CN111798018A - Behavior prediction method, behavior prediction device, storage medium and electronic equipment - Google Patents
Behavior prediction method, behavior prediction device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111798018A CN111798018A CN201910282131.6A CN201910282131A CN111798018A CN 111798018 A CN111798018 A CN 111798018A CN 201910282131 A CN201910282131 A CN 201910282131A CN 111798018 A CN111798018 A CN 111798018A
- Authority
- CN
- China
- Prior art keywords
- data
- window
- time
- sliding
- behavior prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 54
- 238000013075 data extraction Methods 0.000 claims abstract description 41
- 230000006399 behavior Effects 0.000 claims description 130
- 238000013528 artificial neural network Methods 0.000 claims description 112
- 230000000306 recurrent effect Effects 0.000 claims description 53
- 238000012549 training Methods 0.000 claims description 30
- 230000015654 memory Effects 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 18
- 239000010410 layer Substances 0.000 description 37
- 239000000284 extract Substances 0.000 description 15
- 230000008569 process Effects 0.000 description 10
- 230000001133 acceleration Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000008447 perception Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000002356 single layer Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011982 device technology Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The embodiment of the application discloses a behavior prediction method, a behavior prediction device, a storage medium and electronic equipment, wherein the electronic equipment can firstly acquire a time sequence data sequence corresponding to the electronic equipment, the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points, then data extraction is carried out on the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window, then feature extraction is carried out on the window data corresponding to each sliding time window to obtain features corresponding to each sliding time window, finally, behavior prediction is carried out on a user according to the features corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result. Therefore, the user behavior is predicted, and intelligent service can be better provided for the user.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a behavior prediction method, an apparatus, a storage medium, and an electronic device.
Background
At present, with the rapid development of electronic device technology, electronic devices can provide basic services such as audio and video playing and web browsing, and can also recommend routes and restaurants when users go home, however, these intelligent services provided by electronic devices are behaviors that are assumed according to common work and rest habits of the public, and such assumed behaviors are not accurate. For example, assume that the user's behavior at 12:00 is "eat", assume that the user's behavior at 18:00 is "go home", and so on. Therefore, if the user behavior can be accurately predicted, it is possible to provide a more intelligent service to the user.
Disclosure of Invention
The embodiment of the application provides a behavior prediction method and device, a storage medium and electronic equipment, which can predict the behavior of a user.
In a first aspect, an embodiment of the present application provides a behavior prediction method, which is applied to an electronic device, and the behavior prediction method includes:
acquiring a time sequence data sequence corresponding to the electronic equipment, wherein the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points;
performing data extraction on the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window;
and performing behavior prediction on the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result.
In a second aspect, an embodiment of the present application provides a behavior prediction apparatus, which is applied to an electronic device, and the behavior prediction apparatus includes:
the data acquisition module is used for acquiring a time sequence data sequence corresponding to the electronic equipment, and the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points;
the data extraction module is used for extracting data of the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
the characteristic extraction module is used for extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window;
and the behavior prediction module is used for predicting the behavior of the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result.
In a third aspect, the present application provides a storage medium, on which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the steps in the behavior prediction method provided by the embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory has a computer program, and the processor is configured to execute the steps in the behavior prediction method according to the embodiment of the present application by calling the computer program.
In the embodiment of the application, the electronic device may first obtain and acquire a time series data sequence corresponding to the electronic device, where the time series data sequence includes multiple preset types of data corresponding to different time points, then perform data extraction on the time series data sequence according to sliding time windows of different durations to obtain window data corresponding to each sliding time window, then perform feature extraction on the window data corresponding to each sliding time window to obtain features corresponding to each sliding time window, and finally perform behavior prediction on a user according to the features corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result. Therefore, the user behavior is predicted, and intelligent service can be better provided for the user.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a panoramic sensing architecture provided in an embodiment of the present application.
