CN117236707A - Asset optimization configuration method and device, computer equipment and storage medium - Google Patents
Asset optimization configuration method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117236707A CN117236707A CN202310713624.7A CN202310713624A CN117236707A CN 117236707 A CN117236707 A CN 117236707A CN 202310713624 A CN202310713624 A CN 202310713624A CN 117236707 A CN117236707 A CN 117236707A
- Authority
- CN
- China
- Prior art keywords
- asset
- data
- prediction
- historical
- optimization configuration
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 67
- 238000003062 neural network model Methods 0.000 claims abstract description 66
- 238000012360 testing method Methods 0.000 claims abstract description 58
- 238000002372 labelling Methods 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 33
- 210000002569 neuron Anatomy 0.000 claims description 29
- 230000009466 transformation Effects 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 14
- 230000008569 process Effects 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000013528 artificial neural network Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008676 import Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an asset optimization configuration method, an asset optimization configuration device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence and the field of financial asset configuration. According to the method, historical asset data are obtained, the historical asset data are marked, the marked historical asset data are subjected to data set division to obtain a training set and a testing set, a preset neural network model is trained through the training set, the trained neural network model is adjusted through the testing set to obtain an asset prediction model, asset data to be predicted are obtained, the asset data to be predicted are imported into the asset prediction model to obtain an asset prediction result, a matched asset optimization configuration combination is selected according to the asset prediction result, and the asset optimization configuration combination is output. In addition, the present application relates to blockchain technology in which asset data to be predicted may be stored. According to the method, the manpower investment and the subjectivity of prediction in the asset profit prediction process are reduced, and the prediction efficiency is improved.
Description
Technical Field
The application belongs to the technical field of artificial intelligence and the field of financial asset allocation, and particularly relates to an asset optimization allocation method, an asset optimization allocation device, computer equipment and a storage medium.
Background
The enterprise large-class asset allocation planning and asset profit prediction are important works of strategic allocation departments, the existing mode is that the lower large-class asset allocation planning and profit prediction are independently cut, an asset allocation system usually obtains large-class asset allocation planning according to a model, an allocation planning post adjusts to obtain optimal allocation and derives asset allocation planning data to an asset profit prediction post, and the asset profit prediction post manually calculates asset profit of each asset in the future year/quarter according to the allocation planning data received offline. Therefore, the prediction of asset benefit of most enterprises at present is performed by manpower, a large amount of manpower is required to be input, the efficiency is low, and a certain subjectivity exists.
Disclosure of Invention
The embodiment of the application aims to provide an asset optimization configuration method, an asset optimization configuration device, computer equipment and a storage medium, so as to solve the technical problems that a great amount of manpower is required to be input, the efficiency is low and a certain subjectivity exists in the existing asset optimization configuration scheme.
In order to solve the technical problems, the embodiment of the application provides an asset optimization configuration method, which adopts the following technical scheme:
an asset optimization configuration method, comprising:
acquiring historical asset data, wherein the historical asset data comprises taken warehouse data, transaction data, income data and default data;
preprocessing the historical asset data and labeling the preprocessed historical asset data, wherein labeling the preprocessed historical asset data comprises labeling the holding data, the transaction data, the income data and the default data respectively;
carrying out data set division on the marked historical asset data to obtain a training set and a testing set;
training a preset neural network model through the training set, and adjusting the trained neural network model by utilizing the testing set to obtain an asset prediction model;
acquiring asset data to be predicted, and importing the asset data to be predicted into the asset prediction model to obtain an asset prediction result;
and selecting a matched asset optimization configuration combination according to the asset prediction result, and outputting the asset optimization configuration combination.
Further, the preprocessing includes data deduplication, normalization processing and missing value processing, the preprocessing is performed on the historical asset data, and the preprocessed historical asset data is marked, which specifically includes:
sequentially carrying out data deduplication, standardization processing and missing value processing on the historical asset data;
obtaining a labeling label, wherein the labeling label comprises a warehouse holding label, a transaction label, a profit label and a default label;
extracting keywords from the historical asset data, and respectively matching the extracted keywords with the labeling labels;
and marking the historical asset data according to the matching result.
Further, the neural network model is a multi-layer perceptron, the neural network model comprises an input layer, a hidden layer and an output layer, and the training of the preset neural network model by the training set specifically comprises the following steps:
extracting features of training samples in the training set through the input layer to obtain a plurality of sample features;
performing nonlinear transformation on all the sample characteristics through the hidden layer, and mapping the sample characteristics after the nonlinear transformation to the same high-dimensional space;
And obtaining a sample feature combination from the high-dimensional space, and outputting the sample feature combination through an activation function in the output layer to obtain an asset prediction result corresponding to the training sample.
