Network signal resource allocation method, device, equipment, medium and product

Abstract

The invention discloses a network signal resource allocation method, device and equipment, a medium and a product, and relates to the technical field of communication. The method comprises the following steps: collecting surrounding environment data of a target place; based on an analytic hierarchy process and a fuzzy comprehensive evaluation model, determining initial network signal resources allocated to the target place according to the surrounding environment data; allocating initial network signal resources to the target place, and analyzing a network pressure state of terminal equipment in the target place; and adjusting the initial network signal resource according to the network pressure state to obtain a target network signal resource allocated to the target place. According to the method, an analytic hierarchy process and a fuzzy comprehensive evaluation model are adopted, qualitative environmental factors are converted into quantitative resource requirements, an initial distribution scheme of network resources is scientifically determined from multiple dimensions, a feedback mechanism based on network pressure state data is introduced, and a network signal resource distribution scheme is optimized.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method, apparatus, device, medium, and product for allocating network signal resources. Background Technology

[0002] With the widespread adoption of mobile communication technologies such as 5G, the demand for high-speed, stable network signals is becoming increasingly urgent in densely populated areas such as subways, shopping malls, and train stations. Strong 5G signals are not only fundamental to ensuring users' personal experiences such as internet access, video calls, and instant messaging, but also a key infrastructure supporting security monitoring, remote equipment operation and maintenance, real-time dispatching, and future intelligent development in these locations.

[0003] Currently, in places like subways, network signal allocation schemes typically rely on relatively traditional technologies. Common practices include static planning based on simple population density models, or fixed allocation of signal transmission power based on pre-set empirical values. However, these traditional methods have several significant limitations:

[0004] First, signal allocation relies on a single factor and lacks comprehensive consideration of multiple factors. Existing technologies often focus on real-time pedestrian traffic within the target location, while neglecting the profound impact of the complex surrounding environment on network load.

[0005] Second, the dynamic adjustment capability is insufficient, and the response is lagging. Many existing systems lack effective real-time monitoring and feedback mechanisms. They usually set a fixed signal allocation scheme at the beginning of deployment and cannot make rapid and adaptive adjustments according to the actual usage pressure of the network (such as data throughput, number of connections, bit error rate, etc. of each access point).

[0006] Therefore, existing network signal resource allocation schemes cannot meet the growing network signal demand in densely populated areas. Summary of the Invention

[0007] This invention provides a method, apparatus, device, medium, and product for allocating network signal resources, in order to solve the problem that existing network signal resource allocation schemes cannot meet the growing network signal demand in densely populated areas.

[0008] In a first aspect, embodiments of the present invention provide a method for allocating network signal resources, including:

[0009] Collect environmental data of the target location;

[0010] Based on the analytic hierarchy process and fuzzy comprehensive evaluation model, the initial network signal resources allocated to the target location are determined according to the surrounding environmental data;

[0011] Allocate the initial network signal resources to the target location and analyze the network pressure status of the terminal devices in the target location;

[0012] The initial network signal resources are adjusted based on the network pressure status and surrounding environment data to obtain the target network signal resources allocated to the target location.

[0013] Secondly, embodiments of the present invention provide a network signal resource allocation device, comprising:

[0014] The surrounding environment data acquisition module is used to collect surrounding environment data of the target location;

[0015] The initial network resource allocation module is used to determine the initial network signal resources allocated to the target location based on the surrounding environmental data, using the analytic hierarchy process and fuzzy comprehensive evaluation model.

[0016] The network pressure status analysis module is used to allocate the initial network signal resources to the target location and analyze the network pressure status of the terminal devices in the target location.

[0017] The target network resource allocation module is used to adjust the initial network signal resources according to the network pressure status and surrounding environment data to obtain the target network signal resources allocated to the target location.

[0018] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0019] At least one processor;

[0020] and a memory communicatively connected to the at least one processor;

[0021] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the network signal resource allocation method according to any embodiment of the present invention.

[0022] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement the network signal resource allocation method described in any embodiment of the present invention.

[0023] Fifthly, embodiments of the present invention provide a computer program product including a computer program, which, when executed by a processor, implements the network signal resource allocation method described in any embodiment of the present invention.

