Access method and device of terminal, storage medium and electronic device

Abstract

The application discloses a terminal access method and device, a storage medium and an electronic device. The method comprises the following steps: obtaining a target signal from a physical random access channel (PRACH) of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; classifying the target signal according to a reference signal feature and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal feature is a feature possessed by a reference signal, the reference signal is an air interface signal transmitted before the target signal on the PRACH, and the reference signal type is used for indicating whether the reference signal is a RACH message; and performing an access operation on a target terminal sending the target signal in the case that the target signal type is used for indicating that the target signal is a RACH message, wherein the access operation is used for accessing the target terminal to the target base station. By using the above technical solution, the problem of low detection efficiency of a random access signal in a random access channel in the related art is solved.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a terminal access method and device, a storage medium, and an electronic device. Background Art

[0002] In the LTE (Long Time Evolution) / NR (New Radio) system, when a UE (User Equipment) needs to establish or restore uplink synchronization with a base station, it needs to obtain the PRACH (Physical Random Access Channel) configuration parameters broadcast by the base station and send a random access request on the PRACH. The base station periodically detects the PRACH based on the configuration parameters. Since the base station cannot know in advance whether a UE has sent a random access request at the current moment, it needs to perform blind detection on the PRACH, and it is necessary to consider possible false detections.

[0003] In base station implementations, PRACH channel detection is typically performed at the physical layer. The physical layer uses an algorithm to process PRACH signals to determine whether a UE is currently transmitting a signal. The MAC (Media Access Control) layer receives the detection results from the physical layer and performs the next scheduling. In related art, fixed detection parameters are set at the physical layer to determine whether a UE is currently transmitting a random access signal intervening in the target base station. When the signal matches the detection parameters, the signal is considered to be the random access signal corresponding to the random access request. However, in actual applications, due to the complexity and variability of the environment, the parameters of the random access signal may vary and are not fixed. In addition, many interfering signals may exist in actual applications, making these interfering signals easily detected as random access signals, resulting in false detections. Therefore, in high-interference conditions, the probability of PRACH false detection is high. The MAC layer will receive a large number of PRACH requests and reserve RNTI (Radio Network Temporary Identity) resources and RAR scheduling for these requests. In this case, the RAR scheduling will not be detected by the UE, resulting in the base station performing multiple MSG3 retransmission scheduling, resulting in a large waste of air interface resources.

[0004] In view of the problems in the related art such as low detection efficiency of random access signals in random access channels, no effective solution has been proposed yet. Summary of the Invention

[0005] The embodiments of the present application provide a terminal access method and device, a storage medium, and an electronic device to at least solve the problem of low detection efficiency of random access signals in random access channels in related technologies.

[0006] According to one embodiment of the embodiments of the present application, a terminal access method is provided, including: acquiring a target signal from a physical random access channel (PRACH) of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; classifying the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; and when the target signal type is used to indicate that the target signal is a RACH message, performing an access operation on the target terminal that sends the target signal, wherein the access operation is used to access the target terminal to the target base station.

[0007] Optionally, classifying the target signal according to the reference signal feature and the reference signal type to obtain the target signal type of the target signal includes: inputting the target signal feature of the target signal into a target classification model, wherein the target classification model is obtained by training an initial classification model using the reference signal feature labeled with the reference signal type; and obtaining the target signal type output by the target classification model.

[0008] Optionally, before inputting the target signal characteristics of the target signal into the target classification model, the method also includes: obtaining a first number of first signals whose first signal type is RACH messages from the air interface signals transmitted before the target signal on the PRACH, and obtaining a second number of second signals whose second signal type is non-RACH messages from the air interface signals transmitted before the target signal on the PRACH; extracting the first signal characteristics of the first signal as a first signal sample, and extracting the second signal characteristics of the second signal as a second signal sample; labeling the first signal sample with the first signal type, and labeling the second signal sample with the second signal type, to obtain the reference signal characteristics labeled with the reference signal type as a sample set; using the sample set to train an initial support vector machine model to obtain a target support vector machine model as the target classification model.

[0009] Optionally, after obtaining the target signal type output by the target classification model, the method further includes: when the target classification model meets the target update condition, obtaining the air interface signal transmitted after the reference signal on the PRACH as an update signal, and obtaining the update signal type and update signal characteristics of the update signal; using the update signal characteristics marked with the update signal type to update the target classification model to obtain an updated classification model.