Further, the hidden layer includes a plurality of neurons, and the method includes performing nonlinear transformation on all the sample features through the hidden layer, and mapping the sample features after the nonlinear transformation to a same high-dimensional space, which specifically includes:
sequentially introducing the sample features into neurons of the hidden layer, wherein each of the neurons receives an input of one of the sample features;
acquiring a weight value of a neuron, and weighting an output vector of the corresponding neuron according to the weight value;
mapping the weighted output vector to the same high-dimensional space.
Further, the training neural network model is adjusted by using the test set to obtain an asset prediction model, which specifically includes:
importing the test samples in the test set into the trained neural network model, and outputting asset prediction results corresponding to the test samples;
comparing the asset prediction result corresponding to the test sample with the labeling label of the test sample to obtain a prediction error;
Comparing the prediction error with a preset error threshold;
and if the prediction error is greater than the preset error threshold, adjusting model parameters of the trained neural network model until the prediction error is less than or equal to the preset error threshold, so as to obtain the asset prediction model.
Further, the comparing the prediction error with a preset error threshold specifically includes:
transmitting the prediction error in each network layer of the neural network model based on a back propagation algorithm to obtain error parameters of each network layer;
and comparing the error parameters of each network layer with the preset error threshold value respectively.
Further, selecting a matched asset optimization configuration combination according to the asset prediction result, and outputting the asset optimization configuration combination, which specifically comprises the following steps:
calculating the configuration duty ratio of various assets in the asset data to be predicted based on the asset prediction result by using a preset mean variance model;
determining a matched asset optimization configuration combination in a preset configuration library according to the configuration duty ratio of various assets in the asset data to be predicted;
outputting the asset optimization configuration combination.
In order to solve the technical problems, the embodiment of the application also provides an asset optimization configuration device, which adopts the following technical scheme:
an asset optimization configuration device comprising:
the data acquisition module is used for acquiring historical asset data, wherein the historical asset data comprises warehouse holding data, transaction data, income data and default data;
the data processing module is used for preprocessing the historical asset data and labeling the preprocessed historical asset data, wherein labeling the preprocessed historical asset data comprises labeling the warehouse holding data, the transaction data, the income data and the default data respectively;
the data dividing module is used for dividing the data set of the marked historical asset data to obtain a training set and a testing set;
the model training module is used for training a preset neural network model through the training set, and adjusting the trained neural network model by utilizing the testing set to obtain an asset prediction model;
the asset prediction module is used for acquiring asset data to be predicted, and importing the asset data to be predicted into the asset prediction model to obtain an asset prediction result;
And the asset configuration module is used for selecting a matched asset optimization configuration combination according to the asset prediction result and outputting the asset optimization configuration combination.
In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:
a computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the asset optimization configuration method of any of the preceding claims.
In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:
a computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the asset optimization configuration method of any of the above claims.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
the application discloses an asset optimization configuration method and device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence and the field of financial asset configuration. According to the method, historical asset data are obtained, the historical asset data are preprocessed, the preprocessed historical asset data are marked, the marked historical asset data are subjected to data set division to obtain a training set and a testing set, a preset neural network model is trained through the training set, the trained neural network model is adjusted through the testing set to obtain an asset prediction model, asset data to be predicted are obtained, the asset data to be predicted are imported into the asset prediction model to obtain an asset prediction result, a matched asset optimization configuration combination is selected according to the asset prediction result, and the asset optimization configuration combination is output. According to the application, the asset prediction model is trained through the neural network, the profit data of the current asset data is predicted through the asset prediction model, and the labor investment and the subjectivity of prediction in the asset profit prediction process are reduced through the asset optimization configuration combination of automatic matching of the predicted profit data, so that the prediction efficiency is improved.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 illustrates an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 illustrates a flow chart of one embodiment of an asset optimization configuration method in accordance with the present application;
FIG. 3 illustrates a schematic diagram of one embodiment of an asset optimization configuration device according to the present application;
fig. 4 shows a schematic structural diagram of an embodiment of a computer device according to the application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server that provides various services, such as a background server that provides support for pages displayed on the terminal devices 101, 102, 103, and may be a stand-alone server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
It should be noted that, the asset optimization configuration method provided by the embodiment of the application is generally executed by a server, and correspondingly, the asset optimization configuration device is generally arranged in the server.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow chart of one embodiment of an asset optimization configuration method according to the present application is shown. The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include 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 other directions.
