Adjustment method and device, equipment, medium and program product

Abstract

The invention discloses an adjustment method and device, equipment, a medium and a program product. Comprises: obtaining an initial analysis result; wherein the initial analysis result comprises a result of analyzing a path connection state among at least part of network nodes in the target network; obtaining adjustment indication information of a user; and adjusting the initial analysis result based on the adjustment indication information through an adjustment model to obtain a target adjustment result. According to the scheme, the initial analysis result can be flexibly and efficiently adjusted, so that diversified data analysis requirements of users can be met.

Description

Technical Field

[0001] The present application relates to the field of network technology, and in particular to an adjustment method, device, equipment, medium and program product. Background Art

[0002] In practical applications, the path status between node devices in the network is analyzed to obtain the path analysis result. However, the above path analysis result cannot meet the diverse data analysis needs of users. Summary of the invention

[0003] Based on the above technical problems, the embodiments of the present application provide an adjustment method, device, equipment, medium and program product.

[0004] The technical solution provided by the embodiment of the present application is as follows:

[0005] The present application embodiment first provides an adjustment method, the method comprising:

[0006] Obtaining initial analysis results; wherein the initial analysis results include results of analyzing the path connectivity status between at least some network nodes in the target network;

[0007] Obtaining adjustment instruction information from the user;

[0008] The initial analysis result is adjusted based on the adjustment indication information through the adjustment model to obtain a target adjustment result.

[0009] The present application also provides an adjustment device, which includes:

[0010] An acquisition module, used to acquire an initial analysis result and user adjustment instruction information; wherein the initial analysis result includes a result of analyzing the path connectivity status between at least some network nodes in the target network;

[0011] An adjustment module is used to adjust the initial analysis result based on the adjustment indication information through an adjustment model to obtain a target adjustment result.

[0012] An embodiment of the present application further provides an electronic device, comprising a processor and a memory; wherein a computer program is stored in the memory; and when the computer program is executed by the processor, it can implement any of the above-described adjustment methods.

[0013] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored; when the computer program is executed by a processor of an electronic device, it can implement any of the above-mentioned adjustment methods.

[0014] An embodiment of the present application further provides a computer program product, which includes a computer program; when the computer program is executed by a processor of an electronic device, it can implement any of the above-mentioned adjustment methods.

[0015] The adjustment method provided in the embodiment of the present application, after obtaining the initial analysis result obtained by analyzing the path connectivity status between at least part of the network nodes in the target network and obtaining the adjustment indication information of the user, adjusts the initial analysis result based on the adjustment indication information through the adjustment model to obtain the target adjustment result. In this way, through the above operation, the automatic and intelligent adjustment of the initial analysis result is realized, and the matching degree between the target adjustment result and the user's adjustment indication information is improved; and, since the adjustment indication information is added as a factor in the process of adjusting the initial analysis result, the targeted adjustment of the initial analysis result can be realized, so that the target adjustment result obtained through the above adjustment can match the user's adjustment needs; at the same time, in the case of changes in the adjustment indication information, through the above operation, the initial analysis result can be adjusted in a diversified and flexible manner; on the other hand, with the help of the high efficiency of the adjustment model in the data processing dimension, the initial analysis result can be adjusted flexibly and efficiently, so as to meet the user's diverse data analysis needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of the adjustment method provided in the embodiment of the present application;

[0017] Figure 2 A schematic diagram of the structure of the adjustment device provided in an embodiment of the present application;

[0018] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0020] 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.

[0021] In practical applications, the path status between node devices in the network is analyzed to obtain the path analysis result. However, the above path analysis result cannot meet the diverse data analysis needs of users.

[0022] Based on the above technical problems, the embodiments of the present application provide an adjustment method, device, equipment, medium and program product.

[0023] Figure 1A flow chart of the adjustment method provided in the embodiment of the present application is shown in FIG. Figure 1 As shown, the method may include the following steps:

[0024] Step 101: Obtain initial analysis results.

[0025] The initial analysis result includes a result of analyzing the path connectivity status between at least some network nodes in the target network.

[0026] In one implementation, the target network may include a public network or a private network; illustratively, the target network may include multiple network nodes; illustratively, the network nodes may include virtual machine devices and / or physical machine devices.

[0027] In one implementation, at least part of the network nodes may be pre-selected or determined, or may be adjusted according to actual network connectivity test requirements.

[0028] In one embodiment, the network node may include a cloud host and related cloud product devices for providing elastic computing service (ECS) functions.

[0029] In one implementation, the path connectivity status may include at least one of whether any two nodes in at least some of the network nodes are connected, unidirectionally connected, or bidirectionally connected.

[0030] In one embodiment, the initial analysis result may include data such as whether at least some network nodes in the target network are connected, path transmission delay between at least some network nodes, and packet loss rate during data transmission between at least some network nodes.