[0024] The technical solution of this invention involves collecting surrounding environmental data of a target location; determining initial network signal resources allocated to the target location based on the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation model; allocating initial network signal resources to the target location and analyzing the network pressure status of terminal devices in the target location; and adjusting the initial network signal resources according to the network pressure status to obtain the target network signal resources allocated to the target location. By employing the AHP and fuzzy comprehensive evaluation model, qualitative environmental factors are transformed into quantitative resource requirements, scientifically determining the initial allocation scheme of network resources from multiple dimensions. Furthermore, a feedback mechanism based on network pressure status data is introduced to optimize the network signal resource allocation scheme. This solves the problem that existing network signal resource allocation schemes cannot meet the ever-increasing network signal demand in densely populated areas. It has the beneficial effect of maximizing network resource utilization while ensuring user experience, and simultaneously improving the automation and intelligence level of network operation.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a network signal resource allocation method provided in Embodiment 1 of the present invention;

[0028] Figure 2 This is a flowchart of a network signal resource allocation method provided in Embodiment 2 of the present invention;

[0029] Figure 3 This is a schematic diagram of a network signal resource allocation device provided in Embodiment 3 of the present invention;

[0030] Figure 4 A schematic diagram of the structure of an electronic device for implementing the network signal resource allocation method of this invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] It is understood that before using the technical methods disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0034] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technology, based on the prompt message.

[0035] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0036] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0037] Example 1

[0038] Figure 1 This is a flowchart of a network signal resource allocation method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where network signal resources are allocated to a target scenario. This method can be executed by a network signal resource allocation device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0039] S110. Collect environmental data of the target location.

[0040] The target location can be any place that requires network resources. In this embodiment, the target location can be a densely populated place with high network demand, such as subways, airports, train stations, and shopping malls. The surrounding environment data can be relevant data about the environment surrounding the target location, and can involve data on multiple environmental factors. For example, influencing factors can include business district factors, cultural institution factors, and office unit factors; data on business district factors can include the number of shops, foot traffic, and frequency of commercial activities within the business district; data on cultural institution factors can include: the reputation of the cultural institution, the number of participants, the frequency of cultural activities, an assessment of its historical and cultural heritage, and the quality level of its members; data on office unit factors can include: the number of employees, business volume, network dependence, and the level of office automation; the above information can be collected through public channels such as the internet and official reports.

[0041] S120. Based on the analytic hierarchy process and fuzzy comprehensive evaluation model, the initial network signal resources allocated to the target location are determined according to the surrounding environmental data.

[0042] The initial network signal resources can be considered as the initially configured network signal resources. In this embodiment, the initial network signal resources are configured solely based on surrounding environmental data. Since the user's network usage status is not considered, further optimization is needed. Network signal resources may include spectrum resources, power resources, and spatiotemporal resources of 4G or 5G networks.

[0043] In this embodiment, the weights of each environmental factor are determined by applying the hierarchical analysis method, thus stratifying the complex network signal resource allocation problem and clearly clarifying the relationships between the various environmental factors. Then, a fuzzy comprehensive evaluation model is used to combine the subjective experience of experts with objective surrounding environmental data to achieve a quantitative evaluation of resource allocation.

[0044] For example, a hierarchical model is first constructed; the hierarchical model may include: a target layer, a criterion layer, and a scheme layer. The target layer determines the objective of scientifically allocating initial network signal resources to the target location. The criterion layer is used to identify key environmental factors affecting resource allocation. The scheme layer is used to determine resource allocation schemes. In this embodiment, a fuzzy comprehensive evaluation model is used at the scheme layer to determine the initial network signal resources allocated to the target location.

[0045] This embodiment uses the Analytic Hierarchy Process (AHP) combined with a fuzzy comprehensive evaluation model to comprehensively analyze the environmental factors surrounding the target location, and preliminarily determines the allocation scheme of network signal resources, which can better meet the network usage needs of users in the target location. Whether it is daily communication, information inquiry, online entertainment, or mobile office work, more stable and faster network support can be obtained. This will improve user satisfaction with the relevant services in the target location and enhance user stickiness.

[0046] S130. Allocate initial network signal resources to the target location and analyze the network pressure status of terminal devices in the target location.

[0047] In this embodiment, the network stress state of a terminal device can be considered as the stress state exhibited by the terminal device when using network resources at the target location. Network stress state can be the ratio between the demand for network resources (generally actual usage demand) and the supply. When demand approaches or exceeds supply, the network is in a high-stress state. Alternatively, it can be the difference between the actual network state and the ideal network state; the greater the difference, the worse the network stress state.