In the existing asset configuration scheme, a large-class asset configuration plan is generally obtained through an asset configuration system according to a model, a configuration planning post is adjusted to obtain optimal configuration, asset configuration planning data are exported to an asset profit prediction post, asset profit of each asset in the future is calculated manually according to the configuration planning data received offline, a large amount of labor is required to be input, efficiency is low, and a certain subjectivity exists.
In order to solve the technical problems, the application discloses an asset optimization configuration method, an asset optimization configuration device, computer equipment and a storage medium, belongs to the technical field of artificial intelligence and the field of financial asset configuration, trains an asset prediction model through a neural network, predicts the income data of current asset data through the asset prediction model, and reduces the manpower investment and the subjectivity of prediction in the asset income prediction process through the asset optimization configuration combination of automatic matching of the predicted income data so as to improve the prediction efficiency.
The asset optimization configuration method comprises the following steps:
s201, historical asset data is acquired, wherein the historical asset data comprises warehouse holding data, transaction data, income data and default data.
In this embodiment, before asset prediction is performed, an asset prediction model is trained through historical asset data so as to predict a profit situation of the asset data, where the server invokes the historical asset data from the enterprise database, and the historical asset data includes at least a holding data, a transaction data, a profit data, and a default data.
In other embodiments, the historical asset data may further include indexes such as a volatility, a summer ratio, an information ratio, a maximum withdrawal, and the like, so that the trained asset prediction model has higher prediction precision and can predict more parameter indexes by acquiring the historical asset data with more indexes.
S202, preprocessing the historical asset data and labeling the preprocessed historical asset data, wherein labeling the preprocessed historical asset data comprises labeling the holding data, the transaction data, the income data and the default data respectively.
The preprocessing at least comprises data deduplication, standardization processing and missing value processing, and the history asset data is enabled to be more in accordance with the model training standard through the preprocessing, so that the model training efficiency is improved, and the neural network is convenient to learn more characteristics.
In this embodiment, the server performs data normalization operations such as data deduplication, normalization processing, and missing value processing on the historical asset data, and then obtains a labeling tag, and labels the preprocessed historical asset data by the labeling tag, where labeling the preprocessed historical asset data includes labeling the holding data, the transaction data, the profit data, and the default data, respectively.
Further, preprocessing the historical asset data and labeling the preprocessed historical asset data, and specifically comprises the following steps:
sequentially carrying out data deduplication, standardization processing and missing value processing on the historical asset data;
Obtaining a labeling label, wherein the labeling label comprises a warehouse holding label, a transaction label, a benefit label and a default label;
extracting keywords from the historical asset data, and respectively matching the extracted keywords with the labeling labels;
and marking the historical asset data according to the matching result.
In this embodiment, the server sequentially performs data deduplication, normalization processing, and missing value processing on the historical asset data, wherein the normalization processing causes all values of the historical asset data to fall between [0,1], and the missing value processing fills the item with a true value with "0". And then the server acquires labeling labels, wherein the labeling labels comprise a warehouse holding label, a transaction label, a profit label and a default label, and the labeling of the historical asset data is completed by extracting keywords from the historical asset data and respectively matching the extracted keywords with the labeling labels. For example, taking the "avail" tag as an example, all data related to the "avail" keyword is extracted from the historical asset data, and the "avail" tag is inserted for these data.
S203, carrying out data set division on the marked historical asset data to obtain a training set and a testing set.
In this embodiment, after the labeling operation is completed, the server executes a data set dividing program, and performs data set division on the labeled historical asset data to obtain a training set and a testing set. The training set is used for training the neural network model, and the testing set is used for performing parameter tuning on the trained neural network model, so that the neural network model is fitted.
S204, training a preset neural network model through a training set, and adjusting the trained neural network model by utilizing a testing set to obtain an asset prediction model.
In this embodiment, the server trains the neural network model through the training set by introducing the training set into a preset neural network model, and performs parameter tuning on the trained neural network model through the testing set, so that the neural network model is fitted, and an asset prediction model is obtained.
It should be noted that in the embodiment of the present application, various neural network models may be selected to construct the asset prediction model, for example, a linear regression model, a random forest model, a support vector machine, a convolutional neural network model, and the like.