[0031] In one embodiment, the initial analysis results may be determined by:

[0032] The tracking results are obtained by tracking the transmission process of the traffic data in the target network, and the tracking results are analyzed and integrated to obtain the initial analysis results.

[0033] Step 102: Obtain the user's adjustment instruction information.

[0034] In one embodiment, the adjustment indication information may include indication information input by the user to represent adjustments to the initial analysis results; illustratively, the adjustment indication information may be input in the form of text, voice, gesture, etc., which is not limited in this embodiment of the present application.

[0035] Step 103: Adjust the initial analysis result based on the adjustment indication information by adjusting the model to obtain a target adjustment result.

[0036] In one embodiment, the adjustment model may be a pre-trained neural network model specifically used to adjust and optimize the initial analysis results.

[0037] In one implementation, the target adjustment result may differ from the initial analysis result in at least one dimension such as data structure, presentation form, and data volume.

[0038] In one implementation, the target adjustment result may be obtained by any of the following methods:

[0039] Based on the adjustment indication information, the adjustment model is controlled to filter the path connectivity status associated with the target node in the initial analysis result to obtain a first result, and the first result is determined as the target adjustment result; wherein the target node can be at least some of the network nodes.

[0040] Based on the data structure information included in the adjustment instruction information, the adjustment model is controlled to adjust the data structure of the initial analysis result to obtain the target adjustment result.

[0041] From the above, it can be seen that the adjustment method provided in the embodiment of the present application, after obtaining the initial analysis result obtained by analyzing the path connectivity status between at least part of the network nodes in the target network and obtaining the user's adjustment indication information, adjusts the initial analysis result based on the adjustment indication information through the adjustment model to obtain the target adjustment result. In this way, through the above operation, the automatic and intelligent adjustment of the initial analysis result is realized, and the matching degree between the target adjustment result and the user's adjustment indication information is improved; and, since the adjustment indication information is added as a factor in the process of adjusting the initial analysis result, the targeted adjustment of the initial analysis result can be achieved, so that the target adjustment result obtained through the above adjustment can match the user's adjustment needs; at the same time, in the case of changes in the adjustment indication information, through the above operation, the initial analysis result can be adjusted in a diversified and flexible manner; on the other hand, with the help of the high efficiency of the adjustment model in the data processing dimension, the initial analysis result can be efficiently adjusted, so as to meet the user's diverse data analysis needs.

[0042] Based on the foregoing embodiments, in the adjustment method provided in the embodiments of the present application, the adjustment model includes at least a feature extraction module and a sentiment analysis module.

[0043] In one implementation, the feature extraction module may include a convolutional neural network (CNN); illustratively, the CNN may include a convolutional layer, a pooling layer, and a fully connected layer.

[0044] In one embodiment, the emotion recognition module may include a neural network model with emotion tendency analysis function.

[0045] Accordingly, the initial analysis result is adjusted based on the adjustment indication information by adjusting the model to obtain the target adjustment result, which can be achieved by the following steps:

[0046] Step A1: Perform pattern recognition on the initial analysis result through a feature extraction module to obtain a pattern recognition result.

[0047] In one embodiment, the pattern recognition result may include a result of recognition or prediction of a network transmission pattern or a network structure pattern represented by the initial analysis result.

[0048] In one embodiment, the pattern recognition result can be obtained by:

[0049] The initial analysis result is preprocessed to obtain a preprocessing result, and the feature extraction module is used to extract features of the path connectivity status between different network nodes contained in the preprocessing result to obtain a second result, and then the second result is integrated to obtain a pattern recognition result; wherein the data format corresponding to the preprocessing result can be the data format required by the feature extraction module.

[0050] Step A2: Analyze the adjustment instruction information through the sentiment analysis module to obtain the sentiment analysis result.

[0051] In one embodiment, the sentiment analysis result may include the sentiment tendency represented by the adjustment indication information; illustratively, the sentiment tendency may include categories such as positive tendency, negative tendency, and neutrality.

[0052] In one implementation, sentiment analysis results may be obtained in the following manner:

[0053] The adjustment indication information is subjected to semantic recognition and context feature extraction through the sentiment analysis module to obtain a third result, and the context features and semantic features in the third result are integrated to obtain a sentiment analysis result.

[0054] Step A3: Determine an adjustment strategy based on the sentiment analysis results and pattern recognition results.

[0055] In one embodiment, the adjustment strategy may include at least one of a method, a step, and a link for adjusting the initial analysis result.

[0056] In one implementation, the adjustment strategy may be determined by:

[0057] Based on the sentiment analysis results, the user's satisfaction with the initial analysis results and the user's expected results are determined, and then the adjustment strategy is determined based on the satisfaction level and the degree of difference between the expected results and the pattern recognition results; for example, if the satisfaction level is unsatisfactory and the expected results do not match the pattern recognition results, the adjustment strategy can be determined as: adjusting the initial analysis results with target steps until the matching degree between the adjusted initial analysis results and the expected results is greater than or equal to the matching threshold.

