44 results about "Market prediction" patented technology

The invention discloses a method for scale prediction of a regional distributed type comprehensive energy-supply system. A scenario analysis method, a factor correlation analysis method and a market predicting model method are selected for conducting comprehensive prediction at different angles; prediction models are respectively established combined with the three prediction methods and prediction condition setting and prediction parameter setting are conducted on the three modules respectively; parameters and conditions are introduced into the prediction modules to obtain prediction results; the prediction results of the three methods are processed through an equal-weight allocation method, the stability and the practicability of the prediction results can be improved, and therefore a relatively-reasonable scale prediction value of the regional distributed type comprehensive energy-supply system is obtained. The method is simple in principle, diversified in prediction angle, good in prediction accuracy, capable of accurately predicting the development scale of a future distribution type comprehensive energy-supply system of each region and directing development and construction of the regional distributed type comprehensive energy-supply system, and high in practicability and popularization.

The invention provides a deep-learning-based method for predicting a stock market. The method comprises the following steps of data pretreatment and construction of an LSTM-DCC stock market predictionmodel. According to the invention, on the basis of combination of advantages of an expansion cause-and-effect convolution network and a recurrent neural network, data features of an own stock sequence and correlated influence factors are learned automatically and thus the future price and trend are predicted.

The invention provides a power market aided decision-making system comprising a basic information acquisition module, a market prediction analysis module, a transaction simulation deduction module, abid strategy evaluation module, a break-even analysis module and a transaction replay analysis module. The advantages are that the power market aided decision-making system provided by the invention becomes an independent and comprehensive closed-loop transaction aided decision-making system through the functional modules for collection and analysis of basic information related to the power market, market prediction, transaction simulation deduction, bid strategy evaluation, break-even analysis and transaction replay, provides an efficient, fast, comprehensive and systematic analysis system for market entities such as power sales companies, large users, and power generation companies in power market transactions, thereby helping the market entities to participate in the market transactionsefficiently and quickly and improving the market transaction efficiency.

The invention belongs to the technical field of chaotic systems. The invention discloses a chaotic time sequence prediction method based on attention mechanism deep learning. The method comprises thefollowing steps: (1) constructing a chaotic time sequence data set; (2) carrying out phase space reconstruction on a chaotic time sequence; (3) training chaotic time sequence data by using an LSTM neural network model; (4) constructing a prediction-based attention mechanism model, (5) constructing an offline training model, and (6) carrying out online prediction. The chaotic time sequence prediction method based on attention mechanism deep learning is clear in model structure, has a reference value, and can be applied to the aspects of financial market prediction or energy prediction and the like of a chaotic system.

The present invention is provided with: a player action prediction unit that predicts the action of a player and calculates a sales order information prediction value; a market physical restraint prediction unit that predicts the state of a power transfer path, which includes grid-connection line available capacity indicating excess transferred power between areas, and calculates a prediction value for the state of the power transport path; and a market prediction unit that predicts a market price on the basis of the sales order information prediction value and the prediction value for the power transfer path state.

The invention discloses an automatic market analysis method based on multi-mode learning. The automatic market analysis method comprises the steps that firstly, a learning device is trained, and then in practical use, the trained learning device is used for predicting a market. A method for training the learning device comprises the steps that firstly, different-mode information of the market is collected and labeled; then, a multi-example generating method of market data features and character features is used for converting low-level features into a multi-example-packet format; finally, a multi-example multi-label learning method capable of utilizing various modes is adopted to conduct fusion processing on the data, and multi-label learning is conducted. According to the automatic market analysis method based on multi-mode learning, by acquiring multiple pieces of side information of the market, market changes can be depicted more comprehensively and market changes can be predicted more accurately. According to the method for conducting market prediction by using the multi-mode information, the different-mode data information can be used in the implementation process, adaptability is high and effects are good.

The invention discloses a market prediction data processing method and device. The method comprises steps that a pre-acquired preliminary prediction data set is taken as a first training set; a convolutional neural network module is employed to classify the first training set, and the first training set after classification is predicted to acquire a first prediction result; the first prediction result is added to a first training set after classification to acquire a second training set; according to the second training set, a bagging method is employed to acquire multiple target prediction sets, and market prediction is carried out based on the multiple target prediction sets. The method is advantaged in that a technical problem of inaccuracy of the prediction result because of a single prediction model existing in a method in the prior art is solved.

