Terminal access mode adaptation method and terminal equipment
Through the prediction model, the problem of insufficient adaptability of monitoring terminals and access methods is solved, and high-quality communication for service data transmission is achieved.
Patent Information
- Application Number
- CN202111215440.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-19
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-10-19
AI Technical Summary
The prior art does not consider the adaptability of the monitoring terminal and the access method, resulting in the communication quality of service data transmission cannot be guaranteed.
By obtaining the performance indicators of each optional communication method and inputting a pre-trained target service adaptation prediction model, predicting the adaptation between each communication method and the target service, and selecting the communication method with the highest adaptation as the optimal access method.
It ensures the communication quality of monitoring terminal service data transmission and meets the performance requirements of different services such as delay, bandwidth, security, reliability and terminal power consumption.
Smart Images

Figure CN114070802B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of power grids, and in particular relates to a terminal access mode adaptation method and terminal equipment. Background Art
[0002] As an important part of the distribution network network management system, distribution business monitoring is the main means to maintain the healthy operation of the power grid and optimize network resources. With the access of massive distribution business status monitoring terminals, the integration of heterogeneous energy systems, and the diversified development of user-side electricity demand, the operation mode of the distribution network has become more complex. Each distribution monitoring business has different requirements for service performance indicators such as latency, bandwidth, security, reliability, and terminal power consumption. Therefore, different monitoring terminals have different requirements for access methods.
[0003] In the prior art, the compatibility between the monitoring terminal and the access mode is not considered, so the communication quality of the monitoring terminal service data transmission cannot be guaranteed. Summary of the invention
[0004] In view of this, the embodiments of the present invention provide a terminal access mode adaptation method and a terminal device to solve the problem that the adaptability of the terminal and the access mode is not considered in the prior art and the quality of the monitoring terminal service data transmission cannot be guaranteed.
[0005] A first aspect of an embodiment of the present invention provides a terminal access mode adaptation method, including:
[0006] For each optional communication mode corresponding to the target service, a first preset number of performance indicators corresponding to the communication mode are obtained, and the first preset number of performance indicators corresponding to the communication mode are input into a pre-trained target service fitness prediction model to obtain fitness between the communication mode and the target service; wherein the target service has a second preset number of optional communication modes;
[0007] The maximum value among the second preset number of adaptability is found, and the communication mode corresponding to the maximum value is used as the optimal communication mode for the target service.
[0008] A second aspect of an embodiment of the present invention provides a terminal access mode adaptation device, including:
[0009] A model prediction module is used to obtain, for each optional communication mode corresponding to the target service, a first preset number of performance indicators corresponding to the communication mode, and input the first preset number of performance indicators corresponding to the communication mode into a pre-trained target service fitness prediction model to obtain fitness between the communication mode and the target service; wherein the target service has a second preset number of optional communication modes;
[0010] The result output module is used to find the maximum value among the second preset number of adaptability, and use the communication mode corresponding to the maximum value as the optimal communication mode for the target service.
[0011] A third aspect of an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the terminal access mode adaptation method provided in the first aspect of the embodiment of the present invention are implemented.
[0012] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the terminal access mode adaptation method provided in the first aspect of the embodiment of the present invention are implemented.
[0013] The embodiment of the present invention provides a terminal access mode adaptation method and terminal device, the method comprising: for each optional communication mode corresponding to the target service, obtaining a first preset number of performance indicators corresponding to the communication mode, and inputting the first preset number of performance indicators corresponding to the communication mode into a pre-trained target service adaptation prediction model to obtain the adaptation between the communication mode and the target service; finding the maximum value among the second preset number of adaptations, and using the communication mode corresponding to the maximum value as the optimal communication mode for the target service. The embodiment of the present invention adopts a model to predict the adaptation between the target service and various communication modes, and further selects the communication mode with the highest adaptation as the access mode of the target service, selects different communication modes for different services, and ensures the communication quality of the data transmission of the monitoring terminal service. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0015] Figure 1 It is a schematic diagram of an implementation flow of a terminal access mode adaptation method provided by an embodiment of the present invention;
[0016] Figure 2 It is a power distribution monitoring service performance indicator system provided by an embodiment of the present invention;
[0017] Figure 3 is a schematic diagram of a terminal access mode adaptation device provided by an embodiment of the present invention;
[0018] Figure 4It is a schematic diagram of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0019] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0020] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.