Further, in a specific embodiment of the present application, the neural network model is a multi-layer perceptron, the neural network model includes an input layer, a hidden layer and an output layer, and the training set is used to train a preset neural network model, which specifically includes:
Extracting features of training samples in a training set through an input layer to obtain a plurality of sample features;
carrying out nonlinear transformation on all sample characteristics through a hidden layer, and mapping the sample characteristics after nonlinear transformation to the same high-dimensional space;
and obtaining a sample feature combination from the high-dimensional space, and outputting the sample feature combination through an activation function in an output layer to obtain an asset prediction result corresponding to the training sample.
In this embodiment, the neural network model is a multi-layer perceptron (MLP), which can handle multiple input variables and multiple output variables. In the training process of the model, the historical data is divided into a training set and a testing set, and model parameters are optimized by using a back propagation algorithm, so that the accuracy of prediction is improved.
The MLP model comprises 1 input layer, a plurality of hidden layers and 1 output layer, wherein the input layer is used for extracting the characteristics of a training sample; the hidden layer is used for carrying out nonlinear transformation on the sample characteristics, and mapping the sample characteristics after the nonlinear transformation to the same high-dimensional space so as to better capture the complex relation between the characteristics, and the arrangement of the number of neurons and the number of layers of the hidden layer is very important, so that the expression capacity and the training effect of the model can be directly influenced; an activation function is built in the output layer, and the main function is to introduce nonlinear feature mapping, enhance the expression capacity of the model, and facilitate nonlinear feature transformation and output. Common activation functions include Sigmoid, reLU, leakyReLU, tanh, etc., and different activation functions are applicable to different problems and scenes, and need to be selected according to specific situations.
Further, the hidden layer includes a plurality of neurons, and performs nonlinear transformation on all sample features through the hidden layer, and maps the sample features after the nonlinear transformation to the same high-dimensional space, which specifically includes:
sequentially importing sample features into neurons of a hidden layer, wherein each neuron receives an input of one sample feature;
acquiring a weight value of a neuron, and weighting an output vector of the corresponding neuron through the weight value;
and mapping the weighted output vector to the same high-dimensional space.
Each hidden layer contains a plurality of neurons, which are the basic units in the network, each neuron receives a set of inputs, performs weighted summation on the inputs, and obtains outputs through nonlinear processing of the activation function. The weights and biases of the neurons are the learnable parameters of the model, updated by a back propagation algorithm to minimize the loss function.
In this embodiment, the server sequentially imports the sample features into neurons of the hidden layer, wherein each neuron is arranged to receive an input of one sample feature, then obtains a weight value of each neuron, weights output vectors of the corresponding neurons by the weight value, and maps the weighted output vectors to the same high-dimensional space. The complex relation between the features is represented by a weighted summation mode and mapped in the same high-dimensional space, so that the features of the training samples are intensively represented.
Further, the trained neural network model is adjusted by using the test set to obtain an asset prediction model, which specifically comprises:
importing the test samples in the test set into a trained neural network model, and outputting asset prediction results corresponding to the test samples;
comparing the asset prediction result corresponding to the test sample with the labeling label of the test sample to obtain a prediction error;
comparing the prediction error with a preset error threshold;
and if the prediction error is greater than the preset error threshold, adjusting model parameters of the trained neural network model until the prediction error is less than or equal to the preset error threshold, so as to obtain an asset prediction model.
In this embodiment, the server imports the test sample in the test set into the trained neural network model, outputs the asset prediction result corresponding to the test sample, and the processing mode of the test sample in the trained neural network model is consistent with the processing mode of the training sample in the neural network model, which sequentially passes through the input layer, the hidden layer and the output layer, so as to finally obtain the asset prediction result. After the asset prediction result is obtained, the server calculates the error between the asset prediction result corresponding to the test sample and the labeling label of the test sample through the loss function of the neural network model to obtain a prediction error, transmits the prediction error in the neural network model, compares the prediction error with a preset error threshold, and adjusts model parameters of the trained neural network model, such as weight values and bias values of neurons, if the prediction error is larger than the preset error threshold, until the prediction error is smaller than or equal to the preset error threshold, so as to obtain the asset prediction model.
Further, comparing the prediction error with a preset error threshold value specifically includes:
transmitting prediction errors in each network layer of the neural network model based on a back propagation algorithm to obtain error parameters of each network layer;
and comparing the error parameters of each network layer with preset error thresholds respectively.
