Data intelligent storage method, device, computer equipment and storage medium

By sorting, feature extraction and classification processing of user behavior data, the problem of difficulty in accurately hierarchical storage in the prior art is solved, and intelligent storage and efficient query of data are realized.

CN113449036BActive Publication Date: 2024-11-05GUIZHOU WUJIANG HYDROPOWER DEV
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202110725706.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-29
Publication Date
2024-11-05
Estimated Expiration
2041-06-29

AI Technical Summary

Technical Problem

Existing users use data storage methods to accurately store information hierarchical storage, which affects the efficiency of data storage and the efficiency of analytical queries.

Method used

By receiving user behavior data, sorting event information, extracting key feature information, calculating comprehensive feature information, and classifying based on the classification model, obtaining event tag information, and classifying and storing.

Benefits of technology

It greatly improves the storage efficiency of users' data usage, and realizes intelligent storage and efficient query of data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113449036B_ABST
    Figure CN113449036B_ABST
Patent Text Reader

Abstract

The present invention discloses a data intelligent storage method, device, computer equipment and storage medium, the method comprising: sorting the event information contained in the received user behavior data to obtain event sorting information, extracting key feature information of each event node from the event sorting information and obtaining comprehensive feature information of each event node, obtaining classification information of each event node according to the comprehensive feature information and obtaining event label information of each event node based on the classification information, and classifying and storing the event sorting information and event label information according to the classification information. The present invention belongs to the field of distributed storage technology, can intelligently obtain the comprehensive feature information of each event node, and obtain the corresponding classification information and event label information based on the comprehensive feature information, classify and store the event sorting information and event label information, and greatly improve the efficiency of storing user usage data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of distributed storage technology, and belongs to an application scenario of intelligently storing user usage data in a smart city, and in particular to a data intelligent storage method, device, computer equipment and storage medium. Background Art

[0002] With the development of Internet technology, the emergence of various applications has greatly facilitated the lives, work and study of users. When each user uses an application, a large amount of usage data will be generated. In order to facilitate the analysis and query of the user's usage data in the later stage, the usage data of each user obtained can be stored. Conventional technical methods all store the user's usage data in a log. However, the usage data of a large number of users are stored in the log at the same time, resulting in a large amount of data information contained in the log. Therefore, it is difficult to accurately extract and hierarchically store the data information stored in the log, which affects the efficiency of storing the user's usage data and makes it difficult to analyze and efficiently query the data information stored in the log. Therefore, the existing user usage data storage method has the problem of difficulty in accurately storing information in a hierarchical manner. Summary of the invention

[0003] The embodiments of the present invention provide a data intelligent storage method, device, computer equipment and storage medium, aiming to solve the problem that it is difficult to accurately perform information hierarchical storage when using existing user data storage methods.

[0004] In a first aspect, an embodiment of the present invention provides a data intelligent storage method, which includes:

[0005] If the input user behavior data is received, the event information contained in the user behavior data is sorted to obtain corresponding event sorting information;

[0006] Extracting key feature information corresponding to each event node from the event sorting information according to a preset feature extraction model;

[0007] Acquire comprehensive feature information corresponding to each of the event nodes according to a preset comprehensive feature calculation rule;

[0008] Classifying each event node according to a preset classification model and the comprehensive feature information to obtain classification information of each event node;

[0009] Extracting event label information of each event node from the event sorting information according to the classification information of each event node and a pre-stored extraction template set;

[0010] The event sorting information and the event tag information are classified and stored in an event database according to the classification information of each event node.

[0011] In a second aspect, an embodiment of the present invention provides a data intelligent storage device, comprising:

[0012] An event ranking information acquisition unit, configured to, upon receiving the input user behavior data, sort the event information contained in the user behavior data to obtain corresponding event ranking information;

[0013] A key feature information acquisition unit, configured to extract key feature information corresponding to each event node from the event sorting information according to a preset feature extraction model;

[0014] A comprehensive feature information acquisition unit, used to acquire the comprehensive feature information corresponding to each of the event nodes according to a preset comprehensive feature calculation rule;

[0015] A classification processing unit, used to classify each event node according to a preset classification model and the comprehensive feature information to obtain classification information of each event node;

[0016] An event label information acquisition unit, configured to extract the event label information of each event node from the event sorting information according to the classification information of each event node and a pre-stored extraction template set;

[0017] The classification storage unit is used to classify and store the event sorting information and the event tag information into an event database according to the classification information of each event node.