[0010] Optionally, before obtaining the air interface signal transmitted after the reference signal on the PRACH as an update signal, the method further includes: matching the target running time of the target classification model with the preset running time, wherein the target running time is the time duration for classifying the signal using the target classification model; when the target running time is less than the preset running time, determining that the target classification model does not meet the target update condition; when the target running time is greater than or equal to the preset running time, determining that the target classification model meets the target update condition.

[0011] Optionally, before classifying the target signal according to the reference signal characteristics and the reference signal type to obtain the target signal type of the target signal, the method also includes: determining whether the signal identifier carried by the target signal matches the target signal identifier corresponding to the target base station, wherein the signal identifier is used to indicate the transmission information of the target signal; when the signal identifier matches the target signal identifier, extracting the target signal characteristics of the target signal, wherein the target signal characteristics include: time advance and received signal strength indication; classifying the target signal characteristics according to the reference signal characteristics and the reference signal type to obtain the target signal type.

[0012] Optionally, the classifying the target signal according to the reference signal and the reference signal type corresponding to the reference signal to obtain the target signal type of the target signal includes: obtaining a target signal characteristic of the target signal; and detecting whether the target signal characteristic falls within a target parameter range, wherein a range threshold of the target parameter range is determined based on the reference signal characteristic and the reference signal type having a corresponding relationship, and the target parameter range is used to indicate the signal characteristics of a signal whose signal type is a RACH message.

[0013] According to another embodiment of the embodiments of the present application, an access device for a terminal is also provided, including: a first acquisition module, used to obtain a target signal from a physical random access channel PRACH of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; a first classification module, used to classify the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; an access module, used to perform an access operation on the target terminal that sends the target signal when the target signal type is used to indicate that the target signal is a RACH message, wherein the access operation is used to connect the target terminal to the target base station.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the above-mentioned terminal access method when running.

[0015] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the terminal access method through the computer program.

[0016] In an embodiment of the present application, a target signal is obtained from a physical random access channel PRACH of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; the target signal is classified according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; when the target signal type is used to indicate that the target signal is a RACH message, the target base station that sends the target signal is The terminal performs an access operation, wherein the access operation is used to access the target terminal to the target base station. Since the reference signal is an air interface signal transmitted before the target signal on the PRACH channel, after obtaining the target signal from the physical random access channel PRACH of the target base station, the target signal is classified by using the reference signal characteristics and the reference signal type, so that the currently received target signal can be classified according to the reference signal characteristics of the reference signal already obtained by the base station and the corresponding reference signal type, thereby being able to determine whether the currently received target signal is a RACH message, avoiding false detection of the signal in the random access channel, and improving the accuracy of the signal detection in the random access channel. The above technical solution solves the problem of low detection efficiency of random access signals in random access channels in related technologies, and achieves the technical effect of improving the detection efficiency of random access signals in random access signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a hardware environment diagram of a terminal access method according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a terminal access method according to an embodiment of the present application;

[0021] Figure 3 This is an optional base station module architecture diagram according to an embodiment of the present application;

[0022] Figure 4is an optional base station module interaction timing diagram according to an embodiment of the present application;

[0023] Figure 5 is an optional signal classification flow chart according to an embodiment of the present application;

[0024] Figure 6 This is a structural block diagram of a terminal access device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a device terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 FIG. 1 is a schematic diagram of a hardware environment of a terminal access method according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. In an exemplary embodiment, the computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1More or fewer components than shown, or with Figure 1 Equivalent functions or comparisons shown Figure 1 Shown are different configurations with more functionality.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for sending message push in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a computer terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a terminal access method is provided, which is applied to the above-mentioned computer terminal. Figure 2 1 is a flow chart of a terminal access method according to an embodiment of the present application, the flow comprising the following steps:

[0031] Step S202: Acquire a target signal from a physical random access channel (PRACH) of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH.

[0032] Step S204: Classify the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message;

[0033] Step S206 : When the target signal type indicates that the target signal is a RACH message, perform an access operation on the target terminal that sends the target signal, wherein the access operation is used to connect the target terminal to the target base station.