In this embodiment, the server transmits the prediction error in each network layer of the neural network model through the back propagation algorithm, so as to ensure that each network layer can obtain a corresponding error value, namely an error parameter, and then compares the error parameter of each network layer with a preset error threshold value, identifies the network layer in which the error parameter is greater than the preset error threshold value, and performs parameter tuning on the network layer in which the error parameter is greater than the preset error threshold value until the error parameters of all network layers are less than or equal to the preset error threshold value, and at this time, the model is fitted to obtain the asset prediction model after training is completed.
S205, acquiring asset data to be predicted, and importing the asset data to be predicted into an asset prediction model to obtain an asset prediction result.
In this embodiment, when an asset configuration instruction is received, corresponding asset data to be predicted is obtained based on the asset configuration instruction, and the asset data to be predicted is imported into an asset prediction model to obtain an asset prediction result, where the asset prediction result at least includes a yield, a volatility, a market index, and the like.
In this embodiment, the electronic device (for example, the server shown in fig. 1) on which the asset optimization configuration method operates may receive the asset configuration instruction through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means.
S206, selecting a matched asset optimization configuration combination according to the asset prediction result, and outputting the asset optimization configuration combination.
In this embodiment, the asset prediction result is imported into a preset mean variance model to obtain an asset allocation duty ratio, and then a suitable asset optimization configuration combination is matched according to the asset allocation duty ratio, and the asset optimization configuration combination is output.
Further, selecting a matched asset optimization configuration combination according to the asset prediction result, and outputting the asset optimization configuration combination, which specifically comprises the following steps:
calculating configuration duty ratios of various assets in asset data to be predicted based on asset prediction results by using a preset mean variance model;
determining a matched asset optimization configuration combination in a preset configuration library according to the configuration duty ratio of various assets in asset data to be predicted;
And outputting asset optimization configuration combinations.
In this embodiment, the asset prediction result is imported into a preset mean variance model, the expected benefit rate and the risk benefit rate are calculated through the mean variance model, meanwhile, the covariance between different assets is required to be calculated to reflect the association degree between the different assets, then, according to the mean variance theory, the effective leading edge (Efficient Frontier) of each type of asset under different benefit rates and risk levels can be obtained, the configuration proportion with the highest benefit rate and the smallest risk is selected, the asset optimization configuration combination matching the configuration proportion is determined in a preset configuration library, and the asset optimization configuration combination is output.
In other embodiments of the present application, after the asset optimization configuration combination is determined, the optimization of asset configuration may be further performed by using the mean variance model, and by minimizing the variance of the combination, a better asset configuration scheme may be found, and in actual operation, mathematical tools such as linear programming may be used to solve the optimization problem.
In the above embodiment, the application discloses an asset optimization configuration method, which belongs to the technical field of artificial intelligence and the field of financial asset configuration. According to the method, historical asset data are obtained, the historical asset data are preprocessed, the preprocessed historical asset data are marked, the marked historical asset data are subjected to data set division to obtain a training set and a testing set, a preset neural network model is trained through the training set, the trained neural network model is adjusted through the testing set to obtain an asset prediction model, asset data to be predicted are obtained, the asset data to be predicted are imported into the asset prediction model to obtain an asset prediction result, a matched asset optimization configuration combination is selected according to the asset prediction result, and the asset optimization configuration combination is output. According to the application, the asset prediction model is trained through the neural network, the profit data of the current asset data is predicted through the asset prediction model, and the labor investment and the subjectivity of prediction in the asset profit prediction process are reduced through the asset optimization configuration combination of automatic matching of the predicted profit data, so that the prediction efficiency is improved.
It is emphasized that to further ensure the privacy and security of the asset data to be predicted, the asset data to be predicted may also be stored in a node of a blockchain.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Those skilled in the art will appreciate that implementing all or part of the processes of the methods of the embodiments described above may be accomplished by way of computer readable instructions, stored on a computer readable storage medium, which when executed may comprise processes of embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an asset optimization configuration device, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device is specifically applicable to various electronic devices.
As shown in fig. 3, the asset optimization configuration device 300 according to the present embodiment includes:
a data acquisition module 301, configured to acquire historical asset data, where the historical asset data includes a taken data, a transaction data, a profit data, and a default data;
The data processing module 302 is configured to pre-process the historical asset data and label the pre-processed historical asset data, where labeling the pre-processed historical asset data includes labeling the holding data, the transaction data, the profit data, and the default data, respectively;
the data dividing module 303 is configured to divide the data set of the annotated historical asset data to obtain a training set and a testing set;
the model training module 304 is configured to train a preset neural network model through a training set, and adjust the trained neural network model by using a test set to obtain an asset prediction model;
the asset prediction module 305 is configured to obtain asset data to be predicted, and import the asset data to be predicted into the asset prediction model to obtain an asset prediction result;
the asset configuration module 306 is configured to select a matched asset optimization configuration combination according to the asset prediction result, and output the asset optimization configuration combination.