[0058] Step A4: Adjust the initial analysis result based on the adjustment strategy to obtain the target adjustment result.

[0059] In one implementation, the target adjustment result may be obtained in the following manner:

[0060] Based on the set of steps and links included in the adjustment strategy, the initial analysis results are gradually adjusted to obtain the target adjustment results.

[0061] From the above, it can be seen that in the adjustment method provided in the embodiment of the present application, the feature extraction module in the adjustment model is used to perform pattern recognition on the initial analysis results to obtain pattern recognition results. In this way, with the help of the superiority of the feature extraction module in the feature extraction dimension, the accuracy of the pattern recognition results can be improved, and the efficiency of obtaining the pattern recognition results can also be improved; and, the adjustment indication information is analyzed by the sentiment analysis module to obtain the sentiment analysis results, which can achieve targeted extraction of the sentiment categories in the adjustment indication information; on this basis, based on the sentiment analysis results and the pattern recognition results, the adjustment strategy is determined, which can improve the accuracy of the adjustment strategy; in this way, the initial analysis results are adjusted based on the adjustment strategy to obtain the target adjustment results, which can not only achieve targeted and automatic adjustment of the initial analysis results, but also improve the accuracy of the target adjustment results.

[0062] Based on the foregoing embodiment, in the adjustment method provided in the embodiment of the present application, before adjusting the initial analysis result based on the adjustment indication information by adjusting the model, the following steps may also be performed:

[0063] Step B1: Obtain state sample data.

[0064] Among them, the state sample data includes a first set and a second set; the first set includes a set of results of analyzing the path connectivity status between at least some network nodes in at least one network; the second set includes a set of network patterns corresponding to the results in the first set.

[0065] In one implementation, at least one network may include a target network; at least one network may include a local area network, a metropolitan area network, or a wide area network.

[0066] In one implementation, the first set may be predetermined, and accordingly, the network patterns in the second set may be label data corresponding to the first set.

[0067] Step B2: Obtain indication sample data.

[0068] The indication sample data includes a set of mutually related adjustment indication information emotion labels.

[0069] In one embodiment, the adjustment indication information in the indication sample data may include a set of data adjusted for the results in the first set.

[0070] In one embodiment, the emotional label in the indication sample data may include the emotional tendency corresponding to the adjustment indication information in the indication sample data, and may also include the target pattern of the analysis results expected by the user for the path connectivity status between at least some network nodes in at least one network.

[0071] In one implementation, the emotion tags in the indication sample data may be preset.

[0072] Step B3: Based on the first set and the second set in the state sample data, a feature extraction module of the initial state is trained to obtain a feature extraction module.

[0073] In one implementation, the feature extraction module can be obtained by:

[0074] The kth result in the first set is input into the feature extraction module of the initial state, so that the feature extraction module of the initial state performs pattern recognition on the kth result in the first set to obtain the kth recognition result, and then based on the degree of matching between the kth recognition result and the kth network pattern in the second set corresponding to the kth result of the first set, the parameters of the feature extraction module of the initial state are adjusted until the above-mentioned matching degree is greater than or equal to the matching degree threshold. At this time, the feature extraction module after parameter adjustment can be determined as the feature extraction module; wherein k is an integer greater than or equal to 1.

[0075] Exemplarily, the above-mentioned matching degree can be determined by calculating the first loss function between the kth recognition result and the kth network pattern in the second set corresponding to the kth result of the first set.

[0076] Step B4: Based on the adjustment indication information and the emotion label in the indication sample data, the parameters of the emotion analysis module in the initial state are adjusted to obtain the emotion analysis module.

[0077] In one implementation, the sentiment analysis module may be obtained in the following manner:

[0078] The mth adjustment indication information in the indication sample data is input into the sentiment analysis module in the initial state so that it analyzes the mth adjustment indication information to obtain the mth sentiment analysis result, and the mth sentiment analysis result and the mth sentiment label are calculated by the second loss function to determine the degree of difference between the mth sentiment analysis result and the mth sentiment label, and the parameters of the sentiment analysis module in the initial state are adjusted based on the above-mentioned degree of difference until the above-mentioned degree of difference is less than or equal to the difference threshold. At this time, the sentiment analysis module in the initial state after the parameters are adjusted can be determined as the sentiment analysis module; wherein m is an integer greater than or equal to 1, and the mth sentiment label can be the sentiment label corresponding to the mth adjustment indication information in the indication sample data.

[0079] It should be noted that in the above training process, the state sample data can be divided into a first training data set and a first verification data set, and the feature extraction module of the initial state is trained based on the first training data set, and the pattern recognition accuracy of the feature extraction module is verified based on the first verification data set.