[0034] Through the above steps, since the reference signal is an air interface signal transmitted before the target signal on the PRACH channel, after obtaining the target signal from the physical random access channel PRACH of the target base station, the target signal is classified by using the reference signal characteristics and reference signal type, so that the currently received target signal can be classified according to the reference signal characteristics and corresponding reference signal type of the reference signal already obtained by the base station, thereby determining whether the currently received target signal is a RACH message, avoiding false detection of signals in the random access channel, and improving the accuracy of signal detection in the random access channel. The above technical solution solves the problem of low detection efficiency of random access signals in random access channels in related technologies, and achieves the technical effect of improving the detection efficiency of random access signals in random access signals.

[0035] In the technical solution provided in the above step S202, the target signal is a signal detected by the base station on the physical random access channel. The target signal can be an access request signal detected by the target base station, in which the terminal requests to access the target base station, or it can also be an interference signal collected by the target base station signal (for example, an access request signal collected by the target base station, in which the terminal device requests to access other base station devices).

[0036] In the technical solution provided in the above step S204, the reference signal characteristics may include, but are not limited to, Preamble ID (preamble code ID), TA (Time Advance), and RSSI (Received Signal Strength Indicator).

[0037] Optionally, in this embodiment, the reference signal feature may be obtained by detecting the collected reference signal, or may be carried in the reference signal, and the reference signal feature carried in the reference signal may be obtained by extracting the feature of the reference signal.

[0038] Optionally, in this embodiment, the reference signal may be a signal received within a target time period before the target signal is received, or may be a target number of signals before the target signal in the order of signal reception. For example, the reference signal may be a signal received within a time period such as 5-10 minutes, 10-11 minutes, 15-20 minutes, etc. before the target signal is received as a reference signal. It may also be a signal received 10-20 times before the target signal, a signal received 10-30 times before the target signal, a signal received 20-40 times before the target signal, etc. as a reference signal.

[0039] Optionally, in this embodiment, the target signal is classified according to the reference signal feature and the reference signal type by detecting the similarity between the reference signal feature and the signal feature of the target signal. When the similarity is higher than a first threshold, the reference signal type of the reference signal is used as the target signal type of the target signal. Alternatively, a parameter interval of the signal feature is determined based on the reference signal feature of the reference signal. When the value of the target signal feature falls within the parameter interval, the target signal type of the target signal is determined to be used to indicate that the target signal is a RACH message. Alternatively, an initial classification model is trained based on the reference signal feature and the reference signal type, and the target signal feature of the target signal is input into the trained target classification model to obtain the target signal type of the target signal.

[0040] Optionally, in this embodiment, the reference signal type is determined based on a random access result of whether the reference terminal that sends the reference signal accesses the target base station through the reference signal. When the reference terminal accesses the target base station through the reference signal, the reference signal type is determined to be used to indicate that the reference signal is a RACH message. When the reference signal terminal accesses the target base station through the reference, the reference signal type is determined to be used to indicate that the reference signal is a non-RACH message.

[0041] In the technical solution provided in the above step S206, the RACH message is used to instruct the target terminal to request access to the target base station.

[0042] Optionally, in this embodiment, the access operation is access scheduling performed by the target base station on the target terminal. The access scheduling may include, but is not limited to, MAC layer reservation of RNTI resources and RAR scheduling, and MSG3 scheduling of the target terminal.

[0043] The above terminal access method can be applied to, but is not limited to, a base station. To implement the above method, the functions of the base station can be modularized. Figure 3 This is an optional base station module architecture diagram according to an embodiment of the present application, such as Figure 3As shown, the target base station includes at least: a PRACH channel detection module, a scheduling processing module, a training data acquisition module, a decision module and a periodic timing module, wherein the PRACH channel detection module is used to collect signals in the PRACH channel and store the collected signals in the scheduling processing module; the scheduling processing module is used to store the operation data of the base station, wherein the TA and RSSI of the signals collected in the PRACH channel are stored correspondingly, the access result of the random access operation performed by the base station on the terminal corresponding to the signal, and the classification result obtained by the decision module for classifying the signals collected by the PRACH channel, and the scheduling processing module can perform subsequent terminal access operations on the target base station according to the classification result of the target signal by the decision module; the training sample data acquisition module is used to collect training samples for the decision module from the retrieval processing module, and the training samples include those with corresponding relationships The TA and RSSI of the signal and the access result of the random access operation of the terminal corresponding to the signal by the base station are collected, and the sample set composed of the training samples collected from the scheduling processing module is transmitted to the decision module; the decision module stores the target classification model for classifying the collected signals, and the target classification model is obtained by training the initial classification model using the training samples; the target classification model is used to classify the target signal according to the TA and RSSI of the target signal collected by the PRACH channel output by the scheduling processing module, and obtain the target signal type of the target signal; the periodic timing module can set the model period P, and start the timer after each model training is completed. The timer duration is P. When the timer times out, the decision process is stopped, the training data acquisition module is started for collection, and a new round of model training is carried out. After the training is completed, the new model parameters are used for classification prediction.

