to a communication device; receiving first model identification request information sent by the communication device based on the first information; The first model recognition request information is used to request recognition of a target model.

41. The network device according to claim 40, wherein: The target model is: A first model set; or, a second model set, where the second model set is a model in the first model set that is not recognized by the network device; or A third model set, wherein the third model set is a model in the first model set that is permitted by the network device to perform model recognition; or A fourth model set, wherein the fourth model set is a model in the first model set that is not recognized by the network device and is permitted by the network device to perform model recognition.

42. The network device according to claim 41, wherein: The receiving first model identification request information sent by the communication device based on the first information includes: Sending information about the model that has been identified by the network device to the communication device, and receiving the first model identification request information sent by the communication device based on the information about the model that has been identified by the network device, wherein the first model identification request information is used to request identification of the second model set; or, sending model recognition permission information to the communication device, and receiving the first model recognition request information sent by the communication device based on the model recognition permission information, wherein the first model recognition request information is used to request recognition of the third model set; or The method further comprises: sending information about the model identified by the network device and model identification permission information to the communication device, receiving the first model identification request information sent by the communication device based on the information about the model identified by the network device and the model identification permission information, wherein the first model identification request information The information is used to request the recognition of the fourth model set.

43. The network device according to claim 42, wherein: The information of the model identified by the network device includes at least one of the following: a set of models that the network device has identified; A list of identifications of models that the network device has identified; The maximum value of the identification of the model identified by the network device; the number of models that the network device has identified; a combination of an identification area of ​​a model that has been identified by the network device and a maximum value of an identification in the identification area, wherein different identification areas are used to classify the model that has been identified by the network device; The identification area of ​​the model identified by the network device and the number of models in the identification area.

44. The network device according to claim 42, wherein: The model identifies licensing information, including at least one of the following: First indication information that the network device permits model recognition; second indication information of the number of models permitted by the network device for model identification; third indication information of the model identification of the network device allowing the model identification; fourth indication information of the identification area where the network device is permitted to perform model recognition; The network device identifies the area where model recognition is permitted and fifth indication information of the number of models in the identification area where model recognition is permitted.

45. The network device according to claim 42, wherein: The model recognition permission information and / or information of the model recognized by the network device are included in the first information.

46. ​​The network device according to any one of claims 40 to 45, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: Second model identification request information sent by the communication device is received, where the second model identification request information is used to request model identification.

47. The network device according to claim 42, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: receiving a third model recognition request message sent by the communication device, wherein the third model recognition request message is used to request recognition of a first model set, wherein the target model is a first model set; A subset of the combination.

48. The network device according to any one of claims 40 to 47, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: Confirmation information is sent to the communication device, where the confirmation information is used to indicate the model in the target model recognized by the network device.

49. The network device according to claim 48, wherein: The confirmation information is indicated by a bitmap.

50. The network device according to claim 48, wherein: The processor is configured to read the computer program in the memory and further perform the following operations: After sending the confirmation information, stop identifying the models in the target model that are not identified by the network device until a preset condition is met.

51. The network device according to claim 50, wherein: The preset conditions include: After a first time period, the first time period is predefined by the protocol or configured by the network side; or, In the case where the first information is sent in a unicast manner, after sending the first information, sending the next first information to the communication device; or, In the case where the first information is sent by broadcasting, after the first information is sent, the Lth first information is sent to the communication device.

52. The network device according to claim 48, wherein: The confirmation information is used to indicate at least one of the following: Updated information of the model identified by the network device; Updated model identification licensing information; Instruction information requesting model identification before the Mth broadcast period after the confirmation information; prohibiting the instruction information for requesting model identification before the Nth broadcast period after the confirmation information; Wherein, M and N are integers greater than or equal to 1.

53. A model recognition device, comprising: The first sending unit is used to send a first message to the network device according to the first message sent by the network device. Send the first model recognition request information; The first model recognition request information is used to request recognition of a target model.

54. A model recognition device, comprising: A first sending unit, configured to send first information to a communication device; A first receiving unit, configured to receive first model identification request information sent by the communication device based on the first information; The first model recognition request information is used to request recognition of a target model.

55. A non-transitory readable storage medium storing a computer program, wherein the computer program is used to cause a computer to execute the method according to any one of claims 1 to 13.

56. A non-transitory readable storage medium storing a computer program, wherein the computer program is used to cause a computer to execute the method according to any one of claims 14 to 26.

Images