Network communication method and apparatus, communication device, and computer-readable storage medium

Abstract

The application relates to a network communication method and device, a communication device and a computer readable storage medium. The application is applied to a network architecture based on network slicing, semantic communication and cache combination. In the case that the query content of a user terminal is received, the query content is subjected to semantic analysis based on a semantic communication module to obtain the query semantics corresponding to the query content. In the case that the user corresponding to the user terminal is a slice user of a current slice, the cache content of the current slice is searched based on the semantic communication module and the query semantics. Finally, the data address or data content corresponding to the searched query semantics is returned to the user terminal. The received query content can be quickly understood through the semantic communication module, thereby improving the accuracy and effectiveness of the search. Furthermore, the cache content is managed by using a slice, the efficiency of obtaining result data is improved, data leakage can be avoided, the data security is improved, and the network communication security and data transmission efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication network, in particular to a network communication method and device, a communication device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the rapid development of information technology, users gradually increase the recognition of virtual private network and other dedicated line tasks. Network slicing technology, as a new network resource allocation method, divides the physical network into multiple virtual networks to provide customized network services for different users or businesses.

[0003] However, the current communication method using network slicing has the problem of low communication efficiency. SUMMARY

[0004] Therefore, it is necessary to provide a network communication method, device, communication device, computer readable storage medium and computer program product capable of improving communication efficiency to solve the above technical problems.

[0005] In a first aspect, the present application provides a network communication method applied to a network architecture combining network slicing, semantic communication and caching; comprising:

[0006] receiving query content of a user terminal, obtaining query semantics corresponding to the query content based on a semantic communication module;

[0007] if the user corresponding to the user terminal is a slice user of the current slice, searching the cache content of the current slice based on the semantic communication module and the query semantics; the cache content of the current slice is stored in cloud resources of the current slice and / or storage resources of at least one slice user;

[0008] returning the data address or data content corresponding to the searched query semantics to the user terminal.

[0009] In combination with the first aspect, in one of the embodiments, the method further comprises: if no data address or data content matching the query semantics is searched in the cache content of the current slice, searching external resources based on the semantic communication module and the query semantics; the external resources include external resources providing services to the current slice or slice users.

[0010] In combination with the first aspect, in one of the embodiments, the method further comprises: obtaining content summaries generated by each slice user for the cache content perceived by the slice user; the cache content perceived by the slice user includes local cache content and / or cache content of cloud resources; training a large model preset for the current slice according to the content summaries generated by multiple slice users to obtain the semantic communication module.

[0011] With reference to the first aspect, in one of the embodiments, the method further comprises: in response to the query content of the user terminal being data content of other slice users of the current slice or data content outside the slice, when returning the searched data address or data content to the user terminal, also returning recommended content to the user terminal based on the cache content of the current slice to trigger the user terminal to display the data address or data content while also displaying the recommended content in the form of a sidebar.

[0012] With reference to the first aspect, in one of the embodiments, the method further comprises: verifying the cache content of the current slice according to a set period; in response to the verification result indicating that there is missing data content in the cache content, restoring the missing data content in the storage resource of the current slice.

[0013] With reference to the first aspect, in one of the embodiments, the method further comprises: in response to the verification result indicating that certain cache content of the current slice is expired, removing or replacing the expired cache content from the storage resource of the current slice.

[0014] With reference to the first aspect, in one of the embodiments, the method further comprises: obtaining historical behavior data of the slice users of the current slice; inputting the historical behavior data into a pre-constructed behavior prediction model to obtain predicted behavior data of the slice users of the current slice through the behavior prediction model; and pre-obtaining corresponding data content according to the predicted behavior data and caching the data content in the storage resource of the current slice.

[0015] With reference to the first aspect, in one of the embodiments, the cache content of the current slice is limited to be open and shared to the slice users of the current slice, and the method further comprises: performing machine learning on the historical behavior data of the slice users of the current slice to obtain a matching degree between the slice users and the current slice; and adjusting the slice users of the current slice or adjusting the slice resources of the current slice according to the matching degree between the slice users and the current slice.

[0016] The second aspect, the application also provides a network communication device applied to a network architecture based on network slicing, semantic communication and cache combination; comprising:

[0017] A query semantic obtaining module is configured to receive query content of a user terminal and obtain query semantics corresponding to the query content based on a semantic communication module;

[0018] A cache content searching module is configured to search cache content of a current slice based on the semantic communication module and the query semantics in a case where a user corresponding to the user terminal is a slice user of the current slice; the cache content of the current slice is stored in a cloud resource of the current slice and / or a storage resource of at least one slice user;

[0019] A search result returning module is configured to return data address or data content corresponding to the searched query semantics to the user terminal.

[0020] In a third aspect, the present application provides a communication device, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0021] receiving query content of a user terminal, obtaining query semantics corresponding to the query content based on the semantic communication module;

[0022] in a case where a user corresponding to the user terminal is a slice user of a current slice, searching cache content of the current slice based on the semantic communication module and the query semantics; the cache content of the current slice being stored in cloud resources of the current slice and / or storage resources of at least one slice user;

[0023] returning a data address or data content corresponding to the searched query semantics to the user terminal.