[0021] refer to Figure 1 , an embodiment of the present invention provides a terminal access mode adaptation method, comprising:
[0022] S101: For each optional communication mode corresponding to the target service, a first preset number of performance indicators corresponding to the communication mode is obtained, and the first preset number of performance indicators corresponding to the communication mode is input into a pre-trained target service fitness prediction model to obtain fitness between the communication mode and the target service; wherein the target service has a second preset number of optional communication modes;
[0023] S102: Find the maximum value among a second preset number of adaptability degrees, and use the communication mode corresponding to the maximum value as the optimal communication mode for the target service.
[0024] Distribution business status monitoring involves a wide variety of services, and each service has different performance requirements for network latency, bandwidth, security, reliability, and terminal power consumption. In the process of transmitting monitoring data such as power equipment operation data and environmental information, there are also a variety of communication methods available, that is, access methods, such as wired access methods such as power line carriers and optical fibers, and wireless access methods such as Bluetooth, WiFi, 4G / 5G wireless public networks, and ZigBee.
[0025] Since the communication method affects the performance indicators of the service, different services have different performance indicator requirements, so different services have different adaptability to the same communication method. Since the adaptability of various performance indicators of the same service to different communication methods is different, the adaptability of the same service to different access methods is also different.
[0026] In the embodiment of the present invention, in view of the characteristics of the power distribution monitoring service and its differentiated service requirements for performance requirements such as latency, bandwidth, reliability, security and terminal power consumption, for the target service, a target service adaptability prediction model is established to predict the adaptability of the target service and various communication methods, and a second preset number of adaptabilities is obtained. The communication method with the highest adaptability is further selected as the access method of the target service, and different communication methods are selected for different services, thereby ensuring the communication quality of the monitoring terminal service data transmission. Among them, the second preset number is the number of optional communication methods.
[0027] For example, if there are four optional communication modes, multiple performance indicators corresponding to the four communication modes are respectively input into the target service adaptability prediction model to obtain the adaptability of the four communication modes and the target service, and then the communication mode with the highest adaptability is selected from the four adaptabilities for access, thereby ensuring the communication quality of the monitoring terminal service data transmission.
[0028] In some embodiments, before S101, the method may further include:
[0029] S103: Acquire multiple performance indicator sets corresponding to the target business;
[0030] S104: Using multiple performance indicator sets as training samples to train a basic prediction model, and obtaining a pre-trained target service fitness prediction model; wherein each performance indicator in the performance indicator set corresponds one-to-one to a first preset number of performance indicators.
[0031] In some embodiments, the basic prediction model may be a neural network model.
[0032] The neural network has a self-learning function. By inputting the acquired historical data into the neural network, the network will learn the influence of different indicators on the communication mode through the self-learning function. At the same time, the neural network has the ability of high-speed convergence. For a high-dimensional adaptation problem, a large amount of calculation is often required. By using the high-speed computing power of the computer using the neural network, the rapid iterative convergence of a large number of neuron weights can be achieved, which is suitable for the embodiments of the present invention.
[0033] In some embodiments, S104 may include:
[0034] S1041: Taking the preset fitness as the expected output, and inputting multiple performance indicator sets into the basic prediction model for training, to obtain a pre-trained target business fitness prediction model.
[0035] In some embodiments, S1041 may include:
[0036] 1. Initialize the parameters of the basic prediction model;
[0037] 2. Inputting a first performance indicator set into the basic prediction model to calculate a first degree of fitness; wherein the first performance indicator set is any one of the multiple performance indicator sets;
[0038] 3. Calculate the mean square error between the first fitness degree and the preset fitness degree, and determine whether the mean square error is less than a preset value;
[0039] 4. If the mean square error is not less than the preset value, the parameters of the basic prediction model are adjusted, and the step of inputting the first performance indicator set into the basic prediction model and calculating the first fitness degree is repeatedly executed;
[0040] 5. If the mean square error is less than the preset value, the training is completed and the pre-trained target business fitness prediction model is output.
[0041] Specifically, the neural network model consists of three layers: input layer, hidden layer, and output layer. The input layer is the performance index of the power distribution business communication network, and the output layer is the comprehensive evaluation result of all performance demand indicators. The number of hidden layers is generally obtained according to the following empirical formula:
[0042]
[0043] Among them, o can be any constant between 1 and 10.
