CN115827821B - Judgment strategy generation method and system based on information - Google Patents
Judgment strategy generation method and system based on information Download PDFInfo
- Publication number
- CN115827821B CN115827821B CN202211415733.2A CN202211415733A CN115827821B CN 115827821 B CN115827821 B CN 115827821B CN 202211415733 A CN202211415733 A CN 202211415733A CN 115827821 B CN115827821 B CN 115827821B
- Authority
- CN
- China
- Prior art keywords
- information
- fluctuation
- data
- trend
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 claims abstract description 168
- 238000009826 distribution Methods 0.000 claims abstract description 122
- 239000013598 vector Substances 0.000 claims abstract description 121
- 238000013499 data model Methods 0.000 claims abstract description 111
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 13
- 230000004069 differentiation Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 8
- 238000012098 association analyses Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 18
- 238000000605 extraction Methods 0.000 description 8
- 230000001364 causal effect Effects 0.000 description 5
- 238000010224 classification analysis Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012880 independent component analysis Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a judgment strategy generation method and system based on information, which are used for improving the accuracy of judgment strategy generation. The method comprises the following steps: extracting characteristic information of the historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; inputting the target fluctuation vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; and constructing a target judgment strategy of the next information period according to the target analysis result.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a judgment strategy generation method and system based on information.
Background
Along with the high-speed development of artificial intelligence technology, the high-speed development of various industries is driven, the information industry also uses artificial intelligent models to conduct intelligent analysis more and more, and an enhanced data science support is provided for information judgment decision.
Information has strong timeliness and periodicity, and the information comprises deep dependence, so that trend prediction and judgment are possible, and the trend prediction is a prediction hot spot and a difficulty in the current information industry. The existing scheme usually predicts and analyzes information by using manual experience, the accuracy of the manual experience is low, and the prediction difficulty is high.
Disclosure of Invention
The invention provides a judgment strategy generation method and system based on information, which are used for improving the accuracy of judgment strategy generation.
The first aspect of the present invention provides a method for generating a judgment policy based on information, the method for generating a judgment policy based on information comprising: acquiring historical information of a current information period, and extracting characteristic information of the historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; respectively inputting the target fluctuation vector into a plurality of preset fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; and constructing a target judgment strategy corresponding to the next information period according to the target analysis result.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining the historical information of the current information period, and extracting feature information of the historical information, to obtain standard information includes: receiving an information analysis request sent by a terminal, and generating a data acquisition address according to the information analysis request; inquiring historical information of the current information period from a preset information database according to the data acquisition address; performing information differentiation on the historical information to obtain a plurality of discretized information; and carrying out information comparison and feature screening on the plurality of discretized information to obtain standard information.
Optionally, in a second implementation manner of the first aspect of the present invention, the classifying the standard information to obtain first distribution information and second distribution information, generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information includes: constructing a first distribution class and a second distribution class corresponding to the standard information; extracting first distribution information corresponding to the standard information according to the first distribution class, and extracting second distribution information corresponding to the standard information according to the second distribution class; and generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information.
Optionally, in a third implementation manner of the first aspect of the present invention, the performing data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data includes: acquiring a plurality of first wave band data corresponding to the first trend data model, and acquiring a plurality of second wave band data corresponding to the second trend data model; respectively constructing a first wave band function corresponding to each first wave band data, and calculating first trend fluctuation data according to the first wave band function corresponding to each first wave band data; respectively constructing a second wave band function corresponding to each second wave band data, and calculating second trend fluctuation data according to the second wave band function corresponding to each first wave band data; vector conversion is carried out on the first trend fluctuation data to obtain a first fluctuation vector, and vector conversion is carried out on the second trend fluctuation data to obtain a second fluctuation vector; and carrying out vector fusion on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the inputting the target fluctuation vector into a plurality of preset fluctuation analysis models to perform fluctuation root cause analysis, and generating a target analysis result includes: acquiring weight data corresponding to each fluctuation analysis model in a plurality of preset fluctuation analysis models; vector configuration is carried out on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, and a target input vector corresponding to each fluctuation analysis model is obtained; respectively inputting the target input vector into the plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and obtaining an initial analysis result corresponding to each fluctuation analysis model; and generating a target analysis result according to the weight data and the initial analysis result.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the constructing, according to the target analysis result, a target judgment policy corresponding to a next information period includes: carrying out fluctuation prediction on the next information period according to the target analysis result to generate a fluctuation prediction result; performing judgment policy matching on the fluctuation prediction result to obtain an initial judgment policy; and carrying out strategy adjustment on the initial judgment strategy to generate a target judgment strategy corresponding to the next information period.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the information-based judgment policy generating method further includes: performing association analysis on the target judgment strategy and the historical information to obtain a judgment strategy association relation; generating an optimization strategy according to the judgment strategy association relation; and optimizing the target judgment strategy according to the optimization strategy to obtain an optimized target judgment strategy.
