System adjustment strategy matching method, device, equipment and storage medium

Abstract

The present invention relates to the field of artificial intelligence technology, and provides a system adjustment strategy matching method, device, equipment and storage medium, which are used to match the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of system verification. The system adjustment strategy matching method includes: adjusting the preset grayscale decision strategy in real time according to the real-time monitoring results of the preset business system to obtain the real-time grayscale decision strategy; analyzing the interface request parameters received from the user end based on the real-time grayscale decision strategy to obtain the parameter analysis results; assigning permissions to the user end according to the target function corresponding to the parameter analysis results matched from the functions of the preset business system; analyzing the pulled user point-of-use data to obtain the point-of-use analysis results; calling the matching model to match the point-of-use analysis results with the preset system adjustment strategy library to obtain the target system adjustment strategy. In addition, the present invention also relates to blockchain technology, and the target system adjustment strategy can be stored in the blockchain.

Description

Technical Field

[0001] The present invention relates to the field of intelligent decision-making of artificial intelligence, and in particular to a matching method, device, equipment and storage medium for a system adjustment strategy. Background Art

[0002] With the development of computer technology and business, it is necessary to iterate and update business systems, and after each iterative version of the business system is launched, system function verification and system adjustment are required. At present, system functions are verified and adjusted by adding a function master switch. However, in some cases, the function scenario is not suitable for adding a function master switch. In this case, the system is basically in a naked running state, with security risks and a passive situation. In addition, the verification information is single, which makes it impossible to match the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of system verification. Summary of the invention

[0003] The present invention provides a system adjustment strategy matching method, device, equipment and storage medium, which are used to match the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of system verification.

[0004] A first aspect of the present invention provides a method for matching a system adjustment strategy, comprising:

[0005] Acquire the real-time monitoring results of the preset business system, and adjust the preset grayscale decision strategy in real time according to the real-time monitoring results to obtain the real-time grayscale decision strategy;

[0006] When receiving the interface request parameters from the user end, analyzing the interface request parameters based on the real-time grayscale decision strategy to obtain parameter analysis results;

[0007] Matching a corresponding target function from the functions of the preset business system according to the parameter analysis result, and assigning permissions to the user terminal according to the target function;

[0008] Pull the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result;

[0009] The preset matching model is called to match the embedding point analysis result with the preset system adjustment strategy library to obtain the target system adjustment strategy.

[0010] Optionally, in a first implementation of the first aspect of the present invention, the acquiring of real-time monitoring results of a preset business system, and adjusting a preset grayscale decision strategy in real time according to the real-time monitoring results, before obtaining the real-time grayscale decision strategy, includes:

[0011] Create multiple rule tables, obtain multiple grayscale rules corresponding to the preset grayscale decision strategy, and write each grayscale rule into the corresponding rule table to obtain multiple grayscale rule tables;

[0012] Call the preset user portrait construction model, build the corresponding user portrait based on each grayscale rule table, and obtain the user portrait corresponding to each grayscale rule table;

[0013] A grayscale rule library is constructed based on the multiple grayscale rule tables and the user portrait corresponding to each grayscale rule table.

[0014] Optionally, in a second implementation of the first aspect of the present invention, the step of obtaining a real-time monitoring result of a preset business system, and adjusting a preset grayscale decision strategy in real time according to the real-time monitoring result to obtain a real-time grayscale decision strategy includes:

[0015] Run the preset business system, call the preset functional test cases based on the preset monitoring pool, perform real-time functional tests on the running preset business system, and obtain real-time monitoring results;

[0016] Determine whether the real-time monitoring result meets the preset opening condition. If the real-time monitoring result does not meet the preset opening condition, obtain the target adjustment information corresponding to the real-time monitoring result, and obtain the target grayscale rule table and target user portrait corresponding to the preset grayscale decision strategy from the grayscale rule library;

[0017] The target grayscale rule table and the target user portrait are updated in real time through the target adjustment information to obtain a real-time grayscale decision strategy.

[0018] Optionally, in a third implementation of the first aspect of the present invention, when receiving the interface request parameters from the user terminal, analyzing the interface request parameters based on the real-time grayscale decision strategy to obtain parameter analysis results includes:

[0019] When receiving the interface request parameters from the user end, extracting the user portrait dimension of the real-time grayscale decision strategy to obtain the target function decision parameters;

[0020] Calculating the similarity between the interface request parameter and the target function decision parameter to obtain parameter similarity, and performing comparative analysis on the parameter similarity and a preset threshold to obtain a comparative analysis result;

[0021] The decision result of opening the system function is determined according to the comparative analysis result, and the parameter analysis result is obtained.

[0022] Optionally, in a fourth implementation of the first aspect of the present invention, calling a preset matching model, matching the embedding analysis result with a preset system adjustment strategy library, and obtaining a target system adjustment strategy includes:

[0023] Calling a preset classifier to classify the tracking point analysis result into adjustment categories, obtaining a target adjustment category, and obtaining a system adjustment strategy set corresponding to the target adjustment category from a preset system adjustment strategy library;

[0024] Calling a preset matching model, performing vector conversion on the buried point analysis result, and obtaining target feature information;

[0025] Calculating matching scores between the target feature information and the system adjustment strategy sets corresponding to the target adjustment categories;

[0026] The system adjustment strategy set corresponding to the target adjustment category is sorted and screened according to the matching score to obtain the target system adjustment strategy.

