Network modal game evolution decision-making method and device

Abstract

The invention provides a network modal game evolution decision-making method and device. The method comprises the following steps: acquiring real service information at a target moment; inputting the real service information at the target moment into a pre-trained network modal game evolution decision model to obtain a network modal strategy; wherein the network modal game evolution decision model is obtained by training based on historical service data and network resource change data; the network mode strategy comprises a resource allocation evolution strategy of each network mode on a network element and a network mode addition and deletion evolution strategy in a global network environment. According to the method provided by the invention, for a new service request and network resource change at a certain moment, a resource allocation evolution strategy of each network mode on a network element is generated, and a network mode addition and deletion evolution strategy in a global network environment is given on a longer time scale, so that the network mode evolution strategy is perceived and adjusted through time-space integration; finally, performance is guaranteed and resource utilization rate is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a network modal game evolutionary decision-making method and device. Background Art

[0002] Polymorphic intelligent network is a technology that integrates multiple network technologies into a multimodal network in the form of network modes through programmable technology, striving to integrate the advantages of multiple networks and improve the network's ability to carry multiple services. The network multimodal symbiosis and evolution target model is based on the scalability of the entire life cycle of the infrastructure. In addition to the service quality commitment (S) and resource reusability (M) indicators of the traditional network, it introduces the network modal diversity (V) indicator and proposes the "evolution, generation, and symbiosis" three-aspect architecture of the network modality, which is reflected in the network modalities sharing and collaboratively utilizing the underlying resources in the same infrastructure to form a symbiotic state of network modalities, and constantly evolving with the business and resource conditions (expansion / reduction, generation / optimization / extinction, etc.). For the tasks of the model evolution aspect, it is reflected in the micro-level deduction of cooperative games between network modalities at different times to determine the timing and strategy of evolution; at the macro-level, quantitative evaluation is carried out with the goal of SMV optimality in the joint dimension of time and space throughout the life cycle to regulate the evolution path. The combination of the two provides a strong guarantee for achieving complete SMV intersection of multimodal networks throughout their life cycle.

[0003] Existing technologies are usually developed based on a single network mode scheduling algorithm. This approach usually focuses on the allocation and management of resources in a fixed network mode in a specific scenario, using heuristic methods or some AI algorithms to solve. At present, multimodal networks are still in the exploratory stage. According to the preliminary concept of multimodal networks, the entire plane is divided into data plane, control plane, and service plane, and algorithm optimization is performed under multi-dimensional definitions.

[0004] How to adjust the network mode evolution strategy to ultimately ensure performance and improve resource utilization is a technical problem that needs to be solved at present. Summary of the invention

[0005] The present invention provides a network modal game evolution decision method and device to solve the defects in the prior art.

[0006] The present invention provides a network modal game evolution decision-making method, comprising the following steps: Obtain real business information at the target moment; Inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0007] According to a network modality game evolution decision method provided by the present invention, the network modality game evolution decision model includes: a business situation prediction module, a business clustering and modality adaptation module, a network modality agile regulation module and a network modality long-term evolution module; The step of inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy includes: Inputting the real business information at the target moment into the business situation prediction module to obtain mixed business information; wherein the mixed business information includes: the real business information and the predicted business information; Inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship; wherein the first mapping relationship is: a matching relationship between the hybrid service and the network modality, and the second mapping relationship is: a matching relationship between the predicted service and the network modality; The first mapping relationship is input into the network mode agile control module to obtain the resource allocation evolution strategy of each network mode on the network element, and the second mapping relationship is input into the network mode long-term evolution module to obtain the network mode addition and deletion evolution strategy in the global network environment.

[0008] According to a network modal game evolution decision method provided by the present invention, the real business information at the target moment is input into the business situation prediction module to obtain mixed business information, including: Inputting the real business information at the target time into the business situation prediction module to obtain predicted business information; The real business information at the target moment and the predicted business information are merged according to a preset ratio to obtain the mixed business information.

[0009] According to a network modality game evolutionary decision method provided by the present invention, the service clustering and modality adaptation module comprises: a service clustering submodule and a modality adaptation submodule; The step of inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship includes: Inputting the mixed service information into the service clustering submodule, performing service clustering through meta-learning and adversarial learning algorithms, and obtaining multiple service clusters; The multiple service clusters are input into the modality adaptation submodule, and the service and network modality are adapted by a metric learning method to obtain the first mapping relationship and the second mapping relationship.