[0044] Using multiple performance indicator sets as training data, the weights and thresholds of each neuron are determined. The training process is as follows:
[0045] 1) Let the initial connection weights of the output layer and the hidden layer be w mi , the initial connection weight from the hidden layer to the output layer is w i , the input layer threshold is γ i , hidden layer threshold θ i , output layer threshold β, learning rate η, the expected output is
[0046] 2) Select the sigmoid function as the hidden layer transfer function. The sigmoid function is expressed as:
[0047]
[0048] 3) Calculate the input and output of each neuron in the hidden layer, substitute a performance indicator set, and first calculate the input of each neuron in the hidden layer:
[0049]
[0050] The input of each neuron in the output layer is further calculated through the transfer function and the hidden layer threshold:
[0051] k i=f(h i )+θ i
[0052] Further calculations yield the final output:
[0053]
[0054] 4) According to the mean square error formula Calculate the error E. If E is less than the preset error range ε, execute step 9); otherwise, calculate the generalized error of the output layer.
[0055] 5) Calculate the generalized errors of each unit in the output layer and hidden layer, which are:
[0056]
[0057] e i =ω i d.k i ·(1-k i )
[0058] 6) Adjust the connection weights w between the hidden layer and the output layer i And the output layer threshold β:
[0059]
[0060] 7) Adjust the connection weights w between the input layer and the hidden layer mi and hidden layer threshold θ i :
[0061]
[0062] 8) Go to step 3) and substitute the next performance indicator set to continue learning and training.
[0063] 9) After the network training is completed, the current network weights are recorded to obtain the pre-trained target business fitness prediction model.
[0064] In the embodiment of the present invention, the multiple performance indicator sets used as training samples are the demand indicators of the target business, that is, the demand of the target business for each performance indicator, that is, the performance indicator can meet the application demand of the target business, and the performance indicator has a good degree of fit with the target business. For example, in the embodiment of the present invention, the demand values of each performance indicator of the target business can be given by several experts through the expert scoring method to form several training samples, and the preset fitness (expected fitness output) can be 1, and the model is trained to obtain a pre-trained target business fitness prediction model.
[0065] Furthermore, the network weights and output thresholds of the neural network model have been determined through the above steps, and the actual performance indicators of various communication methods arema Input the above model to get the input of each neuron in the hidden layer:
[0066]
[0067] According to the transfer function, the input of the output layer is obtained as:
[0068] k i =f(h i )+θ i
[0069] Further obtain the fitness of the final output:
[0070]
[0071] Compare the adaptability of all access methods output, and select the access method with the highest adaptability as the actual access method for the target service. If the performance indicators of the communication method are closer to the demand indicators of the target service, the higher the adaptability, and the more it can meet the needs of the target service; if the performance indicators of the communication method are farther away from the demand indicators of the target service, the lower the adaptability, and the less it can meet the needs of the target service. Therefore, the communication method with the highest adaptability is selected as the access method for the target service, so as to achieve reasonable adaptation of the differentiated service requirements of the power distribution service and the access method, and ensure the communication quality of the terminal.
[0072] Among them, different target businesses correspond to different models.
[0073] In some embodiments, S103 may include:
[0074] S1031: Obtain multiple performance indicator sets corresponding to the target business based on the expert scoring method.
[0075] In an embodiment of the present invention, each performance indicator in the performance indicator set corresponds one-to-one to a first preset number of performance indicators. The selection of performance indicators needs to accurately express the differentiated application requirements of each business. Therefore, in an embodiment of the present invention, a multidimensional performance indicator set is constructed for the differentiated requirements of power distribution monitoring business.
[0076] 1. Common index extraction: Common characteristics are extracted according to the differentiated needs and application scenarios of power distribution monitoring services to form first-level performance indicators, including technical indicators and economic indicators. Technical indicators are mainly used to assess the service quality of communication methods, while economic indicators are mainly used to measure the construction and application costs of the selected communication methods, ensuring that costs are reduced as much as possible without affecting business applications.
[0077] 2. Sub-indicator analysis: Each first-level performance indicator is decomposed to form several sub-indicators, until the bottom-level sub-indicator is a sub-indicator that can directly obtain the indicator value through quantitative detection or qualitative evaluation. Combined with the technical characteristics of each communication method, the technical sub-indicators mainly include communication indicators, security indicators, and terminal energy consumption indicators, while the economic sub-indicators mainly include network deployment costs, traffic costs, etc.