The second aspect of the present invention provides a judgment policy generation system based on information, the judgment policy generation system based on information comprising: the acquisition module is used for acquiring historical information of the current information period, and extracting characteristic information of the historical information to obtain standard information; the classification module is used for carrying out information classification on the standard information to obtain first distribution information and second distribution information, generating a first trend data model according to the first distribution information and generating a second trend data model according to the second distribution information; the detection module is used for carrying out data model fluctuation detection on the first trend data model and the second trend data model respectively to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; the analysis module is used for respectively inputting the target fluctuation vector into a plurality of preset fluctuation analysis models to carry out fluctuation root cause analysis and generate a target analysis result; and the construction module is used for constructing a target judgment strategy corresponding to the next information period according to the target analysis result.
Optionally, in a first implementation manner of the second aspect of the present invention, the acquiring module is specifically configured to: receiving an information analysis request sent by a terminal, and generating a data acquisition address according to the information analysis request; inquiring historical information of the current information period from a preset information database according to the data acquisition address; performing information differentiation on the historical information to obtain a plurality of discretized information; and carrying out information comparison and feature screening on the plurality of discretized information to obtain standard information.
Optionally, in a second implementation manner of the second aspect of the present invention, the classification module is specifically configured to: constructing a first distribution class and a second distribution class corresponding to the standard information; extracting first distribution information corresponding to the standard information according to the first distribution class, and extracting second distribution information corresponding to the standard information according to the second distribution class; and generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information.
Optionally, in a third implementation manner of the second aspect of the present invention, the detection module is specifically configured to: acquiring a plurality of first wave band data corresponding to the first trend data model, and acquiring a plurality of second wave band data corresponding to the second trend data model; respectively constructing a first wave band function corresponding to each first wave band data, and calculating first trend fluctuation data according to the first wave band function corresponding to each first wave band data; respectively constructing a second wave band function corresponding to each second wave band data, and calculating second trend fluctuation data according to the second wave band function corresponding to each first wave band data; vector conversion is carried out on the first trend fluctuation data to obtain a first fluctuation vector, and vector conversion is carried out on the second trend fluctuation data to obtain a second fluctuation vector; and carrying out vector fusion on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the analysis module is specifically configured to: acquiring weight data corresponding to each fluctuation analysis model in a plurality of preset fluctuation analysis models; vector configuration is carried out on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, and a target input vector corresponding to each fluctuation analysis model is obtained; respectively inputting the target input vector into the plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and obtaining an initial analysis result corresponding to each fluctuation analysis model; and generating a target analysis result according to the weight data and the initial analysis result.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the building module is specifically configured to: carrying out fluctuation prediction on the next information period according to the target analysis result to generate a fluctuation prediction result; performing judgment policy matching on the fluctuation prediction result to obtain an initial judgment policy; and carrying out strategy adjustment on the initial judgment strategy to generate a target judgment strategy corresponding to the next information period.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the information-based judgment policy generating system further includes: the optimization module is used for carrying out association analysis on the target judgment strategy and the historical information to obtain a judgment strategy association relation; generating an optimization strategy according to the judgment strategy association relation; and optimizing the target judgment strategy according to the optimization strategy to obtain an optimized target judgment strategy.
In the technical scheme provided by the invention, characteristic information extraction is carried out on historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; inputting the target fluctuation vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; according to the method, the target judgment strategy of the next information period is constructed according to the target analysis result, the historical information is subjected to classification analysis, then trend fluctuation analysis is carried out on the distributed information, and the root cause of fluctuation is analyzed through a plurality of artificial intelligent models, so that the generation accuracy of the target judgment strategy is improved.
