CN113792887A - Component analysis method, device and equipment based on intelligent decision and storage medium - Google Patents
Component analysis method, device and equipment based on intelligent decision and storage medium Download PDFInfo
- Publication number
- CN113792887A CN113792887A CN202111087588.5A CN202111087588A CN113792887A CN 113792887 A CN113792887 A CN 113792887A CN 202111087588 A CN202111087588 A CN 202111087588A CN 113792887 A CN113792887 A CN 113792887A
- Authority
- CN
- China
- Prior art keywords
- data
- component
- theoretical
- dimension
- target object
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a component analysis method, a device, equipment and a storage medium based on intelligent decision, which comprises the following steps: acquiring dimension composition data, dimension value data and overall observation data of a target object; acquiring historical component data of a target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; theoretical analysis data is obtained according to the theoretical component data and the dimensional value data, the theoretical analysis data closest to the overall observation data is identified, the theoretical analysis data is set as an analysis result, and the theoretical component data corresponding to the analysis result is set as component analysis data. The invention realizes the technical effect of analyzing the composition of the target object, so that a manager can conveniently adjust or control the target object according to the requirement, thereby improving the plasticity of the target object and expanding the application range of the target object.
Description
Technical Field
The invention relates to the technical field of intelligent decision making of artificial intelligence, in particular to a component analysis method, a component analysis device, component analysis equipment and a storage medium based on intelligent decision making.
Background
The target objects provided by general external personnel or organizations (such as fund, enterprise public information, etc.) are generally integrated service information, namely: only partial characteristic information (such as dimension composition data, dimension value data and overall observation data) is disclosed so as to be convenient for a user to use, and the inside of the target object usually exists in a form of a black box, so that the user cannot know the composition of each component in the module.
However, the inventor realizes that if the components in the target object cannot be known, the components in the target object cannot be adjusted and controlled according to the needs of the administrator, so that the target object has low plasticity and a narrow application range.
Disclosure of Invention
The invention aims to provide a component analysis method, a component analysis device, a component analysis equipment and a storage medium based on intelligent decision, which are used for solving the problems that in the prior art, components in a target object cannot be adjusted and controlled according to the requirements of a manager because the components in the target object cannot be obtained, so that the plasticity of the target object is low and the application range is narrow.
In order to achieve the above object, the present invention provides a component analysis method based on intelligent decision, comprising:
acquiring dimension composition data, dimension value data and overall observation data of a target object; the dimension composition data reflects the composition of the target object in each dimension, the dimension value data reflects the display effect of the target object in each dimension, and the overall observation data reflects the overall display effect of the target object;
acquiring historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical combined components refer to historical component composition of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components;
theoretical analysis data are obtained according to the theoretical component data and the dimension value data, the theoretical analysis data closest to the overall observation data are identified, the theoretical analysis data are set as analysis results, theoretical component data corresponding to the analysis results are set as component analysis data, and the theoretical analysis data are used for presuming the display effect of the target object based on the theoretical component data.
In the foregoing solution, the acquiring of the dimension composition data, the dimension value data, and the overall observation data of the target object includes:
receiving an object number sent by a control end;
identifying a target object corresponding to the object number from a preset database;
and acquiring dimension composition data, dimension value data and overall observation data associated with the target object from the database.
In the above scheme, after obtaining the dimension composition data, the dimension value data, and the overall observation data of the target object, the method further includes:
and performing data cleaning on the dimension composition data, the dimension value data and the overall observation data to eliminate invalid data and missing data in the dimension composition data, the dimension value data and the overall observation data.
In the above scheme, after obtaining the dimension composition data, the dimension value data, and the overall observation data of the target object, the method further includes:
acquiring component public data and component dimension value data of a target object, acquiring the dimension of the component public data and setting the dimension as dimension public data, and acquiring observation public data according to the component public data and the component dimension value data; deleting the dimension public data in the dimension composition data, and deleting the observation public data in the whole observation data.
In the foregoing scheme, the acquiring the historical component data of the target object includes:
receiving an object number and time information sent by a control end;
acquiring a target object corresponding to the object number from a preset database, and acquiring a history component set associated with the target object, wherein the history component set at least comprises one history component data;
and acquiring historical component data corresponding to the time information from the historical component set.
In the foregoing solution, the constructing at least one theoretical component data according to the dimension composition data and the overall observation data with the historical component data as a limiting condition includes:
creating a theoretical component matrix and acquiring a preset component transformation limiting threshold, constructing a limiting condition which takes the difference between the theoretical component matrix and the historical component data as a variable and takes the component transformation limiting threshold as the upper limit value of the variable;
converting the theoretical component matrix through a preset dimension indication matrix to enable the theoretical component matrix to correspond to the dimension forming data and form a theoretical precalculated expression, wherein the dimension indication matrix is used for marking the dimension of each row in the theoretical component matrix;
and assigning values to the element values in the theoretical component matrix according to the theoretical precomputation and the limiting conditions, so that the theoretical component matrix is converted into theoretical component data.