[0044] Figure 4 This is an optional base station module interaction timing diagram according to an embodiment of the present application, such as Figure 4 As shown, it at least includes the following steps:

[0045] S401, the PRACH channel detection module is used to collect signals in the PRACH channel and store the collected signals in the scheduling processing module;

[0046] S402: The training data acquisition module sends a sample request to the scheduling processing module, requesting to obtain reference signal features marked with reference signal types as training samples, where the reference signal features are signal features of the reference signal, including TA and RSSI. The reference signal is a signal received by the target base station before receiving the target signal. The reference signal type is determined based on the result of a random access operation performed by the target base station on the terminal corresponding to the reference signal.

[0047] S403, the scheduling processing module sends the training sample to the training data acquisition module;

[0048] S404, the training data acquisition module sends the sample set consisting of training samples to the decision module;

[0049] S405, an initial classification model is deployed in the decision module, and the initial classification model is trained using the sample set to obtain a target classification model;

[0050] S406, after the model training is completed, the timer in the periodic timing module is started, the timer duration is P, and when the timer times out, the model is stopped from being used for classification;

[0051] S407, after the model training is completed, the scheduling processing module sends the collected target signal to the decision module;

[0052] S408: The trained target classification model in the decision module classifies the target signal to obtain a target signal type of the target signal, and sends the target signal type to the scheduling processing module to instruct the scheduling processing module whether to perform an access operation on the target terminal corresponding to the target signal;

[0053] S409: When the usage time of the model detected by the timer times out, a model update instruction is sent to the decision module to notify the decision module to update the target classification model;

[0054] S410, the decision module requests the training data acquisition module to update the sample set;

[0055] S411, the training sample acquisition module requests the scheduling processing module to update the sample;

[0056] S412, the scheduling processing module sends the updated sample to the training data acquisition module;

[0057] S413, the training data acquisition module sends the updated sample set consisting of the updated samples to the decision module;

[0058] S414: The decision module updates the target classification model using the updated sample set.

[0059] As an optional embodiment, classifying the target signal according to the reference signal feature and the reference signal type to obtain the target signal type of the target signal includes:

[0060] inputting the target signal features of the target signal into a target classification model, wherein the target classification model is obtained by training an initial classification model using the reference signal features labeled with the reference signal type;

[0061] Obtain the target signal type output by the target classification model.

[0062] Optionally, in this embodiment, the target classification model may include, but is not limited to, a support vector machine model, a random forest model, a decision tree model, a logistic regression model, and the like. This solution does not limit this. For example, taking the classification model as a support vector machine model as an example, training the support vector machine classification model includes at least the following steps:

[0063] (1) Data collection and labeling. During operation, the base station continuously performs blind detection of the reference signal. After detecting the reference signal, it sends the corresponding RAR. After receiving the RAR, the UE sends MSG3. If the base station can receive the MSG3 message scheduled by the reference signal corresponding to the RAR, it can be determined that the RACH message is not a false detection. Otherwise, it can be considered an invalid message of false detection. During operation, the training data collection module is started to record whether the corresponding MSG3 is received for each detected reference signal. The TA and RSSI information in the reference signal are used as samples. The reference signal type of the reference signal is determined based on whether the MSG3 is received, and the samples are labeled using the reference signal type.

[0064] (2) Construct the following function:

[0065]

[0066]

[0067] α i ≥0, i=1, 2, …, N

[0068] And find the optimal solution for the above function Where α is the optimal coefficient vector and T is the transposed sign;

[0069] (3) Calculation and select α * A positive component of Where (xi, yi) corresponds to a set of (TA, RSSI) sampling signals, N is the number of training samples, α is the optimal coefficient vector, W* and b* are the coefficients of the decision function obtained;

[0070] (4) Obtain the separating hyperplane W*·x+b*=0, and the classification decision function: f(x)=sign(W*·x+b*), which is the target classification model mentioned above.