[0018] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the data intelligent storage method described in the first aspect when executing the computer program.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the data intelligent storage method described in the first aspect above.

[0020] The embodiments of the present invention provide a data intelligent storage method, device, and computer-readable storage medium. The event information contained in the received user behavior data is sorted to obtain event sorting information, key feature information of each event node is extracted from the event sorting information, and comprehensive feature information of each event node is obtained, classification information of each event node is obtained based on the comprehensive feature information, and event label information of each event node is obtained based on the classification information, and event sorting information and event label information are classified and stored according to the classification information. Through the above method, the comprehensive feature information of each event node can be intelligently obtained, and the corresponding classification information and event label information can be obtained based on the comprehensive feature information, and the event sorting information and event label information are classified and stored, which greatly improves the efficiency of storing user usage data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0022] Figure 1 A schematic diagram of a flow chart of a data intelligent storage method provided by an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of a sub-process of a data intelligent storage method provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of another sub-process of the data intelligent storage method provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of another sub-process of the data intelligent storage method provided by an embodiment of the present invention;

[0026] Figure 5 A schematic diagram of another sub-process of the data intelligent storage method provided by an embodiment of the present invention;

[0027] Figure 6 A schematic diagram of another sub-process of the data intelligent storage method provided by an embodiment of the present invention;

[0028] Figure 7 Another schematic diagram of a flow chart of a method for intelligent data storage provided by an embodiment of the present invention;

[0029] Figure 8 A schematic block diagram of a data intelligent storage device provided by an embodiment of the present invention;

[0030] Fig. 9A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0033] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0034] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0035] See also Figure 1 , Figure 1 This is a flow chart of the data intelligent storage method provided by an embodiment of the present invention; the data intelligent storage method is applied to the management server, and the data intelligent storage method is executed by the application software installed in the management server. The management server is a server end that can intelligently store the input user behavior data, such as a server built by an enterprise or government department. The management server can establish a network connection with the user terminal to transmit data information. For example, any operation performed by the user in the user terminal can form user behavior data and input it into the management server. Figure 1 As shown, the method includes steps S110 to S160.

[0036] S110: If the input user behavior data is received, the event information contained in the user behavior data is sorted to obtain corresponding event sorting information.

[0037] If the input user behavior data is received, the event information contained in the user behavior data is sorted to obtain the corresponding event sorting information. The management server can establish a network connection with one or more clients, and the management server can provide services to the client. The user uses the corresponding service through the client. In the process of using the corresponding service, there is information interaction between the client and the management server, and the management server needs to process the corresponding data when providing services to the customer. The user behavior data is the interaction information generated by the user in the process of using the corresponding service and the processing information of the server processing the corresponding data to provide services. Then, one user behavior data contains data information corresponding to a series of operations performed by the user using a certain service. A user behavior data can contain multiple event information. The user behavior data of the same user shares a behavior identifier (traceID). Each event information corresponds to an event node and the interface call information corresponding to the event node. The event node can be any operation performed by the user in the user terminal or the node information of the user terminal displaying any page. For example, the multiple event nodes contained in a certain user behavior data can be expressed as: login page-homepage-click event 01-page browsing 01-click event 02-page browsing 02... The event information contained in the user behavior data can be sorted to obtain corresponding event sorting information.

[0038] In one embodiment, if Figure 2 As shown, step S110 includes sub-steps S111, S112 and S113.

[0039] S111, obtaining a trigger time corresponding to each event node from the user behavior data; S112, sorting the event nodes included in the user behavior data according to the trigger time to obtain node sorting information.

[0040] The user behavior data contains the trigger time of each event node. The trigger time is the time information obtained by the management server for triggering and executing a certain event. The multiple event nodes contained in the user behavior data can be sorted according to the trigger time. The earlier the trigger time, the earlier the sorting time, and the later the sorting time. After sorting, the corresponding node sorting information can be obtained.