Drawings
FIG. 1 is a diagram illustrating an embodiment of a method for generating a judgment policy based on information according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating another embodiment of a method for generating a judgment policy based on information according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an embodiment of a system for generating a decision strategy based on information according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating another embodiment of a system for generating a decision strategy based on information according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a judgment strategy generation method and system based on information, which are used for improving the accuracy of judgment strategy generation. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and an embodiment of a method for generating a judgment policy based on information in an embodiment of the present invention includes:
101. acquiring historical information of the current information period, and extracting characteristic information of the historical information to obtain standard information;
it can be understood that the execution subject of the present invention may be a judgment policy generation system based on information, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, historical information data is collected through a preset information database, characteristic extraction is carried out on the historical information data, standard information is obtained, risk data is obtained by combining standard information grades, a subsequent server corrects risk evaluation values obtained by monitoring information and sharing information according to the risk data to obtain a risk correction value, and threshold comparison is carried out on the risk correction value and a preset risk evaluation threshold to judge risk conditions.
When the historical information is subjected to feature extraction, the server pre-processes the input historical information and maps the input historical information into corresponding information word vectors, the bidirectional LSTM network performs feature extraction on the information word vectors of the historical information to obtain semantic feature information of the historical information, the semantic feature information and the attention mechanism of the historical information are utilized to extract feature information of target attributes, and the feature information and the semantic feature information are subjected to information fusion to obtain feature information, so that standard information is obtained.
102. Information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information;
it should be noted that, a classification model of an OS-ELM algorithm is established by using a training set composed of historical information as an initial classification model for classifying standard information, wherein a server establishes a structure learning model by using an online fuzzy clustering method, estimates a global structure of data distribution after the standard information is batched on the basis of prior information of the historical information, marks the standard information by using the classification model, obtains first distribution information and second distribution information by using a batch classification mode, generates a first trend data model according to the first distribution information, and generates a second trend data model according to the second distribution information.
103. Respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data;
Specifically, data model fluctuation detection is performed on the first trend data model and the second trend data model respectively, wherein the server performs debugging and smoothing processing on trend data of a preset data amount to obtain first trend fluctuation data, meanwhile, the server performs debugging processing on the second trend data model of the preset data amount to obtain second trend fluctuation data, fitting operation is performed on the first trend fluctuation data, and a target fluctuation vector is constructed according to the first trend fluctuation data and the second trend fluctuation data.
When the server constructs the target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data, the server predicts the fluctuation data to obtain fluctuation vector prediction data, and constructs the target fluctuation vector according to the fluctuation vector prediction data.
104. Respectively inputting the target fluctuation vector into a plurality of preset fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result;
it should be noted that, in the method, the independent component analysis algorithm is combined to perform fluctuation root cause analysis, firstly, the server performs causal analysis on the fluctuation root cause, a causal relation graph is used to intuitively express causal influence relation among target fluctuation vectors, the propagation trend of fluctuation interference is represented, the causal relation graph is simplified by using priori process knowledge, secondary causal relation branches are filtered through a threshold automatic searching mode, the main development trend of fluctuation is obtained, and the fluctuation root cause analysis is performed to generate a target analysis result.
105. And constructing a target judgment strategy corresponding to the next information period according to the target analysis result.
Specifically, analyzing a data packet of a target analysis result, extracting matching information from the data packet, triggering strategy routing to match by using the matching information, redirecting the target analysis result meeting the matching condition, searching a corresponding strategy according to a redirected target analysis result table for the target analysis result of the matching condition, and constructing a target judgment strategy corresponding to the next information period according to the searched strategy.
In the embodiment of the invention, characteristic information extraction is carried out on the historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; inputting the target fluctuation vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; according to the method, the target judgment strategy of the next information period is constructed according to the target analysis result, the historical information is subjected to classification analysis, then trend fluctuation analysis is carried out on the distributed information, and the root cause of fluctuation is analyzed through a plurality of artificial intelligent models, so that the generation accuracy of the target judgment strategy is improved.
Referring to fig. 2, another embodiment of a method for generating a judgment policy based on information in an embodiment of the present invention includes:
201. acquiring historical information of the current information period, and extracting characteristic information of the historical information to obtain standard information;
specifically, an information analysis request sent by a terminal is received, and a data acquisition address is generated according to the information analysis request; inquiring historical information of the current information period from a preset information database according to the data acquisition address; performing information differentiation on the historical information to obtain a plurality of discretized information; and carrying out information comparison and feature screening on the plurality of discretized information to obtain standard information.