[0080] Accordingly, the indicated sample data can be divided into a second training data set and a second verification data set, and the sentiment analysis module in the initial state is trained based on the second training data set, and the sentiment analysis accuracy of the sentiment analysis module is verified based on the second verification data set.

[0081] Step B5: Integrate the feature extraction module and the sentiment analysis module to obtain an adjustment model.

[0082] In one implementation, the feature extraction and sentiment analysis modules may be arranged in parallel to obtain an adjustment model.

[0083] In one embodiment, the adjustment model may also include a software module for generating an adjustment strategy.

[0084] From the above, it can be seen that in the adjustment method provided in the embodiment of the present application, after obtaining the state sample data, the feature extraction module of the initial state is trained based on the first set and the second set in the state sample data to obtain the feature extraction module, and the first set includes a set of results of analyzing the path connectivity state between at least part of the network nodes in at least one network, and the second set includes a set of network patterns corresponding to the results in the first set. In this way, through the above method, supervised training of the feature extraction module of the initial state is achieved, thereby not only improving the generalization of the feature extraction module, but also improving the accuracy of the pattern recognition function of the feature extraction module; and, after obtaining the indication sample data, based on the adjustment indication information and the emotion label in the indication sample data, the parameters of the emotion analysis module of the initial state are adjusted to obtain the emotion analysis module, and the indication sample data includes a set of mutually related adjustment indication information and emotion labels. In this way, targeted training of the emotion analysis module of the initial state is achieved, thereby improving the targetedness of the emotion analysis module for the adjustment indication information.

[0085] Based on the above embodiments, in the adjustment method provided in the embodiments of the present application, obtaining the initial analysis result can be achieved by the following methods:

[0086] The transmission status of the traffic data in the target network is tracked by using a counting Bloom filter; and an initial analysis result is determined based on the transmission status.

[0087] Among them, the traffic data carries valid data.

[0088] In one implementation, the traffic data may include a collection of data packets actually transmitted by the target network and carrying valid data.

[0089] In one implementation, the valid data may correspond to at least one business processing scenario.

[0090] In one implementation, the transmission status may include whether the traffic data is transmitted to at least one network node in the target network, and may also include a process of transmitting the traffic data between at least some of the network nodes.

[0091] In one embodiment, at least some of the network nodes in the target network may be respectively associated with counting Bloom filters, so that the counting Bloom filters associated with each network node can respectively detect the status of each network node receiving and sending traffic data, and determine the above-mentioned transmission status based on the status of the traffic data being sent and received between each network node.

[0092] In one embodiment, the initial analysis results may be determined by:

[0093] The transmission status may include the node identification and time information of the network node. In this way, the transmission process of the network data in the target network can be sorted out according to the time information and the node identification to obtain the fourth result. At the same time, the network topology structure of the target network is obtained, and the path connectivity status between the network nodes in the network topology structure is identified based on the fourth result to obtain the initial analysis result; wherein, the network topology structure may include a network topology map, which can be a graphical representation of the target network and can intuitively present the connection relationship between each network node in the target network.

[0094] In practical applications, path analysis in cyberspace is an important network management task, which is used to determine whether the path between a data packet from a source device to a destination device is connected.

[0095] In the related art, the path analysis method in cyberspace is mainly based on Internet Control Message Protocol (ICMP) echo request and check item connectivity. This method is usually implemented in the following way: the source device sends an ICMP echo request data packet, uses the Internet Protocol Address (IP) of the target cloud host as the destination address, and sets a suitable survival time; listens to and receives these requests on the target cloud host, and responds to them; by recording the sending and receiving time, the round-trip time can be calculated, thereby determining the path connectivity status of the data packet from the source host to the target host.

[0096] Related technologies also provide a path analysis method based on connectivity of check items, which detects connectivity by judging specific check items including peer-to-peer connection, Internet Content Provider (ICP) filing, etc.

[0097] However, the above method needs to send real ICMP data packets to determine the path connectivity status between device nodes, which will generate additional load and interference on the network, and may also expose the real network topology structure, posing a security risk; and the above method cannot fully cover all device nodes and connections in the network, so that the path connectivity status obtained by the above method has a blind spot in the network node; at the same time, the above method cannot detect the path connectivity status of a dynamic network structure.

[0098] The adjustment method provided in the embodiment of the present application tracks the transmission status of the flow data in the target network through a counting Bloom filter, and determines the initial analysis result based on the transmission status, and the flow data carries valid data. In this way, through the above operation, the network load generated by the need to send specific data packets including ICMP data packets to analyze the path connectivity status is reduced; and by tracking the transmission status of the actual flow data in the target network, it is possible to achieve diversified, flexible, and dynamic automatic tracking of the target network, thereby improving the accuracy of the initial analysis results; at the same time, it is also possible to reduce the risk of leaking the network topology of the target network or causing network attacks, thereby improving the security of the process of determining the initial analysis results.

