Model enhancement training method, device, electronic device and storage medium

Abstract

The present invention discloses a model enhancement training method, device, electronic device and storage medium, the method comprising: obtaining an analysis information request of a service consumer, transmitting the analysis information request to a multi-node cluster; obtaining multiple network data analysis function groups according to the analysis information request; and obtaining corresponding machine learning models; when it is a model training for non-common members, generating a key based on the obtained network data analysis function group and the corresponding machine learning model; then obtaining an encrypted sample based on the key; obtaining a fusion machine learning model based on the machine learning model and the encrypted sample; training the fusion machine learning model through all local samples, transmitting the trained fusion machine learning model to each network data analysis function group; updating and iterating each machine learning model until a preset condition is met. The present invention can efficiently perform model enhancement training and can be widely used in the field of data processing technology.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a model enhancement training method, device, electronic device and storage medium. Background Art

[0002] In the 5G network architecture, NWDAF network elements are introduced in the core network as the bearer entity for customized data collection and intelligent analysis. It can not only collect data from NF, AF, and OAM of the 5G core network (5GC), but also has the ability of intelligent analysis (such as calculation, training, reasoning and prediction, etc.), and output the analysis results to NF or AF or OAM for NF, AF or OAM decision-making. With the continuous evolution of standards, the NWDAF network element itself, the network analysis process, and the data collection process have been enhanced. The R16 and R17 standards define 14 and 7 UCs mainly for network self-optimization, such as: assisting UPF selection, assisting QoS parameter adjustment, assisting AMF in mobility management, assisting in achieving network element / slice load balancing, UE-related data collection and analysis, and assisting in abnormal time detection and positioning, such as congestion feedback. At present, NWDAF deployment and implementation are basically carried out around each UC, and model training is centered around each UC, while combining user portraits, terminal behavior, network experience portraits, and connection portraits. Summary of the invention

[0003] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the present invention proposes a model enhancement training method, device, electronic device and storage medium, which can efficiently perform model enhancement training.

[0004] On the one hand, an embodiment of the present invention provides a model enhancement training method, comprising:

[0005] Obtaining analysis information requests from service consumers, and transmitting the analysis information requests to a multi-node cluster; the multi-node cluster includes a number of network data analysis function groups;

[0006] According to the analysis information request, multiple network data analysis function groups are obtained from the multi-node cluster; and the machine learning model in each network data analysis function group is obtained;

[0007] When the machine learning models trained in the obtained multiple network data analysis function groups are model training for non-common members, a key is generated based on the obtained network data analysis function groups and the corresponding machine learning models; and then an encrypted sample is obtained based on the key;

[0008] Based on the machine learning model corresponding to the obtained network data analysis function group, a fusion machine learning model is obtained in combination with the encrypted sample; the fusion machine learning model is trained through all local samples, and the trained fusion machine learning model is transmitted to each network data analysis function group of the multi-node cluster;

[0009] Based on the trained fusion machine learning model, the machine learning model corresponding to each network data analysis function group of the multi-node cluster is updated and iterated until the preset conditions are met.

[0010] Optionally, the request for obtaining analysis information of the service consumer includes at least one of the following:

[0011] Get subscription messages to machine learning models sent by service consumers;

[0012] Get the request message for the machine learning model sent by the service consumer.

[0013] Optionally, the analysis information request includes an analysis ID; and according to the analysis information request, multiple network data analysis function groups are obtained from the multi-node cluster, including:

[0014] The pre-selected model type is determined based on the analysis ID, and then the cluster members are dynamically selected through the multi-node cluster to obtain multiple network data analysis function groups.

[0015] Optionally, before the step of obtaining multiple network data analysis function groups from the multi-node cluster, the method further includes:

[0016] Each network data analysis function group uses local data to train the machine learning model of the network data analysis function group.

[0017] Optionally, obtaining an encrypted sample based on a key includes:

[0018] The sample data of multiple network data analysis function groups obtained are encrypted by using a key to obtain encrypted samples.

[0019] Optionally, based on the trained fusion machine learning, the machine learning model corresponding to each network data analysis function group of the multi-node cluster is updated and iterated until a preset condition is met, including:

[0020] Based on the trained fusion machine learning model, new sample training is performed on each network data analysis function group of the multi-node cluster respectively, and then the machine learning model of each network data analysis function group is updated accordingly until the model training reaches the preset accuracy.