In the foregoing solution, the obtaining theoretical analysis data according to the theoretical component data and the dimensional value data, identifying theoretical analysis data closest to the overall observation data, and setting the theoretical analysis data as an analysis result includes:
inputting the theoretical component data and the dimension value data into a preset effect formula, and operating the effect formula to obtain theoretical analysis data;
and calculating Euclidean distances between the overall observation data and each theoretical analysis data through a preset support vector machine, and setting the theoretical analysis data closest to the Euclidean distances between the overall observation data and the theoretical analysis data as an analysis result.
In order to achieve the above object, the present invention further provides an intelligent decision-based component analysis apparatus, comprising:
the data input module is used for acquiring dimension composition data, dimension value data and overall observation data of the target object; the dimension composition data reflects the composition of the target object in each dimension, the dimension value data reflects the display effect of the target object in each dimension, and the overall observation data reflects the overall display effect of the target object;
the theoretical component module is used for acquiring historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical combined components refer to historical component composition of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components;
and the theoretical analysis module is used for obtaining theoretical analysis data according to the theoretical component data and the dimensional value data, identifying the theoretical analysis data closest to the overall observation data, setting the theoretical analysis data as an analysis result, and setting the theoretical component data corresponding to the analysis result as component analysis data, wherein the theoretical analysis data is used for presuming the display effect of the target object based on the theoretical component data.
To achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor of the computer device implements the steps of the intelligent decision-based component analysis method when executing the computer program.
To achieve the above object, the present invention further provides a computer-readable storage medium, which stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the above intelligent decision-based component analysis method.
According to the component analysis method, device, equipment and storage medium based on the intelligent decision, the historical component data of the target object are obtained, the historical component data are used as limiting conditions, at least one theoretical component data is constructed according to the dimension composition data and the overall observation data, the possibility of composition of each component in the target object is analyzed based on the historical component data and the current composition of each dimension of the target object and the effect shown on the whole, and at least one theoretical component data with multiple possibilities is obtained.
Theoretical analysis data are obtained according to the theoretical component data and the dimension composition data, then the theoretical analysis data closest to the overall observation data are identified, the theoretical analysis data are set as analysis results, the theoretical component data corresponding to the analysis information are set as component analysis data, the technical effect of analyzing the component composition of the target object is achieved, a manager can conveniently adjust or control the target object according to needs, the plasticity of the target object is improved, and the application range of the target object is expanded.
Drawings
FIG. 1 is a flow chart of a first embodiment of an intelligent decision-based component analysis method according to the present invention;
FIG. 2 is a schematic diagram of an environmental application of a component analysis method in a second embodiment of the intelligent decision-based component analysis method of the present invention;
FIG. 3 is a flowchart of a specific method of a component analysis method in an embodiment of an intelligent decision-based component analysis method according to the present invention;
FIG. 4 is a schematic diagram of a program module of a third embodiment of an intelligent decision-based component analysis apparatus according to the present invention;
fig. 5 is a schematic diagram of a hardware structure of a computer device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a component analysis method, a device, equipment and a storage medium based on intelligent decision, which are suitable for the technical field of artificial intelligent decision and provide a component analysis method based on a data input module, a theoretical component module and a theoretical analysis module. The method comprises the steps of obtaining dimension composition data, dimension value data and overall observation data of a target object, obtaining historical component data of the target object, taking the historical component data as a limiting condition, constructing at least one theoretical component data according to the dimension composition data and the overall observation data, obtaining theoretical analysis data according to the theoretical component data and the dimension value data, identifying theoretical analysis data closest to the overall observation data, setting the theoretical analysis data as an analysis result, and setting the theoretical component data corresponding to the analysis result as component analysis data.
The first embodiment is as follows:
referring to fig. 1, a method for component analysis based on intelligent decision in this embodiment includes:
s101: acquiring dimension composition data, dimension value data and overall observation data of a target object; the dimension composition data reflects the composition of the target object in each dimension, the dimension value data reflects the display effect of the target object in each dimension, and the overall observation data reflects the overall display effect of the target object;
s104: acquiring historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical combined components refer to historical component composition of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components;
s105: theoretical analysis data are obtained according to the theoretical component data and the dimension value data, the theoretical analysis data closest to the overall observation data are identified, the theoretical analysis data are set as analysis results, theoretical component data corresponding to the analysis results are set as component analysis data, and the theoretical analysis data are used for presuming the display effect of the target object based on the theoretical component data.