Further, the preprocessing includes data deduplication, normalization, and missing value processing, and the data processing module 302 specifically includes:
the preprocessing unit is used for sequentially carrying out data deduplication, standardization processing and missing value processing on the historical asset data;
The label acquisition unit is used for acquiring label labels, wherein the label labels comprise a warehouse holding label, a transaction label, a profit label and a default label;
the tag matching unit is used for extracting keywords from the historical asset data and respectively matching the extracted keywords with the labeling tags;
and the marking unit is used for marking the historical asset data according to the matching result.
Further, the neural network model is a multi-layer perceptron, the neural network model includes an input layer, a hidden layer, and an output layer, and the model training module 304 specifically includes:
the feature extraction unit is used for extracting features of training samples in the training set through the input layer to obtain a plurality of sample features;
the feature mapping unit is used for carrying out nonlinear transformation on all sample features through the hidden layer and mapping the sample features after the nonlinear transformation to the same high-dimensional space;
and the result output unit is used for acquiring the sample feature combination from the high-dimensional space, and outputting the sample feature combination through an activation function in the output layer to obtain an asset prediction result corresponding to the training sample.
Further, the hidden layer includes a plurality of neurons, and the feature mapping unit specifically includes:
A feature importing subunit, configured to import sample features into neurons of the hidden layer in sequence, where each neuron receives an input of a sample feature;
the weighting sub-unit is used for acquiring the weight value of the neuron and weighting the output vector of the corresponding neuron through the weight value;
and the mapping subunit is used for mapping the weighted output vectors to the same high-dimensional space.
Further, the model training module 304 specifically includes:
the test unit is used for importing test samples in the test set into the trained neural network model and outputting asset prediction results corresponding to the test samples;
the error calculation unit is used for comparing the asset prediction result corresponding to the test sample with the labeling label of the test sample to obtain a prediction error;
the error comparison unit is used for comparing the prediction error with a preset error threshold value;
and the model adjusting unit is used for adjusting model parameters of the trained neural network model when the prediction error is larger than a preset error threshold value until the prediction error is smaller than or equal to the preset error threshold value, so as to obtain an asset prediction model.
Further, the error comparison unit specifically includes:
The error transmission subunit is used for transmitting the prediction error in each network layer of the neural network model based on the back propagation algorithm to obtain error parameters of each network layer;
and the error comparison subunit is used for respectively comparing the error parameters of each network layer with a preset error threshold value.
Further, the asset configuration module 306 specifically includes:
the average variance calculation unit is used for calculating the configuration duty ratio of various assets in the asset data to be predicted based on the asset prediction result by using a preset average variance model;
the optimizing configuration matching unit is used for determining a matched asset optimizing configuration combination in a preset configuration library according to the configuration proportion of various assets in the asset data to be predicted;
and the configuration combination output unit is used for outputting the asset optimization configuration combination.
In the embodiment, the application discloses an asset optimization configuration device, and belongs to the technical field of artificial intelligence and the field of financial asset configuration. According to the method, historical asset data are obtained, the historical asset data are preprocessed, the preprocessed historical asset data are marked, the marked historical asset data are subjected to data set division to obtain a training set and a testing set, a preset neural network model is trained through the training set, the trained neural network model is adjusted through the testing set to obtain an asset prediction model, asset data to be predicted are obtained, the asset data to be predicted are imported into the asset prediction model to obtain an asset prediction result, a matched asset optimization configuration combination is selected according to the asset prediction result, and the asset optimization configuration combination is output. According to the application, the asset prediction model is trained through the neural network, the profit data of the current asset data is predicted through the asset prediction model, and the labor investment and the subjectivity of prediction in the asset profit prediction process are reduced through the asset optimization configuration combination of automatic matching of the predicted profit data, so that the prediction efficiency is improved.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of an asset optimization configuration method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing the asset optimization configuration method.
The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.