[0024] In a fourth aspect, the present application provides a computer readable storage medium, storing a computer program, and the computer program implementing the following steps when executed by a processor:

[0025] receiving query content of a user terminal, obtaining query semantics corresponding to the query content based on the semantic communication module;

[0026] in a case where a user corresponding to the user terminal is a slice user of a current slice, searching cache content of the current slice based on the semantic communication module and the query semantics; the cache content of the current slice being stored in cloud resources of the current slice and / or storage resources of at least one slice user;

[0027] returning a data address or data content corresponding to the searched query semantics to the user terminal.

[0028] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program implementing the following steps when executed by a processor:

[0029] receiving query content of a user terminal, obtaining query semantics corresponding to the query content based on the semantic communication module;

[0030] in a case where a user corresponding to the user terminal is a slice user of a current slice, searching cache content of the current slice based on the semantic communication module and the query semantics; the cache content of the current slice being stored in cloud resources of the current slice and / or storage resources of at least one slice user;

[0031] returning a data address or data content corresponding to the searched query semantics to the user terminal.

[0032] The network communication method, device, communication equipment, computer readable storage medium and computer program product can be applied to a network architecture based on network slicing, semantic communication and cache combination. In the case that the query content of the user terminal is received, the semantic analysis of the query content is performed based on the semantic communication module to obtain the query semantics corresponding to the query content. In the case that the user corresponding to the user terminal is a slice user of a current slice, the cache content of the current slice is searched based on the semantic communication module and the query semantics, wherein the cache content of the current slice is stored in the cloud resource of the current slice and / or the storage resource of at least one slice user. Finally, the data address or data content corresponding to the searched query semantics is returned to the user terminal. The semantic communication module can quickly understand the received query content, thereby improving the accuracy and effectiveness of the search. In addition, the cache content is managed by using the slice, thereby improving the efficiency of obtaining the result data, avoiding the leakage of data, improving the security of the data, and improving the network communication security and the data transmission efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0034] Figure 1 The application environment diagram of the network communication method in an embodiment;

[0035] Figure 2 The flowchart of the network communication method in an embodiment;

[0036] Figure 3 The flowchart of determining the semantic communication module in an embodiment;

[0037] Figure 4 The structural block diagram of the network communication device in an embodiment;

[0038] Figure 5 The internal structure diagram of the communication equipment in an embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0040] With the rapid development of information technology, users gradually increase the recognition of virtual private network (VPN) and other dedicated line tasks. Network slicing technology, as a new network resource allocation method, gradually enters the public view. Network slicing can provide customized network services for different users or businesses by dividing the physical network into multiple virtual networks, meeting the diversified needs. However, although network slicing technology has significant advantages, its promotion still faces many challenges, one of which is the lack of significant application scenarios, which makes it difficult to popularize in actual deployment.

[0041] At the same time, semantic communication technology has attracted widespread attention in the communication field due to its high communication efficiency. Semantic communication can significantly reduce data transmission and improve communication efficiency by understanding and analyzing user intent. However, the application of semantic communication technology still faces two major problems: one is the lack of unified architecture support, which leads to compatibility and scalability problems in actual deployment; the second is the lack of high-quality training data sources, which limits the accuracy and intelligence level of semantic models. At the same time, the existing semantic communication technology only focuses on point-to-point communication, but due to the inherent characteristics of semantic communication--community, community memory is needed to achieve more efficient semantic communication.

[0042] In addition, as an important means to improve data transmission efficiency, cache technology has been widely used in local area networks. Through cache technology, repeated data transmission can be significantly reduced, and data reuse rate can be improved. However, the promotion of cache technology also faces many obstacles: one is the low retrieval efficiency of cache data, which is difficult to meet the user's demand for fast response; two is the security and privacy problem of open cache data, and the user's concern about data leakage limits the widespread application of cache technology.

[0043] In summary, although network slicing, semantic communication and cache technology each have significant advantages, due to the lack of effective combination and unified architecture support, these technologies face different degrees of challenges in actual application. Therefore, an innovative network architecture and its implementation method are needed to organically combine the above three technologies, fully exert their respective advantages, and promote the efficient development of the communication industry.

[0044] The network communication method provided by the embodiments of the present application can be applied to, for example Figure 1The application environment shown. The user terminal can communicate with the communication device through a network architecture based on network slicing, semantic communication module and cache technology, which can include multiple slices, each slice can correspond to multiple slice users, the division of the slice can be determined according to the user's interest or through joint signing of the slice user, or it can be configured according to the business demand. The cache content of each slice is stored in the cloud resource of the slice and / or the storage resource of the slice user of the slice, and the cache content in the slice is not open to non-slice users.

