A resource configuration method and device of an RF control system, a storage medium and an equipment

Abstract

The application provides a resource configuration method and device of an RF control system, a storage medium and equipment, and the method comprises the following steps: acquiring a plurality of performance indexes of user preferences and a first relationship model constructed in advance, the first relationship model being used for representing the influence relationship between each resource item of the RF control system and each performance index; generating an initial population containing a plurality of individuals, determining the evaluation result of any individual under the plurality of performance indexes based on the first relationship model, one individual representing one resource configuration strategy, and different resource configuration strategies corresponding to different resource item combinations; selecting the individual from the initial population based on the evaluation result to realize population iterative optimization through mutation to obtain an optimized population, and selecting a high-quality population from the optimized population; and configuring the system resources of the RF control system based on the high-quality individual in the high-quality population. The application can ensure that the resource configuration of the RF control system meets the individualized system performance requirements of the user, and can balance the plurality of performance indexes.

Description

TECHNICAL FIELD

[0001] The present application relates to the wireless technology field, and in particular to a resource configuration method and device of an RF control system, a storage medium and equipment. BACKGROUND

[0002] With the continuous development of the wireless or radio frequency (RF) control technology field, more and more RF control systems have also emerged. The RF control system is a key system for controlling a controlled model such as a model airplane, a drone, an unmanned vehicle, etc. The performance of the RF control system is crucial to the safety and controllability of the controlled model, and the system performance of the RF control system cannot be separated from the configuration of system resources.

[0003] At present, a fixed single resource configuration strategy is usually adopted for the resource configuration of the RF control system. However, the performance of the RF control system is more, and different users have different preferences for the various system performances of the RF control system. If a fixed single resource configuration strategy is adopted, the performance preference of the RF control system is also fixed and single, which will cause the system resource configuration of the RF control system to be unable to meet the individualized system performance requirements of the users. Therefore, how to ensure that the system resource configuration of the RF control system meets the individualized system performance requirements of the users is a technical problem to be solved in the RF control technology field. SUMMARY

[0004] The main purpose of the present application is to provide a resource configuration method, device, storage medium and equipment based on an RF control system, aiming at solving the technical problem that the system resource configuration of the RF control system in the prior art cannot meet the individualized system performance requirements of the users.

[0005] To achieve the above-mentioned purpose, the present application provides a resource configuration method of an RF control system, which comprises:

[0006] obtaining a plurality of performance indicators to which a user is inclined, and a first relationship model constructed in advance, the first relationship model being used to represent the influence relationship between each resource item of the RF control system and each performance indicator;

[0007] generating an initial population containing a plurality of individuals, determining the evaluation result of any individual under a plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual, one individual representing one resource configuration strategy, and different resource configuration strategies corresponding to different resource item combinations;

[0008] selecting individuals from the initial population based on the evaluation result to realize population iterative optimization through mutation, obtaining an optimized population, and selecting a high-quality population from the optimized population, any individual in the high-quality population meeting a plurality of performance indicators.

[0009] configuring system resources of the RF control system based on the high-quality individuals in the high-quality population.

[0010] To achieve the above object, the application further provides a resource configuration device of an RF control system, which comprises:

[0011] an acquisition unit, configured to acquire a plurality of performance indexes of user preferences and a first relationship model constructed in advance, the first relationship model being used to represent an influence relationship between each resource item of the RF control system and each performance index;

[0012] a generation unit, configured to generate an initial population containing a plurality of individuals;

[0013] a determination unit, configured to determine an evaluation result of any individual under a plurality of performance indexes based on the first relationship model and each resource item corresponding to the individual, one individual representing one resource configuration strategy, and different resource configuration strategies corresponding to different resource item combinations;

[0014] an optimization unit, configured to select individuals from the initial population based on the evaluation result to realize population iterative optimization through mutation, obtain an optimized population, and select a high-quality population from the optimized population;

[0015] a configuration unit, configured to configure system resources of the RF control system based on high-quality individuals in the high-quality population.

[0016] To achieve the above object, the application provides a resource configuration device of an RF control system, which comprises a memory and a processor, the memory stores a resource configuration program of the RF control system, and the processor realizes the steps of the resource configuration method of the RF control system as described above when executing the resource configuration program of the RF control system.

[0017] The application provides a resource configuration method and device of an RF control system, a storage medium and equipment, and can obtain a plurality of performance indexes of user preferences, and a first relationship model constructed in advance, which is used to represent the influence relationship between each resource item of the RF control system and each performance index; an initial population containing a plurality of individuals is generated, and the evaluation results of any individual under a plurality of performance indexes are determined based on the first relationship model and each resource item corresponding to the individual, one individual represents one resource configuration strategy, and different resource configuration strategies correspond to different resource item combinations. Meanwhile, the application can select individuals from the initial population based on the evaluation results to realize population iterative optimization through mutation, obtain an optimized population, and any individual in the optimized population meets a plurality of performance indexes, and the system resources of the RF control system are configured based on the excellent individuals in the optimized population. Compared with the prior art, the application can support users to set or select a plurality of performance indexes of their preferences, can meet the performance index preference requirements of different users, can construct the first relationship model in advance, and then can continuously perform iterative optimization on the population containing a plurality of resource configuration strategies based on the first relationship model and the plurality of system performance indexes of user preferences, obtain an optimized population, select an excellent population (any individual simultaneously meets a plurality of performance indexes of user preferences) from the optimized population based on the scoring results, and can perform system resource configuration based on the excellent individuals in the excellent population. That is, the application can generate an excellent resource configuration strategy that simultaneously meets a plurality of performance indexes of user preferences, so that the RF control system can meet the individualized preference requirements of users on system performance indexes when performing resource configuration, and can balance a plurality of performance indexes of the RF control system at the same time. In addition, in the embodiment of the application, the excellent resource configuration strategy can be obtained without manual testing, verification and fine adjustment of resource items by technical personnel, which can not only avoid the problem that the resource configuration effects are inconsistent due to different understandings of technical personnel, but also avoid the problem that the overall system performance of the RF control system is affected due to improper setting of resource items. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the schemes in the application, the drawings needed in the description of the embodiments of the application will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a flowchart of a resource configuration method of an RF control system provided by the embodiment of the application;

[0020] Figure 2 is a flowchart of another resource configuration method of an RF control system provided by the embodiment of the application;

[0021] Figure 3 is a resource configuration device structure schematic diagram of an RF control system provided by an embodiment of the present application.

[0022] Figure 4 is a basic structure block diagram of a resource configuration device of an RF control system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0023] The resource configuration method of the RF control system provided by the embodiment of the present application is applied to the resource configuration method device of the RF control system. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs; the terms used in the specification of the application are only for the purpose of describing the specific embodiments and are not intended to limit the present application; the terms "include" and "have" and any variations thereof in the specification and claims of the present application and the above description of drawings are intended to cover the non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of the present application or the above description of drawings are used to distinguish different objects, not to describe a specific order.

[0024] In this paper, the term "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] In order to better understand the technical scheme of the present application by those skilled in the art, the technical scheme in the embodiment of the present application will be described clearly and completely in conjunction with the drawings.

[0026] With the continuous development of wireless or radio frequency (Radio Frequency, RF) control technology field, more and more RF control systems also appear, the RF control system is a key system for controlling the controlled model such as model aircraft, unmanned aerial vehicle, unmanned vehicle, etc. The system performance of the RF control system is crucial to the safety and controllability of the controlled model, and the system performance of the RF control system cannot be separated from the resource configuration.