The embodiment of the invention provides a text analysis method and device, electronic equipment and a computer storage medium. The text analysis method comprises the following steps that: obtaining atext to be analyzed, wherein the text to be analyzed comprises an evaluation object; identifying the attribute of the evaluation object from the text to be analyzed; extracting an emotion expressioncorresponding to the attribute from the text to be analyzed; and according to the emotion expression, determining an emotion tendency expressed by the text to be analyzed. Compared with a way of manually analyzing texts in the prior art, the embodiment of the invention adopts the above technical scheme to solve the technical problem that text analysis efficiency is low, risk management and controlability, market prediction ability and client relationship management ability can be obviously improved, and the comment data of a sentence level in the fields, including news, televisions, productsand the like, can be more accurately and effectively analyzed.

The invention provides a hedging transaction analysis method and device based on wavelet analysis, and a storage medium. The method comprises the steps: obtaining the historical market data of one group or more groups of combined targets; carrying out the preprocessing of the market data through wavelet analysis, and generating an alpha tendency chart and/or beta oscillation chart based on the preprocessing data; carrying out the transaction based on the alpha tendency chart and/or beta oscillation chart. A signal is decomposed to different frequency channels based on the wavelet analysis theory. Because the number of the frequency components of the decomposed signals is smaller than the number of the frequency components of an original signal and the smoothing processing of the signal isperformed and then the decomposed signals are reconstructed, a non-steady time sequence becomes an approximately steady time sequence after processing. The alpha tendency chart and/or beta oscillationchart is generated based on the reconstructed data after smoothing, and the alpha tendency chart and/or beta oscillation chart are/is used for the prediction of transactions, thereby enabling the market prediction to be more accurate.

The invention discloses a short-term electricity market forecasting system and method. The method comprises the steps of through an electric power control center power grid energy management system, acquiring historical load data of monthly electricity consumption in a power supply business region and storing the historical load data; processing the stored historical load data to make a monthly distribution map of electricity consumption over the years; according to the monthly distribution map of electricity consumption over the years, calculating an electricity consumption season factor f(M), and then determining an annual monthly electricity sale forecasting value calculation formula based on the electricity sale variation value caused by reasons other than seasonal variation; and according to the annual monthly electricity sale forecasting value calculation formula, carrying out a short-term forecast of and displaying the monthly power consumption. The invention can effectively avoid the subjective influence on the forecast accuracy and reduce the forecast risk by using a season factor forecasting method whereby the monthly electricity sale this year can be forecasted based on objective data of electricity consumption over the past years.

The invention discloses a market prediction method based on news corpus. The market prediction method based on the news corpus comprises the steps of: S1, obtaining news corpus information, and pre-processing the news corpus information; S2, according to the news corpus information obtained in the step S1, constructing a first characteristic tensor in the form of two-dimensional information dimension including a news subject and a subject attitude, and furthermore, in combination with a pre-set keyword dictionary, obtaining a second characteristic tensor; S3, extracting emotional information according to the second characteristic tensor, and then, calculating a public opinion factor alpha through a plurality of pieces of emotional information; and S4, obtaining the lagging T-stage yield rate RT corresponding to the obtained public opinion factor alpha, and predicting the future yield rate market. By means of the technical scheme in the invention, the market emotional calculation efficiency and the accuracy rate can be increased; and thus, relative accurate market prediction can be realized.

The invention provides a financial market prediction and decision-making method and system based on artificial intelligence. The system includes: a data acquisition module, a market emotion feature construction module, a special data feature construction module, a volume-price data feature construction module, an LSTM prediction model, a risk hedging calculation module and an investment decision module. The method comprises the following steps: obtaining mass data, performing feature selection on volume-price data, market emotion data and other types of data, inputting the data into an LSTM prediction model, calculating an optimal risk hedging proportion, and providing decision and market analysis for investors. By means of the scheme, the problem that an existing financial market estimation method is not high in prediction and decision result accuracy is solved, the accuracy and reliability of the prediction and decision result can be effectively improved, a reasonable investment strategy is designed, and investment income is increased.