[0045] Based on the above communication network architecture, the communication device receives the query content initiated by the user through the user terminal, obtains the query semantics corresponding to the query content based on the semantic communication module, searches the cache content of the current slice based on the semantic communication module and the query semantics in the case that the user corresponding to the user terminal is a slice user of the current slice n, and finally returns the data address or data content corresponding to the searched query semantics to the user terminal. The user terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The communication device can be an access network device, a node device or a server in the Internet of Things, and no limitation is made to this.

[0046] In an exemplary embodiment, as Figure 2 shown, a network communication method is provided, which is applied to the communication device in Figure 1 for example, including the following steps S201 to S203. Among them:

[0047] Step S201, receiving the query content of the user terminal, and obtaining the query semantics corresponding to the query content based on the semantic communication module.

[0048] Among them, the query content can be understood as the keyword or query statement input by the user on the search page of the user terminal, and the query semantics can be understood as the content reflecting the user's query intention after semantic understanding and analysis of the query content; The semantic communication module can be understood as a functional module for realizing the semantic understanding and analysis of the user's query, including a compression unit, a translation unit, etc., which together realize the understanding of semantics, and can be arranged on the communication device or the user terminal.

[0049] Exemplarily, the communication device receives query content of the user terminal, and based on the semantic communication module, the query content is understood and analyzed to further determine the intention of the user to initiate the query, thereby improving the accuracy of subsequent content search using the query semantics, and improving the user adaptation of the search results.

[0050] In step S202, in the case that the user corresponding to the user terminal is a slice user of the current slice, the cache content of the current slice is searched based on the semantic communication module and the query semantics; the cache content of the current slice is stored in the cloud resource of the current slice and / or the storage resource of at least one slice user.

[0051] The slice cache content can be understood as relevant data associated with the user, and can include user-generated content and common resources, wherein the common resources can be announcement data, high-definition video data, and configuration data, etc.

[0052] The semantic communication module is a functional module covering multiple units, and further includes a retrieval unit to provide retrieval function; the slice can be understood as any one of the virtual networks divided from the physical network, and each virtual network provides customized network service for different users or services.

[0053] In an exemplary embodiment, the cache content in the slice is limited to be open and shared only to the slice users in the slice, i.e. not open to non-slice users. In this context, the communication device can verify whether the user corresponding to the user terminal is a slice user of the current slice according to the identity identifier of the user, or the communication device returns a password verification request to the user terminal, the user inputs the corresponding password in response to the password verification request, and the communication device compares the input key with the stored password to determine whether to allow the user corresponding to the user terminal to access the cache content of the current slice, i.e. to determine whether the user is a slice user of the current slice. In the case that the user corresponding to the user terminal is determined to be a slice user of the current slice, the cache content of the current slice is searched based on the semantic communication module and the query semantics, wherein the cache content exists in the cloud resource of the current slice and / or the storage resource of at least one slice user. By performing security verification on the user corresponding to the user terminal, the security of the cache content in the slice is improved, and the current slice is searched using the semantic communication module, thereby accelerating the data transmission efficiency.

[0054] In step S203, the data address or data content corresponding to the searched query semantics is returned to the user terminal.

[0055] The data address can be understood as the network link address of the data storage node storing the data content, and clicking the data address can jump to the corresponding data storage node to view the data content stored in the data storage node. The data content can be understood as the data corresponding to the query semantics cached by the slice.

[0056] Exemplarily, the communication device returns the data address or data content corresponding to the searched query semantics to the user terminal. In the case of returning the data address, the user terminal can jump to the storage location of the corresponding data content for data access by clicking the data address, while the data access needs to comply with the current slice according to the user's operation permission specification. By feeding back the search results searched to the user terminal, timely response to user operation is realized, and in addition, the data access behavior of the user is regulated, further enhancing the security of data access.

[0057] In the above network communication method, the network architecture applied to the combination of network slicing, semantic communication and caching searches the cache content of the current slice based on the semantic communication module and the query semantics in the case that the user terminal's query content is received, the query semantics corresponding to the query content is obtained by semantic analysis of the query content based on the semantic communication module, and the cache content of the current slice is stored in the cloud resources of the current slice and / or the storage resources of at least one slice user. Finally, the data address or data content corresponding to the searched query semantics is returned to the user terminal. The semantic communication module can quickly understand the received query content, thereby improving the accuracy and effectiveness of the search. Secondly, the cache content is managed by the slice, which improves the efficiency of obtaining result data, avoids data leakage, improves data security, and further improves network communication security and data transmission efficiency.

[0058] In one embodiment, the method further comprises: if no data address or data content matching the query semantics is searched in the cache content of the current slice, searching the out-of-slice resources based on the semantic communication module and the query semantics; the out-of-slice resources include external resources providing services to the current slice or slice users. Correspondingly, the returned data content or data address in the foregoing step S203 can also be the data address or data content searched from the external resources.