In an exemplary embodiment, the dimension composition data, the dimension value data, and the overall observation data are public data of the target object, the dimension composition data reflects composition of the target object in each dimension, the dimension value data reflects a display effect of the target object in each dimension, and the overall observation data reflects a display effect of the target object as a whole.
By acquiring historical component data of the target object and taking the historical component data as a limiting condition, constructing at least one piece of theoretical component data according to the dimension composition data and the overall observation data, wherein the current component composition of the target object is associated with the historical component data, namely: the method has certain consistency, so that the theoretical component data is constructed according to the dimension construction data and the overall observation data by taking the historical component data as a limiting condition, the possibility of the composition of each component in the target object is analyzed based on the historical component data and the composition of the current component of the target object in each dimension and the effect shown in the whole, and at least one theoretical component data with multiple possibilities is obtained.
Theoretical analysis data are obtained according to the theoretical component data and the dimensionality composition data, then the theoretical analysis data closest to the overall observation data are identified through a support vector machine based on an intelligent decision technology, the theoretical analysis data are set as analysis results, and the theoretical component data corresponding to the analysis information are set as component analysis data; therefore, the component composition of the target object is analyzed, so that a manager can conveniently adjust or control the target object according to needs, the plasticity of the target object is improved, and the application range of the target object is expanded.
Example two:
the embodiment is a specific application scenario of the first embodiment, and the method provided by the present invention can be more clearly and specifically explained through the embodiment.
The method provided by the present embodiment is specifically described below by taking, as an example, that in a server running a component analysis method, historical component data is used as a limiting condition, at least one theoretical component data is constructed according to dimension composition data and overall observation data, and the theoretical analysis data closest to the overall observation data is identified. It should be noted that the present embodiment is only exemplary, and does not limit the protection scope of the embodiments of the present invention.
Fig. 2 schematically shows an environmental application diagram of the composition analysis method according to the second embodiment of the present application.
In an exemplary embodiment, the servers 2 where the component analysis methods are located are respectively connected to the control terminals 4 through the network 3; the server 2 may provide services through one or more networks 3, which networks 3 may include various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network 3 may include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like. The network 3 may include wireless links, such as cellular links, satellite links, Wi-Fi links, and/or the like; the control terminal 4 may be a computer device such as a smart phone, a tablet computer, a notebook computer, and a desktop computer.
Fig. 3 is a flowchart of a specific method of a component analysis method according to an embodiment of the present invention, where the method specifically includes steps S201 to S205.
S201: acquiring dimension composition data, dimension value data and overall observation data of a target object; the dimension composition data reflects component composition of the target object in each dimension, the dimension value data reflects a display effect of the target object in each dimension, and the overall observation data reflects an overall display effect of the target object.
In this step, the dimension composition data, the dimension value data, and the overall observation data are public data of the target object, the dimension composition data reflects a composition of the target object in each dimension, the dimension value data reflects a display effect of the target object in each dimension, and the overall observation data reflects an overall display effect of the target object.
Illustratively, the target object is a fund;
the dimension composition data refers to: the stock weight of the fund invested in each industry dimension, in this embodiment, the dimension composition data can be obtained through the quarterly newspaper/annual newspaper periodically disclosed by the fund;
the dimension value data is: profitability of the fund in each industry dimension;
the overall observation data is as follows: the overall investment return of the fund.
In a preferred embodiment, the acquiring dimension composition data, dimension value data, and overall observation data of the target object includes:
s11: receiving an object number sent by a control end;
in this step, the object number is a unique identifier of the target object.
S12: identifying a target object corresponding to the object number from a preset database;
in this step, the database is a database server for storing the target object.
S13: and acquiring dimension composition data, dimension value data and overall observation data associated with the target object from the database.
In this step, the dimension composition data, the dimension value data, and the overall observation data are stored in a sub-database in the database, and the sub-database is associated with the target object by the object number.
S202: and performing data cleaning on the dimension composition data, the dimension value data and the overall observation data to eliminate invalid data and missing data in the dimension composition data, the dimension value data and the overall observation data.
In order to ensure the accuracy of the composition of the target object components, the dimension composition data, the dimension value data and the overall observation data are subjected to data cleaning, so that invalid data are eliminated, and the condition that the invalid data interfere with the subsequent component analysis operation is avoided; wherein, the data cleaning refers to the last procedure for finding and correcting recognizable errors in the data file, and is used for processing invalid values, missing values and the like.
In this embodiment, the data cleansing is implemented by dataWrangler software, which is an online data cleansing, data reorganization software developed by stanford university. The method is mainly used for removing invalid data, sorting the data into a format required by a user and the like. By using dataWrangler, the user is able to save time spent on data grooming, thereby allowing him more energy for data analysis.