[0027] Currently, in order to ensure that the system performance of the RF control system reaches the expected performance, a fixed single resource allocation strategy is usually adopted for resource allocation of the RF control system. However, the system performance of the RF control system is relatively more, different users have different preferences for the system performance of the RF control system, and the system performance preferences of the RF control system are also fixed and single if the fixed single resource allocation strategy is adopted, which can cause that the system resource allocation of the RF control system cannot meet the personalized system performance requirements of the users. Therefore, how to ensure that the system resource allocation of the RF control system meets the personalized system performance requirements of the users is a technical problem to be solved in the RF control technical field. In addition, multiple performance indicators cannot be balanced at the same time, therefore, how to ensure that the system resource allocation of the RF control system can simultaneously balance and meet the multiple performance indicators preferred by the users is also a technical problem to be solved in the RF control technical field.

[0028] Or in order to meet the personalized system performance requirements of the users, the users can be allowed to modify part of the resource items of the RF control system, and then based on the resource items selected or set by the users, the resource allocation strategy is adjusted for resource allocation of the RF control system. However, if this way is adopted, the generated resource allocation strategy is limited and is not planned from the system as a whole, which can cause that multiple performance indicators cannot be balanced, and there is a risk of system abnormality. For example, a certain resource item is adjusted too high, the resource consumption of a single module is too high, and the system cannot process other modules.

[0029] In addition, the fixed single resource allocation strategy is usually pre-configured by the technical personnel based on the personal technical understanding, that is, the technical personnel pre-allocate the system resources, and then test and verify the system stability and effect for fine tuning. However, the system resource allocation takes a long time, the resource allocation effect is unstable, and there are obvious differences in the allocation effects of different people, thereby causing that the efficiency and uniformity of the system resource allocation of the RF control system are poor.

[0030] To achieve the above-mentioned purpose, an embodiment of the present application provides a resource allocation method of an RF control system, which is applied to a resource allocation device of the RF control system, as shown in the figure, the method comprises the following steps. Figure 1 As shown in the figure, the method comprises the following steps.

[0031] Step 101, acquiring multiple performance indicators preferred by the users and a first relationship model pre-constructed, the first relationship model is used to represent the influence relationship between each resource item and each performance indicator of the RF control system.

[0032] In an optional embodiment of the present application, the step of obtaining the performance indicators preferred by the user can specifically include: presenting a configuration interface so that the user can set or select the performance indicators preferred by the user on the configuration interface and trigger the generation of a configuration instruction; and obtaining the performance indicators preferred by the user in response to the generation of the configuration instruction. Specifically, an input box can be set on the configuration interface so that the user inputs the indicator values corresponding to the performance indicators; and any performance indicator value corresponding to the indicator value constraint condition, when the user sets the performance indicators preferred by the user in the form of an input box, it can be detected whether the performance indicator value input by the user exceeds the constraint condition, and if so, the input box is emptied and the user is reminded to re-input. A slide bar or a drop-down box can also be set on the configuration interface, and the user can select the performance indicators by pulling the slide bar or selecting the performance indicators from the drop-down box.

[0033] In another optional embodiment of the present application, the resource items of the RF control system can include: a system operating frequency A1, a timing allocation B1, and a module component control C1. Specifically, the timing allocation B1 can include a fan cooling time slot proportion B11 and a control function time slot proportion B12; and the module component control C1 can include: a radio frequency setting C11, an operation module C12, a screen module C13, a vibration module C14, a loudspeaker component C15, a lamp component C16, and a fan cooling component C17. The performance indicators of the RF control system can include: power consumption D1, endurance E1, temperature E2, the number of control functions E3, radio frequency performance E4, system stability E5, system operation experience F1, and control operation experience F2. The radio frequency performance E4 can specifically include: control distance E41, anti-interference performance E42, and delay performance E43. The first relationship model can be in the form of a formula, a function, a mapping table, or a matrix mapping, which is not limited in the embodiments of the present application. For example, the resource items of the RF control system are ; the performance indicators of the RF control system are , and the first relationship model can be ;

[0034] In order to better explain the embodiments of the present application, Table 1 is provided herein to explain and describe the resource items of the RF control system. It should be emphasized that Table 1 is only used to explain and describe the resource items and facilitate the subsequent example description of the resource configuration method of the embodiments of the present application, and is not intended to limit the resource items involved in the RF control system.

[0035] Table 1

[0036]

[0037] To better explain the embodiments of the present application, the embodiments of the present application provide Table 2 to explain the performance indicators of the RF control system. It should be emphasized that Table 2 is only for the purpose of explaining the performance indicators and facilitating the subsequent example description of the resource configuration method of the embodiments of the present application, and is not intended to limit the performance indicators involved in the RF control system.

[0038] Table 2

[0039]

[0040] To better illustrate the first relationship model, for example, the influence relationship between the power consumption D1 and the system operating frequency A1 can be as follows: , wherein the basic power consumption is 20W, and the power consumption D1 increases by for each 1GHz increase in the system operating frequency A1; for another example, the influence relationship between the system stability E5 and the operation module C12 and the fan cooling assembly C17 can be as follows: , wherein the basic stability is 90%, the system stability E5 increases by 2% for each unit of computing power of the operation module C12, and the system stability E5 increases by 1% for each gear of the fan cooling assembly C17. In the embodiments of the present application, different performance indicators in the first relationship model can be affected by different resource items, or can be affected by the same resource item, can be affected by one resource item, or can be affected by multiple resource items; the same resource item can have different effects on different system performance indicators, and the embodiments of the present application do not enumerate the first relationship model.

[0041] For the embodiments of the present application, the first relationship model is used to represent the influence relationship between the various resource items and the various performance indicators, and the resource configuration method of the RF control system further comprises: pre-constructing the first relationship model. The steps of constructing the first relationship model can include: obtaining the value range of each resource item, and performing a performance control variable experiment on each resource item to obtain the test values of each performance indicator of each resource item at different values; analyzing the test values of each performance indicator of each resource item at different values to obtain the influence relationship between each resource item and each performance indicator; and constructing the first relationship model based on the influence relationship obtained by the analysis.

[0042] It should be noted that when performing the performance control variable experiment on each resource item, in order to ensure the accuracy of each resource item and the test values of each performance indicator of each resource item at different values and not to affect the normal use of the RF control system, the test values of each resource item and each performance indicator need to be repeatedly verified, and after confirming that the verification is correct, the test values of each performance indicator of each resource item at different values are analyzed, and the first relationship model is constructed.

[0043] Step 102, generating an initial population containing a plurality of individuals, determining an evaluation result of any individual under a plurality of performance indexes based on the first relationship model and each resource item corresponding to any individual, one individual representing one resource configuration strategy, different resource configuration strategies corresponding to different resource item combinations.

[0044] In an optional embodiment of the present application, the evaluation result can be represented by fitness or score. For the RF control system, the units or physical quantities (such as time, temperature, quantity, etc.) of different performance indexes can be different. The first relationship model can further include rules for normalizing the physical quantities of the performance indexes or score rules, so that each performance index can be evaluated for the individual in the same evaluation system. If the first relationship model does not include rules for normalizing the physical quantities of the performance indexes or score rules, the physical quantities of any individual under any user-set performance index can be calculated based on the first relationship model; then the physical quantities under each performance index are converted into score form based on the preset normalization rules or the preset score rules, and the individuals in the initial population are evaluated to obtain the evaluation result. For example, the generated initial population has 100 individuals, that is, 100 resource configuration strategies. For each resource configuration strategy, the score under any system performance can be calculated.

[0045] Step 103, selecting individuals from the initial population based on the evaluation result to realize population iterative optimization through mutation, obtaining an optimized population, and selecting a high-quality population from the optimized population, any individual in the high-quality population satisfying a plurality of performance indexes.