The invention belongs to the field of house property valuation and discloses a data processing system and a data processing method for house property valuation. A massive data acquisition module is connected with a massive data screening module, the massive data screening module is connected with a database, a field investigation input module is connected with a housing condition investigation transmission module, the database and the real estate condition investigation transmission module are all connected with a premium estimation module, a cost estimation module and a discount estimation module, and the premium estimation module, the cost estimation module and the discount estimation module are connected with an analysis module, and the analysis module is also connected with a market prediction module and a customer feedback module. The system and the method of the invention are simple and easy to use, the resource information adopted is more comprehensive than the existing manual mode, and the evaluation result is more objective and true, and the system has very important application values.

The invention provides a probability prediction method suidesk for an electric power spot price. The invention discloses an electric power spot market prediction method, belongs to the technical fieldof electric power spot market analysis, and aims to obtain two prediction sequences of a price object based on one prediction method, calculate and output a probability prediction interval of a timeperiod corresponding to a second prediction sequence according to quantile regression analysis of a difference value between a first prediction sequence and a real sequence of the same time period. The invention also provides an output device and visualized output data, and the output data comprises part or all of the data of the probability prediction interval obtained by the method. And a storage device that can read stored data for constituting data showing the probabilistic prediction interval acquired by the method of the present disclosure. According to the method and the device, the prediction result of the electric power spot price with the ideal confidence interval can be obtained, and the electric power spot price prediction interval under the specific confidence level is output.

The invention relates to the technical field of artificial intelligence, and provides an information recommendation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining answer data of a questionnaire submitted by a user; inputting the answer data into a risk evaluation model to obtain a target risk evaluation level; generating large-class asset allocation suggestion information based on the target risk evaluation grade, the answer data and large-class asset market prediction data; determining a first recommended investment product corresponding to the target risk evaluation level; generating an investment capability value of the user; screening a second recommended investment product from the first recommended investment product based on the investment capability value; screening a target recommended investment product from the second recommended investment product based on the investment product data; and pushing the investment recommendation information to the user. According to the invention, the product information recommendation efficiency and accuracy can be improved. The method can also be applied to the field of block chains, and the investment recommendation information can be stored on the block chain.

The invention belongs to the electric power spot market electricity price prediction field, and discloses an electric power spot market marginal electricity price prediction method, system and device, and a storage medium, and the method comprises the steps: obtaining a load influence parameter of an electric power spot market prediction day, and obtaining an electric power load prediction curve of the prediction day according to the load influence parameter; obtaining quotation influence parameters of the prediction day of the power spot market, and obtaining a simulated quotation curve of each power generation enterprise of the prediction day according to the quotation influence parameters; and obtaining a prediction result of the marginal electricity price of each time node of the prediction day according to the power load prediction curve of the prediction day and the simulation quotation curve of each power generation enterprise of the prediction day. Through the power load prediction curve and the simulation quotation curve, the prediction result of the marginal electricity price of each time node of the prediction day is obtained, the accuracy of the prediction result is effectively improved, and the deviation between the prediction result and the actual result is reduced.

The invention provides a multi-model subject matter market prediction method and device, and belongs to artificial intelligence, and the method comprises the steps: obtaining the historical data of a subject matter; preprocessing the historical data of the subject matter to determine preprocessed data; performing feature extraction on the preprocessed data, and establishing a prediction model; dividing the preprocessed data into a training set and a test set, and determining a market condition prediction model based on technical indexes, a market condition prediction model based on information and a user guessing rise and fall transaction emotion model by using the training set; respectively determining respective prediction result accuracy of the three models according to the test set; and according to respective prediction result accuracy rates of the three models, distributing weights to the market condition prediction model based on the technical indexes, the market condition prediction model based on the information and the user guessing rise and fall transaction emotion model, predicting the market condition of the current subject matter after weighted averaging, and determining a market condition prediction result of the current subject matter. According to the invention, the prediction accuracy of the subject matter is effectively improved.