[0027] Optionally, in a fifth implementation of the first aspect of the present invention, the user end corresponding to the preset business system after the pull permission is allocated is used to analyze the user buried data to obtain the buried analysis result, including:

[0028] Pull the user embedding data of the preset business system corresponding to the user end after the permission is assigned, and extract the user embedding data based on the preset embedding event attribute dimension to obtain the target embedding event data;

[0029] The target embedding event data is sequentially subjected to embedding field extraction, preset indicator statistics, and writing into preset data embedding documents to obtain embedding analysis results.

[0030] Optionally, in a sixth implementation of the first aspect of the present invention, after calling a preset matching model, matching the embedding analysis result with a preset system adjustment strategy library, and obtaining a target system adjustment strategy, the method further includes:

[0031] Acquire effect information of the target system adjustment policy execution, and mark and adjust the execution process of the target system adjustment policy according to the effect information.

[0032] A second aspect of the present invention provides a matching device for a system adjustment strategy, comprising:

[0033] An adjustment module is used to obtain real-time monitoring results of a preset business system, and to adjust a preset grayscale decision strategy in real time according to the real-time monitoring results to obtain a real-time grayscale decision strategy;

[0034] A first analysis module is used to analyze the interface request parameters based on the real-time grayscale decision strategy when receiving the interface request parameters from the user end to obtain parameter analysis results;

[0035] An allocation module, used for matching corresponding target functions from the functions of the preset business system according to the parameter analysis result, and allocating permissions to the user terminal according to the target function;

[0036] The second analysis module is used to pull the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result;

[0037] The matching module is used to call a preset matching model, match the embedding point analysis result with a preset system adjustment strategy library, and obtain a target system adjustment strategy.

[0038] Optionally, in a first implementation of the second aspect of the present invention, the system adjustment strategy matching device further includes:

[0039] A writing module is used to create multiple rule tables, obtain multiple grayscale rules corresponding to a preset grayscale decision strategy, and write each grayscale rule into a corresponding rule table to obtain multiple grayscale rule tables;

[0040] The first construction module is used to call a preset user portrait construction model, construct a corresponding user portrait based on each grayscale rule table, and obtain a user portrait corresponding to each grayscale rule table;

[0041] The second construction module is used to construct a grayscale rule library based on the multiple grayscale rule tables and the user portrait corresponding to each grayscale rule table.

[0042] Optionally, in a second implementation of the second aspect of the present invention, the adjustment module is specifically used to:

[0043] Run the preset business system, call the preset functional test cases based on the preset monitoring pool, perform real-time functional tests on the running preset business system, and obtain real-time monitoring results;

[0044] Determine whether the real-time monitoring result meets the preset opening condition. If the real-time monitoring result does not meet the preset opening condition, obtain the target adjustment information corresponding to the real-time monitoring result, and obtain the target grayscale rule table and target user portrait corresponding to the preset grayscale decision strategy from the grayscale rule library;

[0045] The target grayscale rule table and the target user portrait are updated in real time through the target adjustment information to obtain a real-time grayscale decision strategy.

[0046] Optionally, in a third implementation of the second aspect of the present invention, the first analysis module is specifically used to:

[0047] When receiving the interface request parameters from the user end, extracting the user portrait dimension of the real-time grayscale decision strategy to obtain the target function decision parameters;

[0048] Calculating the similarity between the interface request parameter and the target function decision parameter to obtain parameter similarity, and performing comparative analysis on the parameter similarity and a preset threshold to obtain a comparative analysis result;

[0049] The decision result of opening the system function is determined according to the comparative analysis result, and the parameter analysis result is obtained.

[0050] Optionally, in a fourth implementation of the second aspect of the present invention, the matching module is specifically configured to:

[0051] Calling a preset classifier to classify the tracking point analysis result into adjustment categories, obtaining a target adjustment category, and obtaining a system adjustment strategy set corresponding to the target adjustment category from a preset system adjustment strategy library;

[0052] Calling a preset matching model, performing vector conversion on the buried point analysis result, and obtaining target feature information;

[0053] Calculating matching scores between the target feature information and the system adjustment strategy sets corresponding to the target adjustment categories;

[0054] The system adjustment strategy set corresponding to the target adjustment category is sorted and screened according to the matching score to obtain the target system adjustment strategy.

[0055] Optionally, in a fifth implementation of the second aspect of the present invention, the second analysis module is specifically configured to:

[0056] Pull the user embedding data of the preset business system corresponding to the user end after the permission is assigned, and extract the user embedding data based on the preset embedding event attribute dimension to obtain the target embedding event data;

[0057] The target embedding event data is sequentially subjected to embedding field extraction, preset indicator statistics, and writing into preset data embedding documents to obtain embedding analysis results.

[0058] Optionally, in a sixth implementation of the second aspect of the present invention, the system adjustment strategy matching device further includes:

[0059] The marking module is used to obtain effect information of the target system adjustment strategy execution, and mark and adjust the execution process of the target system adjustment strategy according to the effect information.

[0060] The third aspect of the present invention provides a matching device for a system adjustment strategy, comprising: a memory and at least one processor, wherein a computer program is stored in the memory; the at least one processor calls the computer program in the memory so that the matching device for the system adjustment strategy executes the above-mentioned matching method for the system adjustment strategy.

[0061] A fourth aspect of the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned system adjustment strategy matching method.