[0046] For the embodiment of the present application, the specific process of selecting individuals from the initial population based on the evaluation result to realize population iterative optimization and obtain an optimized population can include:

[0047] 1. Selecting a batch of individuals with the highest scores (such as the top 20%) from the initial population as "selected individuals". These individuals are the most likely optimized multi-objective schemes in the current population and need to be retained to the next generation. For example, if the population has 100 individuals, select the top 20 individuals as selected individuals.

[0048] 2. Mutation (generating new individuals): generating new individuals (new schemes) based on the selected individuals through mutation. Mutation is a small random adjustment of the parameters of the selected individuals (such as system working frequency ±0.1 GHz, time slot ratio ±5%), which not only retains the excellent characteristics of the selected individuals, but also introduces new possibilities. For example, after mutation of the selected individual (1.2 GHz, 15%, 30%), (1.1 GHz, 17%, 28%) can be obtained, which is close to the original scheme and has new changes.

[0049] 3. Forming a child population: the child population is composed of "selected individuals" + "new individuals generated by mutation", ensuring that the population size remains unchanged (e.g. 100). Repeat the "evaluation-selection-mutation" process, and the average fitness of each generation of population will gradually improve (i.e. the overall scheme is getting better and better).

[0050] 4. High-quality population: select the optimal scheme that meets multiple objectives: after multiple generations of iteration (e.g. 50-100 generations), the individuals in the population have been fully optimized. At this time, select the top individuals (e.g. the top 10%) from the final population to form a "high-quality population". The individuals in the high-quality population meet the following conditions: the performance indicators of each individual are at a relatively optimal level (e.g. system operation experience F1>90, control operation experience F2>85, D1<35W, E4>95%); can balance conflicting objectives (e.g. will not excessively sacrifice power consumption for high radio frequency performance, and will not give up basic control experience for low power consumption). For example, after 100 generations of iteration, a typical individual in the high-quality population is: (1.3GHz, 20%, 35%) and its corresponding system performance indicators are: system operation experience F1=92 (system operation is smooth), control operation experience F2=88 (control response is timely), power consumption D1=32W (power consumption is moderate), and radio frequency performance E4=96% (radio frequency signal is stable).

[0051] Step 104, based on the high-quality individuals of the high-quality population, configure the system resources of the RF control system.

[0052] For the embodiments of the present application, users can set different biased system performance parameters for different use scenarios of the RF control system. Based on the above steps 101-104, the optimal resource configuration strategy under the use scenario can be generated. And multiple system performance indicators can be balanced to avoid sacrificing other indicators for improving a certain indicator.

[0053] For example, for scenario 1, the user prefers to balance stability and control accuracy:

[0054] Based on the user's biased system performance indicators, population optimization and screening are performed, and the selected high-quality individual 1 can be:

[0055] System operating frequency A1: 1.5GHz (balances computing power and heat dissipation);

[0056] Timing allocation B1:

[0057] Fan cooling time slot proportion B11: 25%;

[0058] Control function time slot proportion B12: 40% (preferentially guaranteeing control response);

[0059] Module component control C1:

[0060] RF setting C11: high gain mode (improve signal penetration);

[0061] Operation module C12: 4-core running (fast processing of multi-device control instructions);

[0062] Fan cooling component C17: 3 gears (efficient cooling, maintain device stability);

[0063] The system performance of the above-mentioned high-quality individual 1 can be:

[0064] Power consumption D1=38W (acceptable range), temperature E2=50℃ (below the safety threshold), RF performance E4=98% (no signal loss), system stability E5=97% (continuous operation without failure), control operation experience F2=92 points (instruction response delay <100ms).

[0065] For scenario 2, outdoor mobile device control (user preference prioritizes battery life)

[0066] Based on the system performance indicators and the first relationship model of user preference, the high-quality population is obtained by population optimization and screening, and the resource configuration details of the high-quality individual 2 are selected from the high-quality population:

[0067] System operating frequency A1: 1.0GHz (reduce energy consumption);

[0068] Timing allocation B1:

[0069] Fan cooling time slot ratio B11: 10%;

[0070] Control function time slot ratio B12: 25% (reduce unnecessary energy consumption);

[0071] Module component control C1:

[0072] RF setting C11: medium gain mode (balance signal and power consumption);

[0073] Operation module C12: 2-core running (satisfy basic control requirements);

[0074] Screen module C13: low brightness (reduce screen power consumption);

[0075] Fan cooling component C17: 1 gear (silent + low power consumption);

[0076] The above-mentioned high-quality individual 2 corresponds to the corresponding performance:

[0077] Power consumption D1=22W (greatly reduced), endurance E1=12 hours (satisfy all-day outdoor work), temperature E2=45℃ (natural cooling is enough), control operation experience F2=85 points (basic function response is smooth).

[0078] In the embodiment of the present application, all resource items capable of affecting the performance indicators can also be displayed on the configuration interface, so that the user can adjust the resource configuration strategy by setting the resource values corresponding to the resource items. When the user changes or adjusts the resource values corresponding to the resource items, the performance sub-indicators or performance indicator values of the RF control system will also change and adjust, and the resource configuration strategy will also change. Compared with the method of displaying only part of the resource items to adjust the resource configuration strategy, by displaying all resource items capable of affecting the performance indicators, the resource configuration strategy can be globally adjusted from the system, conflicts between different performance indicators can be avoided, and system abnormalities can also be avoided.

[0079] The embodiment of the present application provides a resource configuration method of an RF control system. The present application can obtain a plurality of performance indicators preferred by a user and a first relationship model constructed in advance, the first relationship model being used to represent the influence relationship between each resource item of the RF control system and each performance indicator. An initial population containing a plurality of individuals can be generated. Based on the first relationship model and each resource item corresponding to any individual, the evaluation result of any individual under a plurality of performance indicators is determined. One individual represents one resource configuration strategy, and different resource configuration strategies correspond to different resource item combinations. Meanwhile, the embodiment of the present application can select individuals from the initial population based on the evaluation result to realize population iterative optimization through mutation, obtain an optimized population, and any individual in the optimized population satisfies a plurality of performance indicators. Based on the excellent individual in the optimized population, the system resources of the RF control system are configured. Compared with the prior art, the embodiment of the present application can support the user to set or select a plurality of performance indicators preferred by the user, can satisfy the performance indicator preference requirements of different users, can construct the first relationship model in advance, and then can continuously perform iterative optimization on the population containing a plurality of resource configuration strategies according to the first relationship model and the plurality of system performance indicators preferred by the user, obtain an optimized population, select the excellent population (any individual simultaneously satisfies the plurality of performance indicators preferred by the user) from the optimized population based on the scoring result to perform system resource configuration, and can perform system resource configuration based on the excellent individual in the excellent population. That is, the present application can generate an excellent resource configuration strategy that simultaneously satisfies the plurality of performance indicators preferred by the user, so that the RF control system can not only satisfy the individualized performance indicator preference requirements of the user when performing resource configuration, but also balance the plurality of performance indicators of the RF control system. In addition, in the embodiment of the present application, the excellent resource configuration strategy can be obtained without manual testing, verification and fine-tuning of the resource items by technical personnel. Not only can the problem of inconsistent resource configuration effects caused by different understandings of technical personnel be avoided, but also the problem of affecting the overall system performance of the RF control system caused by improper setting of the resource items can be avoided.

[0080] To achieve the above object, the embodiment of the present application provides another resource configuration method of an RF control system, which is applied to a resource configuration device of the RF control system, such as Figure 2 As shown in the figure, the method comprises:

[0081] Step 201, obtaining the value range of each resource item, and performing performance control variable experiment on each resource item to obtain the test value of each performance sub-index of each resource item under different values, and the test value of each performance sub-index and each performance index.