In the above embodiment, the application discloses a computer device, which belongs to the technical field of artificial intelligence and the field of financial asset configuration. According to the method, historical asset data are obtained, the historical asset data are preprocessed, the preprocessed historical asset data are marked, the marked historical asset data are subjected to data set division to obtain a training set and a testing set, a preset neural network model is trained through the training set, the trained neural network model is adjusted through the testing set to obtain an asset prediction model, asset data to be predicted are obtained, the asset data to be predicted are imported into the asset prediction model to obtain an asset prediction result, a matched asset optimization configuration combination is selected according to the asset prediction result, and the asset optimization configuration combination is output. According to the application, the asset prediction model is trained through the neural network, the profit data of the current asset data is predicted through the asset prediction model, and the labor investment and the subjectivity of prediction in the asset profit prediction process are reduced through the asset optimization configuration combination of automatic matching of the predicted profit data, so that the prediction efficiency is improved.
The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the asset optimization configuration method as described above.
In the above embodiments, the present application discloses a storage medium, which belongs to the technical field of artificial intelligence and the field of financial asset allocation. According to the method, historical asset data are obtained, the historical asset data are preprocessed, the preprocessed historical asset data are marked, the marked historical asset data are subjected to data set division to obtain a training set and a testing set, a preset neural network model is trained through the training set, the trained neural network model is adjusted through the testing set to obtain an asset prediction model, asset data to be predicted are obtained, the asset data to be predicted are imported into the asset prediction model to obtain an asset prediction result, a matched asset optimization configuration combination is selected according to the asset prediction result, and the asset optimization configuration combination is output. According to the application, the asset prediction model is trained through the neural network, the profit data of the current asset data is predicted through the asset prediction model, and the labor investment and the subjectivity of prediction in the asset profit prediction process are reduced through the asset optimization configuration combination of automatic matching of the predicted profit data, so that the prediction efficiency is improved.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
The application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (10)
1. An asset optimization configuration method, comprising:
acquiring historical asset data, wherein the historical asset data comprises taken warehouse data, transaction data, income data and default data;
preprocessing the historical asset data and labeling the preprocessed historical asset data, wherein labeling the preprocessed historical asset data comprises labeling the holding data, the transaction data, the income data and the default data respectively;
Carrying out data set division on the marked historical asset data to obtain a training set and a testing set;
training a preset neural network model through the training set, and adjusting the trained neural network model by utilizing the testing set to obtain an asset prediction model;
acquiring asset data to be predicted, and importing the asset data to be predicted into the asset prediction model to obtain an asset prediction result;
and selecting a matched asset optimization configuration combination according to the asset prediction result, and outputting the asset optimization configuration combination.
2. The asset optimization configuration method of claim 1, wherein the preprocessing comprises data deduplication, normalization and missing value processing, the preprocessing is performed on the historical asset data, and the preprocessed historical asset data is marked, specifically comprising:
sequentially carrying out data deduplication, standardization processing and missing value processing on the historical asset data;
obtaining a labeling label, wherein the labeling label comprises a warehouse holding label, a transaction label, a profit label and a default label;
extracting keywords from the historical asset data, and respectively matching the extracted keywords with the labeling labels;
And marking the historical asset data according to the matching result.
3. The asset optimization configuration method of claim 1, wherein the neural network model is a multi-layer perceptron, the neural network model comprises an input layer, a hidden layer and an output layer, and the training of the preset neural network model by the training set specifically comprises:
extracting features of training samples in the training set through the input layer to obtain a plurality of sample features;
performing nonlinear transformation on all the sample characteristics through the hidden layer, and mapping the sample characteristics after the nonlinear transformation to the same high-dimensional space;
and obtaining a sample feature combination from the high-dimensional space, and outputting the sample feature combination through an activation function in the output layer to obtain an asset prediction result corresponding to the training sample.
4. The asset optimization configuration method of claim 3, wherein the hidden layer comprises a plurality of neurons, the non-linear transformation is performed on all the sample features through the hidden layer, and the sample features after the non-linear transformation are mapped to the same high-dimensional space, specifically comprising:
Sequentially introducing the sample features into neurons of the hidden layer, wherein each of the neurons receives an input of one of the sample features;
acquiring a weight value of a neuron, and weighting an output vector of the corresponding neuron according to the weight value;
mapping the weighted output vector to the same high-dimensional space.
5. The asset optimization configuration method of claim 3, wherein the training neural network model is adjusted by using the test set to obtain an asset prediction model, and the method specifically comprises:
importing the test samples in the test set into the trained neural network model, and outputting asset prediction results corresponding to the test samples;
comparing the asset prediction result corresponding to the test sample with the labeling label of the test sample to obtain a prediction error;
comparing the prediction error with a preset error threshold;
and if the prediction error is greater than the preset error threshold, adjusting model parameters of the trained neural network model until the prediction error is less than or equal to the preset error threshold, so as to obtain the asset prediction model.