[0099] Based on the foregoing embodiment, in the adjustment method provided in the embodiment of the present application, tracking the transmission status of traffic data in the target network by counting Bloom filters can be implemented by the following steps:

[0100] Step C1: If a network node in the target network receives the pth data in the traffic data, a segmentation operation is performed on the pth data to obtain a data block set.

[0101] Here, p is an integer greater than or equal to 1.

[0102] Correspondingly, if the network node in the target network does not receive the pth data in the traffic data, the pth data may not be split.

[0103] In one implementation, the pth data may include at least one data packet.

[0104] In one implementation, performing a split operation on the pth data may be obtained in the following manner:

[0105] A counting Bloom filter is constructed, and a data segmentation operation is performed on the pth data through the counting Bloom filter to obtain a data block set, and the data block set is recorded as n_gram; illustratively, the data block set n_gram may include n data block elements; n may be an integer greater than 1.

[0106] Step C2: Encode the data blocks in the data block set to obtain a first encoding set.

[0107] In one implementation, the amount of encoded data in the first encoding set may be smaller than the amount of data of the corresponding data block in the data block set.

[0108] In one implementation, the first code set may be obtained in the following manner:

[0109] By counting the hash functions in the hash function set of the Bloom filter, the data blocks in the data block set are hash-encoded to obtain a first coding set; accordingly, the first coding set may include a set of hash values ​​respectively calculated by the hash functions in the hash function set.

[0110] Step C3: Process the first coding set through a counting Bloom filter to obtain data block statistics.

[0111] In one implementation, the data block statistics result may represent the number of times the network node receives the pth data.

[0112] In one implementation, the data block statistics can be obtained by any of the following methods:

[0113] According to the correspondence between the hash functions in the hash function set and the element storage positions in the counting Bloom filter, the encoding results in the first encoding set are stored in the counting Bloom filter accordingly, and the encoding results stored in the counting Bloom filter are counted to obtain data block statistics.

[0114] The elements corresponding to the pth data in the counting Bloom filter are summed to obtain the statistical result of the data block.

[0115] Step C4: Based on the statistical results of data blocks associated with different network nodes, determine the transmission status of traffic data between different network nodes.

[0116] In one embodiment, each network node in the target network may be constructed with a corresponding counting Bloom filter. Thus, through the counting Bloom filters corresponding to each network node, the transmission status of the data blocks corresponding to the data contained in the traffic data at each network node may be counted respectively.

[0117] From the above, it can be seen that in the adjustment method provided by the embodiment of the present application, if the network node in the target network receives the pth data in the traffic data, a segmentation operation is performed on the pth data to obtain a data block set, and the data blocks in the data block set are encoded to obtain a first encoding set, and then the first encoding set is processed by a counting Bloom filter to obtain data block statistics, and then based on the data block statistics associated with different network nodes, the transmission status of the traffic data between different network nodes is determined. In this way, in the above process, with the help of the superiority of the counting Bloom filter in space efficiency, query efficiency and adaptability to dynamic data, the efficiency of obtaining data block statistics can be improved, the accuracy of data block statistics can be improved, and then the accuracy of the transmission status and its determination efficiency can be improved.

[0118] Based on the foregoing embodiment, in the adjustment method provided in the embodiment of the present application, after obtaining the statistical result of the data block, the following operations may be performed:

[0119] If the statistical result of the data block is greater than a preset threshold, it is determined that the pth data corresponding to the statistical result of the data block is in a threat state.

[0120] Correspondingly, if the statistical result of the data block is less than the preset threshold, it can be determined that the pth data block is not in a threat state.

[0121] In one implementation, if the statistical result of the data block is greater than a preset threshold, it may indicate that the pth data is in a frequently transmitted state, for example, it may indicate that the data is currently in a threat state of private data leakage or frequent attacks.

[0122] As can be seen from the above, the adjustment method provided in the embodiment of the present application determines that the pth data corresponding to the data block statistical result is in a threat state if the data block statistical result is greater than the preset threshold. In this way, through the above operation, threat detection of the traffic data transmitted by at least part of the network nodes in the target network is achieved.

[0123] Based on the foregoing embodiments, in the adjustment method provided in the embodiments of the present application, the transmission status includes the connectivity status between different network nodes in the target network.

[0124] Accordingly, after determining the initial analysis result based on the transmission status, the following operations may also be performed:

[0125] Acquire path connectivity states corresponding to other network nodes in the target network except at least some of the network nodes; incrementally update the initial analysis result based at least on the path connectivity states corresponding to the other network nodes.

[0126] In one implementation, the path connectivity states corresponding to other network nodes may be obtained after determining the initial analysis result, or may be obtained before obtaining the initial analysis result or during the process of obtaining the initial analysis result.

[0127] In one implementation, the path connectivity status corresponding to other network nodes may include connectivity status between network nodes in other network nodes, and / or connectivity status between network nodes in other network nodes and at least some network nodes.