The invention discloses a financial market prediction method based on a complex network and relates to the technical field of finance and computer cross research. A complex network is constructed to represent listed companies and following, departing, co-occurrence and other relationships between the listed companies. The method comprises the following steps of based on complex networks of listedcompanies, selecting information of a plurality of companies closest to a listed company as a prediction basis and using the prediction results as output; constructing a prediction model based on deeplearning; the model comprises an encoder-decoder structure and a convolutional neural network structure with an attention mechanism. The embedding of the related companies and the historical performance data of the companies are taken as input, and the financial index trend of the related companies is taken as output, so that the accuracy of financial index prediction of the listed companies canbe remarkably improved, the performance of the listed companies on the financial market in the future can be judged more accurately, and investment and management decisions can be made better.

The invention discloses an automatic prediction method, device and system for a multi-target time sequence. The method comprises the following steps that data reading, data abnormal value automatic detection and data feature automatic conversion are completed through a DataManager assembly; the automatic adjustment of algorithm parameters and the automatic construction of a model are completed by using an AutoML_Core component; a Model(s) component inherited from the AutoML_Core component is utilized to complete automatic construction, calculation and management of a plurality of models from three dimensions of days, months and quarters; multi-target and multi-model evaluation and result management are completed by using an EvaluateModes component; the management of the model and the automatic selection of the optimal model are realized by utilizing a ModelSelectionManager component; and the market sales volume prediction is realized by utilizing an Estimator component. In the automatic prediction process, a ModelPipeline component and a TableTemplate component are used in a matched mode. Through mutual cooperation of a plurality of components, timely, accurate and automatic market prediction can be carried out on a plurality of products of an enterprise, and the enterprise can be assisted to make rapid and reliable decisions.

The embodiment of the invention discloses a product quality determination method apparatus device and a storage medium, which relate to the technical field of market prediction. The method comprises the following steps: determining a basic historical product similar to the target product in a historical product database according to the label information of the target product; Determining a basicfailure rate estimation value of the target product according to the characteristic information of the target product and the characteristic information of the basic historical product; determining The final failure rate estimate of the target product according to the basic failure rate estimate of the target product, the first type of fluctuation molecular value and the second type of fluctuationmolecular value. According to the characteristic information of the target product and the characteristic information of the basic historical product in the historical product database, Then the final failure rate is estimated according to the first kind of fluctuation molecular value and the second kind of fluctuation molecular value, which realizes the quality prediction of the target product based on the historical data, and improves the accuracy of the prediction.

The invention discloses a cloud-service-based enterprise product market demand prediction system. The invention relates to the technical field of a market prediction system. The loud-service-based enterprise product market demand prediction system includes a market demand prediction system, wherein the market demand prediction system includes a data extraction unit, a prediction period data unit,a data processing unit and a microprocessor, wherein the market demand prediction system is connected with a data acquisition unit and a prediction data unit; the data acquisition unit is connected with an enterprise database; the enterprise database is connected with an enterprise data entry unit; the enterprise data entry unit outputs the collected data to the enterprise database; the enterprisedatabase outputs the data information to the data acquisition unit; the data acquisition unit outputs the data information to the market demand prediction system; and the market demand prediction system outputs the prediction data information in the prediction period to the prediction data unit. The loud-service-based enterprise product market demand prediction system solves the problem that a current enterprise manager cannot scientifically predict the future market so as to increase the investment risk, by means of the market demand prediction system.

The invention discloses an AC charging pile control system. The system comprises a task management module, a data management module, an input and output detection control management module, a communication management module, a background protocol and a UCOS operating system kernel. The task management module is connected with the data management module, the data management module is connected withthe input and output detection control management module, the communication management module and the background protocol module, and the input and output detection control management module, the communication management module and the background protocol module are connected with the UCOS operating system kernel. The invention belongs to the technical field of charging piles, and particularly relates to a method for dividing and designing a series of universal function modules on the basis of market prediction and function analysis of a product. According to the requirements of users, the modules are selected and combined to form the alternating current charging pile control system which has different functions or the same function but different performances and different specifications,is easier to maintain and can meet the delivery task of the market more quickly.