[0010] According to a network modality game evolution decision method provided by the present invention, the first mapping relationship is input into the network modality agile control module to obtain the resource allocation evolution strategy of each network modality on the network element, including: The first mapping relationship and the first network configuration information are input into the network mode agile control module, and the network configuration information at the next moment is generated through cooperative game between different network modes; wherein the network configuration information at the next moment is: the division ratio of each network mode resource on each network element.

[0011] According to a network modality game evolution decision method provided by the present invention, the second mapping relationship is input into the network modality long-term evolution module to obtain the network modality addition and deletion evolution strategy in the global network environment, including: The second mapping relationship and the second network configuration information are input into the network modality long-term evolution module, and the network modality configuration at the next moment is obtained through a reinforcement learning algorithm; wherein, the network modality configuration at the next moment is: the network modality addition and deletion evolution strategy in the global network environment and the characteristic information of the new modality.

[0012] The present invention also provides a network modality game evolution decision-making device, comprising the following modules: An acquisition unit, used to acquire real business information at a target time; A decision-making unit, used for inputting the real business information at the target moment into a pre-trained network modality game evolution decision model to obtain a network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0013] According to a network modality game evolution decision device provided by the present invention, the network modality game evolution decision model includes: a business situation prediction module, a business clustering and modality adaptation module, a network modality agile regulation module and a network modality long-term evolution module; The decision-making unit is specifically used for: Inputting the real business information at the target moment into the business situation prediction module to obtain mixed business information; wherein the mixed business information includes: the real business information and the predicted business information; Inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship; wherein the first mapping relationship is: a matching relationship between the hybrid service and the network modality, and the second mapping relationship is: a matching relationship between the predicted service and the network modality; The first mapping relationship is input into the network mode agile control module to obtain the resource allocation evolution strategy of each network mode on the network element, and the second mapping relationship is input into the network mode long-term evolution module to obtain the network mode addition and deletion evolution strategy in the global network environment.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the network modal game evolution decision method as described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the network modal game evolutionary decision-making methods described above.

[0016] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned network modal game evolution decision-making methods.

[0017] The present invention provides a network modal game evolutionary decision-making method and device, which obtains the real business information at the target moment; inputs the real business information at the target moment into the pre-trained network modal game evolutionary decision model to obtain the network modal strategy; wherein the network modal game evolutionary decision model is: trained based on historical business data and network resource change data; the network modal strategy includes: resource allocation evolutionary strategy of each network mode on the network element and network modal addition and deletion evolutionary strategy in the global network environment. It can be seen that the present invention obtains the network modal game evolutionary decision model through training, generates resource allocation evolutionary strategy of each network mode on the network element for new business requests and network resource changes at a certain moment, and gives the network modal addition and deletion evolutionary strategy in the global network environment on a longer time scale, so as to realize the perception and adjustment of the network modal evolutionary strategy through time-space integration, and finally ensure performance and improve resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0019] Figure 1 It is a flow chart of the network modal game evolutionary decision-making method provided by the present invention.

[0020] Figure 2 It is a complete flow chart of the network modal game evolutionary decision-making method provided by the present invention.

[0021] Figure 3 It is a schematic diagram of the principle of the network modal game evolutionary decision model provided by the present invention.

[0022] Figure 4 It is a structural schematic diagram of the network modal game evolution decision-making device provided by the present invention.

[0023] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Combine the following Figure 1-Figure 5 A network modal game evolution decision-making method and device of the present invention are described.

[0026] It should be noted that in the prior art, (1) scheduling algorithms are developed based on a single network mode. This approach usually focuses on the allocation and management of resources in a fixed network mode under a specific scenario, and uses heuristic methods or some AI algorithms to solve the problem. (2) Attempts based on the concept of multimodal networks. At present, multimodal networks are still in the exploratory stage. According to the preliminary concept of multimodal networks, the entire plane is divided into a data plane, a control plane, and a service plane, and the algorithm is optimized under multi-dimensional definitions. Based on this, the present invention provides a network modal game evolution decision-making method to solve at least one of the above problems.

[0027] Figure 1 is a flow chart of the network modal game evolutionary decision-making method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 100: Obtain real business information at the target time.

[0028] Figure 2 This is a complete flow chart of the network modal game evolution decision method provided by the present invention. Figure 2The network modal game evolution decision-making method provided by the present invention is explained.