[0078] For example, refer to Figure 2 , forming a performance indicator system consisting of the first-level adaptation indicator and sub-indicators at all levels, achieving full coverage of key performance indicators such as communication rate, network coverage, transmission delay, reliability, security, terminal power consumption, construction cost, and business management cost of power distribution monitoring services, and each performance indicator forms a performance indicator set in the embodiment of the present invention. It is also possible to select several of the above performance indicators to form a performance indicator set according to actual application requirements, and there is no limitation on this.
[0079] In order to comprehensively evaluate the quantitative values of the requirements of different power distribution services for the above-mentioned underlying sub-indicators, experts and relevant staff in the fields of electricity and communications are invited as evaluators to provide relevant basis, evaluate each indicator, and give specific values. For example, multiple evaluators are invited to score each performance indicator to obtain multiple performance indicator sets, thereby forming training samples.
[0080] In some embodiments, after S103, the method may further include:
[0081] S105: for each performance indicator set, standardize each performance indicator in the performance indicator set to obtain a standardized performance indicator set;
[0082] S104 may include:
[0083] S1042: Use the multiple standardized performance indicator sets as training samples to train the basic prediction model to obtain a pre-trained target business fitness prediction model.
[0084] In order to improve the training accuracy in the embodiment of the present invention, various performance indicators may also be standardized.
[0085] For performance indicators such as transmission rate and transmission bandwidth, the larger the value, the better, the first formula can be used to perform standardized calculation on the performance indicator;
[0086] The first formula is:
[0087]
[0088] For performance indicators such as transmission delay, the smaller the value, the better, the second formula can be used to perform standardized calculation on the performance indicator;
[0089] The second formula is:
[0090]
[0091] For indicators that cannot be directly quantified, such as safety and economy, they have a certain degree of ambiguity and cannot be directly measured. They need to be quantitatively evaluated using the scoring method of industry experts. This method is based on the above-mentioned evaluators' grading of their performance based on their own practical experience. Refer to Table 1.
[0092] Table 1 Grading scale
[0093]
[0094] There are 5 rating levels, namely weak, relatively weak, moderate, relatively strong, and strong, with a maximum rating of 5. The industry expert scoring method is used, combined with the scoring rules shown in the above table, and the third formula is used to standardize the calculation of the performance indicator;
[0095] The third formula is:
[0096]
[0097] Among them, x m,n The mth performance indicator in the nth performance indicator set; m = 1, 2, ..., M, M is a first preset number; n = 1, 2, ..., N, N is the number of the plurality of performance indicator sets; x m,max is the maximum value of the performance index, x m,min is the minimum value of the performance index, r m,n For x m,n The normalized value.
[0098] Based on the above, a standardized performance indicator set is finally obtained. However, the standardized performance indicator set can only represent the subjective assumptions of different evaluators on the performance requirements of the power distribution monitoring service. Therefore, in the embodiment of the present invention, a neural network model is further used to integrate the opinions of evaluators from various industries, fields, and levels to determine more reasonable business demand indicators, providing a theoretical basis for the adaptation of subsequent communication methods.
[0099] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0100] Corresponding to the above embodiment, reference Figure 3 The embodiment of the present invention further provides a terminal access mode adaptation device, including:
[0101] The model prediction module 21 is used to obtain a first preset number of performance indicators corresponding to each optional communication mode corresponding to the target service, and input the first preset number of performance indicators corresponding to the communication mode into a pre-trained target service fitness prediction model to obtain the fitness of the communication mode and the target service; wherein the target service has a second preset number of optional communication modes;
[0102] The result output module 22 is used to find the maximum value among the second preset number of adaptability, and use the communication mode corresponding to the maximum value as the optimal communication mode for the target service.
[0103] In some embodiments, the above device may further include:
[0104] A training sample acquisition module 23 is used to acquire multiple performance indicator sets corresponding to the target business;
[0105] The model training module 24 is used to train the basic prediction model using multiple performance indicator sets as training samples to obtain a pre-trained target business fitness prediction model; wherein each performance indicator in the performance indicator set corresponds one-to-one to a first preset number of performance indicators.
[0106] In some embodiments, the basic prediction model may be a neural network model.
[0107] In some embodiments, the model training module 24 may include:
[0108] The training unit 241 is used to take the preset fitness as the expected output and input multiple performance indicator sets into the basic prediction model for training to obtain a pre-trained target business fitness prediction model.