The server analyzes an information analysis request initiated by the request information, acquires a Pod-IP list corresponding to the target application from the request analysis information, inquires Pod information corresponding to each Pod-IP in the Pod-IP list, determines a main Pod from all Pods of the target application based on all Pod information and a preset strategy, replaces the Pod-IP list in the request information with the Pod-IP of the main Pod to obtain replaced request information, inquires historical information of a current information period from a preset information database according to a data acquisition address, acquires the address according to the replaced request information, determines to generate the data acquisition address, further downloads historical information of the current information period from a preset information database according to the data acquisition address, performs information differentiation on the historical information to obtain a plurality of discretization information, performs information comparison and feature screening on the plurality of discretization information, and obtains standard information.
When the server performs information differentiation on the historical information, the server disassembles the historical information to be differentiated into a plurality of characteristic words, combines the characteristic words, calculates the similarity between each historical information and the historical information to be differentiated, selects one or more historical information as a differentiation result of the historical information to be differentiated according to the similarity, obtains a plurality of discretization information, and performs information comparison and characteristic screening on the discretization information to obtain standard information.
202. Information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information;
specifically, a first distribution class and a second distribution class corresponding to standard information are constructed; extracting first distribution information corresponding to the standard information according to the first distribution class, and extracting second distribution information corresponding to the standard information according to the second distribution class; and generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information.
The method comprises the steps of screening and cleaning acquired standard information, processing invalid data, analyzing the trend of each point in the standard information, comparing each point with an index weighted moving average of the previous N values to obtain deviation, analyzing the deviation value of the standard information monitored on line by adopting multidimensional Gaussian distribution, extracting first distribution information corresponding to the standard information and second distribution information corresponding to the standard information, generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information by assistance of trend analysis.
203. Respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data;
specifically, a plurality of first wave band data corresponding to a first trend data model are obtained, and a plurality of second wave band data corresponding to a second trend data model are obtained; respectively constructing a first wave band function corresponding to each first wave band data, and calculating first trend fluctuation data according to the first wave band function corresponding to each first wave band data; respectively constructing a second wave band function corresponding to each second wave band data, and calculating second trend fluctuation data according to the second wave band function corresponding to each first wave band data; vector conversion is carried out on the first trend fluctuation data to obtain a first fluctuation vector, and vector conversion is carried out on the second trend fluctuation data to obtain a second fluctuation vector; and carrying out vector fusion on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector.
The method comprises the steps that a server obtains a plurality of first wave band data corresponding to a first trend data model, obtains a plurality of second wave band data corresponding to a second trend data model, determines a corresponding wave band function according to the first wave band data and the second wave band data, determines trend fluctuation data of the wave band data to be analyzed according to the wave band function and the trust domain, performs wave band division according to the obtained trend fluctuation data, matches the divided wave bands with a preset scene, determines a trend fluctuation change similarity set corresponding to the divided wave bands according to a corresponding relation between the preset scene and the trend fluctuation change similarity set, performs vector conversion on the first trend fluctuation data to obtain a first fluctuation vector, performs vector conversion on the second trend fluctuation data to obtain a second fluctuation vector, and performs vector fusion on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector.
204. Acquiring weight data corresponding to each fluctuation analysis model in a plurality of preset fluctuation analysis models;
205. vector configuration is carried out on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, and the target input vector corresponding to each fluctuation analysis model is obtained;
206. Inputting the target input vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and obtaining an initial analysis result corresponding to each fluctuation analysis model;
207. generating a target analysis result according to the weight data and the initial analysis result;
specifically, the server calculates the similarity among a plurality of fluctuation analysis models through an objective weighting method and an entropy weighting method, weights the attribute value of each fluctuation analysis model obtained through the comprehensive calculation, selects K nearest neighbor objects which are most similar to the data through improved gray correlation, fills the missing attribute value by using the average value of the corresponding attribute in the objects, carries out vector configuration on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, obtains the target input vector corresponding to each fluctuation analysis model, respectively inputs the target input vector into a plurality of fluctuation analysis models for fluctuation root cause analysis, obtains the initial analysis result corresponding to each fluctuation analysis model, and generates the target analysis result according to the weight data and the initial analysis result.
208. And constructing a target judgment strategy corresponding to the next information period according to the target analysis result.
Specifically, carrying out fluctuation prediction on the next information period according to the target analysis result to generate a fluctuation prediction result; judging strategy matching is carried out on the fluctuation prediction result, and an initial judging strategy is obtained; and performing strategy adjustment on the initial judgment strategy to generate a target judgment strategy corresponding to the next information period.