[0029] It should be noted that the products or projects applying the present invention are: any environment that supports multimodal networks. For example, by implanting the model framework of this article in the top-level controller in a network environment composed of a series of network elements with multi-network modal processing capabilities, such as communication networks, social networks, and the Internet of Things, and using time-space integrated perception technology to perceive business and network resource changes, and providing network modal evolution strategies at the right time, ultimately improving the overall service quality and resource utilization of the multimodal network. Network operators can achieve precise control and long-term evolution management of network modalities, improve network performance and resource utilization efficiency, and reduce operating costs; users can also obtain better service quality assurance.

[0030] Specifically, see Figure 2 ,The real business information at the target moment can be real-time business information consisting of multiple business requirements.

[0031] Step 200: input the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0032] It should be noted that, continue to refer to Figure 2 The network modality game evolution decision model includes: a business situation prediction module, a business clustering and modality adaptation module, a network modality agile regulation module and a network modality long-term evolution module.

[0033] This embodiment proposes a new network modality game evolution mechanism for a multimodal network environment. Figure 2 As shown in the figure, its core is a decision-making model composed of an agile control module and a long-term evolution module, and a situation prediction module and a business clustering and modal adaptation module to realize space-time integrated perception as the input of the two core modules. The model can use AI technology, especially the ability of reinforcement learning technology to dynamically generate strategies according to changes in environmental states and data-driven situation prediction technology to regulate network modal resource allocation at the micro level and regulate the number of network modes and feature output strategies at the macro level to complete network modal evolution.

[0034] Step 200 inputs the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy, including: Step 210: Input the real business information at the target moment into the business situation prediction module to obtain mixed business information; wherein the mixed business information includes: the real business information and predicted business information.

[0035] Step 210 specifically includes: Step 211: input the real business information at the target moment into the business situation prediction module to obtain predicted business information.

[0036] Step 212: Fuse the real business information at the target moment and the predicted business information according to a preset ratio to obtain the mixed business information.

[0037] In one embodiment, Figure 3 It is a schematic diagram of the principle of the network modal game evolution decision model provided by the present invention, such as Figure 3 As shown, at a moment Taking as an example, the specific description is as follows.

[0038] 1) Data-driven situation prediction module outputs mixed business information .

[0039] Taking into account that business spontaneity (irregular changes, nonlinear growth, etc.) may affect system stability and strategy smoothness, a data-driven situation prediction module is used to use historical business information for the current moment. The timing module in the module fuses the real business input with the predicted business according to a certain ratio to obtain mixed business information. .

[0040] Step 220: input the hybrid service information into the service clustering and modal adaptation module to obtain a first mapping relationship and a second mapping relationship; wherein the first mapping relationship is: a hybrid service and a network modality matching relationship, and the second mapping relationship is: a predicted service and a network modality matching relationship.

[0041] It should be noted that the service clustering and modality adaptation module includes: a service clustering submodule and a modality adaptation submodule.

[0042] Step 220 specifically includes: Step 221: input the mixed service information into the service clustering submodule, perform service clustering through meta-learning and adversarial learning algorithms, and obtain multiple service clusters.

[0043] Step 222: input the multiple service clusters into the modality adaptation submodule, adapt the service and network modality through a metric learning method, and obtain the first mapping relationship and the second mapping relationship.

[0044] In one embodiment, continue to see Figure 3 , the specific instructions are as follows.

[0045] 2) Business clustering to obtain clusters .

[0046] According to the business S, M, V characteristics, based on its characteristic space and time distribution, meta-learning and adversarial learning algorithms are used to complete business adaptive clustering to obtain different business clusters. .

[0047] 3) Network mode adaptation obtains the adaptation of services and network modes .

[0048] Using metric learning methods, such as mapping service cluster characteristics and network modality characteristics to a unified metric space through learnable parameters A , and finally complete the adaptation of the business and network modes to obtain their mapping relationship , together with the situation prediction and business clustering modules, it realizes the spatiotemporal integrated perception of the business, which serves as an important component of the input of the subsequent two core modules.

[0049] Step 230: input the first mapping relationship into the network mode agile control module to obtain the resource allocation evolution strategy of each network mode on the network element, and input the second mapping relationship into the network mode long-term evolution module to obtain the network mode addition and deletion evolution strategy in the global network environment.

[0050] Step 230 specifically includes: Step 231: input the first mapping relationship and the first network configuration information into the network mode agile control module, and generate the network configuration information at the next moment through cooperative game between different network modes; wherein the network configuration information at the next moment is: the division ratio of each network mode resource on each network element.

[0051] In one embodiment, continue to see Figure 3 , the specific instructions are as follows.

[0052] 4) The network mode agile control module obtains the network configuration at the next moment .