S203: acquiring component public data and component dimension value data of a target object, acquiring the dimension of the component public data and setting the dimension as dimension public data, and acquiring observation public data according to the component public data and the component dimension value data; deleting the dimension public data in the dimension composition data, and deleting the observation public data in the whole observation data.
In order to delete the published data in the target object to improve the analysis accuracy of the component composition in the target object, the step obtains component public data and component dimension value data of the target object, wherein the component public data refers to: the disclosed components in the target object, and the component dimension value data refers to the effects displayed by the disclosed components; obtaining the dimension of the component public data and setting the dimension as dimension public data, wherein the dimension public data refers to: the dimensions of the disclosed components. Obtaining observation public data according to the component public data and the component dimension value data, wherein the observation public data refers to: the disclosed composition exhibits an overall effect. Therefore, by deleting the dimension public data in the dimension configuration data and deleting the observation public data in the overall observation data, the dimension of the unknown component is only reserved in the dimension configuration data, and the effect of the unknown component is only reserved in the overall observation data, so that the interference on the analysis of the unknown component is eliminated, and the analysis accuracy of the component configuration of the target object is improved.
Illustratively, the component dimension value data refers to: a stock profitability of a specified stock revealed by the fund; in this embodiment, the stock profitability is obtained by calculating an average profitability of the stocks according to the daily stock profitability of the stocks described in the quarterly report of the fund, for example: calculating the daily average rate of return (R) of said stock ten trading days before and after the fund quarter report dayt). The component public data refer to: the equity S that the fund occupies on the disclosed stock; the observation public data refer to: the profit H of the stock is calculated according to the profit rate of the stock and the right of sharestNamely: according to formula Ht＝∑S*RtAnd (6) calculating. Original overall observation data is marked as FtThen the dimension deleting the observation public data constitutes data PtWill pass through the formula Pt＝Ft-HtAnd (4) obtaining. And recording the original dimension configuration data as U, and deleting the dimension in which the component public data is located, namely the dimension public data G, so that the dimension configuration data for deleting the dimension public data is obtained by a formula Q-U-G.
S204: acquiring historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical composition components refer to historical component compositions of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components.
In order to construct a plurality of theoretical component data reflecting the composition of each component in the target object, the step is to construct at least one theoretical component data according to the dimension composition data and the overall observation data by acquiring historical component data of the target object and taking the historical component data as a limiting condition, wherein the current composition of the target object is associated with the historical component data, namely: the method has certain consistency, so that the theoretical component data is constructed according to the dimension construction data and the overall observation data by taking the historical component data as a limiting condition, the possibility of the composition of each component in the target object is analyzed based on the historical component data and the composition of the current component of the target object in each dimension and the effect shown in the whole, and at least one theoretical component data with multiple possibilities is obtained.
In a preferred embodiment, the obtaining the historical component data of the target object includes:
s41: and receiving the object number and the time information sent by the control end.
In this step, the object number is a unique identifier of the target object, and the time information is time data reflecting a certain historical period required by the control end.
S42: and acquiring a target object corresponding to the object number from a preset database, and acquiring a history component set associated with the target object, wherein the history component set at least comprises one history component data.
In this step, the database is a database server for storing a target object, the historical component sets are stored in sub-databases in the database, and the sub-databases are associated with the target object through the object number; the historical component data is marked with the generation time and is stored in the historical component set.
S43: and acquiring historical component data corresponding to the time information from the historical component set.
In this step, a generation time that matches the time information is identified in the history component set, and history component data to which the generation time is marked is acquired.
In a preferred embodiment, the constructing at least one theoretical component data according to the dimension composition data and the overall observation data with the historical component data as a limiting condition includes:
s44: creating a theoretical component matrix and acquiring a preset component transformation limiting threshold, constructing a limiting condition which takes the difference between the theoretical component matrix and the historical component data as a variable and takes the component transformation limiting threshold as the upper limit value of the variable;
the theoretical component matrix is a matrix constructed by taking components in the target object as unknowns, element values in the theoretical component matrix reflect the number of the components in the target object, and the components belonging to the same dimension are arranged on the same row of the theoretical component matrix.
In this step, the limiting conditions are as follows:
s.t.|W-W0|<δ
wherein the theoretical component matrix is W, the historical component data is W0, and the component transformation limit threshold is delta, s.t | W-W0I represents W and W0The difference therebetween accounts for the proportion of the total data in W0; therefore, the above formula represents a theoretical composition matrix, and the variation between the theoretical composition matrix and the historical composition data, which is also shown in a matrix form, accounts for the proportion of the total amount of data in the historical composition data, and is smaller than the composition transformation limit threshold δ.