The server calculates the actual measurement fluctuation index of the next information period according to the prediction time interval, calculates the average value of the actual measurement fluctuation index, and predicts the data of the previous M time intervals by using a gray prediction model, wherein M is a positive integer greater than or equal to 1, further predicts the fluctuation prediction data of the M+1th time interval by using a time sequence prediction method, and finally carries out judgment strategy matching on the fluctuation prediction result to obtain an initial judgment strategy; and performing strategy adjustment on the initial judgment strategy to generate a target judgment strategy corresponding to the next information period.
Optionally, performing association analysis on the target judgment strategy and the historical information to obtain a judgment strategy association relation; generating an optimization strategy according to the judgment strategy association relation; and optimizing the target judgment strategy according to the optimization strategy to obtain the optimized target judgment strategy.
Under the constraint of the association relation condition, the association degree between the judgment strategy and the information is determined by calculating the performance interference degree of the association relation, association relation measurement is established, then an association model is formed by using all association relation measurement relations, the association relation of the judgment strategy is obtained by using the collected application performance data, an optimization strategy is generated according to the association relation of the judgment strategy, and the target judgment strategy is optimized according to the optimization strategy, so that the optimized target judgment strategy is obtained.
In the embodiment of the invention, characteristic information extraction is carried out on the historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; inputting the target fluctuation vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; according to the method, the target judgment strategy of the next information period is constructed according to the target analysis result, the historical information is subjected to classification analysis, then trend fluctuation analysis is carried out on the distributed information, and the root cause of fluctuation is analyzed through a plurality of artificial intelligent models, so that the generation accuracy of the target judgment strategy is improved.
The method for generating the judgment policy based on the information in the embodiment of the present invention is described above, and the system for generating the judgment policy based on the information in the embodiment of the present invention is described below, referring to fig. 3, an embodiment of the system for generating the judgment policy based on the information in the embodiment of the present invention includes:
the acquisition module 301 is configured to acquire historical information of a current information period, and extract feature information of the historical information to obtain standard information;
the classification module 302 is configured to perform information classification on the standard information to obtain first distribution information and second distribution information, generate a first trend data model according to the first distribution information, and generate a second trend data model according to the second distribution information;
the detection module 303 is configured to perform data model fluctuation detection on the first trend data model and the second trend data model respectively, obtain first trend fluctuation data and second trend fluctuation data, and construct a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data;
the analysis module 304 is configured to input the target fluctuation vector into a plurality of preset fluctuation analysis models to perform fluctuation root cause analysis, so as to generate a target analysis result;
And a construction module 305, configured to construct a target judgment policy corresponding to the next information period according to the target analysis result.
In the embodiment of the invention, characteristic information extraction is carried out on the historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; inputting the target fluctuation vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; according to the method, the target judgment strategy of the next information period is constructed according to the target analysis result, the historical information is subjected to classification analysis, then trend fluctuation analysis is carried out on the distributed information, and the root cause of fluctuation is analyzed through a plurality of artificial intelligent models, so that the generation accuracy of the target judgment strategy is improved.
Referring to fig. 4, another embodiment of a judgment policy generation system based on information in an embodiment of the present invention includes:
the acquisition module 301 is configured to acquire historical information of a current information period, and extract feature information of the historical information to obtain standard information;
the classification module 302 is configured to perform information classification on the standard information to obtain first distribution information and second distribution information, generate a first trend data model according to the first distribution information, and generate a second trend data model according to the second distribution information;
the detection module 303 is configured to perform data model fluctuation detection on the first trend data model and the second trend data model respectively, obtain first trend fluctuation data and second trend fluctuation data, and construct a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data;
the analysis module 304 is configured to input the target fluctuation vector into a plurality of preset fluctuation analysis models to perform fluctuation root cause analysis, so as to generate a target analysis result;
and a construction module 305, configured to construct a target judgment policy corresponding to the next information period according to the target analysis result.
Optionally, the acquiring module 301 is specifically configured to: receiving an information analysis request sent by a terminal, and generating a data acquisition address according to the information analysis request; inquiring historical information of the current information period from a preset information database according to the data acquisition address; performing information differentiation on the historical information to obtain a plurality of discretized information; and carrying out information comparison and feature screening on the plurality of discretized information to obtain standard information.
Optionally, the classification module 302 is specifically configured to: constructing a first distribution class and a second distribution class corresponding to the standard information; extracting first distribution information corresponding to the standard information according to the first distribution class, and extracting second distribution information corresponding to the standard information according to the second distribution class; and generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information.