[0041] S113: Add the interface call information corresponding to each of the event nodes in the user behavior data to the sorting position of the event node matching the interface call information in the node sorting information to obtain the event sorting information.

[0042] The user behavior data also includes interface call information corresponding to each event node. The interface call information is the specific information that the management server uses to call the background interface and process the corresponding data based on the triggered event. The interface call information can be added to the sorting position corresponding to the corresponding event node in the node sorting information to obtain event sorting information containing event nodes and interface call information.

[0043] S120: extract key feature information corresponding to each event node from the event sorting information according to a preset feature extraction model.

[0044] According to the preset feature extraction model, the key feature information corresponding to each event node is extracted from the event sorting information. The interface call information of each event information in the event sorting information is too complex and difficult to classify and organize. Therefore, the key feature information corresponding to each event node in the event sorting information can be extracted through the feature extraction model. The key feature information can be used to quantitatively characterize the features corresponding to each event node. Among them, the feature extraction model includes a keyword set and a feature extraction neural network.

[0045] In one embodiment, if Figure 3 As shown, step S120 includes sub-steps S121, S122 and S123.

[0046] S121. Acquire key information of each event node from the event sorting information according to the keyword set.

[0047] A keyword set is a set composed of multiple preset keywords. It can be determined one by one whether the interface call information of each event node contains key information matching the keyword set. That is, if a word in the interface call information is the same as any keyword in the keyword set, then the word is used as a key information corresponding to the keyword set. According to the above method, the key information corresponding to the keyword set in each interface call information can be obtained, that is, the key information of each event node can be obtained.

[0048] S122. Binarize the key information of each event node according to the keyword set to obtain a corresponding feature vector.

[0049] The key information of each event node can be binarized according to the keyword set. Specifically, a position in the keyword set corresponding to a key information of a certain event node can be marked as "1", and a position in the keyword set that does not correspond to any key information of the event node can be marked as "0". The key information of the event node can be binarized by the above method, and the number of vector values ​​contained in the obtained feature vector is equal to the number of keywords contained in the keyword set.

[0050] S123, inputting the feature vectors corresponding to each of the event nodes into the feature extraction neural network for feature extraction, to obtain key feature information corresponding to each of the event nodes.

[0051] Since the number of keywords contained in the keyword set is too large, in order to improve the efficiency of subsequent analysis, the corresponding key feature information can be extracted from the feature vector of each event node through a feature extraction neural network to reduce the number of eigenvalues ​​in the key feature information. Among them, the feature extraction neural network is an intelligent neural network built based on artificial intelligence. The feature extraction neural network consists of an input layer, multiple intermediate layers and an output layer. The input layer and the intermediate layer, the intermediate layer and other adjacent intermediate layers, and the intermediate layer and the output node are all associated through association formulas. Each association formula can be expressed as a linear function, which contains corresponding parameter values. Each input node in the input layer corresponds to a vector value in the feature vector, and each output node corresponds to a dimension. Each feature vector is input into the feature extraction neural network to obtain the corresponding output result, which is the eigenvalue of the dimension corresponding to each output node. The eigenvalue of each output node can be combined into a corresponding set of key feature vectors. Then, the feature vector of each event node is input into the feature extraction neural network to obtain a corresponding set of key feature information. The number of eigenvalues ​​contained in each set of key feature information is equal. Before using the feature extraction neural network to extract key feature information, the feature extraction neural network can also be iteratively trained through a training data set. Training the feature extraction neural network is to optimize and adjust the parameter values ​​contained in the neural network.

[0052] S130. Obtain comprehensive feature information corresponding to each of the event nodes according to a preset comprehensive feature calculation rule.

[0053] The comprehensive feature information corresponding to each of the event nodes is obtained according to the preset comprehensive feature calculation rules. Since there is usually a certain correlation between adjacent event nodes in a piece of user behavior data, in order to comprehensively analyze the characteristics of each event by integrating the correlation between the event nodes, the key feature information obtained can be superimposed and calculated according to the comprehensive feature calculation rules to obtain the comprehensive feature information of each event node.

[0054] In one embodiment, if Figure 4 As shown, step S130 includes sub-steps S131 and S132.

[0055] S131. Acquire multiple key feature information associated with each of the event nodes from the key feature information as associated feature information corresponding to each of the event nodes.