Illustratively, the theoretical component matrix refers to: related industries of the fund are taken as rows, and stocks belonging to the same industry in a stock pool of the fund are sequentially arranged on the same row in an unknown number mode.
The historical component data refers to: funds have historically been published, reflecting a matrix of the number of its components therein.
The component transformation limit threshold is: the rate of change of each stock in the fund. For example: 1%, 3%, 5%, 10%, etc.
S45: and converting the theoretical component matrix through a preset dimension indication matrix to enable the theoretical component matrix to correspond to the dimension composition data and form a theoretical precalculated expression, wherein the dimension indication matrix is used for marking the dimension of each row in the theoretical component matrix.
In this step, the theoretical budget formula is as follows:
Iind*W＝Q
wherein the dimension indication matrix is IindThe dimension composition data is Q, and the theoretical component matrix is W;
illustratively, the dimension indication matrix IindThe method comprises the following steps: a matrix reflecting the industries invested in the fund, wherein each row represents an investment industry;
the dimension composition data Q is: stock weight reflecting investment of the fund on each industry dimension;
the theoretical composition matrix W is: related industries of the fund are taken as rows, and stocks belonging to the same industry in a stock pool of the fund are sequentially arranged on the same row in an unknown number mode.
S46: and assigning values to the element values in the theoretical component matrix according to the theoretical precomputation and the limiting conditions, so that the theoretical component matrix is converted into theoretical component data.
In this step, a mathematical computation module (such as an xgboost module, MATLAB software, etc.) assigns values of elements in the theoretical component matrix according to the theoretical formula and the constraint condition to obtain at least one theoretical component data satisfying both the theoretical formula and the constraint condition.
S205: theoretical analysis data are obtained according to the theoretical component data and the dimension value data, the theoretical analysis data closest to the overall observation data are identified, the theoretical analysis data are set as analysis results, theoretical component data corresponding to the analysis results are set as component analysis data, and the theoretical analysis data are used for presuming the display effect of the target object based on the theoretical component data.
Identifying theoretical component data which are consistent with the characteristics exhibited by the current target object from a plurality of theoretical component data; obtaining theoretical analysis data according to the theoretical component data and the dimension composition data, identifying the theoretical analysis data closest to the overall observation data through a support vector machine based on an intelligent decision technology, setting the theoretical analysis data as an analysis result, and setting the theoretical component data corresponding to the analysis information as component analysis data; therefore, the component composition of the target object is analyzed, so that a manager can conveniently adjust or control the target object according to needs, the plasticity of the target object is improved, and the application range of the target object is expanded.
In a preferred embodiment, the obtaining theoretical analysis data according to the theoretical component data and the dimensional value data, identifying theoretical analysis data closest to the overall observation data, and setting the theoretical analysis data as an analysis result includes:
s51: and inputting the theoretical component data and the dimension value data into a preset effect formula, and operating the effect formula to obtain theoretical analysis data.
In this step, the effect formula is as follows:
h(Vt)＝W*Vt
wherein h (Vt) is the theoretical analysis data, W is the theoretical combination matrix, VtIt is meant that the dimensions constitute data.
And (3) calculating the effect formula through a preset mathematical calculation module (such as an xgboost module, MATLAB software and the like) to obtain theoretical analysis data.
S52: and calculating Euclidean distances between the overall observation data and each theoretical analysis data through a preset support vector machine, and setting the theoretical analysis data closest to the Euclidean distances between the overall observation data and the theoretical analysis data as an analysis result.
In this step, the support vector machine is a support vector machine running with a least square algorithm, and a target formula of the least square algorithm is as follows:
min∑(h(Vt)-Pt)2
wherein h (Vt) is the theoretical analysis data, PtIs dimension composition data.
And operating the support vector machine, calculating the Euclidean distance between the overall observation data and each theoretical analysis data, and setting the theoretical analysis data closest to the Euclidean distance between the overall observation data and the theoretical analysis data as an analysis result.
Example three:
referring to fig. 4, a component analysis apparatus based on intelligent decision of the present embodiment includes:
the data input module 11 is used for acquiring dimension composition data, dimension value data and overall observation data of the target object; the dimension composition data reflects the composition of the target object in each dimension, the dimension value data reflects the display effect of the target object in each dimension, and the overall observation data reflects the overall display effect of the target object;
a theoretical component module 14, configured to obtain historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical combined components refer to historical component composition of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components;
and a theoretical analysis module 15, configured to obtain theoretical analysis data according to the theoretical component data and the dimensional value data, identify theoretical analysis data closest to the overall observation data, set the theoretical analysis data as an analysis result, and set theoretical component data corresponding to the analysis result as component analysis data, where the theoretical analysis data is used to infer a display effect of the target object based on the theoretical component data.