[0021] Optionally, the method further comprises:

[0022] Return the training results of the machine learning model corresponding to each network data analysis function group to the multi-node cluster;

[0023] The training results are pushed to the service consumers through a multi-node cluster.

[0024] On the other hand, an embodiment of the present invention provides a model enhancement training device, comprising:

[0025] The first module is used to obtain the analysis information request of the service consumer and transmit the analysis information request to the multi-node cluster; the multi-node cluster includes a plurality of network data analysis function groups;

[0026] The second module is used to obtain multiple network data analysis function groups from the multi-node cluster according to the analysis information request; and obtain the machine learning model in each network data analysis function group;

[0027] The third module is used to generate a key based on the obtained network data analysis function group and the corresponding machine learning model when the machine learning model trained in the obtained multiple network data analysis function groups is a model training for non-common members; and then obtain an encrypted sample based on the key;

[0028] The fourth module is used to obtain a fusion machine learning model based on the machine learning model corresponding to the acquired network data analysis function group and in combination with the encrypted sample; the fusion machine learning model is trained through all local samples, and the trained fusion machine learning model is transmitted to each network data analysis function group of the multi-node cluster;

[0029] The fifth module is used to update and iterate the machine learning model corresponding to each network data analysis function group of the multi-node cluster based on the trained fusion machine learning model until the preset conditions are met.

[0030] Optionally, the device further comprises:

[0031] The sixth module is used to return the training results of the machine learning model corresponding to each network data analysis function group to the multi-node cluster;

[0032] The seventh module is used to push the training results to the service consumer through a multi-node cluster.

[0033] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store programs; the processor executes the program to implement the above-mentioned model enhancement training method.

[0034] On the other hand, an embodiment of the present invention provides a computer storage medium, which stores a program executable by a processor, and the program executable by the processor is used to implement the above-mentioned model enhancement training method when executed by the processor.

[0035] The embodiment of the present invention obtains the analysis information request of the service consumer, and transmits the analysis information request to the multi-node cluster; the multi-node cluster includes several network data analysis function groups; according to the analysis information request, multiple network data analysis function groups are obtained from the multi-node cluster; and the machine learning models in each network data analysis function group are obtained; when the machine learning models trained in the obtained multiple network data analysis function groups are model training for non-common members, a key is generated based on the obtained network data analysis function group and the corresponding machine learning model; and then an encrypted sample is obtained based on the key; based on the machine learning model corresponding to the obtained network data analysis function group, a fusion machine learning model is obtained in combination with the encrypted sample; the fusion machine learning model is trained through all local samples, and the trained fusion machine learning model is transmitted to each network data analysis function group of the multi-node cluster; based on the trained fusion machine learning model, the machine learning model corresponding to each network data analysis function group of the multi-node cluster is updated and iterated until the preset conditions are met. The embodiment of the present invention can efficiently perform model enhancement training through the collaborative training of different network data analysis function groups and the model training for non-common members. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0037] Figure 1 It is a schematic diagram of an implementation environment for model enhancement training provided by an embodiment of the present invention;

[0038] Figure 2 It is a flowchart of a model enhancement training method provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of the expansion process of obtaining an analysis information request provided by an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of the development process of the model enhancement training method provided by an embodiment of the present invention based on local data training;

[0041] Figure 5 A schematic diagram of the expanded flow of training result push provided in an embodiment of the present invention;

[0042] Figure 6A schematic diagram of the overall business process of the model enhancement training method provided in an embodiment of the present invention;

[0043] Figure 7 A schematic diagram of a business process for subscription to an NWDAF service provided in an embodiment of the present invention;

[0044] Figure 8 A schematic diagram of the structure of a model enhancement training device provided by an embodiment of the present invention;

[0045] Fig. 9 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0046] Fig.10 A block diagram of the computer system structure of an electronic device suitable for implementing the embodiment of the present invention is provided for the embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0049] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0050] It should be noted that, in order to facilitate the understanding of the technical solution of the present invention, the professional and technical terms that may appear in the embodiments of the present invention are first explained:

[0051] NWDAF (Network Data Analytics Function);

[0052] OAM (Operation Administration and Maintenance);

[0053] In the 5G core network (5GC), each node is called a network function (NF), among which the node of the external application server is called AF (application function);

[0054] QoS (Quality of Service) refers to a network's ability to use various basic technologies to provide better service capabilities for specified network communications. It is a network security mechanism and a technology used to solve problems such as network delays and congestion.