[0082] Step 202, analyzing the test value of each performance sub-index of each resource item under different values and the test value of each performance index to obtain the influence relationship between each resource item and each performance sub-index, and the influence relationship between each resource item and each performance index.

[0083] Step 203, constructing a first relationship model based on the influence relationship obtained by analysis, and the first relationship model is used to represent the influence relationship between each resource item and each performance sub-index, and the influence relationship between each performance sub-index and each performance index.

[0084] It should be noted that when the performance control variable experiment is performed on each resource item, in order to ensure the accuracy of each resource item, and the test value of each performance sub-index of each resource item under different values, and the test value of each performance sub-index and each performance index, and not to affect the normal use of the RF control system, it is necessary to repeatedly perform product verification on each resource item, the test value of each performance sub-index of each resource item under different values, and the test value of each performance sub-index and each performance index, and after confirming that the verification is correct, the test value of each performance sub-index of each resource item under different values and the test value of each performance index are analyzed, and the first relationship model is constructed.

[0085] In an optional embodiment of the present application, in order to simplify the calculation and workload of screening the offspring population into the next round of iteration, the performance indicators of the RF control system can be redefined, that is, the performance indicators are hierarchically defined, and some performance indicators are separated as performance sub-indicators, which are not open to users for setting and adjusting during the strategy optimization and generation stage, and then some other performance indicators are open to users for setting and adjusting. For example, the indicators for representing user experience (user experience indicators) and the indicators for representing system performance (system performance indicators) can be hierarchically defined, and the user experience indicators can be defined as performance indicators open to users for setting and adjusting, and the system performance indicators can be defined as performance sub-indicators. Therefore, during the model building stage, the influence relationship of each resource item on each system performance indicator (performance sub-indicator) can be fitted and analyzed, and the influence relationship of each system performance indicator (performance sub-indicator) on the user experience indicator (performance indicator) can be fitted and analyzed. Specifically, the performance indicators of the RF control system can be defined to include: system operation experience, control operation experience; and the performance sub-indicators of the RF control system can be defined to include: power consumption, endurance, temperature, control function quantity, radio frequency performance, system stability.

[0086] In order to better explain the embodiments of the present application, the embodiments of the present application provide Table 3 to explain and illustrate the performance sub-indicators and the performance indicators. It should be emphasized that Table 3 is only used to facilitate the example explanation of the resource configuration method of the embodiments of the present application, and is not intended to limit the performance sub-indicators and the performance indicators involved in the RF control system.

[0087] Table 3

[0088]

[0089] It should be noted that in order to better understand the embodiments of the present application, each resource item, each performance sub-indicator and performance indicator is illustrated by example. The resource items of the RF control system can include: system operating frequency A1, timing allocation B1, module component control C1. Specifically, the timing allocation B1 can include fan cooling time slot ratio B11, control function timing ratio B12; the module component control C1 can include: radio frequency setting C11, operation module C12, screen module C13, vibration module C14, loudspeaker component C15, lamp component C16, fan cooling component C17. The performance sub-indicators of the RF control system can include: power consumption D1, endurance E1, temperature E2, control function quantity E3, radio frequency performance E4, system stability E5, and the performance indicators of the RF control system can include: system operation experience F1, control operation experience F2. The resource items of the RF control system are , and the performance sub-indicators of the RF control system are The performance indicators of the RF control system are The first relational model can , in, Used to represent the various performance sub-indicators and the influence relationships between them. Used to represent the influence relationship between various resource items and various performance sub-indicators.

[0090] For example, if the performance metric is system operation experience F1, that is, system operation experience F1 is affected by several performance sub-metrics such as battery life E1, temperature E2, and system stability E5: Specifically:

[0091] Battery life (E1): The longer the battery life (E1), the less frequent the charging will be, and the better the control and operation experience (F1). For example, if the battery life (E1) increases from 5 hours to 10 hours, the control and operation experience (F1) may improve from 70 points to 85 points.

[0092] Temperature E2: An excessively high temperature E2 can cause the system to throttle or lag, affecting the smoothness of operation. For example, if the temperature drops from 60℃ to 45℃, the control operation experience may improve by 10-15 points.

[0093] System stability E5: The higher the system stability E5 (e.g., an increase in the percentage of trouble-free operation time), the more reliable the control operation experience F1. For example, if the system stability E5 increases from 90% to 98%, the control operation experience F1 may improve by 5-8 points.

[0094] For example, if the performance indicator is the control operation experience F2, the control operation experience F2 is affected by the performance sub-indicators of battery life E1, temperature E2, number of control functions E3, and radio frequency performance E4: Specifically:

[0095] Battery Life E1: The longer the battery life, the less frequent the charging required, and the better the user experience. For example, if the battery life increases from 5 hours to 10 hours, the user experience score (F2) might improve from 70 to 85.

[0096] Number of Control Functions (E3): The more functions a user has, the more tasks they can complete, and the higher their F2 score. For example, increasing the number of control functions from 5 to 10 might improve the control experience F2 score from 75 to 90.

[0097] RF Performance E4: The better the RF signal quality, the more timely the control command transmission, and the higher the control operation experience F2. For example, improving the RF performance E4 from 90% to 99% may improve the control operation experience F2 by 8-12 points.

[0098] Temperature E2: Temperature is too high, which will cause the system to slow down or lag, and the command execution is delayed. For example, the temperature E2 decreases from 60℃ to 45℃, and the control operation experience F2 can be improved by 10-12 points.

[0099] Step 204, obtaining a plurality of performance indicators of the user's preference, and a first relationship model constructed in advance.

[0100] Step 205, generating an initial population containing a plurality of individuals, determining the evaluation results of any individual under the plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual, wherein one individual represents one resource configuration strategy, and different resource configuration strategies correspond to different combinations of resource items.

[0101] In another embodiment of the present disclosure, the first relationship model includes a first relationship sub-model and a second relationship sub-model, and the step of determining the evaluation results of any individual under the plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual can specifically include: determining a plurality of performance sub-indicators corresponding to any individual based on the first relationship sub-model and each resource item corresponding to the individual, wherein the first relationship sub-model is used to represent the influence relationship between each resource item of the RF control system and each performance sub-indicator; determining the evaluation results of any individual under the plurality of performance indicators based on the second relationship sub-model and the plurality of performance sub-indicators corresponding to the individual, wherein the second relationship sub-model is used to represent the influence relationship between each performance sub-indicator and each performance indicator.

[0102] For example, the resource configuration strategy 1 in the initial population contains the following resource items: system operating frequency A1 (1.2 GHz), fan cooling time slot ratio B11 (20%), control function time slot ratio B12 (35%), RF setting C11 (standard gain mode), and operation module C12 (1 core running).

[0103] Based on the first relationship sub-model and the above resource items, the performance sub-indicators can be calculated: endurance E1 (8 hours), temperature E2 (48℃), control function number E3 (8 items), RF performance E4 (93%), and system stability (E5) 85%.

[0104] Based on the second relationship sub-model and the above performance sub-indicators, the performance indicators can be calculated: system operation experience F1 (82 points); and control operation experience F2 (85 points).

[0105] Similarly, the scores of all resource configuration strategies in the initial population under each performance indicator can be calculated.