[0059] Among them, the external resources can be understood as various resources external to a specific system or organization, which are opposite to the internal resources of the specific system, application program or organization. It can be known that the range of data content covered by the external resources is much larger than that of the specific system, such as data resources, cloud services, third-party tools, network services, etc.

[0060] In an exemplary embodiment, if the communication device does not search for the data address or data content matching the query semantics in the cache content of the current slice, it indicates that the user's intention to initiate the request is not for the data within the slice, and therefore, further searches only the external resources of the current slice or the slice user for services based on the semantic communication module and the query semantic search. The cache content of the current slice is searched first, and if the data address or data content matching the query semantics cannot be searched from the cache content, the search range is timely expanded, i.e., the resources outside the slice are searched based on the semantic communication module and the query semantic search.

[0061] Based on this implementation, the user's demand is fully met, and the search range is timely converted to ensure the timeliness and adaptability of demand response.

[0062] In an embodiment, as shown in Figure 3 the method further comprises:

[0063] Step S301: obtaining the content summary generated by each slice user for the cache content perceived by the user; the cache content perceived by the slice user includes local cache content and / or cache content of cloud resources.

[0064] In an exemplary embodiment, each slice user uses the lightweight artificial intelligence model loaded thereon to perceive the local cache content and / or cache content of cloud resources in real time. First, the local cache content and / or cache content of cloud resources are accessed. The cache content includes specific data content and corresponding data addresses, including text, documents, conversation records or other types of data. Before extracting key information, the content may need to be preprocessed, such as removing irrelevant information (e.g., advertisements, noise), formatting text, etc. Natural language processing (NLP) techniques (such as TF-IDF (Term Frequency-Inverse Document Frequency), word embedding, etc.) are used to identify keywords and phrases in the text, determine the theme and focus of the content, and identify important entities (such as names, places, organizations, etc.) in the text so that these key factors can be highlighted in the summary. Representative sentences are selected from the original text. This can be determined by a scoring mechanism (such as importance score). The selected sentences are combined into a summary, retaining the main information of the original text.

[0065] A large amount of text data is trained using a deep learning model such as a Transformer model, and the model learns how to generate a coherent summary. According to the input content, the model generates a natural and fluent language summary, which is tested for readability to ensure that the summary is easy to understand. Some readability indicators such as Flesch-Kincaid grade can be used to evaluate the content summary, and the content summary that meets the grade evaluation condition is retained. The content summary is stored in the storage resource of the corresponding slice user or uniformly saved to the cloud resource, and the content summary is uploaded to the communication device.

[0066] The content summary is generated for the cached content of the slice user, and the relevant cached content is extracted and organized for key information, which helps to reduce the data processing amount of the subsequent semantic communication module and thus speeds up the query. The generated content summary can be stored in the storage resource of the slice user or the cloud resource of the current slice, which facilitates subsequent access and management.

[0067] Step S302, according to the content summary generated by the plurality of slice users, the preset large model of the current slice is trained to obtain the semantic communication module.

[0068] The preset large model can be understood as a large artificial intelligence model, a machine learning model with a large number of parameters and complex structure, which can process and analyze a large amount of data to perform various tasks such as natural language processing, image recognition and voice processing.

[0069] Exemplarily, the communication device trains the large artificial intelligence model deployed in the current slice according to the content summary and the user behavior log, learns the user preferences and behavior patterns: first, the content summary and the user behavior log are preprocessed, including denoising, standardization and formatting, to ensure the consistency of the data in format and content, features are extracted from the content summary and the user behavior log, including keywords, sentiment analysis, behavior patterns, etc., the extracted features are input as training data into the model, according to the size of the large artificial intelligence model, small batch training is used, and multiple iterations are performed. In each iteration, the model parameters are adjusted using the backpropagation algorithm to learn user preferences. During the training process, the training progress is monitored, including loss value, accuracy, etc., and the model is evaluated whether it meets the user's expectations through investigation or direct user feedback. Based on this, fine-tuning is performed, and finally the trained large artificial intelligence model is obtained, that is, the semantic communication module for subsequent user semantic analysis and search is obtained.

[0070] The slice users belonging to the same slice can be understood as a social group, and can be called a group, which means that the individuals in the group have commonality, and it is easier to interact information than with individuals who are not in the same social group. The content summary of each slice user can be considered as summarizing and analyzing the information in the social group, and forming an in-depth understanding of a specific topic or problem. A more comprehensive knowledge graph can be generated using each content summary. The graph can capture semantic relationships from different slice user perspectives, and can provide rich context for training of a large model. The content summary can be used as the basis data for model training, and the relationship between the semantic communication module and the model can be identified and established.

[0071] Based on this implementation, by training the preset large model in the semantic communication module, the semantic analysis capability of the large model is improved, which helps to understand the real intention of the user-initiated query, and thus improves the accuracy of the search. At the same time, by embedding the common theme and topic of the social group in the content summary, the dynamic adaptation of the model to different situations is promoted, thereby meeting the semantic communication needs of the social group level.