Optionally, the component analysis apparatus 1 further includes:
and a data cleaning module 12, configured to perform data cleaning on the dimension composition data, the dimension value data, and the overall observation data, so as to eliminate invalid data and missing data in the dimension composition data, the dimension value data, and the overall observation data.
Optionally, the component analysis apparatus 1 based on intelligent decision further includes:
the public processing module 13 is configured to obtain component public data and component dimension value data of a target object, obtain a dimension in which the component public data is located, set the dimension as dimension public data, and obtain observation public data according to the component public data and the component dimension value data; deleting the dimension public data in the dimension composition data, and deleting the observation public data in the whole observation data.
Optionally, the data input module 11 further includes:
a number input unit 111, configured to receive an object number sent by a control end;
an object identifying unit 112 for identifying a target object corresponding to the object number from a preset database;
a data obtaining unit 113, configured to obtain, from the database, dimension composition data, dimension value data, and overall observation data associated with the target object.
Optionally, the theoretical component module 14 further includes:
an analysis input unit 141 for receiving the object number and the time information transmitted from the control terminal;
a history identification unit 142, configured to obtain a target object corresponding to the object number from a preset database, and obtain a history component set associated with the target object, where the history component set at least has one history component data;
a history acquisition unit 143 configured to acquire history component data corresponding to the time information from the history component set;
a condition creating unit 144, configured to create a theoretical component matrix and obtain a preset component transformation limiting threshold, construct a limiting condition that takes a difference between the theoretical component matrix and the historical component data as a variable, and takes the component transformation limiting threshold as an upper limit of the variable;
the budget creating unit 145 is configured to convert the theoretical component matrix through a preset dimension indication matrix, so that the theoretical component matrix corresponds to the dimension configuration data and forms a theoretical precalculation, where the dimension indication matrix is used to label the corresponding dimension of each row in the theoretical component matrix;
and the data calculation unit 146 is configured to assign values to the element values in the theoretical component matrix according to the theoretical precomputation and the limiting condition, so that the theoretical component matrix is converted into theoretical component data.
Optionally, the theoretical analysis module 15 further includes:
and the analysis calculation unit 151 is configured to enter the theoretical component data and the dimension value data into a preset effect formula, and calculate the effect formula to obtain theoretical analysis data.
A theoretical analysis unit 152, configured to calculate an euclidean distance between the overall observation data and each theoretical analysis data through a preset support vector machine, and set, as an analysis result, the theoretical analysis data closest to the euclidean distance between the overall observation data and the theoretical analysis data.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The method is applied to the field of artificial intelligence intelligent decision making, historical component data of a target object are obtained by obtaining dimension composition data, dimension value data and overall observation data of the target object, at least one theoretical component data is constructed according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition, theoretical analysis data is obtained according to the theoretical component data and the dimension value data by taking a support vector machine based on the field of intelligent decision making as a classification model, the theoretical analysis data with the nearest distance to the overall observation data is identified, the theoretical analysis data is set as an analysis result, and the theoretical component data corresponding to the analysis result is set as component analysis data.
Example four:
in order to achieve the above object, the present invention further provides a computer device 5, in which components of the component analysis apparatus based on intelligent decision in the third embodiment can be distributed in different computer devices, and the computer device 5 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster composed of a plurality of application servers) or the like executing a program. The computer device of the embodiment at least includes but is not limited to: a memory 51, a processor 52, which may be communicatively coupled to each other via a system bus, as shown in FIG. 5. It should be noted that fig. 5 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.
In this embodiment, the memory 51 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 51 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 51 may be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 51 may also include both internal and external storage devices of the computer device. In this embodiment, the memory 51 is generally used to store an operating system and various application software installed on the computer device, such as the program code of the intelligent decision-making based component analysis apparatus in the third embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 52 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device. In this embodiment, the processor 52 is configured to run the program code stored in the memory 51 or process data, for example, run the component analysis apparatus based on intelligent decision, so as to implement the component analysis method based on intelligent decision in the first embodiment and the second embodiment.
Example five:
to achieve the above objects, the present invention also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor 52, implements corresponding functions. The computer-readable storage medium of this embodiment is used for storing a computer program for implementing the intelligent decision-based component analysis method, and when being executed by the processor 52, implements the intelligent decision-based component analysis method of the first embodiment and the second embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A component analysis method based on intelligent decision is characterized by comprising the following steps:
acquiring dimension composition data, dimension value data and overall observation data of a target object; the dimension composition data reflects the composition of the target object in each dimension, the dimension value data reflects the display effect of the target object in each dimension, and the overall observation data reflects the overall display effect of the target object;
acquiring historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical combined components refer to historical component composition of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components;
theoretical analysis data are obtained according to the theoretical component data and the dimension value data, the theoretical analysis data closest to the overall observation data are identified, the theoretical analysis data are set as analysis results, theoretical component data corresponding to the analysis results are set as component analysis data, and the theoretical analysis data are used for presuming the display effect of the target object based on the theoretical component data.