[0053] On a smaller time scale Based on the input mixed business information and the first network configuration information , through cooperative games between different network modes, the network configuration information for the next moment is generated , the network configuration information is the allocation ratio of each network modality resource on each network element. By using the reinforcement learning algorithm and adopting the multi-agent structure, different network elements are modeled as tuples of state, action, and reward. ,in Represents a state set, Representing an Agent The set of actions and rewards. The time input is , through the observed value of the reward Generating action policies , and finally obtain the network configuration at the next moment The action space of this part is the ratio of each network mode resource on each network element, and the reward is resource utilization and business service quality (QoS considerations such as latency, etc.). This module can generate resource configuration strategies on network elements to ensure network mode resource utilization and business service quality.

[0054] Step 232: input the second mapping relationship and the second network configuration information into the network modality long-term evolution module, and obtain the network modality configuration at the next moment through a reinforcement learning algorithm; wherein, the network modality configuration at the next moment is: the network modality addition and deletion evolution strategy in the global network environment and the feature information of the new modality.

[0055] In one embodiment, continue to see Figure 3 , the specific instructions are as follows.

[0056] 5) The network mode long-term evolution module obtains the network mode configuration at the next moment .

[0057] On a larger time scale Based on the input, predict business information and the second network configuration information , generate the network mode configuration at the next moment through reinforcement learning algorithm In the reinforcement learning setting, the input is , through the observed value of the reward Generate the configuration of each mode in the network at the next moment, that is, the action strategy , and finally obtain the network status at the next moment . In this part, the action space of the algorithm is the number of network modes and feature configuration, and the optimization goal is to improve the average task service quality and overall network resource utilization. The triggering conditions of this module are divided into three parts: ① When the previous step network mode agile control module cannot continuously optimize the task service quality and resource utilization; ② or when the existing network mode cannot meet the new business needs; ③ or when a certain preset time is reached, this module is executed, and by fully weighing the network mode deployment cost and adjustment benefits, the network mode addition and deletion strategy and the feature information of the new mode are given.

[0058] Based on the above embodiments, in this embodiment, the training of the model includes three parts, namely, the training of four modules: the business clustering and modal adaptation module, the network modal agile regulation module, and the network modal long-term evolution module. In particular, when training the network modal agile regulation module, the input used is a mixture of real business and predicted business information, in order to prevent the business from changing with the trend and affecting the stability of the system. At the same time, when training the network modal long-term evolution module, the input used is only the predicted business information, in order to enhance the smoothness of the strategy and reduce the impact of business mutations on the quality of the strategy.

[0059] In the network system, a large amount of existing business data and network resource change data can be used to train the network modality agile control module and the network modality long-term evolution module according to the method described in the above embodiment. For new business requests and network resource changes at a certain moment, the previously trained network modality agile control model is used to generate the resource allocation evolution strategy of each network mode on the network element, and the network modality addition and deletion evolution strategy in the global network environment is given through the network modality long-term evolution model on a longer time scale.

[0060] On a smaller time scale, the number and characteristics of existing network modes are considered quantitative. The business data obtained by mixing real business information with the predicted business information obtained through the timing module in proportion and the information matched to the corresponding network mode can be injected into the network mode agile control model to meet the demand for network resources caused by business changes and improve resource utilization and network service quality.

[0061] On a larger time scale, the business information and network resource change information obtained after the situation prediction of the time series module are fully used and injected into the long-term evolution model of the network mode, fully considering the costs caused by the addition and deletion of network modes and the gains of existing network modes, to provide guarantees for the stable operation of the network and long-term resource utilization.

[0062] The network modality game evolution decision method provided by the embodiment of the present invention, at the micro level, based on the spatiotemporal sequence prediction model, uses historical network data to realize accurate situation prediction of future business and resources, and provides a basis for network situation deduction; the network modality competition network local resources are modeled as a micro game decision problem, and a network modality agile regulation mechanism is constructed to realize multi-agent cooperative game deduction of multiple network modalities in the local network, providing accurate timing and strategy for network modality evolution; at the macro level, based on long-term SMV quantitative indicator evaluation and feedback, a deep learning model for the characteristics of network modality data is used to construct a long-term evolution mechanism of network modality, adjust the evolution path of network modality and provide network modality evolution strategy. The problem it solves is to perceive and adjust the network modality evolution strategy through spatiotemporal integration in the multi-network modality ring competition and cooperation environment, and ultimately guarantee performance and improve resource utilization.