[0106] In an embodiment of the present application, the step of generating an initial population comprising a plurality of individuals can specifically include: randomly generating a plurality of first resource items; generating a plurality of second resource items based on the plurality of first resource items and a pre-constructed second relationship model, wherein the second relationship model is used to represent the influence relationship between the first resource items and the second resource items; or randomly generating a plurality of first resource items and a plurality of second resource items; and constructing the initial population based on the plurality of first resource items and the plurality of second resource items. That is, whether there is an influence relationship between the resource items can be determined based on a controlled variable experiment, if there is an influence relationship, a second relationship model can be constructed, and then the second resource items can be generated based on the randomly generated first resource items to ensure the accuracy of the generation of the second resource items. If there is no influence relationship, the first resource items and the second resource items are independent of each other and can also be randomly generated. For example, the timing allocation B1 is affected by the system operating frequency A1, when the timing allocation B1 is generated, the influence relationship between the timing allocation B1 and the system operating frequency A1 can be considered to ensure the accuracy of the generation of the second resource items.

[0107] In order to better generate a resource allocation strategy that can meet the personalized needs of a user and balance multiple performance targets at the same time, the way in which an embodiment of the present application generates a high-quality resource allocation strategy is more flexible, and the embodiment of the present application can use two ways to screen individuals entering the next round of population iteration.

[0108] In an embodiment of the present application, the target weights of a plurality of performance indicators of a user can be set, and the step of determining the evaluation results of any individual under a plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual can specifically include: obtaining the target weights corresponding to the plurality of performance indicators set by the user; and determining the evaluation results of any individual under a plurality of performance indicators based on the first relationship model, the target weights and each resource item corresponding to the individual. At this time, the evaluation results generated based on the target weights can be comprehensive evaluation results, that is, the plurality of objective functions can be converted into a total objective function through the target weights, and then the overall evaluation results can be used to subsequently select individuals from the current population to enter the next round of population iteration. For example, the overall performance F = weight 1 * system operation experience F1 + weight 2 * control operation experience F2. Therefore, the overall performance scores of all individuals can be obtained, and then the individuals can be sorted according to the overall performance scores, and the top 20 individuals in the overall performance scores can be selected as the selected individuals to enter the next round of screening.

[0109] In still another embodiment of the present disclosure, the step of determining the evaluation result of each individual under the plurality of performance indicators based on the first relationship model and the respective resource items corresponding to each individual can specifically include: determining a basic evaluation result of each individual under the plurality of performance indicators based on the first relationship model and the respective resource items corresponding to each individual; obtaining the first constraint condition corresponding to each resource item and the second constraint condition corresponding to each performance indicator; and adjusting the basic evaluation result based on a preset reward and punishment mechanism, the first constraint condition and the second constraint condition to obtain the evaluation result of each individual under the plurality of performance indicators.

[0110] The preset reward and punishment mechanism includes a reward rule and a punishment rule. The reward rule gives extra points for performance indicators that exceed the performance constraints, and the punishment rule deducts points for performance indicators that violate the performance constraints. For example: for each hour that the endurance E1 exceeds the constraint of 7 hours, the system operation experience F1 is additionally added by 2 points; for each 1℃ that the temperature E2 is lower than the constraint of 55℃, the system operation experience F1 is additionally added by 1 point; for each 1% that the system stability E5 is higher than the constraint of 95%, the system operation experience F1 is additionally added by 1.5 points; for each item that the control function quantity E3 exceeds the constraint of 6, the control operation experience F2 is additionally added by 3 points; for each 1% that the radio frequency performance E4 is higher than the constraint of 96%, the control operation experience F2 is additionally added by 2 points. For each 0.1 hour that the endurance E1 is lower than the constraint of 7 hours, the system operation experience F1 is deducted by 1 point; for each 1℃ that the temperature E2 is higher than the constraint of 55℃, the system operation experience F1 is deducted by 2 points; for each 1% that the system stability E5 is lower than the constraint of 95%, the system operation experience F1 is deducted by 3 points; for each item that the control function quantity E3 is lower than the constraint of 6, the control operation experience F2 is deducted by 5 points; for each 1% that the radio frequency performance E4 is lower than the constraint of 96%, the control operation experience F2 is deducted by 4 points.

[0111] In order to better understand the embodiments of the present application, the way of determining the evaluation result based on the preset reward and punishment mechanism and the constraint condition is exemplified. The plurality of resource items (A1, B1, C1) corresponding to each individual:

[0112] 1. By means of the first relationship model, the resource items of the individual are converted into specific values of the performance sub-indicators (E1-E5). For example: through the influence relationship between the system working frequency A1 and the radio frequency performance E4 and the power consumption D1, the radio frequency performance E4=97% and the power consumption D1=53W are calculated;

[0113] 2. The influence relationship between the power consumption D1 and the endurance E1 (E1=10-0.05×D1) is combined to deduce that the endurance E1=7.2h. In this way, the temperature E2=52℃ and the system stability E5=97% are obtained;

[0114] 3. The performance sub-indicators are weighted and calculated to obtain the basic score of the performance indicators:

[0115] System operation experience F1 basic score = 0.3*E1 + 0.3*(100-E2) + 0.4*E5 (when endurance E1 = 7.2h, temperature E2 = 52℃, system stability E5 = 97%, the system operation experience F1 basic score is 84.6 points);

[0116] Control operation experience F2 basic score = 0.4*E3 + 0.6*E4 (when control function quantity E3 = 7, radio frequency performance E4 = 97%, the control operation experience F2 basic score is 86.2 points).

[0117] 4. Basic score modification by incorporating constraint conditions and rewards and punishments:

[0118] The basic score is adjusted according to the preset reward and punishment mechanism, the reward item: if the temperature E2 = 52℃ (lower than the constraint 3℃) add 3 points, the system stability E5 = 97% (exceeds the constraint 2%) add 3 points, then the system operation experience F1 is modified to 84.6+3+3=90.6 points; the punishment item: if the control function quantity E3 = 5 (lower than the constraint 1) deduct 5 points, the control operation experience F2 is modified to 86.2-5=81.2 points.

[0119] Step 206, based on the evaluation result of any individual in the initial population, select individuals from the initial population to form a selected population; perform two-by-two crossover operation on the individuals in the selected population to obtain a child population.

[0120] In the embodiment of the application, the evaluation result can be a total evaluation result of multiple performance indicators (total performance score) or a score result set under a single performance indicator (single performance score set). Therefore, the top 20 individuals with the highest total performance score can be selected as the "selected individuals", and the selected individuals are used to form a selected population, and two-by-two crossover operation is performed to obtain a child population, which enters the next round of screening. Alternatively, the top 20 individuals can be selected as the "selected individuals" based on the single performance score set and the non-dominated sorting algorithm; the selected individuals are used to form a selected population, and two-by-two crossover operation is performed to obtain a child population, which enters the next round of screening. The non-dominated sorting algorithm is used to sort the individuals according to the "domination relationship", and a group of Pareto optimal solutions that balance all performance indicators are finally found (i.e. solutions that cannot improve one performance target without compromising other performance targets).

[0121] Step 207, perform mutation operation on the individuals in the child population; if the mutated individual does not meet the preset condition, perform mutation operation again; determine the next generation population according to the mutated individual that meets the preset condition, and repeat the above operation to realize population iterative optimization.

[0122] The preset condition can be that each resource item in the individual satisfies a corresponding constraint condition.

[0123] Step 208: Stopping population iteration to obtain an optimized population when a preset iteration stopping condition is reached.

[0124] In the embodiment of the present application, the preset iteration stopping condition can be that the number of iterations reaches a predetermined threshold, or the evaluation result corresponding to the individual in the population converges and no longer changes. At this time, the optimized population obtained contains individuals that cannot balance multiple performance indicators at the same time, and contains individuals based on balancing multiple performance indicators at the same time. Therefore, the obtained optimized population needs to be further screened to obtain a Pareto optimal solution set.

[0125] Step 209: Determining the evaluation result of any individual in the optimized population under multiple performance indicators based on the first relationship model.