Optionally, the detection module 303 is specifically configured to: acquiring a plurality of first wave band data corresponding to the first trend data model, and acquiring a plurality of second wave band data corresponding to the second trend data model; respectively constructing a first wave band function corresponding to each first wave band data, and calculating first trend fluctuation data according to the first wave band function corresponding to each first wave band data; respectively constructing a second wave band function corresponding to each second wave band data, and calculating second trend fluctuation data according to the second wave band function corresponding to each first wave band data; vector conversion is carried out on the first trend fluctuation data to obtain a first fluctuation vector, and vector conversion is carried out on the second trend fluctuation data to obtain a second fluctuation vector; and carrying out vector fusion on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector.
Optionally, the analysis module 304 is specifically configured to: acquiring weight data corresponding to each fluctuation analysis model in a plurality of preset fluctuation analysis models; vector configuration is carried out on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, and a target input vector corresponding to each fluctuation analysis model is obtained; respectively inputting the target input vector into the plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and obtaining an initial analysis result corresponding to each fluctuation analysis model; and generating a target analysis result according to the weight data and the initial analysis result.
Optionally, the construction module 305 is specifically configured to: carrying out fluctuation prediction on the next information period according to the target analysis result to generate a fluctuation prediction result; performing judgment policy matching on the fluctuation prediction result to obtain an initial judgment policy; and carrying out strategy adjustment on the initial judgment strategy to generate a target judgment strategy corresponding to the next information period.
Optionally, the information-based judgment policy generation system further includes: the optimizing module 306 is configured to perform association analysis on the target judgment policy and the historical information to obtain a judgment policy association relationship; generating an optimization strategy according to the judgment strategy association relation; and optimizing the target judgment strategy according to the optimization strategy to obtain an optimized target judgment strategy.
In the embodiment of the invention, characteristic information extraction is carried out on the historical information to obtain standard information; information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information; respectively carrying out data model fluctuation detection on the first trend data model and the second trend data model to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data; inputting the target fluctuation vector into a plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result; according to the method, the target judgment strategy of the next information period is constructed according to the target analysis result, the historical information is subjected to classification analysis, then trend fluctuation analysis is carried out on the distributed information, and the root cause of fluctuation is analyzed through a plurality of artificial intelligent models, so that the generation accuracy of the target judgment strategy is improved.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The information-based judgment policy generation method is characterized by comprising the following steps of:
acquiring historical information of a current information period, and extracting characteristic information of the historical information to obtain standard information;
information classification is carried out on the standard information to obtain first distribution information and second distribution information, a first trend data model is generated according to the first distribution information, and a second trend data model is generated according to the second distribution information;
carrying out data model fluctuation detection on the first trend data model and the second trend data model respectively to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data, wherein the method specifically comprises the following steps of: acquiring a plurality of first wave band data corresponding to the first trend data model, and acquiring a plurality of second wave band data corresponding to the second trend data model; respectively constructing a first wave band function corresponding to each first wave band data, and calculating first trend fluctuation data according to the first wave band function corresponding to each first wave band data; respectively constructing a second wave band function corresponding to each second wave band data, and calculating second trend fluctuation data according to the second wave band function corresponding to each first wave band data; vector conversion is carried out on the first trend fluctuation data to obtain a first fluctuation vector, and vector conversion is carried out on the second trend fluctuation data to obtain a second fluctuation vector; vector fusion is carried out on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector;
Respectively inputting the target fluctuation vector into a plurality of preset fluctuation analysis models to carry out fluctuation root cause analysis, and generating a target analysis result, wherein the method specifically comprises the following steps of: acquiring weight data corresponding to each fluctuation analysis model in a plurality of preset fluctuation analysis models; vector configuration is carried out on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, and a target input vector corresponding to each fluctuation analysis model is obtained; respectively inputting the target input vector into the plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and obtaining an initial analysis result corresponding to each fluctuation analysis model; generating a target analysis result according to the weight data and the initial analysis result;
and constructing a target judgment strategy corresponding to the next information period according to the target analysis result.
2. The information-based decision strategy generation method according to claim 1, wherein the steps of obtaining the history information of the current information cycle, and extracting the feature information of the history information to obtain the standard information include:
receiving an information analysis request sent by a terminal, and generating a data acquisition address according to the information analysis request;
Inquiring historical information of the current information period from a preset information database according to the data acquisition address;
performing information differentiation on the historical information to obtain a plurality of discretized information;
and carrying out information comparison and feature screening on the plurality of discretized information to obtain standard information.