2. An intelligent decision-making component analysis method according to claim 1, wherein the obtaining of dimension composition data, dimension value data and overall observation data of the target object comprises:
receiving an object number sent by a control end;
identifying a target object corresponding to the object number from a preset database;
and acquiring dimension composition data, dimension value data and overall observation data associated with the target object from the database.
3. An intelligent decision-making component analysis method according to claim 1, wherein after obtaining dimension composition data, dimension value data and overall observation data of the target object, the method further comprises:
and performing data cleaning on the dimension composition data, the dimension value data and the overall observation data to eliminate invalid data and missing data in the dimension composition data, the dimension value data and the overall observation data.
4. An intelligent decision-making component analysis method according to claim 1, wherein after obtaining dimension composition data, dimension value data and overall observation data of the target object, the method further comprises:
acquiring component public data and component dimension value data of a target object, acquiring the dimension of the component public data and setting the dimension as dimension public data, and acquiring observation public data according to the component public data and the component dimension value data; deleting the dimension public data in the dimension composition data, and deleting the observation public data in the whole observation data.
5. An intelligent decision-making component analysis method according to claim 1, wherein said obtaining historical component data of the target object comprises:
receiving an object number and time information sent by a control end;
acquiring a target object corresponding to the object number from a preset database, and acquiring a history component set associated with the target object, wherein the history component set at least comprises one history component data;
and acquiring historical component data corresponding to the time information from the historical component set.
6. An intelligent decision-making component analysis method according to claim 1, wherein the construction of at least one theoretical component data from the dimension composition data and the overall observation data using the historical component data as a constraint comprises:
creating a theoretical component matrix and acquiring a preset component transformation limiting threshold, constructing a limiting condition which takes the difference between the theoretical component matrix and the historical component data as a variable and takes the component transformation limiting threshold as the upper limit value of the variable;
converting the theoretical component matrix through a preset dimension indication matrix to enable the theoretical component matrix to correspond to the dimension forming data and form a theoretical precalculated expression, wherein the dimension indication matrix is used for marking the dimension of each row in the theoretical component matrix;
and assigning values to the element values in the theoretical component matrix according to the theoretical precomputation and the limiting conditions, so that the theoretical component matrix is converted into theoretical component data.
7. An intelligent decision-making based component analysis method according to claim 1, wherein the obtaining theoretical analysis data from the theoretical component data and the dimensional value data, identifying the theoretical analysis data closest to the overall observation data, and setting the theoretical analysis data as an analysis result comprises:
inputting the theoretical component data and the dimension value data into a preset effect formula, and operating the effect formula to obtain theoretical analysis data;
and calculating Euclidean distances between the overall observation data and each theoretical analysis data through a preset support vector machine, and setting the theoretical analysis data closest to the Euclidean distances between the overall observation data and the theoretical analysis data as an analysis result.
8. An intelligent decision-based component analysis apparatus, comprising:
the data input module is used for acquiring dimension composition data, dimension value data and overall observation data of the target object; the dimension composition data reflects the composition of the target object in each dimension, the dimension value data reflects the display effect of the target object in each dimension, and the overall observation data reflects the overall display effect of the target object;
the theoretical component module is used for acquiring historical component data of the target object; constructing at least one theoretical component data according to the dimension composition data and the overall observation data by taking the historical component data as a limiting condition; the historical combined components refer to historical component composition of the target object, the theoretical component data is a data array formed by displaying the components in a matrix form, and the rows of the data array reflect the dimensions of the components;