[0063] The above is a description of the steps of the network modality game evolutionary decision method provided by the present invention. From the description of the above steps, it can be seen that according to the network modality game evolutionary decision method provided by the present invention, by obtaining the real business information at the target moment; the real business information at the target moment is input into the pre-trained network modality game evolutionary decision model to obtain the network modality strategy; wherein, the network modality game evolutionary decision model is: trained based on historical business data and network resource change data; the network modality strategy includes: resource allocation evolution strategy of each network mode on the network element and network modality addition and deletion evolution strategy in the global network environment. It can be seen that the present invention obtains the network modality game evolutionary decision model through training, generates the resource allocation evolution strategy of each network mode on the network element for new business requests and network resource changes at a certain moment, and gives the network modality addition and deletion evolution strategy in the global network environment on a longer time scale, so as to realize the perception and adjustment of the network modality evolution strategy through time and space integration, and finally ensure performance and improve resource utilization.

[0064] The network modal game evolution decision-making device provided by the present invention is described below. The network modal game evolution decision-making device described below and the network modal game evolution decision-making method described above can be referred to each other.

[0065] Figure 4 is a schematic diagram of the structure of the network modal game evolution decision-making device provided by the present invention, such as Figure 4 As shown, the network modality game evolution decision-making device provided by the present invention includes: An acquisition unit 401 is used to acquire real business information at a target time; A decision unit 402, configured to input the real business information at the target moment into a pre-trained network modality game evolution decision model to obtain a network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0066] The network modality game evolution decision device provided by the present invention obtains the real business information at the target moment; inputs the real business information at the target moment into the pre-trained network modality game evolution decision model to obtain the network modality strategy; wherein the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: resource allocation evolution strategy of each network mode on the network element and network modality addition and deletion evolution strategy in the global network environment. It can be seen that the present invention obtains the network modality game evolution decision model through training, generates resource allocation evolution strategy of each network mode on the network element for new business requests and network resource changes at a certain moment, and gives the network modality addition and deletion evolution strategy in the global network environment on a longer time scale, so as to realize the perception and adjustment of the network modality evolution strategy through time and space integration, and finally ensure performance and improve resource utilization.

[0067] Based on the above embodiment, in this embodiment, the network modality game evolution decision model includes: a business situation prediction module, a business clustering and modality adaptation module, a network modality agile regulation module and a network modality long-term evolution module; The decision unit 402 is specifically configured to: Inputting the real business information at the target moment into the business situation prediction module to obtain mixed business information; wherein the mixed business information includes: the real business information and the predicted business information; Inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship; wherein the first mapping relationship is: a matching relationship between the hybrid service and the network modality, and the second mapping relationship is: a matching relationship between the predicted service and the network modality; The first mapping relationship is input into the network mode agile control module to obtain the resource allocation evolution strategy of each network mode on the network element, and the second mapping relationship is input into the network mode long-term evolution module to obtain the network mode addition and deletion evolution strategy in the global network environment.

[0068] Based on the above embodiment, in this embodiment, the device further includes a fusion unit, which is specifically used for: Inputting the real business information at the target time into the business situation prediction module to obtain predicted business information; The real business information at the target moment and the predicted business information are merged according to a preset ratio to obtain the mixed business information.

[0069] Based on the above embodiment, in this embodiment, the service clustering and modality adaptation module includes: a service clustering submodule and a modality adaptation submodule; The device also includes a mapping unit, which is specifically configured to: Inputting the mixed service information into the service clustering submodule, performing service clustering through meta-learning and adversarial learning algorithms, and obtaining multiple service clusters; The multiple service clusters are input into the modality adaptation submodule, and the service and network modality are adapted by a metric learning method to obtain the first mapping relationship and the second mapping relationship.

[0070] Based on the above embodiments, in this embodiment, the decision unit 402 is specifically used for: The first mapping relationship and the first network configuration information are input into the network mode agile control module, and the network configuration information at the next moment is generated through cooperative game between different network modes; wherein the network configuration information at the next moment is: the division ratio of each network mode resource on each network element.

[0071] Based on the above embodiments, in this embodiment, the decision unit 402 is specifically used for: The second mapping relationship and the second network configuration information are input into the network modality long-term evolution module, and the network modality configuration at the next moment is obtained through a reinforcement learning algorithm; wherein, the network modality configuration at the next moment is: the network modality addition and deletion evolution strategy in the global network environment and the characteristic information of the new modality.