[0048] In this embodiment, after determining the initial network signal resources, the determined initial network signal resources are allocated to the target location, and the actual network status data of the terminal devices in the target location is collected within a preset detection time. The network pressure status of the terminal devices is determined by analyzing the actual network status data.

[0049] S140. Adjust the initial network signal resources according to the network pressure status and surrounding environment data to obtain the target network signal resources allocated to the target location.

[0050] In this embodiment, a strategy optimization algorithm or a neural network is used to adjust the initial network signal resources based on the analyzed network pressure state and the collected surrounding environmental data, so that the obtained target network signal resources can meet the network requirements of the target location.

[0051] In this embodiment, a network prediction model can be constructed and trained. Network stress status and surrounding environmental data are input into the trained model to obtain target network signal resources allocated to the target location. Real-time monitoring and analysis of network usage stress allows for the rational allocation of network resources, preventing network congestion and failures, and improving network stability and reliability. Simultaneously, this also helps reduce network maintenance and management costs and improve operational efficiency.

[0052] The technical solution of this invention involves collecting surrounding environmental data of a target location; determining initial network signal resources allocated to the target location based on the analytic hierarchy process (AHP) and a fuzzy comprehensive evaluation model; allocating initial network signal resources to the target location and analyzing the network pressure status of terminal devices within the target location; and adjusting the initial network signal resources according to the network pressure status to obtain the target network signal resources allocated to the target location. By employing the AHP and fuzzy comprehensive evaluation model, qualitative environmental factors are transformed into quantitative resource requirements, scientifically determining the initial allocation scheme of network resources from multiple dimensions. Furthermore, a feedback mechanism based on network pressure status data is introduced to optimize the network signal resource allocation scheme. This maximizes network resource utilization while ensuring user experience, and simultaneously improves the automation and intelligence level of network operation.

[0053] Example 2

[0054] Figure 2 This is a flowchart of a network signal resource allocation method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further refines the method of determining the initial network signal resources allocated to the target location based on the analytic hierarchy process (AHP) and a fuzzy comprehensive evaluation model, according to the surrounding environmental data. The method includes: acquiring environmental factor vectors and evaluation level vectors corresponding to the surrounding environmental data; determining a fuzzy relation matrix between the environmental factor vectors and the evaluation level vectors; determining a weight vector corresponding to the environmental factor vectors based on the AHP; performing fuzzy synthesis operations on the fuzzy relation matrix and the weight vectors to obtain an environmental factor evaluation vector; and determining the initial network signal resources allocated to the target location based on the environmental factor evaluation vector.

[0055] like Figure 2 As shown, the method includes:

[0056] S210. Collect environmental data of the target location.

[0057] S220. Obtain the environmental factor vector and evaluation level vector corresponding to the surrounding environmental data, and determine the fuzzy relationship matrix between the environmental factor vector and the evaluation level vector.

[0058] In this embodiment, environmental factor vectors are obtained. , Let i represent the i-th environmental factor, and n be the number of evaluation indicators; obtain the evaluation level vector. , Let represent the j-th evaluation level, and m be the number of evaluation levels. For the i-th environmental factor... The degree of membership to each evaluation level is determined through methods such as expert scoring or data statistics. , Represents the i-th environmental factor For the j-th evaluation level Determine the degree of membership and construct a fuzzy relation matrix. .

[0059] S230. Determine the weight vectors corresponding to the environmental factor vectors based on the analytic hierarchy process.

[0060] In this embodiment, network planning experts are invited to perform pairwise comparisons of each environmental factor in the environmental factor vector, using a 1-9 scale to score them and construct a judgment matrix. The largest eigenvalue of the judgment matrix is ​​then calculated. And obtain the environmental factor vector. Corresponding weight vector To ensure the logical consistency of expert judgments, a consistency check can be performed on the weight vector. This involves calculating a consistency index. Where D is the order of the judgment matrix, and the consistency ratio is calculated based on the consistency index CI. RI is a random consistency index that can be obtained by looking up a table based on the order of the judgment matrix.

[0061] S240. Perform fuzzy synthesis operation on the fuzzy relation matrix and weight vector to obtain the environmental factor evaluation vector; determine the initial network signal resources allocated to the target site based on the environmental factor evaluation vector.