[0128] In one implementation, an incremental update module based on a differential algorithm may be constructed to incrementally update the initial analysis results to reduce update overhead.

[0129] Specifically, the data structure of the incremental update module can be designed in advance, and a persistent data structure can be used to record the initial analysis results and the connectivity status corresponding to other network nodes; wherein, the above data structure can effectively store the initial analysis results and implement efficient incremental update operations.

[0130] Secondly, a differential algorithm may be implemented to compare the cached initial analysis results with the connectivity states corresponding to other network nodes, and determine the difference data between the initial analysis results and the above connectivity states.

[0131] Then, the incremental information corresponding to the above difference data can be incrementally updated to the initial analysis result through a differential algorithm, thereby completing the incremental update of the initial analysis result.

[0132] As can be seen from the above, the adjustment method provided in the embodiment of the present application, after obtaining the path connectivity status corresponding to other network nodes excluding at least some network nodes in the target network, incrementally updates the initial analysis result based on at least the path connectivity status corresponding to other network nodes. Through the above operation, the incremental update of the initial analysis result is achieved, thereby reducing the consumption of storage space due to re-storing the path connectivity status corresponding to other network nodes.

[0133] Based on the above embodiments, the adjustment method provided in the embodiments of the present application may also perform the following operations:

[0134] Compressing the initial analysis result and / or the target adjustment result to obtain compressed data; and storing the compressed data.

[0135] In one implementation, the data volume of the compressed data may be smaller than the data volume of the initial analysis result, and may also be smaller than the data volume of the target adjustment result.

[0136] In one implementation, the compression of the initial analysis results and / or the target adjustment results may be achieved by:

[0137] A compression algorithm is determined, and the initial analysis result and / or the target adjustment result is compressed by the compression algorithm to obtain compressed data; wherein the compression algorithm may include a Lempel-Ziv-Welch (LZW) compression algorithm.

[0138] From the above, it can be seen that the adjustment method provided in the embodiment of the present application, by compressing the initial analysis results and / or target adjustment results, obtains and stores compressed data, which can reduce the consumption of storage space caused by storing a large number of initial analysis results and / or target adjustment results.

[0139] Based on the above embodiments, in the adjustment method provided in the embodiments of the present application, compressing the initial analysis result and / or the target adjustment result can be achieved by the following steps:

[0140] Step D1, determine the second coding set.

[0141] In one embodiment, the second coding set may include a set of elements such as characters or numbers; illustratively, the data volume of character elements or number elements in the second coding set may be smaller than the data volume of data in the initial analysis results and / or target adjustment results.

[0142] In one implementation, the second coding set may be predetermined.

[0143] Step D2: construct a dynamic dictionary based on the traffic data and the second coding set.

[0144] In one implementation, the dynamic dictionary may include elements in the traffic data and elements in the second coding set, and in the dynamic dictionary, there may be a one-to-one correspondence relationship between the elements in the traffic data and the elements in the second coding set.

[0145] In one implementation, the dynamic dictionary may be constructed in the following manner:

[0146] Initialize the dynamic dictionary, and add the elements in the data block set represented by the n-gram corresponding to the p-th data in the traffic data to the dynamic dictionary; if the p+1-th data in the traffic data is received, determine the data block set corresponding to the p+1-th data; if the data block set corresponding to the p+1-th data does not exist in the dynamic dictionary, add the data block set corresponding to the p+1-th data to the dynamic dictionary; if the data block set corresponding to the p+1-th data exists in the dynamic dictionary, expand the p+1-th data based on the characters in the p+2-th data, and determine whether the expanded p+1-th data exists in the dynamic dictionary; if not, add the expanded p+1-th data to the dynamic dictionary, and recursively perform the above operations until the data block sets corresponding to all the data in the traffic data are processed, and the dynamic dictionary can be obtained at this time; wherein p is an integer greater than or equal to 1.

[0147] Step D3: compress the initial analysis results and / or target adjustment results based on the dynamic dictionary.

[0148] In one embodiment, compressing the initial analysis results and / or the target adjustment results may be achieved by:

[0149] Obtain the qth data from the initial analysis result and / or the target adjustment result, search the qth data in the dynamic dictionary, if the qth data exists in the dynamic dictionary, obtain the q+1th data, and expand the qth data based on the characters in the q+1th data to obtain the q+ith extended result, then find out whether the q+ith extended result exists in the dynamic dictionary, repeat the above operation until the q+I+1th extended result does not exist in the dynamic dictionary, at this time, the coding element corresponding to the q+Ith extended result in the dynamic dictionary can be determined as the coding result corresponding to the q+Ith extended result, and repeat this cycle until all the data in the initial analysis result and / or the target adjustment result are encoded; wherein q is an integer greater than or equal to 1, i is an integer greater than or equal to 1 and less than or equal to I, and I is an integer greater than or equal to 2.