[0126] It should be noted that the specific determination method of step 209 can refer to steps 102 and 105, which will not be described here.

[0127] Step 210: Selecting a Pareto optimal solution set from the optimized population as a high-quality population based on the evaluation result of any individual in the optimized population.

[0128] The Pareto optimal solution set is a set of optimal solutions that cannot improve one performance indicator without compromising other performance indicators in the multiple performance indicators of the user's preference. Specifically, the Pareto optimal solution set can be selected by referring to the method of step 206, sorting each individual through the "dominance relationship" of the non-dominated sorting algorithm, and finally finding a group of Pareto optimal solutions that balance each performance indicator.

[0129] Step 211: Displaying each high-quality individual in the high-quality population and / or each resource item corresponding thereto on the configuration interface.

[0130] For example, the performance indicators set by the user are: system operation experience F1 (85 points), control operation experience F2 (90 points), and the generated high-quality population has 3 high-quality individuals, which can be displayed on the configuration interface as follows: Title - Recommended resource configuration strategy; Prompt: Based on the system operation experience (F1: 85) and control operation experience (F2: 90) set by you, the following optimization scheme is generated:

[0131] Scheme one: Balanced performance and power consumption system

[0132] System working frequency (1.2 GHz), fan cooling time slot ratio (20%), control function time slot ratio (35%), RF setting (standard gain mode), operation module (2-core running), screen module (low brightness), vibration module (off), speaker component (off), lamp component (off), fan cooling component (1 gear-quiet), this scheme optimizes power consumption while ensuring system performance, suitable for long-time continuous working scenarios.

[0133] Scheme two: extreme control experience

[0134] System working frequency (1.5 GHz), fan cooling time slot ratio (25%), control function time slot ratio (35%), RF setting (high gain mode), operation module (2-core running), screen module (medium brightness), vibration module (on), speaker component (off), fan cooling component (2 gears-standard), this scheme maximizes the number of control functions and RF performance, suitable for scenarios with high control accuracy requirements.

[0135] Scheme three: low power consumption and long endurance

[0136] System working frequency (1.0 GHz), fan cooling time slot ratio (15%), control function time slot ratio (25%), RF setting (low gain mode), operation module (1-core running), screen module (low brightness), vibration module (off), speaker component (off), fan cooling component (1 gear-quiet). This scheme focuses on optimizing power consumption and endurance, suitable for mobile use or power limited scenarios.

[0137] The system performance indicators of the above three optimization schemes are shown in Table 4:

[0138] Table 4

[0139]

[0140] After displaying the above information on the configuration interface, the user can select any optimization scheme. When the user selects an optimization scheme and clicks Apply this strategy, the RF control system's various resource items are modified and adjusted to the resource items in the user's selected strategy.

[0141] Step 212, when receiving the high-quality individual selection instruction, determine the selected high-quality individual.

[0142] Step 213, based on the selected high-quality individual, configure the system resources of the RF control system.

[0143] In the embodiment of the present application, all resource items capable of affecting the user experience index can also be displayed on the configuration interface, so that the user can adjust the resource configuration strategy by setting the resource values corresponding to each resource item. When the user changes or adjusts the resource values corresponding to each resource item, the performance sub-index or performance index value of the RF control system will also change and adjust, and the resource configuration strategy will also change. Compared with the method of displaying only part of the resource items to adjust the resource configuration strategy, by displaying all resource items capable of affecting the user experience index, the resource configuration strategy can be globally adjusted from the system, avoiding conflicts between different performance indexes, and also avoiding system abnormalities.

[0144] For the embodiment of the present application, in order to ensure the accuracy of the resource configuration of the RF control system and ensure that the generated resource configuration strategy can meet the user's demand, after the user selects the high-quality individual, resource configuration simulation can be performed on the RF control system, that is, the system resources of the RF control system are simulated and configured as each resource item in the high-quality individual. After the simulation configuration, the RF control system does not have abnormal problems and can normally operate, and meets the performance index set by the user. Then, based on each resource item in the high-quality individual, the system resources of the RF control system are actually configured.

[0145] It should be noted that, in order to further ensure the accuracy of the resource configuration of the RF control system and further ensure that the generated resource configuration strategy can meet the user's demand, the embodiment of the present application also supports continuous optimization and improvement of the first relationship model, so that the construction of the relationship model, the resource configuration strategy and the configuration of the system resources of the RF control system form a complete optimization closed loop. Specifically, a large number of actually applied resource configuration strategies and actual performance indexes corresponding to the applied resource configuration strategies can be collected. Based on each resource item in the applied resource configuration strategy and the actual performance index corresponding thereto, the first relationship model is optimized. Specifically, based on the theoretical performance index and the actual performance index corresponding to each resource item, it can be determined whether the first relationship model has a problem. If there is a problem, the first relationship model can be corrected based on the difference performance index between the theoretical performance index and the actual performance index.

[0146] The embodiment of the present application provides a resource configuration method of an RF control system. The present application can obtain multiple performance indexes of user preference, and a first relationship model which is used for representing the influence relationship between each resource item of the RF control system and each performance index, and can generate an initial population containing multiple individuals, determine the evaluation result of any individual under multiple performance indexes based on the first relationship model and each resource item corresponding to the individual, wherein one individual represents one resource configuration strategy, different resource configuration strategies correspond to different resource item combinations. Meanwhile, the present application can select individuals from the initial population based on the evaluation result to realize population iterative optimization through variation, obtain an optimized population, and any individual in the optimized population meets multiple performance indexes, and configure system resources of the RF control system based on the excellent individual in the optimized population. Compared with the prior art, the present application can support user to set or select multiple performance indexes of user preference, can meet the preference demand of different users on multiple performance indexes, can pre-construct the first relationship model, and then can continuously perform iterative optimization on the population containing multiple resource configuration strategies based on the first relationship model and multiple system performance indexes of user preference, obtain an optimized population, select the excellent population (any individual meets multiple performance indexes of user preference) from the optimized population based on the score result to configure system resources, and can configure system resources based on the excellent individual in the excellent population. That is, the present application can generate the excellent resource configuration strategy which meets multiple performance indexes of user preference, so that the RF control system can meet the individualized preference demand of the user on system performance indexes when performing resource configuration, and can balance multiple performance indexes of the RF control system at the same time. In addition, in the embodiment of the present application, the excellent resource configuration strategy can be obtained without manual testing, verification and fine adjustment of resource items by technical personnel, which can not only avoid the problem that the resource configuration effect is inconsistent due to the different understanding of technical personnel, but also can avoid the problem that the overall system performance of the RF control system is affected due to improper setting of resource items.

[0147] To achieve the above object, the embodiment of the present application further provides a resource configuration device of an RF control system, which is applied to a resource configuration equipment of the RF control system, as shown in the figure, the resource configuration device of the RF control system comprises: Figure 3

[0148] The obtaining unit 31 is used for obtaining multiple performance indexes of user preference and a first relationship model which is pre-constructed and used for representing the influence relationship between each resource item of the RF control system and each performance index.

[0149] The generating unit 32 is used for generating an initial population containing multiple individuals.

[0150] ​The determining unit 33 is configured to determine the evaluation result of each individual under the performance indicators based on the first relationship model and each resource item corresponding to the individual, wherein each individual represents a resource configuration strategy, and different resource configuration strategies correspond to different resource item combinations.

[0151] The optimizing unit 34 is configured to select individuals from the initial population for mutation to realize iterative optimization of the population based on the evaluation result, and obtain an optimized population; and select a high-quality population from the optimized population.

[0152] The configuring unit 35 is configured to configure system resources of the RF control system based on the high-quality population.