[0071] Optionally, in this embodiment, the target classification model can directly output the target signal type, and can also output a character used to indicate whether the target signal is a RACH message. For example, the target model outputs the character "0" or the character "1". When the character "1" is output, it can be determined that the target signal is a RACH message. When the character "0" is output, it can be determined that the target signal is not a RACH message.

[0072] Figure 5 is an optional signal classification flow chart according to an embodiment of the present application, such as Figure 5 As shown, it at least includes the following steps:

[0073] S501: The base station obtains a reference signal, performs a random access operation on a reference device corresponding to the reference signal, and records the TA and RSSI carried by the reference signal. Whether the random access operation on the reference device receives MSG3 (i.e., the access result) is then determined, and the reference signal type of the reference signal is determined. The TA and RSSI marked with the reference signal type of the reference signal are used as training samples.

[0074] S502, using the training samples to train the initial classification model to obtain a target classification model;

[0075] S503: Receive a target signal, input the TA and RSSI of the target signal into a target classification model for classification, and obtain a target signal type of the target signal.

[0076] Through the above steps, the initial classification model is trained by using the reference signal features marked with the reference signal type, and the trained target training model is used to classify the target signal according to the target signal features, thereby determining the signal type corresponding to the currently received signal features based on the signal features of the already determined signal type, rather than classifying the signal type by simply setting the feature parameter value, thereby ensuring the accuracy of the signal type of the determined target signal.

[0077] As an optional embodiment, before inputting the target signal feature of the target signal into the target classification model, the method further includes:

[0078] Acquire a first number of first signals whose first signal type is RACH messages from air interface signals transmitted on the PRACH before the target signal, and acquire a second number of second signals whose second signal type is non-RACH messages from air interface signals transmitted on the PRACH before the target signal;

[0079] extracting a first signal feature of the first signal as a first signal sample, and extracting a second signal feature of the second signal as a second signal sample;

[0080] labeling the first signal samples using the first signal type and labeling the second signal samples using the second signal type, to obtain the reference signal features labeled with the reference signal type as a sample set;

[0081] The sample set is used to train an initial support vector machine model to obtain a target support vector machine model as the target classification model.

[0082] Optionally, in this embodiment, the first signal sample is a positive sample for training the model, and the second signal sample is a negative sample for training the model memory.

[0083] Optionally, in this embodiment, the values ​​of the first quantity of the first signal and the second quantity of the second signal can be set randomly, or the values ​​of the first quantity and the second quantity can also be set according to a certain ratio, that is, the ratio between the first quantity and the second quantity is the target sample ratio, and the target sample ratio can be set according to the training accuracy requirement of the classification model. For example, the target sample ratio corresponding to the target training accuracy is determined from the sample ratios and model training accuracy with corresponding relationships, and the first quantity of the first signal and the second quantity of the second signal are set according to the target sample ratio.

[0084] Optionally, in this embodiment, the sample set is used to train a support vector machine to obtain a classification hyperplane for classifying the target signal, and the signal type of the target signal is determined through the classification hyperplane.

[0085] Through the above steps, by setting positive and negative samples and using the positive and negative samples to train the initial support vector machine, the model accuracy of the trained model is guaranteed, thereby improving the accuracy of the result obtained by using the target support vector machine to classify the target signal.

[0086] As an optional embodiment, after obtaining the target signal type output by the target classification model, the method further includes:

[0087] When the target classification model satisfies a target update condition, obtaining an air interface signal transmitted after the reference signal on the PRACH as an update signal, and obtaining an update signal type and an update signal feature of the update signal;

[0088] The target classification model is updated using the update signal feature marked with the update signal type to obtain an updated classification model.

[0089] Optionally, in this embodiment, the target update condition can be used to indicate that the usage time of the target classification model is greater than or equal to a first threshold. For example, a timer is set for the target classification model, and the timer duration is the first threshold. The timer is started after each model training is completed. When the timer times out, it is determined that the target update condition is met.

[0090] Optionally, in this embodiment, the target update condition can be used to indicate that the number of target signals classified using the target classification model is greater than or equal to a second threshold. For example, when using the trained target classification model to classify the target signal, the number of target signals classified using the target classification model is recorded. When the number of target signals is greater than or equal to the second threshold, it is determined that the target update condition is met.