[0062] In this embodiment, the environmental factor evaluation vector is obtained through fuzzy comprehensive evaluation. ,in This represents fuzzy synthesis operations, which can be calculated using various methods such as weighted average and main factor prominence. The membership degree in the environmental factor evaluation vector is used as a weight to perform weighted calculations on various resources, obtaining the initial network signal resources allocated to the target location.

[0063] S250. Obtain the ideal network status data vector of the terminal equipment in the target location; the ideal network status data vector includes the ideal status values ​​of the terminal equipment in each preset network indicator.

[0064] The ideal network state data vector can include the network state of the terminal device under ideal conditions with multiple preset network indicators, such as the number of user connections, data traffic, and network latency. The ideal network state can be defined according to requirements.

[0065] In this embodiment, the ideal network state data vector can be , This sets the number of preset network metrics. For example, ideal network status data can be set as follows: number of user connections in the range of [500, 800], data traffic in the range of [1000 Mbps, 1500 Mbps], and network latency in the range of [10 ms, 30 ms].

[0066] S260. Collect the actual network status data vector of the terminal devices in the target location under various scenarios; the actual network status data vector includes the actual status values ​​of the terminal devices under preset network indicators.

[0067] The actual network status data vector can include the network status of terminal devices under multiple scenarios (different times or locations) and multiple preset network indicators. This network status can be represented by the average value of the network status of multiple terminal devices.

[0068] In this embodiment, the actual network state data vector collected in the g-th scenario can be represented as:

[0069] .

[0070] S270. Calculate the grey relational degree based on the ideal network state data vector and each actual network state data vector. The grey relational degree is used to measure the network pressure status of terminal devices in the target location under each scenario.

[0071] In this embodiment, based on the ideal network state data vector Each of the g-th actual network state data vectors Calculate the grey relational coefficient:

[0072]

[0073] in, The resolution coefficient is typically set to 0.5.

[0074] Then, the grey relational degree is calculated based on the grey relational coefficient. .

[0075] In this embodiment, the magnitude of the gray relational degree represents the degree of closeness between the actual network state and the ideal network state in each scenario. The smaller the closeness between the actual network state and the ideal network state, the lower the network pressure state of the terminal devices in the target location; conversely, the larger the closeness between the actual network state and the ideal network state, the higher the network pressure state of the terminal devices in the target location.

[0076] S280. Input the network stress state and surrounding environment data into the target network prediction model to obtain the target network signal resources of the target location output by the target network prediction model; wherein, the target network prediction model includes an input layer, a hidden layer and an output layer.

[0077] In this embodiment, the input layer is used to receive network stress status and surrounding environment data; the hidden layer has multiple neurons used to perform nonlinear transformations on the input data; and the output layer is used to predict target network signal resources.

[0078] The technical solution of this invention involves: collecting surrounding environmental data of a target location; obtaining environmental factor vectors and evaluation level vectors corresponding to the surrounding environmental data; determining a fuzzy relation matrix between the environmental factor vectors and evaluation level vectors; determining weight vectors corresponding to the environmental factor vectors based on the analytic hierarchy process (AHP); performing fuzzy synthesis operations on the fuzzy relation matrix and weight vectors to obtain environmental factor evaluation vectors; determining the initial network signal resources allocated to the target location based on the environmental factor evaluation vectors; acquiring ideal network state data vectors of terminal devices in the target location; the ideal network state data vectors include the ideal state values ​​of the terminal devices in each preset network indicator; collecting actual network state data vectors of terminal devices in the target location under each scenario; the actual network state data vectors include the actual state values ​​of the terminal devices in each preset network indicator; calculating gray relational degrees based on the ideal network state data vectors and each actual network state data vector, whereby the gray relational degrees are used to measure the network pressure state of the terminal devices in the target location under each scenario; and inputting the network pressure state and surrounding environmental data into a target network prediction model to obtain the target network signal resources of the target location output by the target network prediction model. The target network prediction model includes an input layer, a hidden layer, and an output layer. By employing the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation model, qualitative environmental factors are transformed into quantitative resource requirements. The initial allocation scheme of network resources is scientifically determined from multiple dimensions. Furthermore, a feedback mechanism based on network pressure status data is introduced to optimize the allocation scheme of network signal resources. This maximizes the utilization rate of network resources while ensuring user experience, and simultaneously improves the automation and intelligence level of network operation.