[0072] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may be a robot or other electronic device, and the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the network modal game evolution decision method, including: Obtain real business information at the target moment; Inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0073] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0074] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the network modal game evolution decision method provided by the above methods, including: Obtain real business information at the target moment; Inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0075] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the network modal game evolution decision method provided by the above methods, including: Obtain real business information at the target moment; Inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

[0076] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A network modal game evolutionary decision-making method, characterized in that: include: Obtain real business information at the target moment; Inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

2. The network modality game evolution decision-making method according to claim 1, characterized in that: The network modality game evolution decision model includes: a business situation prediction module, a business clustering and modality adaptation module, a network modality agile regulation module and a network modality long-term evolution module; The step of inputting the real business information at the target time into the pre-trained network modality game evolution decision model to obtain the network modality strategy includes: Inputting the real business information at the target moment into the business situation prediction module to obtain mixed business information; wherein the mixed business information includes: the real business information and the predicted business information; Inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship; wherein the first mapping relationship is: a matching relationship between the hybrid service and the network modality, and the second mapping relationship is: a matching relationship between the predicted service and the network modality; The first mapping relationship is input into the network mode agile control module to obtain the resource allocation evolution strategy of each network mode on the network element, and the second mapping relationship is input into the network mode long-term evolution module to obtain the network mode addition and deletion evolution strategy in the global network environment.

3. The network modality game evolution decision-making method according to claim 2, characterized in that: The step of inputting the real business information at the target time into the business situation prediction module to obtain mixed business information includes: Inputting the real business information at the target time into the business situation prediction module to obtain predicted business information; The real business information at the target moment and the predicted business information are merged according to a preset ratio to obtain the mixed business information.

4. The network modality game evolution decision-making method according to claim 2, characterized in that: The business clustering and modality adaptation module includes: a business clustering submodule and a modality adaptation submodule; The step of inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship includes: Inputting the mixed service information into the service clustering submodule, performing service clustering through meta-learning and adversarial learning algorithms, and obtaining multiple service clusters; The multiple service clusters are input into the modality adaptation submodule, and the service and network modality are adapted by a metric learning method to obtain the first mapping relationship and the second mapping relationship.

5. The network modality game evolution decision-making method according to claim 2, characterized in that: The step of inputting the first mapping relationship into the network mode agile control module to obtain a resource allocation evolution strategy for each network mode on a network element includes: The first mapping relationship and the first network configuration information are input into the network mode agile control module, and the network configuration information at the next moment is generated through cooperative game between different network modes; wherein the network configuration information at the next moment is: the division ratio of each network mode resource on each network element.

6. The network modality game evolution decision-making method according to claim 2, characterized in that: The step of inputting the second mapping relationship into the network modality long-term evolution module to obtain a network modality addition and deletion evolution strategy in a global network environment includes: The second mapping relationship and the second network configuration information are input into the network modality long-term evolution module, and the network modality configuration at the next moment is obtained through a reinforcement learning algorithm; wherein, the network modality configuration at the next moment is: the network modality addition and deletion evolution strategy in the global network environment and the characteristic information of the new modality.

7. A network modal game evolution decision-making device, characterized in that: include: An acquisition unit, used to acquire real business information at a target time; A decision-making unit, used for inputting the real business information at the target moment into a pre-trained network modality game evolution decision model to obtain a network modality strategy; Among them, the network modality game evolution decision model is: obtained by training based on historical business data and network resource change data; the network modality strategy includes: the resource allocation evolution strategy of each network mode on the network element and the network modality addition and deletion evolution strategy in the global network environment.

8. The network modality game evolution decision-making device according to claim 7, characterized in that: The network modality game evolution decision model includes: a business situation prediction module, a business clustering and modality adaptation module, a network modality agile regulation module and a network modality long-term evolution module; The decision-making unit is specifically used for: Inputting the real business information at the target moment into the business situation prediction module to obtain mixed business information; wherein the mixed business information includes: the real business information and the predicted business information; Inputting the hybrid service information into the service clustering and modality adaptation module to obtain a first mapping relationship and a second mapping relationship; wherein the first mapping relationship is: a matching relationship between the hybrid service and the network modality, and the second mapping relationship is: a matching relationship between the predicted service and the network modality; The first mapping relationship is input into the network mode agile control module to obtain the resource allocation evolution strategy of each network mode on the network element, and the second mapping relationship is input into the network mode long-term evolution module to obtain the network mode addition and deletion evolution strategy in the global network environment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the network modal game evolution decision method as described in any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the network modal game evolution decision method as described in any one of claims 1 to 6 is implemented.

Images