[0055] UC (Use Case).

[0056] It is understandable that the model enhancement training method provided in the embodiment of the present invention can be applied to any computer device with data processing computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud data blocks, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, a tablet computer, a laptop computer, and a desktop computer, but is not limited to this.

[0057] like Figure 1 FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention. Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0058] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud data blocks, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0059] In addition, the server 101 can also be a node server in the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0060] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present invention.

[0061] Based on the example Figure 1 In the implementation environment shown, an embodiment of the present invention provides a model enhancement training method. The following is an example of the model enhancement training method being applied in the server 101. It can be understood that the model enhancement training method can also be applied in the terminal 102.

[0062] Reference Figure 2 , Figure 2 The flowchart of the model enhancement training method applied to the server provided in the embodiment of the present invention, the execution subject of the model enhancement training method can be any of the aforementioned computer devices (including servers or terminals). Figure 2 , the method comprises the following steps:

[0063] S100, obtaining an analysis information request from a service consumer, and transmitting the analysis information request to a multi-node cluster;

[0064] It should be noted that the multi-node cluster includes several network data analysis function groups; Figure 3 As shown, in some embodiments, obtaining the analysis information request of the service consumer may include at least one of the following: S101, obtaining the subscription message for the machine learning model sent by the service consumer; S102, obtaining the request message for the machine learning model sent by the service consumer.

[0065] For example, in some specific embodiments, the subscription of NWDAF service:

[0066] 1. NWDAF service consumers subscribe to ML (machine learning) models from NWDAF (including MTLF): ① Parameters that NWDAF service consumers can provide include a list of analysis IDs and the ability to select ML models, such as selecting ML models based on the S-NSSAI and region to which the ML model applies; ② ML model address, ML model applicable time, and applicable region, etc.

[0067] 2. The NWDAF service consumer requests the ML model from the NWDAF (including MTLF): ① Request the ML model associated with the analysis ID for analysis and derivation; ② When the NWDAF (including MTLF) receives the request for ML model information, it determines whether the existing ML model needs further training. If so, the NWDAF needs to start the data collection operation and use it for ML model training. After the training is completed, it provides the ML model address, etc.

[0068] S200, obtaining multiple network data analysis function groups from a multi-node cluster according to an analysis information request; and obtaining a machine learning model in each network data analysis function group;

[0069] It should be noted that the analysis information request includes an analysis ID; in some embodiments, obtaining multiple network data analysis function groups from a multi-node cluster based on the analysis information request may include: determining a pre-selected model type based on the analysis ID, and then dynamically selecting cluster members through the multi-node cluster to obtain multiple network data analysis function groups.

[0070] For example, in some specific embodiments, non-common members need to dynamically select NWDAF based on parameters such as user type, request analysis ID, inference ML model, and model training time.

[0071] It should also be noted that if Figure 4 As shown, in some embodiments, before the step of obtaining multiple network data analysis function groups from a multi-node cluster, the method may also include: each network data analysis function group uses local data to train a machine learning model of the network data analysis function group.

[0072] Exemplarily, in some specific embodiments, the multi-node cluster NWDAF selects the corresponding NWDAF group based on the requested analysis ID and the allowed selection of the ML model, and uses local data to train the model. The local data includes terminal information, network information, user information, and application information, etc. The multi-node cluster will dynamically select cluster members.

[0073] S300, when the machine learning models trained in the obtained multiple network data analysis function groups are model training for non-common members, a key is generated based on the obtained network data analysis function groups and the corresponding machine learning models; and then an encrypted sample is obtained based on the key;

[0074] It should be noted that, in some embodiments, obtaining an encrypted sample based on a key may include: encrypting sample data of multiple network data analysis function groups obtained by using a key to obtain an encrypted sample.