3. The information-based decision strategy generation method according to claim 1, wherein the classifying the standard information to obtain first distribution information and second distribution information, generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information, comprises:
constructing a first distribution class and a second distribution class corresponding to the standard information;
extracting first distribution information corresponding to the standard information according to the first distribution class, and extracting second distribution information corresponding to the standard information according to the second distribution class;
and generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information.
4. The information-based decision strategy generation method according to claim 1, wherein the constructing a target decision strategy corresponding to a next information period according to the target analysis result includes:
Carrying out fluctuation prediction on the next information period according to the target analysis result to generate a fluctuation prediction result;
performing judgment policy matching on the fluctuation prediction result to obtain an initial judgment policy;
and carrying out strategy adjustment on the initial judgment strategy to generate a target judgment strategy corresponding to the next information period.
5. The information-based judgment policy generation method according to claim 1, wherein the information-based judgment policy generation method further comprises:
performing association analysis on the target judgment strategy and the historical information to obtain a judgment strategy association relation;
generating an optimization strategy according to the judgment strategy association relation;
and optimizing the target judgment strategy according to the optimization strategy to obtain an optimized target judgment strategy.
6. A judgment policy generation system based on information, characterized in that the judgment policy generation system based on information includes:
the acquisition module is used for acquiring historical information of the current information period, and extracting characteristic information of the historical information to obtain standard information;
the classification module is used for carrying out information classification on the standard information to obtain first distribution information and second distribution information, generating a first trend data model according to the first distribution information and generating a second trend data model according to the second distribution information;
The detection module is used for carrying out data model fluctuation detection on the first trend data model and the second trend data model respectively to obtain first trend fluctuation data and second trend fluctuation data, and constructing a target fluctuation vector according to the first trend fluctuation data and the second trend fluctuation data, and specifically comprises the following steps: acquiring a plurality of first wave band data corresponding to the first trend data model, and acquiring a plurality of second wave band data corresponding to the second trend data model; respectively constructing a first wave band function corresponding to each first wave band data, and calculating first trend fluctuation data according to the first wave band function corresponding to each first wave band data; respectively constructing a second wave band function corresponding to each second wave band data, and calculating second trend fluctuation data according to the second wave band function corresponding to each first wave band data; vector conversion is carried out on the first trend fluctuation data to obtain a first fluctuation vector, and vector conversion is carried out on the second trend fluctuation data to obtain a second fluctuation vector; vector fusion is carried out on the first fluctuation vector and the second fluctuation vector to obtain a target fluctuation vector;
The analysis module is used for respectively inputting the target fluctuation vector into a plurality of preset fluctuation analysis models to carry out fluctuation root cause analysis and generating a target analysis result, and specifically comprises the following steps: acquiring weight data corresponding to each fluctuation analysis model in a plurality of preset fluctuation analysis models; vector configuration is carried out on the target fluctuation vector according to the weight data corresponding to each fluctuation analysis model, and a target input vector corresponding to each fluctuation analysis model is obtained; respectively inputting the target input vector into the plurality of fluctuation analysis models to carry out fluctuation root cause analysis, and obtaining an initial analysis result corresponding to each fluctuation analysis model; generating a target analysis result according to the weight data and the initial analysis result;
and the construction module is used for constructing a target judgment strategy corresponding to the next information period according to the target analysis result.
7. The information-based decision strategy generation system of claim 6, wherein the acquisition module is specifically configured to:
receiving an information analysis request sent by a terminal, and generating a data acquisition address according to the information analysis request;
inquiring historical information of the current information period from a preset information database according to the data acquisition address;
Performing information differentiation on the historical information to obtain a plurality of discretized information;
and carrying out information comparison and feature screening on the plurality of discretized information to obtain standard information.