6. The asset optimization configuration method of claim 5, wherein the comparing the prediction error with a preset error threshold specifically comprises:
transmitting the prediction error in each network layer of the neural network model based on a back propagation algorithm to obtain error parameters of each network layer;
and comparing the error parameters of each network layer with the preset error threshold value respectively.
7. The asset optimization configuration method according to any one of claims 1 to 6, characterized by selecting a matched asset optimization configuration combination according to the asset prediction result, and outputting the asset optimization configuration combination, and specifically comprising:
calculating the configuration duty ratio of various assets in the asset data to be predicted based on the asset prediction result by using a preset mean variance model;
determining a matched asset optimization configuration combination in a preset configuration library according to the configuration duty ratio of various assets in the asset data to be predicted;
outputting the asset optimization configuration combination.
8. An asset optimization configuration device, comprising:
the data acquisition module is used for acquiring historical asset data, wherein the historical asset data comprises warehouse holding data, transaction data, income data and default data;
The data processing module is used for preprocessing the historical asset data and labeling the preprocessed historical asset data, wherein labeling the preprocessed historical asset data comprises labeling the warehouse holding data, the transaction data, the income data and the default data respectively;
the data dividing module is used for dividing the data set of the marked historical asset data to obtain a training set and a testing set;
the model training module is used for training a preset neural network model through the training set, and adjusting the trained neural network model by utilizing the testing set to obtain an asset prediction model;
the asset prediction module is used for acquiring asset data to be predicted, and importing the asset data to be predicted into the asset prediction model to obtain an asset prediction result;
and the asset configuration module is used for selecting a matched asset optimization configuration combination according to the asset prediction result and outputting the asset optimization configuration combination.
9. A computer device comprising a memory having stored therein computer readable instructions which when executed by the processor implement the steps of the asset optimization configuration method of any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the asset optimization configuration method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310713624.7A CN117236707A (en) | 2023-06-15 | 2023-06-15 | Asset optimization configuration method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310713624.7A CN117236707A (en) | 2023-06-15 | 2023-06-15 | Asset optimization configuration method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117236707A true CN117236707A (en) | 2023-12-15 |
Family
ID=89083287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310713624.7A Pending CN117236707A (en) | 2023-06-15 | 2023-06-15 | Asset optimization configuration method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117236707A (en) |
-
2023
- 2023-06-15 CN CN202310713624.7A patent/CN117236707A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112925911A (en) | Complaint classification method based on multi-modal data and related equipment thereof | |
| CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN115099326A (en) | Behavior prediction method, behavior prediction device, behavior prediction equipment and storage medium based on artificial intelligence | |
| CN116402625B (en) | Customer evaluation method, apparatus, computer device and storage medium | |
| CN117234844A (en) | Cloud server abnormality management method and device, computer equipment and storage medium | |
| CN116777646A (en) | Artificial intelligence-based risk identification method, apparatus, device and storage medium | |
| CN117093477A (en) | Software quality assessment method and device, computer equipment and storage medium | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN115392361A (en) | Intelligent sorting method and device, computer equipment and storage medium | |
| CN117236707A (en) | Asset optimization configuration method and device, computer equipment and storage medium | |
| CN113792342B (en) | Desensitization data reduction method, device, computer equipment and storage medium | |
| CN116307742B (en) | Risk identification method, device and equipment for subdivision guest group and storage medium | |
| CN116934506A (en) | User behavior prediction method and device, computer equipment and storage medium | |
| CN117312991B (en) | Method for constructing classification recognition system and related equipment thereof | |
| CN116756147A (en) | Data classification method, device, computer equipment and storage medium | |
| CN117252712A (en) | Product claim settlement method, device, equipment and storage medium based on transfer learning | |
| CN117611352A (en) | Vehicle insurance claim processing method, device, computer equipment and storage medium | |
| CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
| CN117078406A (en) | Customer loss early warning method and device, computer equipment and storage medium | |
| CN116775776A (en) | Multi-label text classification method, device, computer equipment and storage medium | |
| CN117217812A (en) | User behavior prediction method and device, computer equipment and storage medium | |
| CN117034114A (en) | Data prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN117709801A (en) | Client data processing method, device, computer equipment and storage medium | |
| CN116757771A (en) | Scheme recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN117235257A (en) | Emotion prediction method, device, equipment and storage medium based on artificial intelligence |
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 |