[0056] According to the preset association rules, multiple key feature information related to each event node can be obtained from the key feature information as the corresponding association feature information. For example, if the association rule is that an event node is associated with the two event nodes before the event node and the event node after the event node, then according to the association rule, the key feature information of the two event nodes before a certain event node, the key feature information of the after event node and the key feature information of the event node itself can be obtained, and the four key feature information are combined as the association feature information corresponding to the event node.

[0057] S132: Perform superposition calculation on the associated feature information of each of the event nodes according to the comprehensive feature calculation rule to obtain comprehensive feature information corresponding to each of the event nodes.

[0058] The associated feature information of each event node can be superimposed and calculated according to the comprehensive feature calculation rules, that is, the multiple groups of key feature information contained in the associated feature information can be superimposed and calculated, and the comprehensive feature information corresponding to each event node can be obtained after calculation. Multiple feature values ​​corresponding to the multiple groups of key feature information contained in each associated feature information in the same dimension can be obtained, and the superimposed feature values ​​with each dimension can be superimposed and calculated according to the comprehensive feature calculation rules. The superimposed feature values ​​corresponding to a group of associated feature information and each dimension can be combined to obtain the comprehensive feature information, and the number of superimposed feature values ​​contained in the comprehensive feature information is equal to the number of feature values ​​contained in the key feature information.

[0059] For example, the comprehensive feature calculation rule can be expressed by formula (1):

[0060]

[0061] Among them, Z is the calculated superposition eigenvalue corresponding to one dimension, g i is a set of key feature information and the i-th eigenvalue corresponding to the dimension, f i is the i-th weighted value corresponding to the dimension in the calculation rule, M is the number of key feature information contained in a set of associated feature information.

[0062] S140: Classify each event node according to a preset classification model and the comprehensive feature information to obtain classification information of each event node.

[0063] Each event node is classified according to the preset classification model and the comprehensive feature information to obtain the classification information of each event node. The comprehensive feature information can quantitatively represent the comprehensive features corresponding to each event node, and the classification information corresponding to each event node can be obtained through the classification model and the obtained comprehensive feature information. The classification model is an intelligent neural network constructed based on artificial intelligence.

[0064] In one embodiment, step S140 includes sub-steps: inputting the comprehensive feature information of each of the event nodes into the classification model in sequence to obtain model output information corresponding to each of the event nodes; obtaining a classification with the highest matching degree in each of the model output information as the classification information corresponding to each of the event nodes.

[0065] Among them, the classification model consists of an input layer, multiple intermediate layers and an output layer. The input layer and the intermediate layer, the intermediate layer and other adjacent intermediate layers, and the intermediate layer and the output node are all associated through association formulas. Each association formula can be expressed as a linear function, which contains corresponding parameter values. Each input node in the input layer corresponds to a superimposed feature value in the comprehensive feature information, and each output node corresponds to a classification. For example, in this embodiment, the classification corresponding to the output node can be product information, promotional activities, information or help information. The comprehensive feature information of each event node is input into the above-mentioned classification model to obtain the corresponding model output information. The model output information contains the matching degree of the type corresponding to each output node. The comprehensive feature information of each event node is input into the classification model to obtain a corresponding set of model output information. The classification with the highest matching degree in each set of model output information can be obtained as the classification information of the event node corresponding to each set of model output information.

[0066] S150: extracting event label information of each event node from the event sorting information according to the classification information of each event node and a pre-stored extraction template set.

[0067] The event label information of each event node is correspondingly extracted from the event sorting information according to the classification information of each event node and the pre-stored extraction template set. The extraction template set is a set composed of multiple extraction templates pre-configured in the management server. The extraction template set contains extraction templates matching each classification. Then, based on the classification information of the event node, a matching extraction template can be obtained from the extraction template set, and based on the extraction template, the event label information of each event node can be extracted from the interface call information of the event node. The event label information can be used as the label of each event node to describe the corresponding event node.

[0068] In one embodiment, if Figure 5As shown, step S150 includes sub-steps: S151 and S152.

[0069] S151. Acquire, from the extraction template set according to the classification information of each event node, an extraction template matching each event node as a target extraction template.

[0070] Based on the classification information, an extraction template that matches each event node in the extraction template set can be selected as a target extraction template. There is only one extraction template that matches one classification in the extraction template set.

[0071] S152. According to the project fields contained in the target extraction template of each of the event nodes, extract the field values ​​corresponding to the corresponding project fields from the event sorting information and the interface call information corresponding to each of the event nodes as the event label information of each of the event nodes.

[0072] Each extraction template contains at least one project field. Based on the project fields contained in the target extraction template, the field value corresponding to the corresponding project field can be extracted from the interface call information of the event node corresponding to the target extraction template as the event label information of each event node. There is only one field value corresponding to one project field in the interface call information of an event node.

[0073] The step S152 also includes the following steps: determining whether the field value contained in each of the event tag information is a preset character type; if the field value is not the preset character type, mapping the field value according to a pre-stored mapping set to obtain a mapping field value that matches the preset character type; replacing the field value that is not the preset character type in each of the event tag information according to the mapping field value to obtain the replaced event tag information.

[0074] In the specific implementation process, it is also possible to determine whether each field value is of a preset character type. If it is not of a preset character type, the field value can be mapped according to the mapping to obtain a mapped field value, and the original field value can be replaced with a matching mapped field value to obtain the replaced event label information. For example, it is possible to determine whether the characters of each field value are all Chinese characters or numbers. If the characters of the field value are all Chinese characters or numbers, the field value is not mapped; if the characters of the field value are not all Chinese characters or numbers, that is, it indicates that the field value contains English characters, the English characters can be mapped through the field mapping relationship contained in the mapping set to obtain the corresponding mapped character value, and the characters contained in the mapped character value are all Chinese characters.

[0075] S160: Classify and store the event sorting information and the event tag information into an event database according to the classification information of each event node.

[0076] The event sorting information and the event tag information are classified and stored according to the classification information of each event node. The event sorting information and the event expression information can be classified and stored according to the classification information of each event node. The event database is a database pre-configured in the management server for storing event information. Multiple storage areas can be configured in the event database, and each storage area corresponds to a classification.

[0077] In one embodiment, if Figure 6 As shown, step S160 includes sub-steps: S161, S162, S163 and S164.

[0078] S161. Acquire event nodes corresponding to each classification from the event sorting information according to the classification information; S162. Store the event nodes corresponding to each classification in sequence in the storage area corresponding to the classification in the event database.

[0079] First, each event node can be classified according to its classification information to obtain the event node corresponding to each classification, and then the event nodes contained in each classification are stored in the storage area corresponding to each classification in the event database in the order of triggering time.

[0080] S163: After hierarchically organizing the interface call information of the event node corresponding to each of the categories, the information is stored in a storage location corresponding to the event node in the storage area of ​​the category.

[0081] The interface call information of each event node is hierarchically organized. Specifically, each event node may correspond to calling multiple interfaces. The interface request information of each event node is used as the next layer of information of the event node. Each interface request information may correspond to multiple interface call chains. The multiple interface call chains corresponding to the interface request information may be used as the next layer of information of the interface request information. Each interface call chain may correspond to multiple CAT (concatenate) command monitoring information. The multiple CAT command monitoring information corresponding to each interface call chain may be used as the next layer of information of the interface call chain. The interface call information of each event node may be hierarchically organized according to the above hierarchical rules, and the interface call hierarchical information obtained after organization may be stored in the storage area corresponding to the corresponding category of the event database and in the storage location corresponding to the corresponding event node.

[0082] S164. Store the event label information of the event node corresponding to each of the categories into a storage location corresponding to the event node in the storage area of ​​the category.

[0083] The event label information of the event node corresponding to each classification can be stored in the storage location corresponding to the corresponding event node in the storage area of ​​the corresponding classification of the event database. The information associated with each event node in each storage area in the event database includes interface call hierarchical information and event label information. The event label information can be used as the first-level information of each event node.

[0084] In one embodiment, if Figure 7 As shown, after step S160, the following step may be further included: S170: if an information acquisition request input by a user terminal is received, target information corresponding to the information acquisition request is acquired from the event database according to the information acquisition request and fed back to the user terminal.

[0085] If an information acquisition request input by a user terminal is received, the target information corresponding to the information acquisition request is acquired from the event database according to the information acquisition request and fed back to the user terminal, wherein the management server establishes a network connection with the user terminal to realize the transmission of data information, and the information acquisition request includes role information and behavior identification. Specifically, the user behavior data matching the behavior identification in the event database can be acquired as the target user behavior data according to the behavior identification; the corresponding role classification and acquisition level are determined according to the role information. According to the role classification, the alternative event information of the type matching the role classification is acquired from the event information contained in the target user behavior data; each of the alternative event information corresponds to an event node, and each of the alternative event information includes the interface call information and event label information corresponding to the corresponding event node; the alternative event information is arranged in sequence according to the trigger time of each of the alternative event information; according to the acquisition level, the information corresponding to the acquisition level is intercepted from the alternative event information as the target information and fed back to the user terminal.

[0086] For example, if the role information is an operation and maintenance promoter, then the corresponding role classification can be determined as a promotion activity, and the corresponding acquisition level can be determined to be 2. Then, the alternative event information that matches the behavior identifier in the information acquisition request and the classification as "promotion activity" can be obtained, and the event label information and interface request information corresponding to each event node in the alternative event information can be obtained as the target information corresponding to the acquisition level.

[0087] The technical method in this application can be applied to scenarios such as smart government affairs / smart urban management / smart communities / smart security / smart logistics / smart medical care / smart education / smart environmental protection / smart transportation, etc., where user usage data is intelligently stored, thereby promoting the construction of smart cities.

[0088] In the data intelligent storage method provided in the embodiment of the present invention, the event information contained in the received user behavior data is sorted to obtain event sorting information, key feature information of each event node is extracted from the event sorting information and comprehensive feature information of each event node is obtained, classification information of each event node is obtained based on the comprehensive feature information, and event label information of each event node is obtained based on the classification information, and event sorting information and event label information are classified and stored according to the classification information. Through the above method, the comprehensive feature information of each event node can be intelligently obtained, and the corresponding classification information and event label information can be obtained based on the comprehensive feature information, and the event sorting information and event label information are classified and stored, which greatly improves the efficiency of storing user usage data.

[0089] The embodiment of the present invention further provides a data intelligent storage device, which can be configured in a management server, and is used to execute any embodiment of the aforementioned data intelligent storage method. Figure 8 , Figure 8 A schematic block diagram of a data intelligent storage device provided in an embodiment of the present invention.

[0090] like Figure 8 As shown, the data intelligent storage device 100 includes an event sorting information acquisition unit 110, a key feature information acquisition unit 120, a comprehensive feature information acquisition unit 130, a classification processing unit 140, an event tag information acquisition unit 150 and a classification storage unit 160.

[0091] The event ranking information acquisition unit 110 is used to, upon receiving the input user behavior data, sort the event information contained in the user behavior data to obtain corresponding event ranking information.

[0092] In one embodiment, the target topic acquisition unit 110 includes sub-units: a trigger time acquisition unit, which is used to obtain the trigger time corresponding to each event node from the user behavior data; a node sorting information acquisition unit, which is used to sort the event nodes contained in the user behavior data according to the trigger time to obtain node sorting information; an interface call information adding unit, which is used to add the interface call information corresponding to each event node in the user behavior data to the sorting position of the event node matching the interface call information in the node sorting information to obtain the event sorting information.

[0093] The key feature information acquisition unit 120 is used to extract key feature information corresponding to each event node from the event sorting information according to a preset feature extraction model.

[0094] In one embodiment, the key feature information acquisition unit 120 includes subunits: a key information acquisition unit, used to obtain the key information of each event node from the event sorting information according to the keyword set; a feature vector acquisition unit, used to binarize the key information of each event node according to the keyword set to obtain a corresponding feature vector; a feature extraction unit, used to input the feature vector corresponding to each event node into the feature extraction neural network for feature extraction, so as to obtain the key feature information corresponding to each event node.

[0095] The comprehensive feature information acquisition unit 130 is used to acquire the comprehensive feature information corresponding to each of the event nodes according to a preset comprehensive feature calculation rule.

[0096] In one embodiment, the comprehensive feature information acquisition unit 130 includes subunits: an associated feature information acquisition unit, which is used to acquire multiple key feature information associated with each of the event nodes from the key feature information as associated feature information corresponding to each of the event nodes; and an overlay calculation unit, which is used to perform overlay calculation on the associated feature information of each of the event nodes according to the comprehensive feature calculation rules to obtain the comprehensive feature information corresponding to each of the event nodes.

[0097] The classification processing unit 140 is used to classify each event node according to a preset classification model and the comprehensive feature information to obtain classification information of each event node.

[0098] The event label information acquisition unit 150 is used to extract the event label information of each event node from the event sorting information according to the classification information of each event node and a pre-stored extraction template set.

[0099] In one embodiment, the event label information acquisition unit 150 includes sub-units: a target extraction template acquisition unit, which is used to acquire an extraction template matching each of the event nodes from the extraction template set as a target extraction template according to the classification information of each of the event nodes; an event label information acquisition unit, which is used to extract a field value corresponding to a corresponding project field from the event sorting information and the interface call information corresponding to each of the event nodes according to the project field contained in the target extraction template of each of the event nodes as the event label information of each of the event nodes.

[0100] The classification storage unit 160 is used to classify and store the event sorting information and the event tag information into an event database according to the classification information of each event node.

[0101] In one embodiment, the classification storage unit 160 includes sub-units: an event node classification unit, which is used to obtain the event node corresponding to each classification from the event sorting information according to the classification information; an event node classification storage unit, which is used to sequentially store the event nodes corresponding to each of the classifications into the storage area corresponding to the classification in the event database; an interface call information hierarchical storage unit, which is used to hierarchically organize the interface call information of the event node corresponding to each of the classifications, and store it in the storage area of ​​the classification at the storage location corresponding to the event node; an event label information storage unit, which is used to store the event label information of the event node corresponding to each of the classifications into the storage area of ​​the classification at the storage location corresponding to the event node.

[0102] In one embodiment, the data intelligent storage device 100 also includes a sub-unit: a target information feedback unit, which is used to obtain target information corresponding to the information acquisition request from the event database according to the information acquisition request and feed it back to the user terminal if an information acquisition request input by the user terminal is received.

[0103] The data intelligent storage device provided in the embodiment of the present invention applies the above data intelligent storage method, sorts the event information contained in the received user behavior data to obtain event sorting information, extracts the key feature information of each event node from the event sorting information and obtains the comprehensive feature information of each event node, obtains the classification information of each event node based on the comprehensive feature information and obtains the event tag information of each event node based on the classification information, and classifies and stores the event sorting information and event tag information according to the classification information. Through the above method, the comprehensive feature information of each event node can be intelligently obtained, and the corresponding classification information and event tag information can be obtained based on the comprehensive feature information, and the event sorting information and event tag information can be classified and stored, which greatly improves the efficiency of storing user usage data.

[0104] The above-mentioned data intelligent storage device can be implemented in the form of a computer program, which can be used in Fig. 9 Runs on the computer device shown.

[0105] See also Fig. 9 , Fig. 9 1 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a management server for executing a data intelligent storage method to intelligently store user usage data.

[0106] See also Fig. 9 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0107] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute a data intelligent storage method, wherein the storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0108] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0109] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the data intelligent storage method.

[0110] The network interface 505 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above-mentioned data intelligent storage method.

[0112] Those skilled in the art will understand that Fig. 9 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Fig. 9 The embodiments shown are consistent and will not be described again here.

[0113] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0114] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps included in the above-mentioned data intelligent storage method are implemented.

[0115] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment, devices and units can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0116] In the several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. Units with the same function may also be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a computer-readable storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a magnetic disk or an optical disk.

[0120] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A data intelligent storage method, characterized in that: The method comprises: If the input user behavior data is received, the event information contained in the user behavior data is sorted to obtain corresponding event sorting information; Extracting key feature information corresponding to each event node from the event sorting information according to a preset feature extraction model; Obtaining comprehensive feature information corresponding to each of the event nodes according to a preset comprehensive feature calculation rule; Classifying each event node according to a preset classification model and the comprehensive feature information to obtain classification information of each event node; Extracting event label information of each event node from the event sorting information according to the classification information of each event node and a pre-stored extraction template set; The event sorting information and the event tag information are classified and stored in an event database according to the classification information of each event node.

2. The data intelligent storage method according to claim 1, characterized in that: The step of sorting the event information contained in the user behavior data to obtain corresponding event sorting information includes: Acquire a trigger time corresponding to each event node from the user behavior data; The event nodes included in the user behavior data are sorted according to the trigger time to obtain node sorting information; the event node is an operation performed by the user in the user terminal or node information of a page displayed by the user terminal; The interface call information corresponding to each of the event nodes in the user behavior data is added to the sorting position of the event node matching the interface call information in the node sorting information to obtain the event sorting information.

3. The data intelligent storage method according to claim 1, characterized in that: The feature extraction model includes a keyword set and a feature extraction neural network. The key feature information corresponding to each event node is extracted from the event sorting information according to the preset feature extraction model, including: Acquire key information of each event node from the event sorting information according to the keyword set; Binarize the key information of each event node according to the keyword set to obtain a corresponding feature vector; The feature vectors corresponding to each of the event nodes are respectively input into the feature extraction neural network for feature extraction to obtain key feature information corresponding to each of the event nodes.

4. The data intelligent storage method according to claim 1, characterized in that: The step of obtaining the comprehensive feature information corresponding to each event node according to a preset comprehensive feature calculation rule includes: Acquire a plurality of key feature information associated with each of the event nodes from the key feature information as associated feature information corresponding to each of the event nodes; According to the comprehensive feature calculation rule, the associated feature information of each event node is superimposed and calculated to obtain the comprehensive feature information corresponding to each event node.

5. The data intelligent storage method according to claim 1, characterized in that: The extracting event label information of each event node from the event sorting information according to the classification information of each event node and the pre-stored extraction template set includes: According to the classification information of each event node, an extraction template matching each event node is obtained from the extraction template set as a target extraction template; According to the project fields included in the target extraction template of each event node, the field values ​​corresponding to the corresponding project fields are extracted from the event sorting information and the interface call information corresponding to each event node as the event label information of each event node.

6. The data intelligent storage method according to claim 1, characterized in that: The step of classifying and storing the event sorting information and the event tag information in an event database according to the classification information of each event node includes: Acquire event nodes corresponding to each classification from the event sorting information according to the classification information; Sequentially storing the event nodes corresponding to each of the categories in the storage area corresponding to the category in the event database; After the interface call information of the event node corresponding to each of the categories is hierarchically sorted, the information is stored in a storage location corresponding to the event node in the storage area of ​​the category; The event tag information of the event node corresponding to each of the categories is stored in a storage location corresponding to the event node in the storage area of ​​the category.

7. The data intelligent storage method according to claim 1, characterized in that: After the event sorting information and the event tag information are classified and stored in the event database according to the classification information of each event node, the method further includes: If an information acquisition request input by a user terminal is received, target information corresponding to the information acquisition request is acquired from the event database according to the information acquisition request and fed back to the user terminal.

8. A data intelligent storage device, characterized in that: The device comprises: An event ranking information acquisition unit, configured to, upon receiving the input user behavior data, sort the event information contained in the user behavior data to obtain corresponding event ranking information; A key feature information acquisition unit, configured to extract key feature information corresponding to each event node from the event sorting information according to a preset feature extraction model; A comprehensive feature information acquisition unit, used to acquire the comprehensive feature information corresponding to each of the event nodes according to a preset comprehensive feature calculation rule; A classification processing unit, used to classify each event node according to a preset classification model and the comprehensive feature information to obtain classification information of each event node; An event label information acquisition unit, configured to extract the event label information of each event node from the event sorting information according to the classification information of each event node and a pre-stored extraction template set; The classification storage unit is used to classify and store the event sorting information and the event tag information into an event database according to the classification information of each event node.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the data intelligent storage method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the data intelligent storage method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Mass data communication concurrent processing method and system

    CN104615684A

  • Real-time dynamic interactive scene application-based recommendation method, system and equipment

    CN107301585A

  • Multidimensional hierarchical hash coding method, multidimensional hierarchical hash decoding method, equipment and storage medium

    CN107807795A

  • Data storage method and device, storage medium and edge server

    CN110297959A

  • Hybrid cloud storage method under cloud computing architecture

    CN110555138A