[0150] From the above, it can be seen that the adjustment method provided in the embodiment of the present application, after determining the second coding set, constructs a dynamic dictionary based on the traffic data and the second coding set, and compresses the initial analysis results and / or target adjustment results based on the dynamic dictionary. In this way, through the flexibility, dynamism, scalability and high efficiency of data operations of the dynamic dictionary, it is possible to achieve a full range of stable and efficient compression processing of the initial analysis results and / or target adjustment results; and through the above compression processing, it is possible to reduce the probability of data explosion caused by storing the initial analysis results and / or target adjustment results.

[0151] It should be noted that in the embodiments of the present application, data sources including log data and performance indicator data of the target network can also be integrated to analyze the path connectivity status between network nodes in the target network, and the initial analysis results can be adjusted and optimized with the help of the above data sources; at the same time, the technical solution provided in the embodiments of the present application can also be applied to path analysis across multi-cloud environments in a multi-cloud environment to provide data support for the management and optimization of network paths across cloud environments; on the other hand, when performing sentiment analysis, natural language processing technology can be used to analyze feedback data such as network logs and user adjustment support information to explore more path optimization suggestions and user needs.

[0152] Based on the above embodiments, the present application also provides an adjustment device. Figure 2 A schematic diagram of the structure of the adjustment device provided in the embodiment of the present application is shown in FIG. Figure 2 As shown, the adjustment device 2 may include:

[0153] The acquisition module 201 is used to acquire the initial analysis result and the user's adjustment instruction information; wherein the initial analysis result includes the result of analyzing the path connectivity status between at least some network nodes in the target network;

[0154] The adjustment module 202 is used to adjust the initial analysis result based on the adjustment indication information through the adjustment model to obtain a target adjustment result.

[0155] In some embodiments, the adjustment model includes at least a feature extraction module and a sentiment analysis module; the adjustment device may also include a processing module for performing pattern recognition on the initial analysis results through the feature extraction module to obtain pattern recognition results; analyzing the adjustment indication information through the sentiment analysis module to obtain sentiment analysis results; determining an adjustment strategy based on the sentiment analysis results and the pattern recognition results; and adjusting the initial analysis results based on the adjustment strategy to obtain a target adjustment result.

[0156] In some embodiments, the acquisition module 201 is used to acquire state sample data; wherein the state sample data includes a first set and a second set; the first set includes a set of results of analyzing the path connectivity state between at least some network nodes in at least one network; the second set includes a set of network modes corresponding to the results in the first set;

[0157] The acquisition module 201 is further used to acquire indication sample data; wherein the indication sample data includes a set of mutually related adjustment indication information and emotion labels;

[0158] The processing module is used to train the feature extraction module of the initial state based on the first set and the second set in the state sample data to obtain the feature extraction module; adjust the parameters of the sentiment analysis module of the initial state based on the adjustment indication information and the sentiment label in the indication sample data to obtain the sentiment analysis module; integrate the feature extraction module and the sentiment analysis module to obtain the adjustment model.

[0159] In some embodiments, the processing module is used to track the transmission status of the flow data in the target network through the counting Bloom filter; wherein the flow data carries valid data;

[0160] The processing module is further used to determine an initial analysis result based on the transmission state.

[0161] In some embodiments, the processing module is used to perform a segmentation operation on the pth data to obtain a data block set if the network node in the target network receives the pth data in the traffic data; wherein p is an integer greater than or equal to 1;

[0162] The processing module is also used to encode the data blocks in the data block set to obtain a first coding set; process the first coding set through a counting Bloom filter to obtain data block statistics; and determine the transmission status of traffic data between different network nodes based on the data block statistics associated with different network nodes.

[0163] In some embodiments, the processing module is used to determine that the pth data corresponding to the data block statistical result is in a threat state if the data block statistical result is greater than a preset threshold.

[0164] In some embodiments, the transmission state includes connectivity states between different network nodes in the target network; the acquisition module 201 is used to acquire path connectivity states corresponding to other network nodes in the target network except at least some of the network nodes;

[0165] The processing module is used to incrementally update the initial analysis result based on at least the path connectivity status corresponding to other network nodes.

[0166] In some embodiments, the processing module is used to compress the initial analysis results and / or the target adjustment results to obtain compressed data; and store the compressed data.

[0167] In some embodiments, the processing module is used to determine a second coding set; construct a dynamic dictionary based on the traffic data and the second coding set; and compress the initial analysis results and / or the target adjustment results based on the dynamic dictionary.

[0168] Based on the above embodiments, the present application also provides an electronic device, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device 3 includes a processor 301 and a memory 302; wherein the memory 302 stores a computer program; when the computer program is executed by the processor 301, it can implement the adjustment method provided in any of the previous embodiments.

[0169] Based on the foregoing embodiments, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored; when the computer program is executed by a processor of an electronic device, it can implement an adjustment method provided in any of the previous embodiments.