[0072] In one of the embodiments, the method further includes: in response to the query content of the user terminal being data content of other slice users of the current slice or data content outside the slice, when returning the searched data address or data content to the user terminal, also returning recommended content to the user terminal based on the cache content of the current slice, to trigger the user terminal to display the data address or data content, and also display the recommended content in the form of a sidebar.

[0073] In the embodiments of the present application, the slice users of the same slice can communicate with each other, and the communication means include but are not limited to establishing a communication channel between each other, or directly broadcasting communication. When the slice users communicate with each other, i.e., when the slice user 1 requests the cache content in the storage resource of the slice user n, the slice user n can directly send the required data to the slice user 1, or indirectly send the data through the access network device. In addition, the slice user can not only query the related data in the slice, but also query the data outside the slice, without limiting the scope of the query action, thereby ensuring the comprehensiveness of the response to user demand.

[0074] Illustratively, in response to the query content of the user terminal being data content of other slice users of the current slice or data content outside the slice, the former can be understood as mutual communication between slice users, which can be communicated through broadcast communication or by establishing a communication channel. The other slice users directly return the data address or data content matching the query semantics to the user terminal, and the remaining data address or data content in the other slice users is also returned to the user terminal.

[0075] The user terminal shows the user the data address or data content matched by the query semantics, and also shows other recommended content in the form of a sidebar; the latter can be understood as the user requesting out-of-slice resources. The semantic communication module generates the corresponding query semantics based on the query content, further analyzes the user to generate predicted semantics, and the communication device returns the out-of-slice data address or out-of-slice data content matched by the query semantics to the user terminal, searches the cache content of the current slice based on the predicted semantics, and returns the corresponding data address or data content to the user terminal if there is a search result. The user terminal shows the user the out-of-slice data address or out-of-slice data content, and shows the data address or data content corresponding to the predicted semantics in the form of a sidebar.

[0076] The recommended content is displayed through a sidebar. In addition to the prediction of the user, the recommended content can also be related data queried by friends who are mutually followed by the slice user. The sidebar can also show the dynamics in the user's social circle, such as which friends recently visited the related data or shared a certain slice, arousing the curiosity of the user who initiated the query. In addition, the user can be allowed to tag the content. When the user initiates a query, the recommended content can be cached content in the same group.

[0077] Based on this real-time approach, while returning the corresponding data to the user based on the user's query content, the corresponding recommended content can also be returned based on the cache content of the current slice. This highly integrated feedback of information helps to improve the user's service experience, thereby enhancing user stickiness. The recommended content is displayed in the form of a sidebar, which is distinguished from the actual query feedback content. The simple and efficient page setting helps to improve the user's information acquisition speed and enhances the user's sociality. At the same time, it provides the user with diversified information and improves the user's service experience.

[0078] In one embodiment, the method further comprises: verifying the cache content of the current slice according to a set period; and in response to the verification result indicating that there is mistakenly deleted data content in the cache content, restoring the mistakenly deleted data content in the storage resource of the current slice.

[0079] In an exemplary embodiment, the communication device verifies the cache content of the current slice according to a set period. This action can be coordinated by a lightweight artificial intelligence model deployed on the slice user and a large artificial intelligence model deployed in the current slice. For example, the lightweight artificial intelligence model first verifies the local cache content of the slice user, and then the large artificial intelligence model verifies the corresponding content summary. In response to the verification result indicating that there is mistakenly deleted data content in the cache content, such as the slice user accidentally deleting a certain cache content, the source data content corresponding to the mistakenly deleted data content is obtained, and the source data content is re-added in the storage resource of the current slice.

[0080] By periodically verifying the cache content of the current slice, recovering the mis-deleted data content, the integrity and effectiveness of the data content in the current slice are ensured, and the user's query service experience is ensured.

[0081] In one embodiment, the method further comprises: in response to the verification result representing that certain cache content of the current slice is expired, removing or replacing the expired cache content from the storage resource of the current slice.

[0082] Illustratively, the periodic verification of the communication device not only verifies the integrity of the data content, but also verifies the timeliness of the cache content. Since the communication device correspondingly timestamps each cache content when the relevant data content is stored into the current slice as the corresponding cache content, by obtaining the timestamp of each cache content and comparing the timestamp with the current time point, if the interval between the timestamp and the time point does not satisfy the preset timeliness condition, it means that the cache content associated with the timestamp is expired, and the expired cache content can be removed from the storage resource of the current slice, or the corresponding latest cache content is obtained to replace the expired cache content.

[0083] Based on this implementation, the timeliness of the cache content is verified by using the timestamp, and in the case where the expired cache content is verified, the expired cache content is removed or replaced, ensuring the timeliness of the cache content in the storage resource of the current slice, and further improving the credibility and accuracy of the searched data content or data address.

[0084] In one of the embodiments, the method further comprises: obtaining historical behavior data of a slice user of the current slice; inputting the historical behavior data into a pre-constructed behavior prediction model to obtain predicted behavior data of the slice user of the current slice by the behavior prediction model; and pre-obtaining corresponding data content according to the predicted behavior data and caching the data content into the storage resource of the current slice.