[0075] For example, in some specific embodiments, non-common members need to dynamically select NWDAF based on parameters such as user type, request analysis ID, inference ML model, model training time, etc., and dynamically generate a one-time key based on the data thereon.

[0076] In some embodiments, common data (associated with common members) will be trained through public keys. Specifically, by distributing the public keys to multiple NWDAF groups, multiple NWDAF groups align encrypted samples of common users and perform encryption training in conjunction with the central NWDAF.

[0077] It should also be noted that, based on the service consumer's request or subscription information, the multi-node cluster NWDAF selects the relevant NWDAF based on the user and subscription type. NWDAF1,…,NWDAFN are responsible for different training models ML1,…,MLQ and have different samples (such as: UE ID, slice ID, group ID, DNN, application ID, priority, expected UE behavior parameters, UE communication behavior [rate, start time], UE location, timestamp, TAC, base station hardware and software resource group, user ID, used network element ID, network element load, etc.) according to different UCs. Since the participants have different data, the model trained by the terminal finally has different model parameters, and the cost factor of the algorithm will also be considered.

[0078] S400, based on the obtained machine learning model corresponding to the network data analysis function group, combined with the encrypted sample to obtain a fusion machine learning model; the fusion machine learning model is trained through all local samples, and the trained fusion machine learning model is transmitted to each network data analysis function group of the multi-node cluster;

[0079] Exemplarily, in some specific embodiments, after the training of each NWDAF1, ..., NWDAFN is completed, the multi-node cluster NWDAF forms a fusion ML model based on the encrypted samples and models ML1, ..., MLQ, and performs fusion ML model training based on all existing samples.

[0080] S500, based on the trained fusion machine learning model, the machine learning model corresponding to each network data analysis function group of the multi-node cluster is updated and iterated until the preset conditions are met.

[0081] It should be noted that, in some embodiments, step S500 may include: based on the trained fusion machine learning model, performing new sample training on each network data analysis function group of the multi-node cluster, and then updating and iterating the machine learning model corresponding to each network data analysis function group until the model training reaches a preset accuracy.

[0082] Exemplarily, in some specific embodiments, the fused ML model is sent to NWDAF1, ..., NWDAFN for respective new sample training, and the original ML model 1*, ..., ML model N* is updated to complete the update iteration until the accuracy meets the result requirements and the result is returned to the multi-node cluster NWDAF for model preservation.

[0083] Among them, in some embodiments, such as Figure 5 As shown, the method may also include: T100, returning the completed training results of the machine learning model corresponding to each network data analysis function group to the multi-node cluster; T200, pushing the completed training results to the service consumer through the multi-node cluster.

[0084] Exemplarily, in some specific embodiments, the multi-node cluster NWDAF model saves the inference output and pushes it to the service consumer through a response or notification.

[0085] In order to explain the principle of the technical solution of the present invention in detail, the overall process of the present invention is described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and cannot be regarded as a limitation of the present invention.

[0086] The embodiment of the present invention implements enhanced model training based on NWDAF, including: according to the subscription / request ML model, the multi-node cluster NWDAF selects the corresponding NWDAF group according to the requested analysis ID and the allowed selection of ML model, the multi-node cluster NWDAF members dynamically select their members according to the relevant algorithm, and dynamically generate keys; if the existing ML model needs to be further trained, relevant data is collected from NF / OAM / AF to train the ML model, after the training of each NWDAF is completed, a fused ML model is formed based on the encrypted full set samples, UC and different ML models, the fused ML model is trained based on all existing samples, the fused ML model is sent to each NWDAF for respective new sample training, the original ML model 1*, ..., ML model Q* is updated, the update iteration is completed, and the result is returned to the multi-node cluster NWDAF for model 1*, ..., model Q* and fused model storage, and the aggregation and update of the training model are completed; it is more applicable to different users, different UCs and different training ML models, and the data of the multi-node cluster NWDAF are all encrypted data, which is more applicable to NF service consumers and has a certain degree of practicality.