[0091] Optionally, in this embodiment, the target update condition can also be used to indicate that the error rate of the classification result of classifying the target signal using the target model is greater than or equal to a third threshold, that is, whether the classification result of the target classification model is accurate is determined based on the actual access result of the target terminal corresponding to the target signal by the target base station, and the probability value of the classification error of the target classification model is calculated. When the probability value is greater than or equal to the target probability value, it is determined that the target update condition is met.

[0092] Optionally, in this embodiment, the target update condition may also be that the difference between a characteristic parameter of a signal characteristic of a target signal for indicating access to the target base station and a characteristic parameter of a signal characteristic of a reference signal whose reference signal type indicates that the reference signal is a RACH message is greater than or equal to a fourth threshold. For example, a target classification model is used to determine that the target signal type of the target signal is used to indicate that the target signal is a RACH signal, and the actual result of the target base station performing access scheduling on the target terminal corresponding to the target signal is determined. When the actual result is that the target terminal accesses the target base station, the reference signal type is determined to indicate that the reference signal is a RACH message. The difference between the characteristic parameters of the reference signal characteristic and the target signal characteristic of the reference signal is determined. When the characteristic parameter difference is greater than or equal to the fourth threshold, it is determined that the target update condition is met.

[0093] Optionally, in this embodiment, updating the target classification model may be retraining the target classification model using the updated signal feature labeled with the updated signal type, thereby shortening the training process of the target model.

[0094] Optionally, in this embodiment, the update signal features marked with the update signal type may be used to train the initial classification model, and the classification model obtained after training may be used to replace the target classification model.

[0095] Through the above steps, by setting the target update conditions for the target classification model, the target update model is updated when the target classification model meets the target update conditions, thereby achieving the target classification model being updated according to demand during the use of the target classification model, so that the target classification model can be more adapted to environmental changes, thereby ensuring the accuracy of classifying target signals using the target classification model.

[0096] As an optional embodiment, before obtaining the air interface signal transmitted after the reference signal on the PRACH as the update signal, the method further includes:

[0097] Matching a target running time of the target classification model with a preset running time, wherein the target running time is a time duration for classifying a signal using the target classification model;

[0098] When the target running time is less than the preset running time, determining that the target classification model does not meet the target update condition;

[0099] When the target running time is greater than or equal to the preset running time, it is determined that the target classification model meets the target update condition.

[0100] Optionally, in this embodiment, the target running time of the target classification model may be determined by setting a timer for the target classification model.

[0101] Through the above steps, by matching the target running time of the target classification model with the preset running time, it is determined whether the target classification model meets the target update conditions based on the running time of the target classification model, thereby realizing the timed update of the target classification model and avoiding the problem of inaccurate classification caused by classifying the target signal according to the same fixed standard.

[0102] As an optional embodiment, before classifying the target signal according to the reference signal feature and the reference signal type to obtain the target signal type of the target signal, the method further includes:

[0103] determining whether a signal identifier carried by the target signal matches a target signal identifier corresponding to the target base station, wherein the signal identifier is used to indicate transmission information of the target signal;

[0104] In the case where the signal identifier matches the target signal identifier, extracting target signal features of the target signal, wherein the target signal features include: a timing advance and a received signal strength indicator;

[0105] The target signal feature is classified according to the reference signal feature and the reference signal type to obtain the target signal type.

[0106] Optionally, in this embodiment, the signal identifier can be a PreambleID (preamble code ID), which is configured by the base station and notified to the terminal in the broadcast message SIB. The random access request sent by the terminal will carry the PreambleID. The base station verifies whether the PreambleID is within the range corresponding to the base station. Signals that are not within the range will be discarded.

[0107] As an optional embodiment, classifying the target signal according to the reference signal and the reference signal type corresponding to the reference signal to obtain the target signal type of the target signal includes:

[0108] acquiring a target signal characteristic of the target signal;

[0109] detecting whether the target signal characteristic falls within a target parameter range, wherein a range threshold of the target parameter range is determined based on the reference signal characteristic and the reference signal type having a corresponding relationship, and the target parameter range is used to indicate the signal characteristic of a signal whose signal type is a RACH message.

[0110] Optionally, in this embodiment, the target parameter range may be calculated based on a reference signal characteristic of a reference signal whose reference signal type is used to indicate that the reference signal is a reference signal for a RACH message. For example, a reference signal characteristic of a reference signal whose reference signal type is used to indicate that the reference signal is a reference signal for a RACH message is obtained, and an interval range formed by a maximum value and a minimum value of the reference signal characteristic is used as the target parameter range.