[0109] In some embodiments, the training unit 24 may be specifically configured to:
[0110] 1. Initialize the parameters of the basic prediction model;
[0111] 2. Inputting a first performance indicator set into the basic prediction model to calculate a first degree of fitness; wherein the first performance indicator set is any one of the multiple performance indicator sets;
[0112] 3. Calculate the mean square error between the first fitness degree and the preset fitness degree, and determine whether the mean square error is less than a preset value;
[0113] 4. If the mean square error is not less than the preset value, the parameters of the basic prediction model are adjusted, and the step of inputting the first performance indicator set into the basic prediction model and calculating the first fitness degree is repeatedly executed;
[0114] 5. If the mean square error is less than the preset value, the training is completed and the pre-trained target business fitness prediction model is output.
[0115] In some embodiments, the training sample acquisition module 23 may be specifically used to obtain a plurality of performance indicator sets corresponding to the target business based on an expert scoring method.
[0116] In some embodiments, the above device may further include:
[0117] A standardization module 25 is used to standardize each performance indicator in each performance indicator set to obtain a standardized performance indicator set;
[0118] The model training module 24 can be specifically used to: use a plurality of standardized performance indicator sets as training samples to train the basic prediction model, and obtain a pre-trained target business fitness prediction model.
[0119] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the terminal device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0120] Figure 4 is a schematic block diagram of a terminal device provided by an embodiment of the present invention. Figure 4 As shown, the terminal device 4 of this embodiment includes: one or more processors 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned terminal access mode adaptation method embodiments are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned terminal access mode adaptation device embodiment are realized, for example Figure 3 The functions of modules 21 to 22 are shown.
[0121] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units are stored in the memory 41, and are executed by the processor 40 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal device 4. For example, the computer program 42 may be divided into a model prediction module 21 and a result output module 22.
[0122] The model prediction module 21 is used to obtain a first preset number of performance indicators corresponding to each optional communication mode corresponding to the target service, and input the first preset number of performance indicators corresponding to the communication mode into a pre-trained target service fitness prediction model to obtain the fitness of the communication mode and the target service; wherein the target service has a second preset number of optional communication modes;
[0123] The result output module 22 is used to find the maximum value among the second preset number of adaptability, and use the communication mode corresponding to the maximum value as the optimal communication mode for the target service.
[0124] Other modules or units are not described in detail here.
[0125] The terminal device 4 includes but is not limited to a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of a terminal device and does not constitute a limitation on the terminal device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 4 may also include an input device, an output device, a network access device, a bus, etc.
[0126] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
[0127] The memory 41 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The memory 41 may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device. Further, the memory 41 may also include both an internal storage unit of the terminal device and an external storage device. The memory 41 is used to store the computer program 42 and other programs and data required by the terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
[0128] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0129] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0130] In the embodiments provided in the present application, it should be understood that the disclosed terminal devices and methods can be implemented in other ways. For example, the terminal device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0133] If the integrated module / 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 computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0134] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A terminal access mode adaptation method, characterized in that: include: For each optional communication mode corresponding to the target service, a first preset number of performance indicators corresponding to the communication mode are obtained, and the first preset number of performance indicators corresponding to the communication mode are input into a pre-trained target service fitness prediction model to obtain fitness between the communication mode and the target service; wherein the target service has a second preset number of optional communication modes; Finding a maximum value among a second preset number of adaptability degrees, and using a communication mode corresponding to the maximum value as an optimal communication mode for the target service; Before obtaining, for each optional communication mode corresponding to the target service, a first preset number of performance indicators corresponding to the communication mode, and inputting the first preset number of performance indicators corresponding to the communication mode into a pre-trained target service fitness prediction model to obtain the fitness of the communication mode and the target service, the method further includes: Acquire multiple performance indicator sets corresponding to the target business; Using the multiple performance indicator sets as training samples to train the basic prediction model, to obtain the pre-trained target service fitness prediction model; Wherein, each performance indicator in the performance indicator set corresponds one-to-one to the first preset number of performance indicators; The basic prediction model is a neural network model; After acquiring the multiple performance indicator sets corresponding to the target service, the method further includes: For each performance indicator set, each performance indicator in the performance indicator set is standardized to obtain a standardized performance indicator set; The step of training the basic prediction model using the multiple performance indicator sets as training samples to obtain the pre-trained target service fitness prediction model includes: Using a plurality of standardized performance indicator sets as training samples to train the basic prediction model, thereby obtaining the pre-trained target service fitness prediction model; When the performance indicator is a transmission rate or a transmission bandwidth, the first formula is used to perform a standardized calculation on the performance indicator; The first formula is: When the performance indicator is transmission delay, a second formula is used to perform standardized calculation on the performance indicator; The second formula is: When the performance index is safety or economy, the performance index is determined by an expert scoring method, and the third formula is used to perform standardized calculation on the performance index; The third formula is: Among them, x m,n The mth performance indicator in the nth performance indicator set; m=1, 2, ..., M, M is the first preset number; n=1, 2, ..., N, N is the number of the plurality of performance indicator sets; x m,max is the maximum value of the performance index, x m,min is the minimum value of the performance index, r m,n For x m,n The normalized value.