[0085] The historical behavior data of the slice user can be understood as historical query data or historical browsing data of the slice user, including the click frequency of a certain content, the browsing time length, and the feedback information given to the query content. These data can be obtained from the historical records of the slice or from the storage resource of the slice user. The predicted behavior data of the slice user can be understood as the content that the slice user may query in the future time, or other data requirements that the user may have.

[0086] The behavior prediction model can be understood as a model constructed by machine learning (such as decision tree, random forest, deep learning, etc.), focusing on user behavior prediction, predicting possible user behaviors in a future period of time through analysis and learning of historical behavior data, and having foresight to construct and deploy relevant policies in advance.

[0087] In an exemplary embodiment, the communication device obtains historical behavior data of slice users of the current slice, such as click frequency, browsing time, interactive content, etc., extracts time features, content features, and behavior patterns from the historical behavior data, inputs the time features, content features, and behavior patterns into a pre-constructed behavior prediction model, obtains predicted behavior data of the slice users of the current slice, such as possible click content and possible browsing time, etc., through the behavior prediction model, evaluates content that users may be interested in, and pre-obtains data content that may be of interest and caches it to storage resources of the current slice.

[0088] Through the intelligent scheduling algorithm, the related data content is pre-cached in the slice, and efficient access and efficient transmission of the cached content are determined.

[0089] In an embodiment, the cached content of the current slice is limited to be open and shared to slice users of the current slice, and the method further comprises: performing machine learning on historical behavior data of each slice user of the current slice to obtain a matching degree between the slice user and the current slice; and adjusting the slice users of the current slice or adjusting the slice resources of the current slice according to the matching degree between the slice user and the current slice.

[0090] The matching degree can be understood as the degree of adaptation between the slice user and the current slice, i.e., the proportion of user query content from the current slice.

[0091] Exemplarily, the communication device performs machine learning on the historical behavior data of the slice users of the current slice, mainly according to the query actions initiated by the slice users and the feedback contents returned for the query actions. When the feedback contents come from the cache contents of the current slice, it indicates that the matching degree between the slice user and the current slice is high, and there is no need to adjust the network slice to which the slice user belongs, and there is no need to adjust the slice resources of the current slice. When the feedback contents come from external resources, it indicates that the matching degree between the slice user and the current slice is high, that is, the slice user always queries external resources, which indicates that the slice division is unreasonable or the cache contents in the slice resources are unreasonable, and it is necessary to adjust the network slice to which the slice user belongs or adjust the slice resources of the current slice, that is, store the data contents frequently searched by the slice user into the storage resources of the current slice. By adjusting the resources of the current slice in real time, including adjusting the attribution of the slice user or adjusting the slice resources of the current slice, the matching degree between the slice user and the current slice is improved, and thus the data security during data access is ensured and the data transmission efficiency is improved.

[0092] In an exemplary embodiment, a specific implementation of a network communication method is provided, which is applied to an application environment as shown in Figure 1 The application environment includes:

[0093] Preparation:

[0094] 1. The communication device obtains the similarity information between the slice users according to the interests and hobbies of the slice users, divides the slice users into a plurality of slice user groups by using the similarity information, and sets a corresponding network slice for each slice user group.

[0095] 2. For the current slice, the communication device obtains the historical behavior data of the slice users of the current slice, inputs the historical behavior data into a pre-constructed behavior prediction model, obtains the predicted behavior data of the slice users of the current slice through the behavior prediction model, and according to the predicted behavior data, obtains corresponding data contents and caches them into the storage resources of the current slice.

[0096] 3. The communication device obtains the content digest generated by each slice user for the local cache content, trains a large model preset for the current slice according to the content digest, and obtains a semantic communication module.

[0097] Real-time operation:

[0098] 1. Verify the cache contents of the current slice according to the set period, in response to the verification result indicating that there is missing data content in the cache contents, restore the missing data content in the storage resources of the current slice; in response to the verification result indicating that a certain cache content of the current slice is expired, remove or replace the expired cache content from the storage resources of the current slice.

[0099] 2. Machine learning is performed on the historical behavior data of each slice user of the current slice to obtain a matching degree between the slice user and the current slice, and the slice user of the current slice is adjusted or the slice resource of the current slice is adjusted according to the matching degree between the slice user and the current slice.

[0100] Communication process:

[0101] 1. The communication device receives the query content of the user terminal, and obtains the query semantics corresponding to the query content based on the semantic communication module.

[0102] 2. In the case that the user corresponding to the user terminal is a slice user of the current slice, the cache content of the current slice is searched based on the semantic communication module and the query semantics, and if no data address or data content matching the query semantics is searched in the cache content of the current slice, the out-of-slice resource is searched based on the semantic communication module and the query semantics.