[0111] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software and the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0112] Figure 6 is a structural block diagram of an access device for a terminal according to an embodiment of the present application; Figure 6 Shown, including:

[0113] A first acquisition module 62 is configured to acquire a target signal from a physical random access channel PRACH of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH;

[0114] a first classification module 64, configured to classify the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message;

[0115] The access module 66 is configured to, when the target signal type indicates that the target signal is a RACH message, perform an access operation on the target terminal that sends the target signal, wherein the access operation is used to connect the target terminal to the target base station.

[0116] Through the above embodiment, since the reference signal is an air interface signal transmitted before the target signal on the PRACH channel, after obtaining the target signal from the physical random access channel PRACH of the target base station, the target signal is classified by using the reference signal characteristics and reference signal type, so that the currently received target signal can be classified according to the reference signal characteristics of the reference signal already obtained by the base station and the corresponding reference signal type, thereby determining whether the currently received target signal is a RACH message, avoiding false detection of signals in the random access channel, and improving the accuracy of signal detection in the random access channel. The above technical solution solves the problem of low detection efficiency of random access signals in random access channels in related technologies, and achieves the technical effect of improving the detection efficiency of random access signals in random access signals.

[0117] Optionally, the first classification module includes: an input unit for inputting the target signal features of the target signal into a target classification model, wherein the target classification model is obtained by training an initial classification model using the reference signal features marked with the reference signal type; and a first acquisition unit for acquiring the target signal type output by the target classification model.

[0118] Optionally, the device also includes: a second acquisition module, used to obtain a first number of first signals whose first signal type is RACH message from the air interface signal transmitted before the target signal on the PRACH, and obtain a second number of second signals whose second signal type is non-RACH message from the air interface signal transmitted before the target signal on the PRACH, before inputting the target signal feature of the target signal into the target classification model; an extraction module, used to extract the first signal feature of the first signal as a first signal sample, and extract the second signal feature of the second signal as a second signal sample; a labeling module, used to label the first signal sample with the first signal type, and label the second signal sample with the second signal type, to obtain the reference signal feature labeled with the reference signal type as a sample set; a training module, used to train an initial support vector machine model using the sample set to obtain a target support vector machine model as the target classification model.

[0119] Optionally, the device also includes: a third acquisition module, used to obtain the air interface signal transmitted after the reference signal on the PRACH as an update signal after the target signal type output by the target classification model is obtained, when the target classification model meets the target update condition, and obtain the update signal type and update signal characteristics of the update signal; an update module, used to update the target classification model using the update signal characteristics marked with the update signal type to obtain an updated classification model.

[0120] Optionally, the device also includes: a matching module, used to match the target running time of the target classification model with the preset running time before obtaining the air interface signal transmitted after the reference signal on the PRACH as an update signal, wherein the target running time is the time duration for classifying the signal using the target classification model; a first determination module, used to determine that the target classification model does not meet the target update condition when the target running time is less than the preset running time; and a second determination module, used to determine that the target classification model meets the target update condition when the target running time is greater than or equal to the preset running time.

[0121] Optionally, the device also includes: a third determination module, used to determine whether the signal identifier carried by the target signal matches the target signal identifier corresponding to the target base station before classifying the target signal according to the reference signal characteristics and the reference signal type to obtain the target signal type of the target signal, wherein the signal identifier is used to indicate the transmission information of the target signal; an extraction module, used to extract the target signal characteristics of the target signal when the signal identifier matches the target signal identifier, wherein the target signal characteristics include: time advance and received signal strength indication; a second classification module, used to classify the target signal characteristics according to the reference signal characteristics and the reference signal type to obtain the target signal type.

[0122] Optionally, the first classification module includes: a second acquisition unit, used to acquire the target signal characteristics of the target signal; a detection unit, used to detect whether the target signal characteristics fall within a target parameter range, wherein the range threshold of the target parameter range is determined based on the reference signal characteristics and the reference signal type having a corresponding relationship, and the target parameter range is used to indicate the signal characteristics of a signal whose signal type is a RACH message.

[0123] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein when the program is run, any of the above-mentioned terminal access methods is executed.