[0087] The present invention is mainly used to improve NWDAF enhanced model training, and is mainly used for NWDAF service consumers to send subscription / request ML models. The multi-node cluster NWDAF selects the corresponding NWDAF group according to the requested analysis ID and the allowed selection of ML models, and uses local data to train the model. The local data includes terminal information, network information, user information and application information, etc. The multi-node cluster will dynamically select cluster members; if the existing ML model needs further training, relevant data will be collected from NF / OAM / AF to train the ML model. Common data will be trained through public keys, and non-common data will be based on the selected data type, training difficulty, etc. Based on the dynamic selection of UC and different ML models to form a fused ML model, and According to the dynamically generated key pair, the fused ML model is sent to each NWDAF for training with new samples, and the original ML model 1*,…, ML model N* is updated to complete the update iteration. The result is returned to the multi-node cluster NWDAF for saving model 1*,…, model N* and fused model, completing the aggregation and update of the training model, starting the next iteration as required, and saving the timestamp. The multi-node cluster NWDAF is available for NF service consumers to call or actively push after subscription. It is more applicable to different users, different UCs and different training ML models, and can be used in scenarios that integrate different UCs. The multi-node cluster data is encrypted data, which is more applicable to NF service consumers and has a certain degree of practicality.

[0088] The technical principle of the embodiment of the present invention is described below in conjunction with the accompanying drawings. Figure 6 As shown, the process is as follows:

[0089] 1-2 are existing processes: service consumers can send analysis information requests to NRF or multi-node cluster NWDAF;

[0090] Specifically, Figure 7 As shown, subscriptions to NWDAF services:

[0091] 1. NWDAF service consumers subscribe to ML models from NWDAF (including MTLF): ① Parameters that NWDAF service consumers can provide include analysis ID list and ML model selection, such as selecting ML models based on S-NSSAI and region to which the ML models apply; ② ML model address, ML model applicable time, and applicable region, etc.

[0092] 2. The NWDAF service consumer requests the ML model from the NWDAF (including MTLF): ① Request the ML model associated with the analysis ID for analysis and derivation; ② When the NWDAF (including MTLF) receives the request for ML model information, it determines whether the existing ML model needs further training. If so, the NWDAF needs to start the data collection operation and use it for ML model training. After the training is completed, it provides the ML model address, etc.

[0093] 3~5 processes: In the analysis information request, the NF service consumer can provide one or more requested analysis IDs for inferring ML models, such as UE mobility analysis of analysis ID4, QoS parameter adjustment and one or more requested areas of interest. After the multi-node cluster NWDAF is discovered, the cluster members are dynamically formed. The common member method specifically distributes the public key to multiple NWDAF groups. Multiple NWDAF groups align the encrypted samples of common users and jointly perform encryption training with the central NWDAF; non-common members need to dynamically select NWDAF based on parameters such as user type, requested analysis ID, inference ML model, model training time, etc., and dynamically generate a one-time key based on the data on it.

[0094] 6. Based on the service consumer's request or subscription information, the multi-node cluster NWDAF selects the relevant NWDAF according to the user and subscription type. NWDAF1, ..., NWDAFN are responsible for different training models ML1, ..., MLQ according to different UCs and have different samples (such as: UE ID, slice ID, group ID, DNN, application ID, priority, expected UE behavior parameters, UE communication behavior [rate, start time], UE location, timestamp, TAC, base station hardware and software resource group, user ID, used network element ID, network element load, etc.). Since the participants have different data, the final terminal training model has different model parameters, and the cost factor of the algorithm will also be considered.

[0095] 7, 8. After the training of each NWDAF1, ..., NWDAFN is completed, the multi-node cluster NWDAF forms a fusion ML model based on the encrypted samples and models ML1, ..., MLQ, trains the fusion ML model based on all existing samples, sends the fusion ML model to NWDAF1, ..., NWDAFN for their respective new sample training, updates the original ML model 1*, ..., ML model N*, completes the update iteration, until the accuracy meets the result requirements and returns the result to the multi-node cluster NWDAF for model preservation.