[0153] In an optional embodiment of the present application, the determining unit 33 can be specifically configured to determine the performance sub-indicators corresponding to each individual based on the first relationship sub-model and each resource item corresponding to the individual, wherein the first relationship sub-model is used to represent the influence relationship between each resource item and each performance sub-indicator of the RF control system; and determine the evaluation result of each individual under the performance indicators based on the second relationship sub-model and the performance sub-indicators corresponding to the individual, wherein the second relationship sub-model is used to represent the influence relationship between each performance sub-indicator and each performance indicator of the RF control system.

[0154] In another optional embodiment of the present application, the determining unit 33 can be specifically further configured to obtain target weights corresponding to the performance indicators set by a user; and determine the evaluation result of each individual under the performance indicators based on the first relationship model, the target weights and each resource item corresponding to the individual.

[0155] In an optional embodiment of the present application, the function of pre-constructing the first relationship model is supported, and the resource configuration device of the RF control system further comprises an experiment unit, an analysis unit and a construction unit.

[0156] The acquisition unit 31 can be configured to acquire the value range of each resource item.

[0157] The experiment unit can be configured to perform performance control variable experiments on each resource item to obtain the test values of each performance sub-indicator and each performance indicator of each resource item under different values, and the test values of each performance sub-indicator and each performance indicator.

[0158] The analysis unit can be configured to analyze the test values of each performance sub-indicator and each performance indicator of each resource item under different values to obtain the influence relationship between each resource item and each performance sub-indicator, and the influence relationship between each resource item and each performance indicator.

[0159] The construction unit can be configured to construct the first relationship model based on the influence relationship obtained by analysis.

[0160] In yet another optional embodiment of the present application, the generating unit 32 can be specifically configured to randomly generate a plurality of first resource items; generate a plurality of second resource items based on the plurality of first resource items and a pre-constructed second relationship model, wherein the second relationship model is used to represent the influence relationship between the first resource items and the second resource items; or randomly generate a plurality of first resource items and a plurality of second resource items; and construct the initial population based on the plurality of first resource items and the plurality of second resource items.

[0161] In yet another optional embodiment of the present application, the optimizing unit 34 can be specifically configured to select individuals from the initial population to form a selected population based on the evaluation results of any individual in the initial population; perform a two-by-two crossover operation on the individuals in the selected population to obtain a child population; perform a mutation operation on the individuals in the child population; if the individual after mutation does not meet the preset condition, then re-perform the mutation operation; determine the individual after mutation that meets the preset condition as the next generation population, and repeat the above operation to realize population iteration optimization; stop the population iteration to obtain an optimized population when a preset iteration stop condition is reached; determine the evaluation results of any individual in the optimized population under a plurality of performance indicators based on the first relationship model; and select a Pareto optimal solution set from the optimized population as a high-quality population based on the evaluation results of any individual in the optimized population.

[0162] Correspondingly, the configuring unit 35 can be specifically configured to display each high-quality individual in the high-quality population and / or each resource item corresponding to the high-quality individual on a configuration interface; determine a selected high-quality individual when a high-quality individual selection instruction is received; and configure the system resources of the RF control system based on the selected high-quality individual.

[0163] The embodiment of the present application provides a resource configuration device of an RF control system, the embodiment of the present application can acquire a plurality of performance indexes of user preference, and a first relationship model constructed in advance, the first relationship model is used for representing an influence relationship between each resource item of the RF control system and each performance index; an initial population containing a plurality of individuals is generated, the evaluation result of any individual under a plurality of performance indexes is determined based on the first relationship model and each resource item corresponding to the individual, one individual represents one resource configuration strategy, different resource configuration strategies correspond to different resource item combinations, meanwhile, the embodiment of the present application can select an individual from the initial population based on the evaluation result to realize population iterative optimization through variation, and obtain an optimized population, any individual in the high-quality population meets the plurality of performance indexes, and the system resource of the RF control system is configured based on the high-quality individual in the high-quality population. Compared with the prior art, the embodiment of the present application can support a user to set or select a plurality of performance indexes of user preference, can meet the performance index preference demand of different users, can construct the first relationship model in advance, and then can continuously perform iterative optimization on the population containing a plurality of resource configuration strategies based on the first relationship model and the plurality of system performance indexes of user preference, obtain an optimized population, select a high-quality population (any individual simultaneously meets the plurality of performance indexes of user preference) from the optimized population based on the score result to perform system resource configuration, and can perform system resource configuration based on the high-quality individual in the high-quality population. That is, the present application can generate a high-quality resource configuration strategy which simultaneously meets the plurality of performance indexes of user preference, so that the RF control system can meet the individualized preference demand of a user on system performance indexes when performing resource configuration, and can balance the plurality of performance indexes of the RF control system at the same time. In addition, in the embodiment of the present application, the high-quality resource configuration strategy can be acquired without manual testing, verification and fine adjustment of resource items by technical personnel, not only can the problem that the resource configuration effect is inconsistent due to different understandings of technical personnel be avoided, but also the problem that the overall system performance of the RF control system is affected due to improper setting of resource items can be avoided.

[0164] To achieve the above object, the embodiment of the present application provides a storage medium, and the storage medium stores a resource configuration program of an RF control system.

[0165] To achieve the above object, the embodiment of the present application provides a resource configuration device of an RF control system, the resource configuration device comprises a memory and a processor, the memory stores a resource configuration program of an RF control system, and the processor realizes the steps of the resource configuration method of the RF control system when executing the resource configuration program of the RF control system.

[0166] To solve the above technical problems, the embodiment of the present application further provides a resource configuration device of an RF control system. For details, please refer to Figure 4 , Figure 4 The basic structure block diagram of the resource configuration device of the RF control system in the embodiment is shown in FIG. 1.

[0167] The resource configuration device 4 of the RF control system comprises a memory 41, a processor 42 and a network interface 43 which are connected to each other through a system bus. It should be noted that only the resource configuration device 4 of the RF control system with components 41-43 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or less components can be alternatively implemented. Among them, those skilled in the art can understand that the resource configuration device of the RF control system here is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0168] The memory 41 at least comprises a storage medium readable in one type, including flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the resource configuration device 4 of the RF control system, such as the hard disk or memory of the resource configuration device 4 of the RF control system. In other embodiments, the memory 41 can also be an external storage device of the resource configuration device 4 of the RF control system, such as the plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on the resource configuration device 4 of the RF control system. Of course, the memory 41 can also include both the internal storage unit and the external storage device of the resource configuration device 4 of the RF control system. In the embodiment, the memory 41 is usually used to store the operating system and various application software installed on the resource configuration device 4 of the RF control system, such as the program code of the resource configuration method of the RF control system, etc. In addition, the memory 41 can also be used to temporarily store various data that have been output or will be output.

[0169] The processor 42 may, in some embodiments, be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the resource configuration device 4 of the RF control system. In the present embodiment, the processor 42 is used to run program codes or process data stored in the memory 41, such as program codes of the resource configuration method of the RF control system.

[0170] The network interface 43 may include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the resource configuration device 4 of the RF control system and other electronic devices.