8. The information-based decision strategy generation system of claim 6, wherein the classification module is specifically configured to:
constructing a first distribution class and a second distribution class corresponding to the standard information;
extracting first distribution information corresponding to the standard information according to the first distribution class, and extracting second distribution information corresponding to the standard information according to the second distribution class;
and generating a first trend data model according to the first distribution information, and generating a second trend data model according to the second distribution information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415733.2A CN115827821B (en) | 2022-11-11 | 2022-11-11 | Judgment strategy generation method and system based on information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415733.2A CN115827821B (en) | 2022-11-11 | 2022-11-11 | Judgment strategy generation method and system based on information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115827821A CN115827821A (en) | 2023-03-21 |
| CN115827821B true CN115827821B (en) | 2024-01-09 |
Family
ID=85527838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211415733.2A Active CN115827821B (en) | 2022-11-11 | 2022-11-11 | Judgment strategy generation method and system based on information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115827821B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019019346A1 (en) * | 2017-07-25 | 2019-01-31 | 上海壹账通金融科技有限公司 | Asset allocation strategy acquisition method and apparatus, computer device, and storage medium |
| CN114493457A (en) * | 2022-02-11 | 2022-05-13 | 常州刘国钧高等职业技术学校 | Intelligent control method and system for automatic three-dimensional storage |
| CN115049137A (en) * | 2022-06-23 | 2022-09-13 | 中国工商银行股份有限公司 | Prediction method and device of transaction yield, storage medium and electronic equipment |
| CN115098650A (en) * | 2022-08-25 | 2022-09-23 | 华扬联众数字技术股份有限公司 | Comment information analysis method based on historical data model and related device |
| CN115310722A (en) * | 2022-09-29 | 2022-11-08 | 浙江越秀外国语学院 | Agricultural product price prediction method based on data statistics |
-
2022
- 2022-11-11 CN CN202211415733.2A patent/CN115827821B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019019346A1 (en) * | 2017-07-25 | 2019-01-31 | 上海壹账通金融科技有限公司 | Asset allocation strategy acquisition method and apparatus, computer device, and storage medium |
| CN114493457A (en) * | 2022-02-11 | 2022-05-13 | 常州刘国钧高等职业技术学校 | Intelligent control method and system for automatic three-dimensional storage |
| CN115049137A (en) * | 2022-06-23 | 2022-09-13 | 中国工商银行股份有限公司 | Prediction method and device of transaction yield, storage medium and electronic equipment |
| CN115098650A (en) * | 2022-08-25 | 2022-09-23 | 华扬联众数字技术股份有限公司 | Comment information analysis method based on historical data model and related device |
| CN115310722A (en) * | 2022-09-29 | 2022-11-08 | 浙江越秀外国语学院 | Agricultural product price prediction method based on data statistics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115827821A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11734319B2 (en) | Question answering method and apparatus | |
| CN106815252B (en) | Searching method and device | |
| CN110147321B (en) | Software network-based method for identifying defect high-risk module | |
| CN110335168B (en) | Method and system for optimizing power utilization information acquisition terminal fault prediction model based on GRU | |
| Dudas et al. | Integration of data mining and multi-objective optimisation for decision support in production systems development | |
| CN106021361A (en) | Sequence alignment-based self-adaptive application layer network protocol message clustering method | |
| CN113869521A (en) | Method, device, computing equipment and storage medium for constructing prediction model | |
| Tembusai et al. | K-nearest neighbor with k-fold cross validation and analytic hierarchy process on data classification | |
| CN108764541B (en) | Wind energy prediction method combining space characteristic and error processing | |
| Netzer et al. | Intelligent anomaly detection of machine tools based on mean shift clustering | |
| CN115987552A (en) | Network intrusion detection method based on deep learning | |
| CN116382224B (en) | Packaging equipment monitoring method and system based on data analysis | |
| CN112749530B (en) | Text encoding method, apparatus, device and computer readable storage medium | |
| CN115827821B (en) | Judgment strategy generation method and system based on information | |
| CN116561562B (en) | Sound source depth optimization acquisition method based on waveguide singular points | |
| Zhao et al. | Autodes: Automl pipeline generation of classification with dynamic ensemble strategy selection | |
| CN113299380A (en) | Information prompting method based on intelligent medical big data and intelligent medical service system | |
| CN116030955B (en) | Medical equipment state monitoring method and related device based on Internet of things | |
| CN117095247A (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN108363738B (en) | Recommendation method for industrial equipment data analysis algorithm | |
| CN110855519A (en) | Network flow prediction method | |
| CN116089820A (en) | Load identification method and system based on user cooperation, electronic equipment and medium | |
| CN112051479A (en) | Power distribution network operation state identification method and system | |
| CN115865421A (en) | Intrusion detection method and system for power distribution network information system | |
| CN115883182A (en) | Method and system for improving network security situation element identification efficiency |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |