CN113191527A - Prediction method and device for population prediction based on prediction model - Google Patents
Prediction method and device for population prediction based on prediction model Download PDFInfo
- Publication number
- CN113191527A CN113191527A CN202110296454.8A CN202110296454A CN113191527A CN 113191527 A CN113191527 A CN 113191527A CN 202110296454 A CN202110296454 A CN 202110296454A CN 113191527 A CN113191527 A CN 113191527A
- Authority
- CN
- China
- Prior art keywords
- prediction
- population
- predicted
- event
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention discloses a prediction method, a prediction device, computer equipment and a storage medium for population prediction based on a prediction model, wherein the method comprises the following steps: matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event; and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result. Therefore, by adopting the embodiment of the application, based on the plurality of prediction models in the prediction model library, the corresponding prediction model can be selected for any one population prediction event for prediction, and the corresponding prediction model can be selected for any one associated population prediction event for prediction, so that the application range of the prediction application scene applicable to the prediction method of the application is effectively expanded, and the accuracy of the prediction result is greatly improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a prediction method and a prediction device for population prediction based on a prediction model.
Background
With the influence of factors such as rapid economic development, talent exchange, economic globalization and the like of each country at present, the population structure and population number of a certain country or a certain region often dynamically change, and population prediction is needed.
The existing population prediction is performed by using a single population prediction model, for example, a Logistic population growth model. The Logistic population growth model is provided on the basis of a Markas model, considering the constraint action of environment and resources on the population number.
The Logistic population growth model takes the population number of a certain past year as a base, and predicts the future population number in a certain closed environment by introducing a fixed population growth rate. Because the population growth rate is variable and may be different every year, a great error is generated when the population number of the future years is predicted by using the uniform population growth rate, and therefore, the prediction result obtained by predicting the population by using the single Logistic population growth model is not accurate enough, and the prediction result does not have actual reference.
Disclosure of Invention
An object of the embodiments of the present invention is to provide a prediction method, a prediction apparatus, a computer device, and a storage medium for performing population prediction based on a prediction model, so as to solve the above technical problems.
In a first aspect, an embodiment of the present application provides a prediction method for performing population prediction based on a prediction model, where the method includes:
acquiring a plurality of prediction elements selected by a target object;
generating a plurality of predicted events based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events;
analyzing the content in each predicted event of the plurality of predicted events to obtain at least one keyword information matched with each predicted event;
matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event;
and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result.
In one embodiment, before said matching at least one prediction model from a prediction model library comprising a plurality of prediction models based on at least one keyword information of each predicted event, the method further comprises:
a prediction model library is generated that includes a plurality of prediction models including a plurality of population prediction models for making population predictions and a plurality of associated prediction models for making associated predictions of populations.
In one embodiment, the predicting based on each of the plurality of predicted events according to the matched at least one prediction model and the related data selected from the database, and obtaining and outputting the prediction result includes:
if any one of the plurality of predicted events is taken as the current predicted event and the current predicted event is taken as the population predicted event, performing population prediction according to the matched at least one population prediction model and the relevant data selected from the database to obtain and output a population prediction result; and/or the presence of a gas in the gas,
and if any one predicted event selected from the plurality of predicted events is taken as the current predicted event and the current predicted event is the correlated population predicted event, performing correlated prediction according to the matched correlated prediction model and the related data selected from the database to obtain and output a correlated prediction result.
In one embodiment, the population prediction model includes a first population prediction model, a second population prediction model, and a third population prediction model, where the first population prediction model, the second population prediction model, and the third population prediction model are neural network prediction models optimized based on a biological evolution algorithm, and if any one predicted event selected from multiple predicted events is used as a current predicted event, and the current predicted event is a population predicted event, performing population prediction according to at least one matched population prediction model and related data selected from the database, and obtaining and outputting a population prediction result includes:
if the current predicted event is a population predicted event, performing population prediction according to the first population prediction model and relevant data selected from the database to obtain a first population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to the second population prediction model and relevant data selected from the database to obtain a second population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to the third population prediction model and relevant data selected from the database to obtain a third population prediction result;
and selecting any one population prediction result from the first population prediction result, the second population prediction result and the third population prediction result as a determined population prediction result, and outputting the population prediction result.
In one embodiment, said matching at least one prediction model from a prediction model library comprising a plurality of prediction models based on at least one keyword information for each predicted event comprises:
selecting any one predicted event from a plurality of predicted events as a current predicted event;
determining a screening keyword of the current predicted event for screening the matching model according to at least one keyword information of the current predicted event;
according to the screening keywords of the current prediction event, traversing the prediction model label words corresponding to the prediction models, and taking the prediction model corresponding to the prediction model label word with the maximum similarity with the screening keywords of the current prediction event as the matched prediction model.
In one embodiment, before said traversing the prediction model tag words corresponding to each prediction model, the method further comprises:
and configuring corresponding prediction model label words for each prediction model in the prediction model library, wherein each prediction model label word is used for identifying the model attribute characteristics of the corresponding prediction model.
In one embodiment, the generating a plurality of predicted events based on a plurality of predicted elements comprises:
acquiring a plurality of to-be-selected prediction elements, wherein the plurality of to-be-selected prediction elements comprise prediction objects, prediction regions, prediction time periods, event attributes of prediction events and at least one key parameter associated with the generated prediction events;
in response to the touch operation of the target object, selecting a plurality of prediction elements for generating any one prediction event from a plurality of to-be-selected prediction elements;
generating corresponding predicted events according to the plurality of predicted elements;
and traversing a plurality of prediction elements corresponding to each prediction event, and generating the corresponding prediction events until each prediction event is generated.
In a second aspect, an embodiment of the present application provides a prediction apparatus for performing population prediction based on a prediction model, the apparatus including:
the acquisition module is used for acquiring a plurality of prediction elements selected by the target object;
a generating module, configured to generate a plurality of predicted events based on the plurality of predicted elements obtained by the obtaining module, where the plurality of predicted events include a plurality of demographic predicted events and a plurality of associated demographic predicted events;
the analysis module is used for analyzing the content in each predicted event in the plurality of predicted events generated by the generation module to obtain at least one keyword information matched with each predicted event;
the matching module is used for matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to at least one keyword information of each prediction event analyzed by the analysis module;
the prediction module is used for predicting according to at least one prediction model matched by the matching module and relevant data selected from a database based on each prediction event in the plurality of prediction events generated by the generation module to obtain a prediction result;
and the output module is used for outputting the prediction result predicted by the prediction module.
In a third aspect, embodiments of the present application provide a computer device, including a memory and a processor, where the memory stores computer-readable instructions, and the computer-readable instructions, when executed by the processor, cause the processor to perform the above-mentioned method steps.
In a fourth aspect, embodiments of the present application provide a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the above-mentioned method steps.
The technical scheme provided by the embodiment of the application can have the following beneficial effects: in the embodiment of the application, a plurality of prediction elements selected by a target object are obtained; generating a plurality of predicted events based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events; analyzing the content in each predicted event of the plurality of predicted events to obtain at least one keyword information matched with each predicted event; matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event; and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result. Therefore, by adopting the embodiment of the application, based on multiple prediction models in the prediction model library, the corresponding prediction model can be selected for any one population prediction event for prediction, and the corresponding prediction model can be selected for any one associated population prediction event for prediction, so that the application range of the prediction application scene applicable to the prediction method of the application can be effectively expanded; in addition, for each of the plurality of predicted events, the matched at least one predicted model can be selected for prediction, so that not only can the predicted results of the plurality of predicted models be verified with each other, but also at least one predicted result of the plurality of predicted results obtained based on the matched at least one predicted model is closer to the actual population condition, and the accuracy of the predicted result is greatly improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is an environmental diagram illustrating an implementation of a predictive method for population prediction based on a predictive model, as provided in one embodiment;
FIG. 2 is a block diagram showing an internal configuration of a computer device according to an embodiment;
FIG. 3 is a flow chart of a prediction method for population prediction based on a prediction model according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a prediction apparatus for performing population prediction based on a prediction model according to an embodiment of the present disclosure.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Alternative embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Fig. 1 is a diagram of an implementation environment of a prediction method for predicting a population based on a prediction model according to an embodiment, as shown in fig. 1, in the implementation environment, including a computer device 110 and a terminal 120.
It should be noted that the terminal 120 and the computer device 110 may be, but are not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like. The computer device 110 and the terminal 110 may be connected through bluetooth, USB (Universal Serial Bus), or other communication connection methods, which is not limited herein.
FIG. 2 is a diagram showing an internal configuration of a computer device according to an embodiment. As shown in fig. 2, the computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected through a system bus. The non-volatile storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store control information sequences, and the computer readable instructions when executed by the processor can enable the processor to realize a prediction method for population prediction based on a prediction model. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, may cause the processor to perform a prediction method for making a population prediction based on a prediction model. The network interface of the computer device is used for connecting and communicating with the terminal. Those skilled in the art will appreciate that the architecture shown in fig. 2 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
As shown in fig. 3, an embodiment of the present disclosure provides a prediction method for predicting a population based on a prediction model, where the prediction method for predicting a population based on a prediction model specifically includes the following method steps:
s301: acquiring a plurality of prediction elements selected by a target object;
in this embodiment of the present application, the obtained multiple prediction elements selected by the target object may be at least one of the following: a predicted object, a predicted region, a predicted time period, an event attribute of the predicted event, and at least one key parameter associated with the generated predicted event.
In the embodiment of the present application, no specific limitation is imposed on at least one key parameter associated with the generated predicted event, and the selected prediction models are different and the associated key parameters are also different, which is not described herein again.
Only some common prediction elements are listed above, and other prediction elements may also be introduced according to the requirements of different application scenarios, which are not described herein again.
S302: a plurality of predicted events is generated based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events.
In the embodiment of the application, the prediction event not only includes a population prediction event, for example, when the current prediction event is the population prediction event, the population prediction is performed according to a neural network population prediction model optimized based on a biological evolution algorithm to obtain a corresponding population prediction result; moreover, the predicted event may also include a correlated population predicted event correlated to the population predicted event, for example, the health status of the elderly is predicted based on a correlated prediction model of health multiple states, and a corresponding correlated prediction result correlated to the population prediction is obtained.
In the embodiment of the application, because the prediction model library with various prediction models is introduced, and based on various prediction models in the prediction model library, not only can a corresponding prediction model be selected for any one population prediction event to perform prediction, but also a corresponding prediction model can be selected for any one associated population prediction event to perform prediction, so that the application range of the prediction application scenario applicable to the prediction method can be effectively expanded.
In one possible implementation, generating the plurality of predicted events based on the plurality of predicted elements comprises:
acquiring a plurality of to-be-selected prediction elements, wherein the plurality of to-be-selected prediction elements comprise prediction objects, prediction regions, prediction time periods, event attributes of prediction events and at least one key parameter associated with the generated prediction events;
in response to the touch operation of the target object, selecting a plurality of prediction elements for generating any one prediction event from a plurality of to-be-selected prediction elements;
generating corresponding predicted events according to the plurality of predicted elements;
and traversing a plurality of prediction elements corresponding to each prediction event, and generating the corresponding prediction events until each prediction event is generated.
In the embodiment of the present application, no specific limitation is imposed on the prediction object, the prediction region, and the prediction time period included in the multiple candidate prediction elements.
S303: and analyzing the content in each predicted event in the plurality of predicted events to obtain at least one keyword information matched with each predicted event.
In the embodiment of the present application, an analysis method for analyzing the content in each of the plurality of predicted events is a conventional method, and is not described herein again.
In an embodiment of the present application, the obtained at least one keyword information matched with each predicted event may be one of the following: demographic forecasting, education, marital, health, and employment.
S304: at least one prediction model is matched from a prediction model library including a plurality of prediction models according to the at least one keyword information of each predicted event.
In this embodiment of the application, the obtained plurality of prediction models in the prediction model library may be a plurality of population prediction models for population prediction, where the population prediction models include a first population prediction model, a second population prediction model, and a third population prediction model, and the first population prediction model, the second population prediction model, and the third population prediction model are all neural network prediction models optimized based on a biological evolution algorithm, where the first population prediction model may be a neural network population prediction model optimized based on a genetic algorithm, the second population prediction model may be a neural network population prediction model optimized based on a particle swarm algorithm, and the third population prediction model may be a neural network population prediction model optimized based on a differential evolution algorithm.
In the embodiment of the application, the first population prediction model is a neural network population prediction model optimized based on a genetic algorithm. The process of optimizing a neural network by a genetic algorithm specifically comprises the following steps:
step a 1: randomly generating a group of distributions, and encoding each weight value (so as to construct a code chain) in the group by adopting a certain encoding scheme, wherein the code chain corresponds to a neural network with a weight value and a threshold value taking specific values on the premise that a network structure and a learning algorithm are determined;
step a 2: calculating an error function of the generated neural network, and determining a fitness function value of the neural network;
step a 3: arranging the individuals by adopting a fitness proportion method, selecting a plurality of individuals with larger adaptation values, and directly transmitting the individuals to the next generation;
step a 4: performing a crossover operation, namely: randomly selecting two individuals from the population according to a set probability for mutual exchange;
step a 5: and performing variation operation to define random variation points, and performing variation to obtain a value of (-1, 1) at the variation points. Forming a new generation of population by carrying out self-adaptive adjustment such as crossing, mutation and the like on individuals and adopting an improved genetic algorithm;
step a 6: repeating the steps a2 to a5 to enable a group of initially determined weight distribution to be continuously evolved until a training target is met or the iteration number reaches a preset target; and substituting the optimized weight and threshold value into the neural network to obtain network output, namely a prediction result.
In the embodiment of the application, through the steps, the weight and the threshold of the neural network are optimized by using the genetic algorithm to obtain the optimized neural network population prediction model, so that the problem that the traditional neural network learning process is easy to fall into a local optimal solution is effectively solved.
In an embodiment of the present application, the second population prediction model is a neural network population prediction model optimized based on a particle swarm optimization. The following description is made for the second population prediction model:
in the operation of the particle swarm algorithm, the random speed and position of the random particles are initialized in the first step, and the speed and position of the particles are updated according to the following two formulas:
Vt+1＝w×Vt+c1×rand()×(pbest-xt)+c2×rand()×(gbest-xt)
formula (1)
xt+1＝xt+Vt+1
Formula (2)
In the above two formulas, VtIs the velocity, x, of the current particle at time ttGenerating a random number between 0 and 1 for the position of the current particle at the moment t, rand () for a random function, w for an inertial weight, c1、c2Is an acceleration constant.
The function of w is to control the influence of the particle velocity generated by the previous iteration on the current flight velocity, and not only can the global searching capability of the particles be influenced, but also the local searching capability of the particles can be influenced. Specifically, global searching by the particle swarm is realized by a larger w value, and conversely, local searching by the particle swarm is realized by a smaller w value. Therefore, in order to balance the global search capability and the local search capability, it is necessary to select an appropriate value of w so that the minimum number of iterations can be obtained, thereby optimizing the algorithm.
In an embodiment of the present application, the second population prediction model is a neural network population prediction model optimized based on a particle swarm optimization, and a process of predicting based on the neural network population prediction model optimized based on the particle swarm optimization specifically includes the following steps:
step b 1: setting a learning factor c1、c2And inertial weight w andmaximum evolution algebra TmaxSetting the current evolution generation number as t as 1, randomly generating a particle swarm x (k) in a domain definition range, wherein the particle swarm x (k) comprises a particle initial position x (t) and a velocity v (t), and taking the initial position as the historical optimal position of an individual, namely: an individual extremum;
step b 2: according to the current position of each particle, calculating the adaptive value of the particle according to the fitness function, and taking the position of the particle with the highest fitness as the historical optimal position of the particle swarm, namely: a group extremum; .
Step b 3: updating the speed and the position of all particles according to the formula (1) and the formula (2) to generate a new population x (t + 1));
step b 4: recalculating the adaptive value of the current position of each particle, comparing the adaptive value with the individual extreme value of each particle, and if the adaptive value is better, updating the historical optimal position of each particle into the current position of each particle;
step b 5: comparing the individual extreme value of each particle with the group extreme value, if the individual extreme value of each particle is better, updating the individual extreme value of each particle into the current group extreme value, namely taking the current position of each particle as the historical optimal position of each group;
step b 6: checking the convergence condition if T is TmaxIf yes, stopping the algorithm and outputting a prediction result; otherwise, let T be T +1, then return to the above step b3 to repeat the above steps b3 to b6 until the above convergence condition T is reachedmaxAnd terminating the algorithm and outputting a prediction result.
In an embodiment of the present application, the third population prediction model may be a neural network population prediction model optimized based on a differential evolution algorithm. The differential evolution algorithm corresponding to the population prediction model is explained as follows:
the steps of obtaining the optimal solution based on the differential evolution algorithm are specifically as follows:
step c 1: initializing evolution parameters: population size N, crossover probability CR, crossover factor F, evolution algebra t, independent variable lower bound
And upper bound
Randomly generating an initial population
{X1(0),X2(0),X3(0),…,XN(0) And (c) the step of (c) in which,
step c 2: individual evaluation: calculating each individual Xi(t) target value f (X)i(t))；
Step c 3: and (3) population propagation: for each individual X in the populationi(t) randomly generating three integers r different from each other1,r2,r3E {1,2, …, N }, and a random integer jrandE {1,2, …, n }, and
step c 4: the following formula (4) is used for selection:
step c 5: and (5) terminating the check: if the population Xi(t +1) satisfies the termination criterion, X is outputiAnd (t +1) taking the individual with the minimum target value as the optimal solution, otherwise, jumping to the step c2 again, and repeating the flow from the step c2 to the step c5 until the termination criterion is met and the optimal solution is obtained.
The plurality of prediction models in the prediction model library may be a plurality of associated prediction models for performing association with population prediction. For example, the association prediction model may be an education multi-state model for predicting an education state, or may be a marital multi-state model for predicting a marital state, or may be a family multi-state model for predicting a family state, or may be a health multi-state model for predicting a health state, or may be a employment multi-state model for predicting a employment state. The models listed in the correlation prediction model are all conventional models, and are not described in detail herein.
Only some common prediction models are listed above, and other prediction models can be introduced according to the requirements of different application scenarios to predict the state of the population or predict other associated states associated with the population, which is not described herein again.
In one possible implementation, matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to at least one keyword information of each predicted event comprises the following steps:
selecting any one predicted event from a plurality of predicted events as a current predicted event;
determining a screening keyword of the current predicted event for screening the matching model according to at least one keyword information of the current predicted event;
according to the screening keywords of the current prediction event, traversing the prediction model label words corresponding to the prediction models, and taking the prediction model corresponding to the prediction model label word with the maximum similarity with the screening keywords of the current prediction event as the matched prediction model.
For example, in a specific application scenario, when a screening keyword for screening a current prediction event of a matching model is identified as education, the prediction model label words corresponding to the prediction models are traversed according to the screening keyword "education", the prediction model "education multi-state model" corresponding to the prediction model label word having the greatest similarity to the "education" is used as the matched prediction model, and the education state is predicted to obtain a prediction result for predicting the education state. The above are merely examples, and the matching process of matching the prediction model corresponding to the keyword information based on different keyword information is not described in detail here.
In a possible implementation manner, before traversing the prediction model tag words corresponding to each prediction model, the method further includes the following steps:
and configuring a corresponding prediction model label word for each prediction model in the prediction model library, wherein each prediction model label word is used for identifying the model attribute characteristics of the corresponding prediction model.
In the above example, the education is a predictive model tag word that identifies the most prominent model attribute features of the "educational multi-state model". Here, the description is only an example, and is not repeated for different prediction models.
In one possible implementation, before matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to at least one keyword information of each predicted event, the method further comprises the steps of:
a prediction model library is generated that includes a plurality of prediction models including a plurality of population prediction models for making population predictions and a plurality of associated prediction models for making associated predictions of populations.
For the description of the plurality of prediction models in the prediction model library in this step, refer to the description of the same or similar parts, which is not repeated herein.
S305: and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result.
In one possible implementation, the predicting, based on each of the plurality of predicted events, according to the matched at least one prediction model and the relevant data selected from the database, and obtaining and outputting the prediction result includes the following steps:
and if any one of the plurality of predicted events is taken as the current predicted event and the current predicted event is taken as the population predicted event, performing population prediction according to the matched at least one population prediction model and the relevant data selected from the database to obtain and output a population prediction result.
In an embodiment of the present application, the population prediction model includes a first population prediction model, a second population prediction model, and a third population prediction model, the first population prediction model, the second population prediction model, and the third population prediction model are neural network prediction models optimized based on a biological evolution algorithm, and if any one of the prediction events selected from the multiple prediction events is used as a current prediction event and the current prediction event is a population prediction event, performing population prediction according to at least one of the matched population prediction models and related data selected from the database, and obtaining and outputting a population prediction result includes:
if the current predicted event is a population predicted event, performing population prediction according to a first population prediction model and relevant data selected from a database to obtain a first population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to a second population prediction model and relevant data selected from the database to obtain a second population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to a third population prediction model and relevant data selected from the database to obtain a third population prediction result;
and selecting any one of the first population prediction result, the second population prediction result and the third population prediction result as a determined population prediction result, and outputting the population prediction result.
In another possible implementation manner, the predicting according to the matched at least one prediction model and the relevant data selected from the database based on each of the plurality of predicted events, and obtaining and outputting the prediction result includes the following steps:
and if any one predicted event selected from the multiple predicted events is taken as the current predicted event and the current predicted event is the correlated population predicted event, performing correlated prediction according to the matched correlated prediction model and the related data selected from the database to obtain and output a correlated prediction result.
In the embodiment of the application, when the current predicted event is the correlated population predicted event, the prediction is performed according to the matched correlated prediction model. For example, the association prediction model may be an education multi-state model for predicting an education state, or may be a marital multi-state model for predicting a marital state, or may be a family multi-state model for predicting a family state, or may be a health multi-state model for predicting a health state, or may be a employment multi-state model for predicting a employment state.
The matching model can be determined to be the specific one by the at least one keyword information of the current predicted event, for example, when the at least one keyword information of the current predicted event is education, the education state is predicted according to the education multi-state model in the association prediction model. The method steps for predicting the education state are conventional based on the education multi-state model, and therefore, the description is omitted here.
Similarly, according to at least one keyword information of the current prediction event, a matched prediction model can be selected from the correlation prediction models to perform correlation prediction, and a correlation prediction result is obtained and output, which is not described herein again.
In another possible implementation manner, the predicting according to the matched at least one prediction model and the relevant data selected from the database based on each of the plurality of predicted events, and obtaining and outputting the prediction result includes the following steps:
if any one of the plurality of predicted events is taken as the current predicted event and the current predicted event is taken as the population predicted event, performing population prediction according to the matched at least one population prediction model and the relevant data selected from the database to obtain and output a population prediction result; and
and if any one predicted event selected from the multiple predicted events is taken as the current predicted event and the current predicted event is the correlated population predicted event, performing correlated prediction according to the matched correlated prediction model and the related data selected from the database to obtain and output a correlated prediction result.
For a detailed description of this step, refer to the description of the same or similar parts, which are not repeated herein.
In one possible implementation, the prediction includes a population prediction and an associated prediction, and after obtaining and outputting the prediction, the method further includes the steps of:
displaying the population prediction result in a first chart form; and/or the presence of a gas in the gas,
displaying the correlation prediction result in a second chart form; therefore, the population prediction result is displayed in a visual form of a chart, so that the target object can visually see the change trend which can be visually displayed in the population prediction result and the associated prediction result, and the user experience is improved.
In the embodiment of the disclosure, a plurality of prediction elements selected by a target object are obtained; generating a plurality of predicted events based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events; analyzing the content in each predicted event of the plurality of predicted events to obtain at least one keyword information matched with each predicted event; matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event; and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result. Therefore, by adopting the embodiment of the application, due to the fact that the prediction model base is provided with a plurality of prediction models, the corresponding prediction model can be selected for any one population prediction event to predict, and the corresponding prediction model can be selected for any one related population prediction event to predict, so that the application range of the prediction application scene applicable to the prediction method of the application is effectively expanded; in addition, for each of the plurality of predicted events, the matched at least one predicted model can be selected for prediction, so that not only can the predicted results of the plurality of predicted models be verified with each other, but also at least one predicted result of the plurality of predicted results obtained based on the matched at least one predicted model is closer to the actual population condition, and the accuracy of the predicted result is greatly improved.
The following is an embodiment of a prediction apparatus for predicting a population based on a prediction model according to the present invention, which can be used to implement an embodiment of a prediction method for predicting a population based on a prediction model according to the present invention. For details not disclosed in the embodiment of the prediction apparatus for predicting the population based on the prediction model of the present invention, please refer to the embodiment of the prediction method for predicting the population based on the prediction model of the present invention.
Referring to fig. 4, a schematic structural diagram of a prediction apparatus for performing population prediction based on a prediction model according to an exemplary embodiment of the present invention is shown. The prediction device for predicting population based on the prediction model can be implemented by software, hardware or a combination of the two as all or part of the terminal. The prediction device for predicting population based on the prediction model comprises an acquisition module 401, a generation module 402, an analysis module 403, a matching module 404, a prediction module 405 and an output module 406.
Specifically, the obtaining module 401 is configured to obtain a plurality of prediction elements selected by a target object;
a generating module 402, configured to generate a plurality of predicted events based on the plurality of predicted elements obtained by the obtaining module 401, where the plurality of predicted events include a plurality of demographic predicted events and a plurality of associated demographic predicted events;
an analyzing module 403, configured to analyze content in each of the multiple predicted events generated by the generating module 402, so as to obtain at least one piece of keyword information matched with each predicted event;
a matching module 404, configured to match at least one prediction model from a prediction model library including a plurality of prediction models according to the at least one keyword information of each prediction event analyzed by the analyzing module 403;
the prediction module 405 is configured to predict, based on each of the plurality of predicted events generated by the generation module 402, at least one prediction model matched by the matching module 404 and related data selected from the database to obtain a prediction result;
and an output module 406, configured to output the prediction result predicted by the prediction module 405.
Optionally, the generating module 402 is further configured to:
before the matching module 404 matches at least one prediction model from a prediction model library including a plurality of prediction models including a plurality of population prediction models for making a population prediction and a plurality of associated prediction models for making an association with the population prediction, the at least one prediction model is matched from the prediction model library including a plurality of prediction models according to the at least one keyword information of each predicted event parsed by the parsing module 403.
Optionally, the prediction module 405 is configured to:
if any one of the plurality of predicted events is taken as the current predicted event and the current predicted event is taken as the population predicted event, performing population prediction according to the matched at least one population prediction model and the relevant data selected from the database to obtain a population prediction result; and/or the presence of a gas in the gas,
if any one predicted event selected from the multiple predicted events is taken as a current predicted event and the current predicted event is a correlated population predicted event, performing correlated prediction according to the matched correlated prediction model and related data selected from the database to obtain a correlated prediction result;
optionally, the output module 406 is configured to:
output the population prediction results predicted by the prediction module 405; and/or the presence of a gas in the gas,
the associated prediction results predicted by the prediction module 405 are output.
Optionally, the population prediction model includes a first population prediction model, a second population prediction model, and a third population prediction model, the first population prediction model, the second population prediction model, and the third population prediction model are all neural network prediction models optimized based on a biological evolution algorithm, and the prediction module 405 is specifically configured to:
if the current predicted event is a population predicted event, performing population prediction according to a first population prediction model and relevant data selected from a database to obtain a first population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to a second population prediction model and relevant data selected from the database to obtain a second population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to a third population prediction model and relevant data selected from the database to obtain a third population prediction result;
selecting any one population prediction result from the first population prediction result, the second population prediction result and the third population prediction result as a determined population prediction result;
optionally, the output module 406 is specifically configured to:
and outputting any one of the population prediction results selected from the first population prediction result, the second population prediction result and the third population prediction result.
Optionally, the matching module 404 is specifically configured to:
selecting any one predicted event from a plurality of predicted events as a current predicted event;
determining a screening keyword of the current predicted event for screening the matching model according to at least one keyword information of the current predicted event;
according to the screening keywords of the current prediction event, traversing the prediction model label words corresponding to the prediction models, and taking the prediction model corresponding to the prediction model label word with the maximum similarity with the screening keywords of the current prediction event as the matched prediction model.
Optionally, the apparatus further comprises:
a configuration module (not shown in fig. 4) configured to configure a corresponding prediction model tag word for each prediction model in the prediction model library before the matching module 404 traverses the prediction model tag word corresponding to each prediction model, where each prediction model tag word is used to identify a model attribute feature of the corresponding prediction model.
Optionally, the generating module 402 is specifically configured to:
acquiring a plurality of to-be-selected prediction elements, wherein the plurality of to-be-selected prediction elements comprise prediction objects, prediction regions, prediction time periods, event attributes of prediction events and at least one key parameter associated with the generated prediction events;
in response to the touch operation of the target object, selecting a plurality of prediction elements for generating any one prediction event from a plurality of to-be-selected prediction elements;
generating corresponding predicted events according to the plurality of predicted elements;
and traversing a plurality of prediction elements corresponding to each prediction event, and generating the corresponding prediction events until each prediction event is generated.
In addition, when the prediction device for predicting the population based on the prediction model provided in the above embodiment executes the prediction method for predicting the population based on the prediction model, only the division of the functional modules is illustrated, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the functions described above. In addition, the prediction device for predicting the population based on the prediction model and the prediction method for predicting the population based on the prediction model provided in the above embodiments belong to the same concept, and the implementation process is detailed in the prediction method for predicting the population based on the prediction model, and will not be described here again.
In the embodiment of the disclosure, the obtaining module is configured to obtain a plurality of prediction elements selected by a target object; the generating module is used for generating a plurality of predicted events based on the plurality of predicted elements acquired by the acquiring module, and the plurality of predicted events comprise a plurality of demographic predicted events and a plurality of related demographic predicted events; the analysis module is used for analyzing the content in each predicted event in the plurality of predicted events generated by the generation module to obtain at least one keyword information matched with each predicted event; the matching module is used for matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to at least one keyword information of each prediction event analyzed by the analysis module; the prediction module is used for predicting according to at least one prediction model matched by the matching module and relevant data selected from the database based on each prediction event in the plurality of prediction events generated by the generation module to obtain a prediction result; and the output module is used for outputting the prediction result predicted by the prediction module. Therefore, by adopting the embodiment of the application, due to the fact that the prediction model base is provided with a plurality of prediction models, the corresponding prediction model can be selected for any one population prediction event to predict, and the corresponding prediction model can be selected for any one related population prediction event to predict, so that the application range of the prediction application scene applicable to the prediction method of the application is effectively expanded; in addition, for each of the plurality of predicted events, the matched at least one predicted model can be selected for prediction, so that not only can the predicted results of the plurality of predicted models be verified with each other, but also at least one predicted result of the plurality of predicted results obtained based on the matched at least one predicted model is closer to the actual population condition, and the accuracy of the predicted result is greatly improved.
In one embodiment, a computer device is proposed, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring a plurality of prediction elements selected by a target object; generating a plurality of predicted events based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events; analyzing the content in each predicted event of the plurality of predicted events to obtain at least one keyword information matched with each predicted event; matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event; and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result.
In one embodiment, a storage medium is provided that stores computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of: acquiring a plurality of prediction elements selected by a target object; generating a plurality of predicted events based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events; analyzing the content in each predicted event of the plurality of predicted events to obtain at least one keyword information matched with each predicted event; matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event; and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A prediction method for predicting a population based on a prediction model, the method comprising:
acquiring a plurality of prediction elements selected by a target object;
generating a plurality of predicted events based on the plurality of predicted elements, the plurality of predicted events including a plurality of demographic predicted events and a plurality of associated demographic predicted events;
analyzing the content in each predicted event of the plurality of predicted events to obtain at least one keyword information matched with each predicted event;
matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to the at least one keyword information of each prediction event;
and predicting according to the matched at least one prediction model and relevant data selected from the database based on each prediction event in the plurality of prediction events to obtain and output a prediction result.
2. The method of claim 1, wherein prior to said matching at least one predictive model from a predictive model library comprising a plurality of predictive models based on at least one keyword information for each predictive event, the method further comprises:
a prediction model library is generated that includes a plurality of prediction models including a plurality of population prediction models for making population predictions and a plurality of associated prediction models for making associated predictions of populations.
3. The method of claim 2, wherein predicting based on each of the plurality of predicted events based on the matched at least one predictive model and the associated data selected from the database, and wherein obtaining and outputting the predicted result comprises:
if any one of the plurality of predicted events is taken as the current predicted event and the current predicted event is taken as the population predicted event, performing population prediction according to the matched at least one population prediction model and the relevant data selected from the database to obtain and output a population prediction result; and/or the presence of a gas in the gas,
and if any one predicted event selected from the plurality of predicted events is taken as the current predicted event and the current predicted event is the correlated population predicted event, performing correlated prediction according to the matched correlated prediction model and the related data selected from the database to obtain and output a correlated prediction result.
4. The method of claim 3, wherein the population prediction models comprise a first population prediction model, a second population prediction model and a third population prediction model, the first population prediction model, the second population prediction model and the third population prediction model are neural network prediction models optimized based on a biological evolution algorithm, and if any one of the plurality of prediction events is taken as a current prediction event and the current prediction event is a population prediction event, performing population prediction according to at least one matched population prediction model and relevant data selected from the database to obtain and output a population prediction result comprises:
if the current predicted event is a population predicted event, performing population prediction according to the first population prediction model and relevant data selected from the database to obtain a first population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to the second population prediction model and relevant data selected from the database to obtain a second population prediction result;
if the current predicted event is a population predicted event, performing population prediction according to the third population prediction model and relevant data selected from the database to obtain a third population prediction result;
and selecting any one population prediction result from the first population prediction result, the second population prediction result and the third population prediction result as a determined population prediction result, and outputting the population prediction result.
5. The method of claim 1, wherein matching at least one predictive model from a predictive model library comprising a plurality of predictive models based on at least one keyword information for each predictive event comprises:
selecting any one predicted event from a plurality of predicted events as a current predicted event;
determining a screening keyword of the current predicted event for screening the matching model according to at least one keyword information of the current predicted event;
according to the screening keywords of the current prediction event, traversing the prediction model label words corresponding to the prediction models, and taking the prediction model corresponding to the prediction model label word with the maximum similarity with the screening keywords of the current prediction event as the matched prediction model.
6. The method of claim 5, wherein prior to said traversing the predictive model tag words for each predictive model, the method further comprises:
and configuring corresponding prediction model label words for each prediction model in the prediction model library, wherein each prediction model label word is used for identifying the model attribute characteristics of the corresponding prediction model.
7. The method of claim 1, wherein generating the plurality of predicted events based on the plurality of predicted elements comprises:
acquiring a plurality of to-be-selected prediction elements, wherein the plurality of to-be-selected prediction elements comprise prediction objects, prediction regions, prediction time periods, event attributes of prediction events and at least one key parameter associated with the generated prediction events;
in response to the touch operation of the target object, selecting a plurality of prediction elements for generating any one prediction event from a plurality of to-be-selected prediction elements;
generating corresponding predicted events according to the plurality of predicted elements;
and traversing a plurality of prediction elements corresponding to each prediction event, and generating the corresponding prediction events until each prediction event is generated.
8. A prediction apparatus for making a population prediction based on a prediction model, the apparatus comprising:
the acquisition module is used for acquiring a plurality of prediction elements selected by the target object;
a generating module, configured to generate a plurality of predicted events based on the plurality of predicted elements obtained by the obtaining module, where the plurality of predicted events include a plurality of demographic predicted events and a plurality of associated demographic predicted events;
the analysis module is used for analyzing the content in each predicted event in the plurality of predicted events generated by the generation module to obtain at least one keyword information matched with each predicted event;
the matching module is used for matching at least one prediction model from a prediction model library comprising a plurality of prediction models according to at least one keyword information of each prediction event analyzed by the analysis module;
the prediction module is used for predicting according to at least one prediction model matched by the matching module and relevant data selected from a database based on each prediction event in the plurality of prediction events generated by the generation module to obtain a prediction result;
and the output module is used for outputting the prediction result predicted by the prediction module.
9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to carry out the steps of the prediction method according to any one of claims 1 to 7.
10. A storage medium having stored thereon computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the prediction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110296454.8A CN113191527A (en) | 2021-03-19 | 2021-03-19 | Prediction method and device for population prediction based on prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110296454.8A CN113191527A (en) | 2021-03-19 | 2021-03-19 | Prediction method and device for population prediction based on prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113191527A true CN113191527A (en) | 2021-07-30 |
Family
ID=76973490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110296454.8A Pending CN113191527A (en) | 2021-03-19 | 2021-03-19 | Prediction method and device for population prediction based on prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191527A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114328654A (en) * | 2021-12-10 | 2022-04-12 | 北京融信数联科技有限公司 | Demographic method, system and readable storage medium based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108830402A (en) * | 2018-05-07 | 2018-11-16 | 北京百分点信息科技有限公司 | A kind of Ways of Population Prediction and device |
| CN110458333A (en) * | 2019-07-18 | 2019-11-15 | 华南农业大学 | A kind of population spatial distribution prediction technique and system based on POIs data |
| CN111932036A (en) * | 2020-09-23 | 2020-11-13 | 中国科学院地理科学与资源研究所 | Fine spatio-temporal scale dynamic population prediction method and system based on position big data |
| CN112163717A (en) * | 2020-10-20 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Population data prediction method and device, computer equipment and medium |
-
2021
- 2021-03-19 CN CN202110296454.8A patent/CN113191527A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108830402A (en) * | 2018-05-07 | 2018-11-16 | 北京百分点信息科技有限公司 | A kind of Ways of Population Prediction and device |
| CN110458333A (en) * | 2019-07-18 | 2019-11-15 | 华南农业大学 | A kind of population spatial distribution prediction technique and system based on POIs data |
| CN111932036A (en) * | 2020-09-23 | 2020-11-13 | 中国科学院地理科学与资源研究所 | Fine spatio-temporal scale dynamic population prediction method and system based on position big data |
| CN112163717A (en) * | 2020-10-20 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Population data prediction method and device, computer equipment and medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114328654A (en) * | 2021-12-10 | 2022-04-12 | 北京融信数联科技有限公司 | Demographic method, system and readable storage medium based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11829880B2 (en) | Generating trained neural networks with increased robustness against adversarial attacks | |
| US10360517B2 (en) | Distributed hyperparameter tuning system for machine learning | |
| CN111582694B (en) | Learning evaluation method and device | |
| US11694109B2 (en) | Data processing apparatus for accessing shared memory in processing structured data for modifying a parameter vector data structure | |
| WO2021027256A1 (en) | Method and apparatus for processing interactive sequence data | |
| CN110366734A (en) | Optimization neural network framework | |
| US7792769B2 (en) | Apparatus and method for learning and reasoning for systems with temporal and non-temporal variables | |
| CN109923560A (en) | Neural network is trained using variation information bottleneck | |
| CN111611488B (en) | Information recommendation method and device based on artificial intelligence and electronic equipment | |
| CN110598869B (en) | Classification method and device based on sequence model and electronic equipment | |
| US10963802B1 (en) | Distributed decision variable tuning system for machine learning | |
| CN112785005B (en) | Multi-objective task assistant decision-making method and device, computer equipment and medium | |
| CN113011895B (en) | Associated account sample screening method, device and equipment and computer storage medium | |
| Friedman et al. | Learning Bayesian networks from data | |
| KR102293791B1 (en) | Electronic device, method, and computer readable medium for simulation of semiconductor device | |
| CN110162939A (en) | Man-machine recognition methods, equipment and medium | |
| CN114781611A (en) | Natural language processing method, language model training method and related equipment | |
| CN112328646A (en) | Multitask course recommendation method and device, computer equipment and storage medium | |
| CN113869609A (en) | Method and system for predicting confidence of frequent subgraph of root cause analysis | |
| US20210192361A1 (en) | Intelligent data object generation and assignment using artificial intelligence techniques | |
| CN113191527A (en) | Prediction method and device for population prediction based on prediction model | |
| CN112508177A (en) | Network structure searching method and device, electronic equipment and storage medium | |
| CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN109800887B (en) | Generation method and device of prediction process model, storage medium and electronic equipment | |
| CN111582313A (en) | Sample data generation method and device and electronic equipment |
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 |