[0079] As an optional embodiment of this example, the training steps of the target network prediction model include: obtaining a training sample set, the training sample set including at least one sample triplet, the sample triplet including: real environmental sample data of the target location, real network stress state sample data and real network signal resources; and training the model parameters of the initial network prediction model based on the training sample set by combining particle swarm optimization algorithm and machine learning optimization method to obtain the target network prediction model.

[0080] In this embodiment, the training sample set can be obtained by processing and labeling historical real network stress state data and historical real network signal resources collected from the target scene.

[0081] In an optional implementation of this embodiment, the target network prediction model is obtained by combining particle swarm optimization algorithm and machine learning optimization method to train the model parameters of the initial network prediction model based on the training sample set, including:

[0082] Randomly initialize the position and velocity vectors of the particle swarm;

[0083] The position vector of each particle is decoded into a set of model parameters for the initial network prediction model, including weights and biases;

[0084] The real-world sample data is input into the initial network prediction model using the model parameters to obtain the predicted network signal resources;

[0085] For each particle, the initial network prediction model is calculated based on the predicted network signal resources and the real network signal resources. The model parameters are then adjusted based on the gradient descent method and the loss function value.

[0086] For each particle, the current fitness value is calculated based on the mean square error of the predicted network signal resources and the real network signal resources;

[0087] Update the individual optimal position and the global optimal position based on the current fitness value, and update the position and velocity of the particles according to the particle swarm optimization formula;

[0088] Return to the step of decoding the position vector of each particle into a set of model parameters for the initial network prediction model, including weights and biases, until the iteration termination condition is met;

[0089] The model parameters corresponding to the particle at the global optimal position are taken as the optimal model parameters, and the target network prediction model corresponding to the optimal model parameters is output.

[0090] In this embodiment, a predetermined number of particles are randomly generated to form a particle swarm, with each particle representing a set of parameters for the network prediction model. The particle's position vector represents a set of model parameters, and its velocity vector represents the adjustment direction and speed of the model parameters. The fitness function is defined as follows: the mean squared error is used as the fitness function, and the calculation formula is... ;

[0091] Where S is the number of samples in the training dataset. These are the network signal resources actually allocated to the target location. This refers to the network signal resources predicted by the model and allocated to the target location. The position vector of each particle is decoded into a set of model parameters for an initial network prediction model, including weights and biases. Real-world sample data is then input into the initial network prediction model using these model parameters to obtain the predicted network signal resources.

[0092] For each particle in the particle swarm, the loss function value is calculated based on the predicted network signal resources and the actual network signal resources output by the initial network prediction model, and the model parameters are adjusted based on the gradient descent method and the loss function value.

[0093] In each iteration, the parameters are updated along the gradient descent direction by calculating the gradient of the loss function with respect to the parameters, enabling the model to quickly converge to a local optimum. This allows backpropagation using gradient information to achieve a fine-grained local search. Then, the current fitness value is calculated based on the mean squared error of the predicted and actual network signal resources. The individual optimal position and the global optimal position are updated based on the current fitness value. The particle's position and velocity are updated using the individual's historical optimal position and the swarm's historical optimal position, helping to escape local optima and find the global optimum, achieving global exploration based on swarm intelligence. After each particle swarm update, the particle's new position is used as the initial parameters for the next backpropagation. In this way, backpropagation can perform a local search from a globally adjusted starting point. The iteration continues until the termination condition is met. The model parameters corresponding to the particle at the global optimal position are then used as the optimal model parameters, and the target network prediction model corresponding to these optimal model parameters is output.

[0094] In this embodiment, backpropagation in machine learning optimization focuses on local convergence, while particle swarm optimization focuses on global exploration. Combining particle swarm optimization and machine learning optimization methods can avoid getting stuck in local optima and accelerate the convergence speed. Furthermore, the learning rate of backpropagation and the parameters of particle swarm optimization (such as inertia weights) can be dynamically adjusted according to the iteration process to focus on global search in the early stage of iteration and on fine-grained local search in the later stage.

[0095] Example 3

[0096] Figure 3This is a schematic diagram of a network signal resource allocation device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an ambient environment data acquisition module 310, an initial network resource allocation module 320, a network stress status analysis module 330, and a target network resource allocation module 340; wherein:

[0097] The surrounding environment data acquisition module 310 is used to collect surrounding environment data of the target location;

[0098] The initial network resource allocation module 320 is used to determine the initial network signal resources allocated to the target location based on the surrounding environment data, using the analytic hierarchy process and fuzzy comprehensive evaluation model.