[0096] In summary, the embodiment of the present invention sends a subscription / request ML model based on the NWDAF service consumer, and the multi-node cluster NWDAF selects the corresponding NWDAF group based on the requested analysis ID and the allowed selection of the ML model, and uses local data to train the model. The local data includes terminal information, network information, user information, and application information, etc. The multi-node cluster will dynamically select cluster members; if the existing ML model needs further training, relevant data is collected from NF / OAM / AF to train the ML model, common data will be trained through the public key, and non-common data will form a fused ML model based on the dynamic selection of UC and different ML models according to the selected data type, training difficulty, etc., and the fused ML model is sent to each NWDAF according to the dynamically generated key pair for each new sample training, and the original ML model is updated 1*,…,ML Model N*, complete the update iteration, and return the result to the multi-node cluster NWDAF to save model 1*,…, model N* and fusion model, complete the aggregation and update of the training model, start the next iteration as required, and save the timestamp at the same time. The multi-node cluster NWDAF is available for NF service consumers to call or actively push after subscription; it is more applicable to different users, different UCs and different training ML models, and can be used for scenarios that integrate different UCs. Multi-node cluster data is encrypted data, which is more applicable to NF service consumers. A fusion ML model is formed based on the encrypted samples and the original training ML model. The fusion ML model is trained based on all existing samples, and the fusion ML model is sent to the original NWDAF for training of new samples to form ML model 1*,…, ML model N*, and complete the update iteration. Compared with the prior art, the present invention is more suitable for fusion scenario training under different UCs and has stronger adaptability.

[0097] On the other hand, Figure 8As shown, an embodiment of the present invention provides a model enhancement training device 800, including: a first module 810, used to obtain analysis information requests of service consumers, and transmit the analysis information requests to a multi-node cluster; the multi-node cluster includes several network data analysis function groups; a second module 820, used to obtain multiple network data analysis function groups from the multi-node cluster according to the analysis information request; and obtain the machine learning model in each network data analysis function group; a third module 830, used to generate a key based on the obtained network data analysis function group and the corresponding machine learning model when the machine learning model trained in the obtained multiple network data analysis function groups is a model training for non-common members; and then obtain an encrypted sample based on the key; a fourth module 840, used to obtain a fused machine learning model based on the machine learning model corresponding to the obtained network data analysis function group and the encrypted sample; model training is performed on the fused machine learning model through all local samples, and the trained fused machine learning model is transmitted to each network data analysis function group in the multi-node cluster; a fifth module 850, used to update and iterate the machine learning model corresponding to each network data analysis function group in the multi-node cluster based on the trained fused machine learning model until a preset condition is met.

[0098] In some embodiments, the device may also include: a sixth module, used to return the completed training results of the machine learning model corresponding to each network data analysis function group to the multi-node cluster; and a seventh module, used to push the completed training results to the service consumer through the multi-node cluster.

[0099] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0100] On the other hand, Fig. 9 As shown, an embodiment of the present invention further provides an electronic device 900, which includes at least one processor 910 and at least one memory 920 for storing at least one program; taking one processor 910 and one memory 920 as an example.

[0101] The processor 910 and the memory 920 may be connected via a bus or in other ways.

[0102] The memory 920, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 920 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 920 may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0103] The electronic device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, 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 solution of this embodiment.

[0104] Specifically, Fig.10 The structure block diagram of a computer system of an electronic device for implementing an embodiment of the present invention is schematically shown.

[0105] It should be noted that Fig.10 The computer system 1000 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0106] like Fig.10 As shown, the computer system 1000 includes a central processing unit 1001 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 (ROM) or the program loaded from the storage part 1008 to the random access memory 1003 (RAM). Various programs and data required for system operation are also stored in the random access memory 1003. The central processing unit 1001, the read-only memory 1002 and the random access memory 1003 are connected to each other through a bus 1004. The input / output interface 1005 (Input / Output interface, i.e., I / O interface) is also connected to the bus 1004.

[0107] The following components are connected to the input / output interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0108] In particular, according to an embodiment of the present invention, the processes described in the various method flow charts can be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1009, and / or installed from a removable medium 1011. When the computer program is executed by the central processor 1001, various functions defined in the system of the present invention are executed.

[0109] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0110] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0111] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0112] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0113] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] It should be noted that, although several modules of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0115] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0116] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0117] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0118] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of 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.