[0171] The embodiment of the present application provides a resource configuration device of an RF control system, and the embodiment of the present application can obtain a plurality of performance indicators to which a user is inclined, and a first relationship model constructed in advance, the first relationship model being used to represent an influence relationship between each resource item of the RF control system and each performance indicator; an initial population containing a plurality of individuals is generated, and based on the first relationship model and each resource item corresponding to any individual, an evaluation result of any individual under a plurality of performance indicators is determined, one individual representing one resource configuration strategy, and different resource configuration strategies corresponding to different resource item combinations. Meanwhile, the embodiment of the present application can select an individual from the initial population based on the evaluation result to realize population iterative optimization through mutation, obtain an optimized population, and any individual in the high-quality population satisfies a plurality of performance indicators. Based on a high-quality individual in the high-quality population, system resources of the RF control system are configured. Compared with the prior art, the embodiment of the present application can support a user to set or select a plurality of performance indicators to which the user is inclined, can satisfy different user demands for a plurality of performance indicators to which the user is inclined, can construct a first relationship model in advance, and then can continuously perform iterative optimization on a population containing a plurality of resource configuration strategies according to the first relationship model and a plurality of system performances to which the user is inclined, obtain an optimized population, and select a high-quality population (any individual simultaneously satisfying a plurality of performance indicators to which the user is inclined) from the optimized population based on a scoring result to configure system resources. That is, the embodiment of the present application can configure resources based on a plurality of resource configuration strategies simultaneously satisfying a plurality of performance indicators to which the user is inclined, that is, can satisfy individualized inclination demands of a user for system performance indicators, and can simultaneously balance a plurality of performance indicators of the RF control system. In the entire resource configuration process, manual testing, verification and fine-tuning of technical personnel are not required, which not only can avoid problems of inconsistent resource configuration effects caused by different understandings of technical personnel, but also can avoid problems of affecting overall system performance of the RF control system caused by improper setting of resource items.

[0172] Those skilled in the art can clearly understand the method of the above-mentioned embodiments can be realized by means of software and necessary general hardware online platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and include a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device) execute the method of each embodiment of the present application.

[0173] The application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The application can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0174] Obviously, the above-described embodiments are only a part of the embodiments of the present application, and are not all the embodiments. The preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be realized in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or equivalently replace some technical features. Any equivalent structure made by using the content of the present application specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the present application.

Claims

1. A resource configuration method of an RF control system, characterized by, The method comprises: obtaining a plurality of performance indicators of user preferences, and a first relationship model constructed in advance, the first relationship model being used to represent an influence relationship between each resource item of an RF control system and each performance indicator; generating an initial population comprising a plurality of individuals, determining an evaluation result of any individual under a plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual, one individual representing one resource configuration strategy, different resource configuration strategies corresponding to different resource item combinations; selecting individuals from the initial population based on the evaluation result to realize population iterative optimization through mutation, obtaining an optimized population, and selecting a high-quality population from the optimized population, any individual in the high-quality population satisfying the plurality of performance indicators; configuring system resources of the RF control system based on high-quality individuals in the high-quality population.

2. The method of claim 1, wherein, The first relationship model comprises a first relationship sub-model and a second relationship sub-model, and the determining of the evaluation result of any individual under the plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual comprises: determining a plurality of performance sub-indicators corresponding to any individual based on the first relationship sub-model and each resource item corresponding to the individual, the first relationship sub-model being used to represent an influence relationship between each resource item of the RF control system and each performance sub-indicator; determining the evaluation result of any individual under the plurality of performance indicators based on the second relationship sub-model and the plurality of performance sub-indicators corresponding to the individual, the second relationship sub-model being used to represent an influence relationship between each performance sub-indicator and each performance indicator of the RF control system.

3. The method of claim 1, wherein, The determining of the evaluation result of any individual under the plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual comprises: obtaining target weights corresponding to the plurality of performance indicators set by a user; determining the evaluation result of any individual under the plurality of performance indicators based on the first relationship model, the target weights and each resource item corresponding to the individual.

4. The method of claim 1, wherein, The determining of the evaluation result of any individual under the plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual comprises: determining a basic evaluation result of any individual under the plurality of performance indicators based on the first relationship model and each resource item corresponding to the individual; obtaining first constraint conditions corresponding to each resource item and second constraint conditions corresponding to each performance indicator; adjusting the basic evaluation result based on a preset reward and punishment mechanism, the first constraint conditions and the second constraint conditions to obtain the evaluation result of any individual under the plurality of performance indicators.

5. The method according to any one of claims 1 to 4, characterized in that, The first relationship model is used to represent an influence relationship between each resource item and each performance sub-indicator, and an influence relationship between each performance sub-indicator and each performance indicator, and the method further comprises: obtaining a value range of each resource item, and performing a performance control variable experiment on each resource item to obtain test values of each performance sub-indicator and each performance indicator under different values of each resource item; The test values of each performance sub-index and each performance index of each resource item under different values are analyzed to obtain an influence relationship between each resource item and each performance sub-index and an influence relationship between each resource item and each performance index; The first relationship model is constructed based on the obtained influence relationship.

6. The method according to any one of claims 1 to 4, characterized in that, The initial population containing multiple individuals is generated, including: a plurality of first resource items are randomly generated; a plurality of second resource items are generated based on the plurality of first resource items and a second relationship model constructed in advance, wherein the second relationship model is used to represent an influence relationship between the first resource items and the second resource items; or, a plurality of first resource items and a plurality of second resource items are randomly generated; the initial population is constructed based on the plurality of first resource items and the plurality of second resource items.

7. The method according to any one of claims 1 to 4, characterized in that, The population iterative optimization is implemented by selecting individuals from the initial population based on the evaluation results and performing mutation to obtain an optimized population, including: individuals are selected from the initial population based on the evaluation results of any individual in the initial population to form a selected population; the individuals in the selected population are crossed with each other to obtain a child population; mutation is performed on the individuals in the child population; if the individual after mutation does not meet a preset condition, the mutation operation is performed again; the individual after mutation that meets the preset condition is determined as a next generation population, and the above operation is repeated to implement population iterative optimization; when a preset iteration stop condition is reached, the population iteration is stopped to obtain the optimized population; the high-quality population is selected from the optimized population, including: evaluation results of any individual in the optimized population under multiple performance indexes are determined based on the first relationship model; a Pareto front optimal solution set is selected from the optimized population as the high-quality population based on the evaluation results of any individual in the optimized population; system resources of the RF control system are configured based on the high-quality individuals in the high-quality population, including: each high-quality individual in the high-quality population and / or each resource item corresponding to the high-quality individual is displayed on a configuration interface; when a high-quality individual selection instruction is received, the selected high-quality individual is determined; system resources of the RF control system are configured based on the selected high-quality individual, and multiple system performance indexes corresponding to the high-quality individual are displayed.

8. A resource configuration apparatus of an RF control system, characterized by comprising: The apparatus includes: an acquisition unit configured to acquire a plurality of performance indexes to which a user is inclined and a first relationship model constructed in advance, the first relationship model being used to represent an influence relationship between each resource item and each performance index of an RF control system; a generation unit configured to generate an initial population containing multiple individuals; a determination unit configured to determine evaluation results of any individual under multiple performance indexes based on the first relationship model and each resource item corresponding to the individual, one individual representing one resource configuration strategy, and different resource configuration strategies corresponding to different resource item combinations; an optimization unit configured to select individuals from the initial population based on the evaluation results and perform mutation to implement population iterative optimization, obtain an optimized population, and select a high-quality population from the optimized population; a configuration unit configured to configure system resources of the RF control system based on high-quality individuals in the high-quality population.

9. A storage medium, characterized by The storage medium has stored thereon a resource configuration program of an RF control system, and the resource configuration program of the RF control system, when executed by a processor, implements the steps of the resource configuration method of the RF control system according to any one of claims 1 to 7.

10. A resource configuration device of an RF control system, characterized by, The resource configuration device comprises a memory and a processor, the memory has stored thereon a resource configuration program of an RF control system, and the processor, when executing the resource configuration program of the RF control system, implements the steps of the resource configuration method of the RF control system according to any one of claims 1 to 7.

Images