and the theoretical analysis module is used for obtaining theoretical analysis data according to the theoretical component data and the dimensional value data, identifying the theoretical analysis data closest to the overall observation data, setting the theoretical analysis data as an analysis result, and setting the theoretical component data corresponding to the analysis result as component analysis data, wherein the theoretical analysis data is used for presuming the display effect of the target object based on the theoretical component data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the intelligent decision-based composition analysis method according to any one of claims 1 to 7 are implemented by the processor of the computer device when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the intelligent decision-based component analysis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111087588.5A CN113792887A (en) | 2021-09-16 | 2021-09-16 | Component analysis method, device and equipment based on intelligent decision and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111087588.5A CN113792887A (en) | 2021-09-16 | 2021-09-16 | Component analysis method, device and equipment based on intelligent decision and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113792887A true CN113792887A (en) | 2021-12-14 |
Family
ID=78878631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111087588.5A Pending CN113792887A (en) | 2021-09-16 | 2021-09-16 | Component analysis method, device and equipment based on intelligent decision and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792887A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8629872B1 (en) * | 2013-01-30 | 2014-01-14 | The Capital Group Companies, Inc. | System and method for displaying and analyzing financial correlation data |
| US20160224896A1 (en) * | 2015-02-03 | 2016-08-04 | International Business Machines Corporation | Group generation using sets of metrics and predicted success values |
| CN108573021A (en) * | 2018-02-24 | 2018-09-25 | 浙江金华伽利略数据科技有限公司 | A kind of comprehensive value appraisal procedure of dynamic data |
| CN108830726A (en) * | 2018-05-09 | 2018-11-16 | 众安信息技术服务有限公司 | Fund pool screening technique and screening plant |
| CN110210978A (en) * | 2018-06-01 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Determine the method, apparatus, equipment and storage medium of fund factor validity |
| CN111126726A (en) * | 2018-10-30 | 2020-05-08 | 北京同方软件有限公司 | Intelligent decision multi-target analysis method based on heterogeneous fusion data |
| CN111782701A (en) * | 2020-05-29 | 2020-10-16 | 上海羽时互联网金融信息服务有限公司 | Method and device for selecting cattle stocks and method and device for screening cross-industry stock data |
-
2021
- 2021-09-16 CN CN202111087588.5A patent/CN113792887A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8629872B1 (en) * | 2013-01-30 | 2014-01-14 | The Capital Group Companies, Inc. | System and method for displaying and analyzing financial correlation data |
| US20160224896A1 (en) * | 2015-02-03 | 2016-08-04 | International Business Machines Corporation | Group generation using sets of metrics and predicted success values |
| CN108573021A (en) * | 2018-02-24 | 2018-09-25 | 浙江金华伽利略数据科技有限公司 | A kind of comprehensive value appraisal procedure of dynamic data |
| CN108830726A (en) * | 2018-05-09 | 2018-11-16 | 众安信息技术服务有限公司 | Fund pool screening technique and screening plant |
| CN110210978A (en) * | 2018-06-01 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Determine the method, apparatus, equipment and storage medium of fund factor validity |
| CN111126726A (en) * | 2018-10-30 | 2020-05-08 | 北京同方软件有限公司 | Intelligent decision multi-target analysis method based on heterogeneous fusion data |
| CN111782701A (en) * | 2020-05-29 | 2020-10-16 | 上海羽时互联网金融信息服务有限公司 | Method and device for selecting cattle stocks and method and device for screening cross-industry stock data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11392838B2 (en) | Method, equipment, computing device and computer-readable storage medium for knowledge extraction based on TextCNN | |
| CN110659318A (en) | Big data based strategy pushing method and system and computer equipment | |
| CN109918498B (en) | Problem warehousing method and device | |
| CN111400471B (en) | Question recommendation method, system, electronic device and storage medium | |
| CN112579727A (en) | Document content extraction method and device, electronic equipment and storage medium | |
| CN108805174A (en) | clustering method and device | |
| CN111625567A (en) | Data model matching method, device, computer system and readable storage medium | |
| CN110288191B (en) | Data matching method, device, computer equipment and storage medium | |
| CN110378543A (en) | Leaving office Risk Forecast Method, device, computer equipment and storage medium | |
| CN113570391A (en) | Community division method, device, equipment and storage medium based on artificial intelligence | |
| CN113792887A (en) | Component analysis method, device and equipment based on intelligent decision and storage medium | |
| CN110597977A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN115860835A (en) | Advertisement recommendation method, device and equipment based on artificial intelligence and storage medium | |
| CN113283677B (en) | Index data processing method, device, equipment and storage medium | |
| Amekraz et al. | An adaptive workload prediction strategy for non-Gaussian cloud service using ARMA model with higher order statistics | |
| CN115116080A (en) | Table analysis method and device, electronic equipment and storage medium | |
| CN113420887A (en) | Prediction model construction method and device, computer equipment and readable storage medium | |
| CN113705468A (en) | Digital image identification method based on artificial intelligence and related equipment | |
| CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN113627514A (en) | Data processing method and device of knowledge graph, electronic equipment and storage medium | |
| CN112182320B (en) | Cluster data processing method, device, computer equipment and storage medium | |
| CN112330468B (en) | Method, device, equipment and storage medium for identifying risk clients | |
| CN116227479B (en) | Entity identification method, entity identification device, computer equipment and readable storage medium | |
| CN116862561B (en) | Product heat analysis method and system based on convolutional neural network | |
| CN112035613B (en) | Information pushing method and device based on multi-round dialogue, storage medium and electronic device |
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 |