[0062] In the technical solution provided by the present invention, the real-time monitoring result of the preset business system is obtained, and the preset grayscale decision strategy is adjusted in real time according to the real-time monitoring result to obtain the real-time grayscale decision strategy; when the interface request parameter of the user terminal is received, the interface request parameter is analyzed based on the real-time grayscale decision strategy to obtain the parameter analysis result; according to the parameter analysis result, the corresponding target function is matched from the function of the preset business system, and the user terminal is assigned authority through the target function; the user point data of the preset business system corresponding to the user terminal after the authority allocation is pulled, the user point data is analyzed to obtain the point analysis result; the preset matching model is called, and the point analysis result is matched with the preset system adjustment strategy library to obtain the target system adjustment strategy. In the embodiment of the present invention, the real-time adjustment of the preset grayscale decision strategy is realized, the accuracy of the subsequent analysis of the interface request parameters is improved, and the preset business system is in a state of being protected at all times under the condition of the grayscale verification of the function of the preset business system, the verification information is rich, and the accuracy of the matching of the target system adjustment strategy is improved, thereby achieving the effect of matching the system adjustment strategy on the basis of ensuring the security and rapidity and effectiveness of the system verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of an embodiment of a matching method for system adjustment strategy in an embodiment of the present invention;

[0064] Figure 2 It is a schematic diagram of another embodiment of the matching method of the system adjustment strategy in the embodiment of the present invention;

[0065] Figure 3 A schematic diagram of an embodiment of a matching device for adjusting a system strategy in an embodiment of the present invention;

[0066] Figure 4 It is a schematic diagram of another embodiment of a matching device for adjusting a system strategy in an embodiment of the present invention;

[0067] Figure 5 The figure is a schematic diagram of an embodiment of a matching device for adjusting a system strategy in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The embodiments of the present invention provide a method, device, equipment and storage medium for matching a system adjustment strategy, which achieves the effect of matching the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of system verification.

[0069] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0070] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the matching method of the system adjustment strategy in the embodiment of the present invention includes:

[0071] 101. Obtain real-time monitoring results of a preset business system, and adjust the preset grayscale decision strategy in real time according to the real-time monitoring results to obtain a real-time grayscale decision strategy.

[0072] It is understandable that the execution subject of the present invention may be a matching device for adjusting the system strategy, or may be a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0073] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0074] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0075] The server can be a stand-alone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), as well as big data and artificial intelligence platforms.

[0076] The server obtains a preset grayscale decision strategy in advance, stores the preset grayscale decision strategy through a preset sequential storage structure, and stores the decision strategy in a preset database, or stores the preset grayscale decision strategy through a preset chain storage structure, and stores the decision strategy in a preset database, or creates an index of the preset grayscale decision strategy, and stores the preset grayscale decision strategy in a preset database through the index, or generates a hash value of the preset grayscale decision strategy, and stores the preset grayscale decision strategy in a preset database through the hash value, so as to effectively manage and store the preset grayscale decision strategy, and facilitate subsequent retrieval and matching of the preset grayscale decision strategy.

[0077] Among them, the preset grayscale decision strategy can be a grayscale rule based on user portraits, that is, the preset grayscale decision strategy may include grayscale rules for grayscale verification, and user portraits corresponding to each user end corresponding to the grayscale rules. User portraits may include but are not limited to the following tags: attribute tags, interest tags, scene tags, behavior tags and customized tags, among which attribute tags may include but are not limited to information such as gender, age level, consumption level and occupation, interest tags include shopping, education, audio and video, games and financial management, scene tags include airports, business districts, cinemas, scenic spots and custom scenes, behavior tags include recently active applications and recently visited scenes, and customized tags include new users and old users. Among them, the personal privacy information that may be included (such as user data, personal identity information, financial management, new users and old users, etc.) is obtained with the explicit authorization of the user and complies with relevant legal provisions.

[0078] After the preset business system is put into operation, the server can perform real-time functional testing on the preset business system through the preset monitoring system to obtain real-time monitoring results; or, after the preset business system is put into operation, the server calls the preset monitoring system to perform real-time functional testing on the preset business system to obtain functional test results, and receives functional fault reporting information reported by each user terminal to obtain real-time monitoring results. The real-time monitoring results include functional test results and functional fault reporting information.

[0079] If the content of the real-time monitoring results indicates that there is a problem with the function, adjustment information corresponding to the real-time monitoring results is obtained, and the preset grayscale decision strategy stored in the preset database is updated in real time (including but not limited to deletion, insertion, replacement, addition and modification, etc.) through the adjustment information to obtain the real-time grayscale decision strategy. The real-time update content of the preset grayscale decision strategy may be, for example: only open to new users, open to female users, open to 10% of users, open to 20% of users and open to fixed users; if the content of the real-time monitoring results indicates that there is no problem with the function, the permissions of the system functions are allocated and opened to the user end.

[0080] 102. When receiving the interface request parameters from the user end, the interface request parameters are analyzed based on the real-time grayscale decision strategy to obtain parameter analysis results.

[0081] When the server receives the interface request parameters from the user, it calls the preset grayscale decision interface to determine whether the interface request parameters hit the grayscale rules in the real-time grayscale decision strategy and conform to the user portrait in the real-time grayscale decision strategy, thereby obtaining the parameter analysis results. Furthermore, it calls the preset grayscale decision interface to extract the target function decision parameters in the real-time grayscale decision strategy, calculates the similarity between the interface request parameters and the target function decision parameters, and determines the decision results of the system function opening according to the similarity to determine whether the interface request parameters conform to the target function decision parameters, thereby obtaining the parameter analysis results.

[0082] 103. According to the parameter analysis result, the corresponding target function is matched from the functions of the preset business system, and the authority is allocated to the user end through the target function.

[0083] If the parameter analysis result shows that the system function information requested for access is open to the user terminal, the server searches for the function of the preset business system through the system function information requested for access in the parameter analysis result to obtain the corresponding target function; if the parameter analysis result shows that the system function information requested for access is not open to the user terminal, it is not executed. The permission configuration information file corresponding to the target function is obtained, and the user terminal is configured through the permission configuration information file to realize the permission allocation to the user terminal through the target function.

[0084] 104. Pull the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result.

[0085] The server pulls the user end after permission is allocated, and develops a tracking point for the location corresponding to each event of the user behavior corresponding to the user end (corresponding to the preset business system) after the preset business system is allocated through the pre-designed tracking point event and data collection tracking point plan, and collects the corresponding user tracking point data through the software development kit (software development kit, SDK), where the user tracking point data includes but is not limited to user data, business data and product operation related data corresponding to the preset business system, and the product operation related data includes traffic data and channel data. The user tracking point data of this proposal are pulled with user authorization and obtained through legal channels; the user tracking point data are classified into tracking point events and preset indicator statistics to obtain the tracking point analysis results.

[0086] 105. Call the preset matching model, match the embedding point analysis result with the preset system adjustment strategy library, and obtain the target system adjustment strategy.

[0087] Among them, the preset matching model is a deep matching model based on deep learning, such as: a deep model based on matching function learning or a deep matching model based on representation learning. The server calls the preset matching model, performs feature extraction, key information extraction and vector conversion on the embedding point analysis results in turn, obtains the target key information, calculates the matching score between the target key information and the system adjustment strategy in the preset system adjustment strategy library; sorts and filters the system adjustment strategies in the preset system adjustment strategy library by the matching score to obtain the target system adjustment strategy. The target system adjustment strategy is used to indicate the strategy for adjusting the preset business system. The content of the adjustment includes but is not limited to functional properties, system modules and interface configurations.

[0088] In the embodiment of the present invention, real-time adjustment of the preset grayscale decision strategy is implemented, the accuracy of the analysis of subsequent interface request parameters is improved, and the preset business system is in a state of being protected at all times under the condition of grayscale verification of the functions of the preset business system. The verification information is enriched, and the accuracy of matching the target system adjustment strategy is improved, thereby achieving the effect of matching the system adjustment strategy on the basis of ensuring the security, speed and effectiveness of the system verification.

[0089] See also Figure 2 Another embodiment of the matching method of the system adjustment strategy in the embodiment of the present invention includes:

[0090] 201. Obtain real-time monitoring results of a preset business system, and adjust the preset grayscale decision strategy in real time according to the real-time monitoring results to obtain a real-time grayscale decision strategy.

[0091] Specifically, the server runs the preset business system, calls the preset functional test cases based on the preset monitoring pool, performs real-time functional testing on the running preset business system, and obtains real-time monitoring results; determines whether the real-time monitoring results meet the preset opening conditions. If the real-time monitoring results do not meet the preset opening conditions, obtains the target adjustment information corresponding to the real-time monitoring results, and obtains the target grayscale rule table and target user portrait corresponding to the preset grayscale decision strategy from the grayscale rule library; updates the target grayscale rule table and target user portrait in real time through the target adjustment information to obtain the real-time grayscale decision strategy.

[0092] The server pre-creates multiple information tables in a preset database to obtain various adjustment information, each of which includes various real-time monitoring results and business system adjustment strategies corresponding to the various real-time monitoring results. The server writes various adjustment information into corresponding information tables respectively, thereby obtaining multiple final adjustment information tables, one adjustment information table corresponding to one business system adjustment strategy, wherein the multiple information tables may include one information table and multiple sub-information tables, one sub-information table corresponding to one business system adjustment strategy.

[0093] The preset business system is put online, the server runs the preset business system, and the preset functional test cases are called based on the preset monitoring pool. The running preset business system is tested in real time to obtain real-time monitoring results. The preset monitoring pool is used to indicate the test to be performed every preset period. The real-time monitoring results include but are not limited to the tested function type, function operation (fault) status and function operation (fault) degree, etc. It is judged whether the real-time monitoring results meet the preset opening conditions. The preset opening conditions are used to indicate that there is no functional problem or the function type, function operation (fault) status and function operation (fault) degree do not affect the function opening; if so, the user end is developed (function permission distribution); if not, the multiple adjustment information tables in the preset database are retrieved through the real-time monitoring results to obtain the corresponding target adjustment information; the preset grayscale rule library is retrieved through the preset grayscale decision strategy to obtain the corresponding target grayscale rule table and target user portrait; the target grayscale rule table and target user portrait are updated in real time (including but not limited to deletion, insertion, replacement, addition and modification, etc.) through the target adjustment information to obtain the real-time grayscale decision strategy. The real-time adjustment of the preset grayscale decision strategy is realized, which improves the accuracy of the analysis of subsequent interface request parameters.

[0094] Specifically, the server obtains the real-time monitoring results of the preset business system, and adjusts the preset grayscale decision strategy in real time according to the real-time monitoring results. Before obtaining the real-time grayscale decision strategy, it creates multiple rule tables, obtains multiple grayscale rules corresponding to the preset grayscale decision strategy, and writes each grayscale rule into the corresponding rule table to obtain multiple grayscale rule tables; calls the preset user portrait construction model, constructs the corresponding user portrait based on each grayscale rule table, and obtains the user portrait corresponding to each grayscale rule table; constructs a grayscale rule library based on multiple grayscale rule tables and the user portrait corresponding to each grayscale rule table.

[0095] The server creates multiple rule tables in the preset database in advance, and the multiple rule tables include a main rule table and multiple sub-rule tables. Multiple grayscale rules corresponding to the preset grayscale decision strategy are obtained, and one grayscale rule corresponds to one system function. Each grayscale rule is written into the corresponding rule table respectively, so as to obtain the final multiple grayscale rule tables, one grayscale rule table corresponds to one grayscale rule, one sub-rule table corresponds to one grayscale rule, and the main rule table includes index information of all grayscale rules.

[0096] Among them, the preset user portrait construction model is an artificial intelligence-based model (algorithm), and the user portrait construction model can be an artificial intelligence-based neural network model. The server calls the preset user portrait construction model, performs hierarchical analysis on the grayscale rules in each grayscale rule table, produces labels based on rule definitions, and calculates label weights to obtain the user portrait corresponding to each grayscale rule table; a grayscale rule library is constructed from multiple grayscale rule tables and user portraits corresponding to multiple grayscale rule tables. This improves the accuracy of the subsequent real-time grayscale decision strategy based on the real-time update of the target grayscale rule table and target user portrait in the grayscale rule library, thereby improving the accuracy of the subsequent parameter analysis through the real-time grayscale decision strategy.

[0097] 202. When receiving the interface request parameters from the user end, the interface request parameters are analyzed based on the real-time grayscale decision strategy to obtain parameter analysis results.

[0098] Specifically, when the server receives the interface request parameters from the user, it extracts the user portrait dimension of the real-time grayscale decision strategy to obtain the target function decision parameters; calculates the similarity between the interface request parameters and the target function decision parameters to obtain the parameter similarity, and compares and analyzes the parameter similarity with the preset threshold to obtain the comparative analysis result; determines the decision result of the system function opening according to the comparative analysis result to obtain the parameter analysis result.

[0099] When the server receives the interface request parameters from the user, it extracts the user portrait dimension of the user portrait in the real-time grayscale decision strategy to obtain the target function decision parameters, where the interface request parameters include the system function information requested for access, and the target function decision parameters may be the decision parameters of the grayscale rule corresponding to the system function information requested for access; the preset similarity calculation algorithm (which may be a cosine similarity algorithm, a Tanimoto coefficient algorithm, or a log-likelihood similarity algorithm, etc., not limited here) is called to calculate the similarity between the interface request parameters and the target function decision parameters to obtain the parameter similarity; it is determined whether the parameter similarity is greater than a preset threshold, thereby obtaining a comparative analysis result.

[0100] Among them, the parameter analysis result is used to indicate whether the system function information requested for access is open to the user end. If the comparative analysis result is that the parameter similarity is greater than the preset threshold, the decision result of determining that the system function is open is that the system function information requested for access is open to the user end, thereby obtaining the parameter analysis result; if the comparative analysis result is that the parameter similarity is less than or equal to the preset threshold, the decision result of determining that the system function is open is that the system function information requested for access is not open to the user end, thereby obtaining the parameter analysis result.

[0101] 203. According to the parameter analysis result, a corresponding target function is matched from the functions of the preset business system, and permissions are allocated to the user end through the target function.

[0102] The execution process of step 203 is similar to the execution process of step 103, which will not be described again.

[0103] 204. Pull the user embedding data of the preset business system corresponding to the user end after the permission allocation, analyze the user embedding data, and obtain the embedding analysis result.

[0104] Specifically, the server pulls the user embedding data of the preset business system corresponding to the user end after the permission is allocated, and extracts the user embedding data based on the preset embedding event attribute dimension to obtain the target embedding event data; the target embedding event data is sequentially subjected to embedding field extraction, preset indicator statistics, and writing into the preset data embedding document to obtain the embedding analysis results.

[0105] After the user's authorization, the server pulls the user point data corresponding to the preset business system of the user end after the permission is allocated, wherein the user point data includes but is not limited to user data, business data and product operation related data corresponding to the preset business system, and the product operation related data includes traffic data and channel data. Based on the preset point event attribute dimension, the user point data is extracted and classified to obtain the target point event data. The preset point event attribute dimension may include but is not limited to click events, exposure events and stay events. The point fields in the target point event data are extracted, and the target point data are sorted and written into the event table according to the point fields to obtain the pre-processed point data. The point fields are not limited to function fields, Chinese name fields and event type fields. The pre-processed point data is counted according to the preset indicators to obtain statistical data. The preset indicators may include but are not limited to user type distribution, activity, number of startups, churn probability and version analysis. The statistical data and the pre-processed point data are written into the preset data point document to obtain the point analysis results.

[0106] 205. Call a preset matching model, match the embedding point analysis result with a preset system adjustment strategy library, and obtain a target system adjustment strategy.

[0107] Specifically, the server calls a preset classifier, classifies the tracking point analysis results into adjustment categories, obtains the target adjustment category, and obtains the system adjustment policy set corresponding to the target adjustment category from the preset system adjustment policy library; calls a preset matching model, performs vector conversion on the tracking point analysis results, and obtains target feature information; calculates the matching score between the target feature information and the system adjustment policy set corresponding to the target adjustment category; sorts and filters the system adjustment policy set corresponding to the target adjustment category according to the matching score, and obtains the target system adjustment policy.

[0108] For example, the server calls a preset classifier to perform feature extraction, adjustment category probability value calculation and probability value classification on the buried point analysis results in sequence to obtain the target adjustment category, and obtain the system adjustment strategy set corresponding to the target adjustment category from the preset system adjustment strategy library; the preset matching model is a collaborative denoising auto-encoders (CDAE) model, and the server calls the CDAE model to perform feature extraction, dimension reduction processing and vector conversion on the buried point analysis results in sequence to obtain target feature information; calls a preset matching function to calculate the matching score between the target feature information and the system adjustment strategy set corresponding to the target adjustment category; sorts the system adjustment strategy set corresponding to the target adjustment category in order from large to small according to the matching score to obtain a strategy sequence; determines the system adjustment strategy ranked first in the strategy sequence as the target system adjustment strategy, or reads the system adjustment strategies ranked in the preset range in the strategy sequence in sequence to obtain multiple initial system adjustment strategies, and determines whether the matching score corresponding to each initial system adjustment strategy is greater than the preset target value. If so, the corresponding initial system adjustment strategy is determined as the target system adjustment strategy, and if not, the corresponding initial system adjustment strategy is deleted. The accuracy and matching efficiency of the target system adjustment strategy are further improved.

[0109] 206. Obtain effect information of the target system adjustment strategy execution, and mark and adjust the execution process of the target system adjustment strategy according to the effect information.

[0110] The server sends the target system adjustment strategy and execution instructions to the preset robot. The preset robot adjusts the functions of the preset business system based on the target system adjustment strategy and execution instructions, and tests the adjusted functions. The test results are sent to the target terminal, and the personnel of the target terminal conduct manual review and feedback of the review opinions, so as to obtain the review opinions, that is, the effect information; the review opinions (effect information) are sent to the server. After receiving the review opinions (effect information), the server analyzes the adjustment type of the review opinions (effect information). If the adjustment type is excellent (that is, the adjusted functional effect meets the requirements), it will not be executed. If the adjustment type is required to be re-executed (that is, the adjusted functional effect does not meet the requirements), the execution process of the target system adjustment strategy is marked and automatically adjusted (or manually adjusted) according to the effect information. By marking and adjusting the execution process of the target system adjustment strategy according to the effect information, the accuracy of matching the system adjustment strategy is improved while ensuring the security, rapidity and effectiveness of system verification.

[0111] In the embodiments of the present invention, not only the real-time adjustment of the preset grayscale decision strategy is realized, the accuracy of the analysis of the subsequent interface request parameters is improved, but also the preset business system is always protected under the condition of the grayscale verification of the functions of the preset business system, the verification information is enriched, and the accuracy of the matching of the target system adjustment strategy is improved, thereby achieving the effect of matching the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of the system verification, and also by marking and adjusting the execution process of the target system adjustment strategy according to the effect information, the accuracy of the matching of the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of the system verification is improved.

[0112] The above describes the matching method of the system adjustment strategy in the embodiment of the present invention. The following describes the matching device of the system adjustment strategy in the embodiment of the present invention. Figure 3 , an embodiment of a matching device for adjusting a system strategy in an embodiment of the present invention includes:

[0113] The adjustment module 301 is used to obtain the real-time monitoring results of the preset business system, and adjust the preset grayscale decision strategy in real time according to the real-time monitoring results to obtain the real-time grayscale decision strategy;

[0114] The first analysis module 302 is used to analyze the interface request parameters based on the real-time grayscale decision strategy when receiving the interface request parameters from the user end to obtain parameter analysis results;

[0115] The allocation module 303 is used to match the corresponding target function from the functions of the preset business system according to the parameter analysis result, and allocate permissions to the user terminal according to the target function;

[0116] The second analysis module 304 is used to extract the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result;

[0117] The matching module 305 is used to call a preset matching model, match the embedding point analysis result with a preset system adjustment strategy library, and obtain a target system adjustment strategy.

[0118] The functional implementation of each module in the matching device of the above system adjustment strategy corresponds to each step in the embodiment of the matching method of the above system adjustment strategy, and its functions and implementation processes are not described one by one here.

[0119] In the embodiment of the present invention, real-time adjustment of the preset grayscale decision strategy is implemented, the accuracy of the analysis of subsequent interface request parameters is improved, and the preset business system is in a state of being protected at all times under the condition of grayscale verification of the functions of the preset business system. The verification information is enriched, and the accuracy of matching the target system adjustment strategy is improved, thereby achieving the effect of matching the system adjustment strategy on the basis of ensuring the security, speed and effectiveness of the system verification.

[0120] See also Figure 4 Another embodiment of the matching device of the system adjustment strategy in the embodiment of the present invention includes:

[0121] The adjustment module 301 is used to obtain the real-time monitoring results of the preset business system, and adjust the preset grayscale decision strategy in real time according to the real-time monitoring results to obtain the real-time grayscale decision strategy;

[0122] The first analysis module 302 is used to analyze the interface request parameters based on the real-time grayscale decision strategy when receiving the interface request parameters from the user end to obtain parameter analysis results;

[0123] The allocation module 303 is used to match the corresponding target function from the functions of the preset business system according to the parameter analysis result, and allocate permissions to the user terminal according to the target function;

[0124] The second analysis module 304 is used to extract the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result;

[0125] The matching module 305 is used to call a preset matching model, match the embedding point analysis result with the preset system adjustment strategy library, and obtain the target system adjustment strategy;

[0126] The marking module 306 is used to obtain effect information of the target system adjustment policy execution, and mark and adjust the execution process of the target system adjustment policy according to the effect information.

[0127] Optionally, the matching device of the system adjustment strategy further includes:

[0128] A writing module 307 is used to create multiple rule tables, obtain multiple grayscale rules corresponding to a preset grayscale decision strategy, and write each grayscale rule into a corresponding rule table to obtain multiple grayscale rule tables;

[0129] The first construction module 308 is used to call a preset user portrait construction model, construct a corresponding user portrait based on each grayscale rule table, and obtain a user portrait corresponding to each grayscale rule table;

[0130] The second construction module 309 is used to construct a grayscale rule library based on multiple grayscale rule tables and the user portrait corresponding to each grayscale rule table.

[0131] Optionally, the adjustment module 301 may also be specifically used for:

[0132] Run the preset business system, call the preset functional test cases based on the preset monitoring pool, perform real-time functional tests on the running preset business system, and obtain real-time monitoring results;

[0133] Determine whether the real-time monitoring result meets the preset opening conditions. If the real-time monitoring result does not meet the preset opening conditions, obtain the target adjustment information corresponding to the real-time monitoring result, and obtain the target grayscale rule table and target user portrait corresponding to the preset grayscale decision strategy from the grayscale rule library;

[0134] Through the target adjustment information, the target grayscale rule table and target user portrait are updated in real time to obtain a real-time grayscale decision strategy.

[0135] Optionally, the first analysis module 302 may also be specifically used for:

[0136] When receiving the interface request parameters from the user, the user portrait dimension is extracted for the real-time grayscale decision strategy to obtain the target function decision parameters;

[0137] Calculate the similarity between the interface request parameters and the target function decision parameters to obtain parameter similarity, and compare and analyze the parameter similarity with a preset threshold to obtain a comparative analysis result;

[0138] The decision result of opening the system function is determined based on the comparative analysis results, and the parameter analysis results are obtained.

[0139] Optionally, the matching module 305 may also be specifically used for:

[0140] Call the preset classifier to classify the tracking point analysis results into adjustment categories, obtain the target adjustment category, and obtain the system adjustment strategy set corresponding to the target adjustment category from the preset system adjustment strategy library;

[0141] Call the preset matching model to perform vector conversion on the buried point analysis results to obtain the target feature information;

[0142] Calculate the matching scores between the target feature information and the system adjustment strategy sets corresponding to the target adjustment categories;

[0143] By matching the scores, the system adjustment strategy set corresponding to the target adjustment category is sorted and screened to obtain the target system adjustment strategy.

[0144] Optionally, the second analysis module 304 may also be specifically used for:

[0145] Pull the user embedding data of the preset business system corresponding to the user end after the permission is assigned, and extract the user embedding data based on the preset embedding event attribute dimension to obtain the target embedding event data;

[0146] The target embedding event data is sequentially subjected to embedding field extraction, preset indicator statistics, and written into preset data embedding documents to obtain embedding analysis results.

[0147] The functional implementation of each module and each unit in the matching device of the above system adjustment strategy corresponds to each step in the matching method embodiment of the above system adjustment strategy, and their functions and implementation processes are not repeated here one by one.

[0148] In the embodiments of the present invention, not only the real-time adjustment of the preset grayscale decision strategy is realized, the accuracy of the analysis of the subsequent interface request parameters is improved, but also the preset business system is always protected under the condition of the grayscale verification of the functions of the preset business system, the verification information is enriched, and the accuracy of the matching of the target system adjustment strategy is improved, thereby achieving the effect of matching the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of the system verification, and also by marking and adjusting the execution process of the target system adjustment strategy according to the effect information, the accuracy of the matching of the system adjustment strategy on the basis of ensuring the security, rapidity and effectiveness of the system verification is improved.

[0149] above Figure 3 and Figure 4 The matching device of the system adjustment strategy in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The matching device of the system adjustment strategy in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0150] Figure 51 is a schematic diagram of the structure of a matching device for a system adjustment strategy provided by an embodiment of the present invention. The matching device 500 for the system adjustment strategy may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 may be temporary storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of computer program operations in the matching device 500 for the system adjustment strategy. Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of computer program operations in the storage medium 530 on the matching device 500 for the system adjustment strategy.

[0151] The matching device 500 of the system adjustment strategy may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 5 The structure of the matching device of the system adjustment strategy shown does not constitute a limitation on the matching device of the system adjustment strategy, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0152] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program runs on a computer, the computer executes the steps of the matching method of the system adjustment strategy.