[0099] The network pressure status analysis module 330 is used to allocate the initial network signal resources to the target location and analyze the network pressure status of the terminal devices in the target location.

[0100] The target network resource allocation module 340 is used to adjust the initial network signal resources according to the network pressure status and surrounding environment data to obtain the target network signal resources allocated to the target location.

[0101] Optionally, the initial network resource allocation module 320 is specifically used for:

[0102] Obtain the environmental factor vector and evaluation level vector corresponding to the surrounding environmental data;

[0103] Determine the fuzzy relationship matrix between the environmental factor vector and the evaluation level vector;

[0104] The weight vectors corresponding to the environmental factor vectors are determined based on the aforementioned analytic hierarchy process.

[0105] A fuzzy synthesis operation is performed on the fuzzy relation matrix and the weight vector to obtain the environmental factor evaluation vector;

[0106] The initial network signal resources allocated to the target location are determined based on the environmental factor evaluation vector.

[0107] Optionally, the network stress state analysis module 330 is specifically used for:

[0108] Obtain the ideal network status data vector of the terminal device in the target location; the ideal network status data vector includes the ideal status value of the terminal device in each preset network indicator;

[0109] Collect actual network status data vectors of terminal devices in the target location under various scenarios; the actual network status data vectors include the actual status values ​​of the terminal devices under each of the preset network indicators;

[0110] The grey relational degree is calculated based on the ideal network state data vector and each of the actual network state data vectors. The grey relational degree is used to measure the network pressure status of terminal devices in the target location under each scenario.

[0111] Optionally, the target network resource allocation module 340 includes:

[0112] The network stress state and the surrounding environment data are input into the target network prediction model to obtain the target network signal resources of the target location output by the target network prediction model.

[0113] The target network prediction model includes an input layer, a hidden layer, and an output layer.

[0114] Optionally, it also includes a model training module, which includes:

[0115] The sample set acquisition module is used to acquire a training sample set, which includes at least one sample triplet, and the sample triplet includes: real environmental sample data of the target location, real network stress state sample data, and real network signal resources.

[0116] The model training module is used to combine particle swarm optimization algorithm and machine learning optimization method to train the model parameters of the initial network prediction model based on the training sample set, and obtain the target network prediction model.

[0117] Optionally, the model training module is specifically used for:

[0118] Randomly initialize the position and velocity vectors of the particle swarm;

[0119] The position vector of each particle is decoded into a set of model parameters for the initial network prediction model, including weights and biases;

[0120] The real-world sample data is input into the initial network prediction model using the model parameters to obtain the predicted network signal resources;

[0121] For each particle, the initial network prediction model is calculated based on the predicted network signal resources and the real network signal resources. The model parameters are then adjusted based on the gradient descent method and the loss function value.

[0122] For each particle, the current fitness value is calculated based on the mean square error of the predicted network signal resources and the real network signal resources;

[0123] Update the individual optimal position and the global optimal position based on the current fitness value, and update the position and velocity of the particles according to the particle swarm optimization formula;

[0124] Return to the step of decoding the position vector of each particle into a set of model parameters for the initial network prediction model, including weights and biases, until the iteration termination condition is met;

[0125] The model parameters corresponding to the particle at the global optimal position are taken as the optimal model parameters, and the target network prediction model corresponding to the optimal model parameters is output.

[0126] The network signal resource allocation device provided in this embodiment of the invention can execute the network signal resource allocation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0127] Example 4

[0128] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0129] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0130] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0131] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as network signal resource allocation methods.

[0132] In some embodiments, the network signal resource allocation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the network signal resource allocation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the network signal resource allocation method by any other suitable means (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] In some embodiments, the network signal resource allocation method may be implemented as a computer program, which is implicitly included in a computer program product. When executed by a processor, the computer program implements the network signal resource allocation method of the present invention. The computer program product can be understood as a software product that primarily implements its solution through a computer program. The computer program used to implement the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer program causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer program may be executed entirely on a machine, partially on a machine, partially on a remote machine as a standalone software package, or entirely on a remote machine or server.