[0103] 3. In response to the query content of the user terminal being data content of other slice users of the current slice or data content outside the slice, when the searched data address or data content is returned to the user terminal, the recommended content is also returned to the user terminal based on the cache content of the current slice, and the operation type of the user on different data needs to be regulated according to the operation permission of the user of the current slice when accessing the data. The user terminal shows the data address or data content to the user, and shows the recommended content to the user in the form of a sidebar.

[0104] Compared with the prior art, the present application has the following technical advantages:

[0105] 1. By means of slice division, the data content is saved in the corresponding network slice, and when the slice user initiates a query action, the cache content in the slice is searched first, the network resource utilization is improved, and the network load is reduced.

[0106] 2. By increasing the semantic communication module, the query content initiated by the user is understood and analyzed, the accuracy of the query semantics corresponding to the query content obtained based on the semantic communication module is improved, and the search accuracy is improved, thereby optimizing the user experience and improving the service response speed and accuracy.

[0107] 3. The data content is stored in different network slices, and the cache content of the current slice is not open to non-slice users by means of user identity authentication or access key authentication, thereby enhancing data security and privacy protection, preventing data leakage and illegal access.

[0108] 4. In response to the user's query content for the cache content within the slice and the resource outside the slice, the network communication device returns the relevant data address or data content corresponding to the query content to the user terminal, and generates recommended content based on the cache content within the slice. The recommended content includes cache content corresponding to the predicted semantics based on the analysis of the user, or data content visited by the user's attention user, or data content belonging to the same group as the feedback content received by the current user terminal. The recommended content is displayed in the sidebar to realize personalized service and meet the diversified needs of users.

[0109] It should be understood that, although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0110] Based on the same inventive concept, the embodiments of the present application also provide a network communication device for implementing the above-mentioned network communication method. The implementation scheme of the problem solving provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more network communication device embodiments provided below can refer to the limitations of the network communication method in the above text, which will not be repeated here.

[0111] In one exemplary embodiment, as shown in Figure 4 a network architecture based on network slicing, semantic communication and cache combination is applied; a network communication device is provided, comprising: a query semantic acquisition module 401, a cache content search module 402 and a search result return module 403, wherein:

[0112] The query semantic acquisition module 401 is configured to receive the query content of the user terminal, and obtain the query semantics corresponding to the query content based on the semantic communication module;

[0113] The cache content search module 402 is configured to search the cache content of the current slice based on the semantic communication module and the query semantics in the case that the user terminal corresponding to the user is a slice user of the current slice; the cache content of the current slice is stored in the cloud resource of the current slice and / or the storage resource of at least one slice user;

[0114] The search result returning module 403 is configured to return the data address or data content corresponding to the search result to the user terminal.

[0115] Based on the network communication device in the above embodiment, the query content of the user terminal is received by the query semantic obtaining module, the query semantic corresponding to the query content is obtained based on the semantic communication module, the query semantic is input into the cache content searching module, in the case that the user corresponding to the user terminal is a slice user of the current slice, the cache content stored in the cloud resource and / or the storage resource of at least one slice user of the current slice is searched based on the semantic communication module and the query semantic, and finally the search result returning module returns the data address or data content corresponding to the search result to the user terminal. Based on the network slicing, semantic communication and cache network architecture in the present application, the network communication of the user is realized, the communication security and data transmission efficiency of the network communication are improved, and the communication efficiency is further improved.

[0116] In one embodiment, the cache content searching module 402 is further configured to search the out-of-slice resource based on the semantic communication module and the query semantic if no data address or data content matching the query semantic is searched in the cache content of the current slice. The out-of-slice resource includes an external resource providing service to the current slice or the slice user.

[0117] In one exemplary embodiment, the network communication device further comprises a model pre-training module configured to obtain content summaries generated by slice users in response to the cache content perceived by the slice users, wherein the cache content perceived by the slice users includes local cache content and / or cache content of the cloud resource; and train a large model preset for the current slice according to the content summaries generated by the slice users to obtain the semantic communication module.

[0118] In one embodiment, the network communication device further comprises a content recommendation module configured to, in response to the query content of the user terminal being data content of other slice users of the current slice or data content outside the slice, return recommended content to the user terminal based on the cache content of the current slice when returning the searched data address or data content to the user terminal, so as to trigger the user terminal to display the data address or data content and simultaneously display the recommended content in the form of a sidebar.

[0119] In one embodiment, the network communication device further comprises a cache content verification module configured to verify the cache content of the current slice according to a set period; and in response to a verification result indicating that there is missing data content in the cache content, restore the missing data content in the storage resource of the current slice.

[0120] In one of the embodiments, the cache content verification module is further configured to remove or replace the expired cache content from the storage resource of the current slice in response to the verification result representing that certain cache content of the current slice is expired.

[0121] In one of the embodiments, the network communication device further comprises a pre-cache module configured to obtain historical behavior data of the slice user of the current slice; input the historical behavior data into a pre-constructed behavior prediction model to obtain predicted behavior data of the slice user of the current slice through the behavior prediction model; and pre-obtain corresponding data content according to the predicted behavior data and cache the data content into the storage resource of the current slice.