[0153] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0154] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0155] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0156] 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, in essence, 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. The computer software product is stored in a storage medium, including several computer programs to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0157] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A matching method for a system adjustment strategy, characterized in that: The matching method of the system adjustment strategy includes: Create multiple rule tables, obtain multiple grayscale rules corresponding to the preset grayscale decision strategy, and write each grayscale rule into the corresponding rule table to obtain multiple grayscale rule tables; Call the preset user portrait construction model, build the corresponding user portrait based on each grayscale rule table, and obtain the user portrait corresponding to each grayscale rule table; Building a grayscale rule library based on the multiple grayscale rule tables and the user portrait corresponding to each grayscale rule table; Run the preset business system, call the preset functional test cases based on the preset monitoring pool, perform real-time functional tests on the running preset business system, and obtain real-time monitoring results; Determine whether the real-time monitoring result meets the preset opening condition. If the real-time monitoring result does not meet the preset opening condition, obtain the target adjustment information corresponding to the real-time monitoring result, and obtain the target grayscale rule table and target user portrait corresponding to the preset grayscale decision strategy from the grayscale rule library; The target grayscale rule table and the target user portrait are updated in real time through the target adjustment information to obtain a real-time grayscale decision strategy; When receiving the interface request parameters from the user end, analyzing the interface request parameters based on the real-time grayscale decision strategy to obtain parameter analysis results; Matching a corresponding target function from the functions of the preset business system according to the parameter analysis result, and assigning permissions to the user terminal according to the target function; Pull the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result; The preset matching model is called to match the embedding point analysis result with the preset system adjustment strategy library to obtain the target system adjustment strategy.

2. The system adjustment strategy matching method according to claim 1, characterized in that: When receiving the interface request parameters from the user end, analyzing the interface request parameters based on the real-time grayscale decision strategy to obtain parameter analysis results includes: When receiving the interface request parameters from the user end, extracting the user portrait dimension of the real-time grayscale decision strategy to obtain the target function decision parameters; Calculating the similarity between the interface request parameter and the target function decision parameter to obtain parameter similarity, and performing comparative analysis on the parameter similarity and a preset threshold to obtain a comparative analysis result; The decision result of opening the system function is determined according to the comparative analysis result, and the parameter analysis result is obtained.

3. The system adjustment strategy matching method according to claim 1, characterized in that: The calling of the preset matching model, matching the embedding analysis result with the preset system adjustment strategy library, and obtaining the target system adjustment strategy includes: Calling a preset classifier to classify the tracking point analysis result into adjustment categories, obtaining a target adjustment category, and obtaining a system adjustment strategy set corresponding to the target adjustment category from a preset system adjustment strategy library; Calling a preset matching model, performing vector conversion on the buried point analysis result, and obtaining target feature information; Calculating matching scores between the target feature information and the system adjustment strategy sets corresponding to the target adjustment categories; The system adjustment strategy set corresponding to the target adjustment category is sorted and screened according to the matching score to obtain the target system adjustment strategy.

4. The system adjustment strategy matching method according to claim 1, characterized in that: The user end after the pull permission is allocated corresponds to the user buried point data of the preset business system, and the user buried point data is analyzed to obtain the buried point analysis result, including: Pull the user embedding data of the preset business system corresponding to the user end after the permission is assigned, and extract the user embedding data based on the preset embedding event attribute dimension to obtain the target embedding event data; The target embedding event data is sequentially subjected to embedding field extraction, preset indicator statistics, and writing into preset data embedding documents to obtain embedding analysis results.

5. The method for matching a system adjustment strategy according to any one of claims 1 to 4, characterized in that: The calling of the preset matching model, matching the embedding analysis result with the preset system adjustment strategy library, and obtaining the target system adjustment strategy further includes: Acquire effect information of the target system adjustment policy execution, and mark and adjust the execution process of the target system adjustment policy according to the effect information.

6. A matching device for a system adjustment strategy, characterized in that: The matching device of the system adjustment strategy includes: A writing module is used to create multiple rule tables, obtain multiple grayscale rules corresponding to a preset grayscale decision strategy, and write each grayscale rule into a corresponding rule table to obtain multiple grayscale rule tables; The first construction module is used to call a preset user portrait construction model, construct a corresponding user portrait based on each grayscale rule table, and obtain a user portrait corresponding to each grayscale rule table; A second construction module is used to construct a grayscale rule library based on the multiple grayscale rule tables and the user portrait corresponding to each grayscale rule table; The adjustment module is used to run the preset business system, call the preset functional test case based on the preset monitoring pool, perform real-time functional testing on the running preset business system, and obtain real-time monitoring results; determine whether the real-time monitoring results meet the preset opening conditions, if the real-time monitoring results do not meet the preset opening conditions, then obtain the target adjustment information corresponding to the real-time monitoring results, and obtain the target grayscale rule table and target user portrait corresponding to the preset grayscale decision strategy from the grayscale rule library; through the target adjustment information, the target grayscale rule table and the target user portrait are updated in real time to obtain the real-time grayscale decision strategy; A first analysis module is used to analyze the interface request parameters based on the real-time grayscale decision strategy when receiving the interface request parameters from the user end to obtain parameter analysis results; An allocation module, used for matching corresponding target functions from the functions of the preset business system according to the parameter analysis result, and allocating permissions to the user terminal according to the target function; The second analysis module is used to pull the user embedding data of the preset business system corresponding to the user end after the permission is allocated, analyze the user embedding data, and obtain the embedding analysis result; The matching module is used to call a preset matching model, match the embedding point analysis result with a preset system adjustment strategy library, and obtain a target system adjustment strategy.

7. A matching device for a system adjustment strategy, characterized in that: The matching device of the system adjustment strategy includes: a memory and at least one processor, wherein the memory stores a computer program; The at least one processor calls the computer program in the memory to enable the system adjustment policy matching device to perform the system adjustment policy matching method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the matching method of the system adjustment strategy as described in any one of claims 1 to 5 is implemented.

Images