[0119] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution device, apparatus or device (such as a computer-based device, a device including a processor, or other device that can fetch instructions from an instruction execution device, apparatus or device and execute the instructions), or in conjunction with such instruction execution device, apparatus or device. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution device, apparatus or device, or in conjunction with such instruction execution device, apparatus or device.

[0120] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0121] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0123] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0124] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A model enhancement training method, characterized in that: include: Obtaining an analysis information request from a service consumer, and transmitting the analysis information request to a multi-node cluster; The multi-node cluster includes several network data analysis function groups; According to the analysis information request, a plurality of the network data analysis function groups are obtained from the multi-node cluster; and a machine learning model in each of the network data analysis function groups is obtained; When the machine learning models trained in the obtained multiple network data analysis function groups are models for non-common members, a key is generated based on the obtained network data analysis function groups and the corresponding machine learning models; and then an encrypted sample is obtained based on the key; common members represent common users of multiple network data analysis function groups, and non-common members are the opposite of common members; Based on the obtained machine learning model corresponding to the network data analysis function group, a fusion machine learning model is obtained in combination with the encrypted sample; Performing model training on the fusion machine learning model through all local samples, and transmitting the trained fusion machine learning model to each of the network data analysis function groups in the multi-node cluster; Based on the trained fusion machine learning model, the machine learning model corresponding to each network data analysis function group of the multi-node cluster is updated and iterated until the preset conditions are met.

2. The model enhancement training method according to claim 1, characterized in that: The request for obtaining analysis information of the service consumer includes at least one of the following: Obtaining a subscription message for the machine learning model sent by the service consumer; Obtain a request message for the machine learning model sent by the service consumer.

3. The model enhancement training method according to claim 1, characterized in that: The analysis information request includes an analysis ID; and obtaining a plurality of the network data analysis function groups from the multi-node cluster according to the analysis information request includes: The pre-selected model type is determined based on the analysis ID, and then cluster members are dynamically selected through the multi-node cluster to obtain a plurality of the network data analysis function groups.

4. The model enhancement training method according to claim 1, characterized in that: Before the step of obtaining a plurality of the network data analysis function groups from the multi-node cluster, the method further comprises: Each of the network data analysis function groups uses local data to train the machine learning model of the network data analysis function group.

5. The model enhancement training method according to claim 1, characterized in that: The obtaining of an encrypted sample based on the key comprises: The sample data of the plurality of network data analysis function groups obtained are encrypted by using the key to obtain encrypted samples.

6. The model enhancement training method according to claim 1, characterized in that: The fusion machine learning based on the training is updated and iterated on the machine learning model corresponding to each network data analysis function group of the multi-node cluster until a preset condition is met, including: Based on the trained fusion machine learning model, new sample training is performed on each of the network data analysis function groups in the multi-node cluster, and then the machine learning models corresponding to each of the network data analysis function groups are updated and iterated accordingly until the model training reaches the preset accuracy.

7. The model enhancement training method according to claim 1, characterized in that: The method further comprises: Returning the completed training results of the machine learning model corresponding to each of the network data analysis function groups to the multi-node cluster; The training results are pushed to the service consumer through the multi-node cluster.

8. A model enhancement training device, characterized in that: include: The first module is used to obtain the analysis information request of the service consumer and transmit the analysis information request to the multi-node cluster; The multi-node cluster includes several network data analysis function groups; The second module is used to obtain a plurality of the network data analysis function groups from the multi-node cluster according to the analysis information request; and obtain a machine learning model in each of the network data analysis function groups; The third module is used to generate a key based on the obtained network data analysis function group and the corresponding machine learning model when the machine learning model trained in the obtained multiple network data analysis function groups is a model for non-common members; and then obtain an encrypted sample based on the key; Common members represent the common users of multiple network data analysis function groups, and non-common members are the opposite of common members; A fourth module is used to obtain a fusion machine learning model based on the obtained machine learning model corresponding to the network data analysis function group and in combination with the encrypted sample; Performing model training on the fusion machine learning model through all local samples, and transmitting the trained fusion machine learning model to each of the network data analysis function groups in the multi-node cluster; The fifth module is used to update and iterate the machine learning model corresponding to each network data analysis function group of the multi-node cluster based on the trained fusion machine learning model until the preset conditions are met.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images