[0170] Based on the foregoing embodiments, an embodiment of the present application further provides a computer program product, the program product comprising a computer program; when the computer program is executed by a processor of an electronic device, it can implement the adjustment method provided in any of the previous embodiments.

[0171] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0172] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0173] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0174] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0175] It should be noted that the above-mentioned computer-readable storage medium can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM) and other memories; it can also be various electronic devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0176] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0177] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0178] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus necessary general hardware nodes, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0182] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An adjustment method, characterized in that: The method comprises: Obtaining initial analysis results; wherein the initial analysis results include results of analyzing the path connectivity status between at least some network nodes in the target network; Obtaining adjustment instruction information from the user; The initial analysis result is adjusted based on the adjustment indication information through the adjustment model to obtain a target adjustment result.

2. The method according to claim 1, characterized in that The adjustment model at least includes a feature extraction module and a sentiment analysis module; The adjusting the initial analysis result based on the adjustment indication information by adjusting the model to obtain a target adjustment result includes: Performing pattern recognition on the initial analysis result by the feature extraction module to obtain a pattern recognition result; Analyze the adjustment instruction information by the sentiment analysis module to obtain a sentiment analysis result; Determining an adjustment strategy based on the sentiment analysis result and the pattern recognition result; The initial analysis result is adjusted based on the adjustment strategy to obtain the target adjustment result.

3. The method according to claim 2, characterized in that Before adjusting the initial analysis result based on the adjustment indication information by adjusting the model, the method further includes: Acquire state sample data; wherein the state sample data includes a first set and a second set; the first set includes a set of results of analyzing the path connectivity state between at least some network nodes in at least one network; the second set includes a set of network modes corresponding to the results in the first set; Acquire indication sample data; wherein the indication sample data includes a set of mutually related adjustment indication information and emotion labels; Based on the first set and the second set in the state sample data, training a feature extraction module of an initial state to obtain the feature extraction module; Based on the adjustment indication information in the indication sample data and the emotion label, adjusting the parameters of the emotion analysis module in the initial state to obtain the emotion analysis module; The feature extraction module and the sentiment analysis module are integrated to obtain the adjustment model.

4. The method according to claim 1, characterized in that: The obtaining of the initial analysis result comprises: Tracking the transmission status of the traffic data in the target network through a counting Bloom filter; wherein the traffic data carries valid data; The initial analysis result is determined based on the transmission status.

5. The method according to claim 4, characterized in that Tracking the transmission status of traffic data in the target network through a counting Bloom filter includes: If the network node in the target network receives the pth data in the traffic data, a segmentation operation is performed on the pth data to obtain a data block set; wherein p is an integer greater than or equal to 1; Encoding the data blocks in the data block set to obtain a first encoding set; Processing the first coding set by using the counting Bloom filter to obtain a data block statistical result; Based on the statistical results of the data blocks associated with different network nodes, the transmission status of the flow data between the different network nodes is determined.

6. The method according to claim 5, characterized in that After obtaining the data block statistical results, the method further includes: If the statistical result of the data block is greater than a preset threshold, it is determined that the pth data corresponding to the statistical result of the data block is in a threat state.

7. The method according to claim 4, characterized in that The transmission state includes a connectivity state between different network nodes in the target network; after determining the initial analysis result based on the transmission state, the method further includes: Acquire path connectivity states corresponding to other network nodes in the target network except at least some of the network nodes; The initial analysis result is incrementally updated based at least on the path connectivity status corresponding to the other network nodes.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: compressing the initial analysis result and / or the target adjustment result to obtain compressed data; The compressed data is stored.

9. The method according to claim 8, characterized in that The compressing the initial analysis result and / or the target adjustment result comprises: determining a second encoding set; Building a dynamic dictionary based on the traffic data and the second code set; The initial analysis result and / or the target adjustment result are compressed based on the dynamic dictionary.

10. An adjustment device, characterized in that: The adjusting device comprises: An acquisition module, used to acquire an initial analysis result and user adjustment instruction information; wherein the initial analysis result includes a result of analyzing the path connectivity status between at least some network nodes in the target network; An adjustment module is used to adjust the initial analysis result based on the adjustment indication information through an adjustment model to obtain a target adjustment result.

11. An electronic device, characterized in that: The electronic device comprises a processor and a memory; wherein a computer program is stored in the memory; when the computer program is executed by the processor, the adjustment method as claimed in any one of claims 1 to 9 can be implemented.

12. A computer-readable storage medium, characterized in that: The storage medium stores a computer program; when the computer program is executed by a processor of an electronic device, the adjustment method according to any one of claims 1 to 9 can be implemented.

13. A computer program product, characterized in that The program product comprises a computer program; when the computer program is executed by a processor of an electronic device, the adjustment method according to any one of claims 1 to 9 can be implemented.

Images