[0124] Optionally, in this embodiment, the above-mentioned storage medium can be configured to store program code for performing the following steps: obtaining a target signal from a physical random access channel PRACH of the target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; classifying the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, and the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; when the target signal type is used to indicate that the target signal is a RACH message, performing an access operation on the target terminal that sends the target signal, wherein the access operation is used to connect the target terminal to the target base station.

[0125] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any of the above-mentioned terminal access method embodiments.

[0126] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0127] Optionally, in this embodiment, the above-mentioned processor can be configured to perform the following steps through a computer program: obtaining a target signal from a physical random access channel PRACH of the target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; classifying the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, and the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; when the target signal type is used to indicate that the target signal is a RACH message, performing an access operation on the target terminal that sends the target signal, wherein the access operation is used to connect the target terminal to the target base station.

[0128] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0129] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0130] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices. Alternatively, they can be implemented using program code executable by the computing device, so that they can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described can be performed in a different order than herein, or they can be made into separate integrated circuit modules, or multiple modules or steps can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0131] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A terminal access method, characterized in that: include: Acquire a target signal from a physical random access channel (PRACH) of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; classifying the target signal according to a reference signal characteristic and a reference signal type to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; In a case where the target signal type is used to indicate that the target signal is a RACH message, performing an access operation on a target terminal that sends the target signal, wherein the access operation is used to access the target terminal to the target base station; The target signal is classified according to the reference signal characteristics and the reference signal type to obtain the target signal type of the target signal, including: inputting the target signal characteristics of the target signal into a target classification model, wherein the target classification model is obtained by training an initial classification model using the reference signal characteristics marked with the reference signal type; and obtaining the target signal type output by the target classification model, wherein the reference signal characteristics are the time advance and the strength indication of the received signal, and the target signal characteristics are the time advance and the strength indication of the received signal.

2. The method according to claim 1, characterized in that Before inputting the target signal feature of the target signal into the target classification model, the method further includes: Acquire a first number of first signals whose first signal type is RACH messages from air interface signals transmitted on the PRACH before the target signal, and acquire a second number of second signals whose second signal type is non-RACH messages from air interface signals transmitted on the PRACH before the target signal; extracting a first signal feature of the first signal as a first signal sample, and extracting a second signal feature of the second signal as a second signal sample; labeling the first signal samples using the first signal type and labeling the second signal samples using the second signal type, to obtain the reference signal features labeled with the reference signal type as a sample set; The sample set is used to train an initial support vector machine model to obtain a target support vector machine model as the target classification model.

3. The method according to claim 1, characterized in that After obtaining the target signal type output by the target classification model, the method further includes: When the target classification model satisfies a target update condition, obtaining an air interface signal transmitted after the reference signal on the PRACH as an update signal, and obtaining an update signal type and an update signal feature of the update signal; The target classification model is updated using the update signal feature marked with the update signal type to obtain an updated classification model.

4. The method according to claim 3, characterized in that Before acquiring an air interface signal transmitted after the reference signal on the PRACH as an update signal, the method further includes: Matching a target running time of the target classification model with a preset running time, wherein the target running time is a time duration for classifying a signal using the target classification model; When the target running time is less than the preset running time, determining that the target classification model does not meet the target update condition; When the target running time is greater than or equal to the preset running time, it is determined that the target classification model meets the target update condition.

5. A terminal access device, characterized in that: include: A first acquisition module is configured to acquire a target signal from a physical random access channel (PRACH) of a target base station, wherein the target signal is an air interface signal currently transmitted on the PRACH; a first classification module, configured to classify the target signal according to a reference signal characteristic and a reference signal type, to obtain a target signal type of the target signal, wherein the reference signal characteristic is a characteristic of a reference signal, the reference signal is an air interface signal transmitted on the PRACH before the target signal, and the reference signal type is used to indicate whether the reference signal is a RACH message; an access module, configured to, when the target signal type indicates that the target signal is a RACH message, perform an access operation on the target terminal that sends the target signal, wherein the access operation is used to access the target terminal to the target base station; The first classification module includes: an input unit, used to input the target signal characteristics of the target signal into a target classification model, wherein the target classification model is obtained by training an initial classification model using the reference signal characteristics marked with the reference signal type; a first acquisition unit, used to obtain the target signal type output by the target classification model, the reference signal characteristics are the time advance and the strength indication of the received signal, and the target signal characteristics are the time advance and the strength indication of the received signal.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 4 when executed.

7. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 4 through the computer program.

Images