[0122] In one of the embodiments, the cache content of the current slice is limited to be open and shared by the slice user of the current slice, and the network communication device further comprises a slice optimization module configured to perform machine learning on the historical behavior data of each slice user of the current slice to obtain a matching degree between the slice user and the current slice; and adjust the slice user of the current slice or the slice resource of the current slice according to the matching degree between the slice user and the current slice.

[0123] Each of the above network communication devices can be implemented by software, hardware and a combination thereof in whole or in part. Each of the above modules can be embedded in or independent of the processor in the communication device in hardware form, or can be stored in the memory in the communication device in software form to be called and executed by the processor to perform the operations corresponding to each of the above modules.

[0124] In one of the embodiments, a communication device is provided, which can be a server, and the internal structure diagram of the communication device can be as shown in Figure 5 The communication device comprises a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the communication device is configured to provide computing and control capabilities. The memory of the communication device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the communication device is configured to store query content, query semantics, cache content, data address and data content. The input / output interface of the communication device is configured to exchange information between the processor and external devices. The communication interface of the communication device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a network communication method.

[0125] Those skilled in the art can understand that, Figure 5The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the communication device to which the scheme of the present application is applied. The specific communication device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0126] In an exemplary embodiment, a communication device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the network communication method of the above-mentioned embodiments when executing the computer program.

[0127] In an embodiment, a computer-readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the network communication method of the above-mentioned embodiments.

[0128] In an embodiment, a computer program product is provided, comprising a computer program, and the computer program is executed by a processor to implement the network communication method of the above-mentioned embodiments.

[0129] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0131] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0132] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A network communication method, characterized by, The method is applied to a network architecture based on network slicing, semantic communication and cache combination, and the method comprises the following steps: Receiving query content of a user terminal, obtaining query semantics corresponding to the query content based on a semantic communication module; In the case that a user corresponding to the user terminal is a slice user of a current slice, searching cache content of the current slice based on the semantic communication module and the query semantics; the cache content of the current slice is stored in cloud resources of the current slice and / or storage resources of at least one slice user; Returning a data address or data content corresponding to the query semantics searched to the user terminal.

2. The method of claim 1, wherein, The method further comprises the following steps: If no data address or data content matching the query semantics is searched in the cache content of the current slice, searching external resources of a slice based on the semantic communication module and the query semantics; the external resources of the slice include external resources providing services to the current slice or the slice user.

3. The method of claim 2, wherein, The method further comprises the following steps: Obtaining content summaries generated by each slice user for cache content perceived by the slice user; the cache content perceived by the slice user includes local cache content and / or cache content of the cloud resources; Training a large model preset for the current slice according to the content summaries generated by a plurality of slice users to obtain the semantic communication module.

4. The method of claim 1, wherein, The method further comprises the following steps: In response to the query content of the user terminal being data content of another slice user of the current slice or data content outside the slice, when returning the searched data address or data content to the user terminal, recommended content is also returned to the user terminal based on the cache content of the current slice to trigger the user terminal to display the data address or data content and also display the recommended content in the form of a sidebar.

5. The method of claim 1, wherein, The method further comprises the following steps: Verifying the cache content of the current slice according to a set period; In response to a verification result representing that there is missing data content in the cache content, restoring the missing data content in the storage resources of the current slice.

6. The method of claim 5, wherein, The method further comprises the following steps: In response to a verification result representing that certain cache content of the current slice is expired, removing or replacing the expired cache content from the storage resources of the current slice.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises the following steps: Obtaining historical behavior data of a slice user of the current slice; Inputting the historical behavior data into a pre-constructed behavior prediction model to obtain predicted behavior data of the slice user of the current slice through the behavior prediction model; According to the predicted behavior data, pre-acquiring corresponding data content and caching the data content in the storage resources of the current slice.

8. The method according to any one of claims 1 to 6, characterized in that, The cache content of the current slice is limited to be open and shared to slice users of the current slice, and the method further comprises the following steps: Machine learning historical behavior data of each slice user of the current slice to obtain a matching degree between the slice user and the current slice; According to the matching degree between the slice user and the current slice, adjusting the slice user of the current slice or adjusting slice resources of the current slice.

9. A network communication device, comprising: The application is applied to a network architecture based on network slices, semantic communication and cache combination; the device comprises: A query semantic acquisition module is configured to receive query content of a user terminal and obtain query semantics corresponding to the query content based on a semantic communication module; A cache content search module is configured to search cache content of a current slice based on the semantic communication module and the query semantics in a case where a user corresponding to the user terminal is a slice user of the current slice; the cache content of the current slice is stored in cloud resources of the current slice and / or storage resources of at least one slice user; A search result return module is configured to return a data address or data content corresponding to the query semantics searched to the user terminal.

10. A communication device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

12. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

Images