[0135] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0137] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0138] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0139] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0140] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of allocating network signal resources, characterized by, The method comprises the following steps: collecting surrounding environment data of a target site; determining initial network signal resources allocated to the target site based on the surrounding environment data and a fuzzy comprehensive evaluation model based on an analytic hierarchy process; allocating the initial network signal resources to the target site and analyzing network pressure states of terminal devices in the target site; adjusting the initial network signal resources based on the network pressure states and the surrounding environment data to obtain target network signal resources allocated to the target site.

2. The method of claim 1, wherein, The method of determining the initial network signal resources allocated to the target site based on the surrounding environment data and the fuzzy comprehensive evaluation model based on the analytic hierarchy process comprises the following steps: obtaining an environment factor vector and an evaluation level vector corresponding to the surrounding environment data; determining a fuzzy relation matrix of the environment factor vector and the evaluation level vector; determining a weight vector corresponding to the environment factor vector based on the analytic hierarchy process; performing fuzzy synthesis operation on the fuzzy relation matrix and the weight vector to obtain an environment factor evaluation vector; determining the initial network signal resources allocated to the target site based on the environment factor evaluation vector.

3. The method of claim 1, wherein, The method of analyzing the network pressure states of the terminal devices in the target site comprises the following steps: obtaining an ideal network state data vector of the terminal devices in the target site; the ideal network state data vector comprises ideal state values of the terminal devices under each preset network index; collecting actual network state data vectors of the terminal devices in the target site under each scenario; the actual network state data vector comprises actual state values of the terminal devices under each preset network index; calculating a gray correlation degree based on the ideal network state data vector and each actual network state data vector; the gray correlation degree is used to measure the network pressure state of the terminal devices in the target site under each scenario.

4. The method of claim 1, wherein, The method of adjusting the initial network signal resources based on the network pressure states and the surrounding environment data to obtain the target network signal resources allocated to the target site comprises the following steps: inputting the network pressure states and the surrounding environment data into a target network prediction model to obtain target network signal resources of the target site output by the target network prediction model; wherein, the target network prediction model comprises an input layer, a hidden layer and an output layer.

5. The method of claim 4, wherein, The training steps of the target network prediction model comprise the following steps: obtaining a training sample set, the training sample set comprising at least one sample triple, the sample triple comprising: real environment sample data, real network pressure state sample data and real network signal resources of the target site; training model parameters of an initial network prediction model based on the training sample set by combining a particle swarm optimization algorithm and a machine learning optimization method to obtain the target network prediction model.

6. The method of claim 5, wherein, The method of training model parameters of an initial network prediction model based on the training sample set by combining a particle swarm optimization algorithm and a machine learning optimization method to obtain the target network prediction model comprises the following steps: randomly initializing a position vector and a velocity vector of a particle swarm; decode a position vector of each particle into a set of model parameters of the initial network prediction model, the model parameters including weights and biases; input the real environment sample data into the initial network prediction model using the model parameters to obtain a predicted network signal resource; for each particle pair, calculate a loss function value according to the predicted network signal resource and the real network signal resource, and adjust the model parameters based on a gradient descent method and the loss function value; for each particle, calculate a current fitness value according to a mean square error of the predicted network signal resource and the real network signal resource; update an individual optimal position and a global optimal position according to the current fitness value, and update a position and a speed of the particle according to a particle swarm optimization formula; return to perform the step of decoding the position vector of each particle into the set of model parameters of the initial network prediction model, the model parameters including the weights and the biases, until an iteration end condition is reached; take the model parameters corresponding to the particle of the global optimal position as optimal model parameters, and output a target network prediction model corresponding to the optimal model parameters.

7. A network signal resource allocation device, characterized in that, comprise: an ambient environment data acquisition module configured to acquire ambient environment data of a target site; an initial network resource allocation module configured to determine initial network signal resources allocated to the target site based on an analytic hierarchy process and a fuzzy comprehensive evaluation model according to the ambient environment data; a network pressure state analysis module configured to allocate the initial network signal resources to the target site and analyze network pressure states of terminal devices in the target site; a target network resource allocation module configured to adjust the initial network signal resources according to the network pressure states and the ambient environment data to obtain target network signal resources allocated to the target site.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the network signal resource allocation method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the network signal resource allocation method of any one of claims 1-6 when executed by the processor.

10. A computer program product, characterised in that, The computer program product comprises a computer program, which, when executed by the processor, implements the network signal resource allocation method of any one of claims 1-6. The computer program product comprises a computer program, which, when executed by the processor, implements the network signal resource allocation method of any one of claims 1-6.

Images