2. The terminal access mode adaptation method according to claim 1, characterized in that: The step of training the basic prediction model using the multiple performance indicator sets as training samples to obtain the pre-trained target service fitness prediction model includes: The preset fitness degree is taken as the expected output, and the multiple performance indicator sets are input into the basic prediction model for training to obtain the pre-trained target business fitness degree prediction model.
3. The terminal access mode adaptation method according to claim 2, characterized in that: The method of taking the preset fitness as the expected output and inputting the multiple performance indicator sets into the basic prediction model for training to obtain the pre-trained target business fitness prediction model includes: Initializing parameters of the basic prediction model; Inputting a first performance indicator set into the basic prediction model to calculate a first degree of fitness; wherein the first performance indicator set is any one of the multiple performance indicator sets; Calculating a mean square error between the first fitness degree and the preset fitness degree, and determining whether the mean square error is less than a preset value; If the mean square error is not less than the preset value, the parameters of the basic prediction model are adjusted, and the step of inputting the first performance indicator set into the basic prediction model and calculating the first fitness degree is repeatedly performed; If the mean square error is less than the preset value, the training is completed and the pre-trained target business fitness prediction model is output.
4. The terminal access mode adaptation method according to any one of claims 1 to 3, characterized in that: The obtaining of multiple performance indicator sets corresponding to the target service includes: Based on the expert scoring method, a plurality of performance indicator sets corresponding to the target business are obtained.
5. A terminal access mode adaptation device, characterized in that: include: A model prediction module, for obtaining, for each optional communication mode corresponding to a target service, a first preset number of performance indicators corresponding to the communication mode, and inputting the first preset number of performance indicators corresponding to the communication mode into a pre-trained target service fitness prediction model to obtain fitness between the communication mode and the target service; wherein the target service has a second preset number of optional communication modes; A result output module, used to find the maximum value among the second preset number of adaptability, and use the communication mode corresponding to the maximum value as the optimal communication mode for the target service; A training sample acquisition module, used to acquire multiple performance indicator sets corresponding to the target business; A model training module, used to train a basic prediction model using the multiple performance indicator sets as training samples to obtain the pre-trained target business fitness prediction model; Wherein, each performance indicator in the performance indicator set corresponds one-to-one to the first preset number of performance indicators; The basic prediction model is a neural network model; The above device also includes: A standardization module, used for standardizing each performance indicator in each performance indicator set to obtain a standardized performance indicator set; The model training module is specifically used to: train the basic prediction model using a plurality of standardized performance indicator sets as training samples to obtain the pre-trained target business fitness prediction model; When the performance indicator is a transmission rate or a transmission bandwidth, the first formula is used to perform a standardized calculation on the performance indicator; The first formula is: When the performance indicator is transmission delay, a second formula is used to perform standardized calculation on the performance indicator; The second formula is: When the performance index is safety or economy, the performance index is determined by an expert scoring method, and the third formula is used to perform standardized calculation on the performance index; The third formula is: Among them, x m,n The mth performance indicator in the nth performance indicator set; m=1, 2, ..., M, M is the first preset number; n=1, 2, ..., N, N is the number of the plurality of performance indicator sets; x m,max is the maximum value of the performance index, x m,min is the minimum value of the performance index, r m,n For x m,n The normalized value.
6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the terminal access mode adaptation method according to any one of claims 1 to 4 are implemented.
7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the terminal access mode adaptation method according to any one of claims 1 to 4 are implemented.