Fig. 2 is a flow chart of a behavior prediction method according to an embodiment of the present disclosure.
Fig. 3 is a schematic diagram of a time series data sequence acquired by an electronic device in an embodiment of the present application.
Fig. 4 is a schematic diagram of an electronic device performing data extraction on a time series data sequence according to sliding time windows of different durations in an embodiment of the present application.
Fig. 5 is another schematic flow chart of a behavior prediction method according to an embodiment of the present application.
Fig. 6 is a schematic structural diagram of a behavior prediction apparatus according to an embodiment of the present application.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 8 is another schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Referring to the drawings, wherein like reference numbers refer to like elements, the principles of the present application are illustrated as being implemented in a suitable computing environment. The following description is based on illustrated embodiments of the application and should not be taken as limiting the application with respect to other embodiments that are not detailed herein.
With the miniaturization and intellectualization of sensors, electronic devices such as mobile phones and tablet computers integrate more and more sensors, such as light sensors, distance sensors, position sensors, acceleration sensors, gravity sensors, and the like. The electronic device can acquire more data with less power consumption through the configured sensor. Meanwhile, the electronic device can acquire data related to the state of the electronic device and data related to the state of the user during operation. In general, the electronic device can acquire data related to an external environment (e.g., temperature, light, place, sound, weather, etc.), data related to a user state (e.g., posture, speed, usage habits of a mobile phone, personal basic information, etc.), and data related to a state of the electronic device (e.g., power consumption, resource usage, network status, etc.).
In the embodiment of the application, in order to process the data acquired by the electronic device and provide intelligent service for a user, a panoramic sensing architecture is provided. Referring to fig. 1, fig. 1 is a schematic structural diagram of a panoramic sensing architecture provided in an embodiment of the present application, and the panoramic sensing architecture is applied to an electronic device and includes, from bottom to top, an information sensing layer, a data processing layer, a feature extraction layer, a scene modeling layer, and an intelligent service layer.
As the lowest layer of the panoramic sensing architecture, the information sensing layer is used for acquiring original data capable of describing various types of scenes of a user, including dynamic data and static data. Wherein the information perception layer is composed of a plurality of sensors for data acquisition, including, but not limited to, a distance sensor for detecting a distance between the electronic device and an external object, a magnetic field sensor for detecting magnetic field information of an environment in which the electronic device is located, a light sensor for detecting light information of an environment in which the electronic device is located, an acceleration sensor for detecting acceleration data of the electronic device, a fingerprint sensor for collecting fingerprint information of a user, a hall sensor for sensing magnetic field information, a position sensor for detecting a geographical position in which the electronic device is currently located, a gyroscope for detecting an angular velocity of the electronic device in various directions, an inertial sensor for detecting motion data of the electronic device, a posture sensor for sensing posture information of the electronic device, a barometer for detecting an air pressure of an environment in which the electronic device is located, a heart rate sensor for detecting heart rate information of a user, and the like, which are illustrated.
And as a secondary bottom layer of the panoramic sensing architecture, the data processing layer is used for processing the original data acquired by the information sensing layer and eliminating the problems of noise, inconsistency and the like of the original data. The data processing layer can perform data cleaning, data integration, data transformation, data reduction and other processing on the data acquired by the information perception layer.
And the characteristic extraction layer is used for extracting the characteristics of the data processed by the data processing layer to extract the characteristics included in the data as an intermediate layer of the panoramic perception architecture. The feature extraction layer may extract features or process the extracted features by a method such as a filtering method, a packing method, or an integration method.
The filtering method is to filter the extracted features to remove redundant feature data. Packaging methods are used to screen the extracted features. The integration method is to integrate a plurality of feature extraction methods together to construct a more efficient and more accurate feature extraction method for extracting features.
As a second highest level of the panoramic sensing architecture, the scene modeling layer is used for constructing a model according to the features extracted by the feature extraction layer, and the obtained model can be used for representing the state of the electronic device, the user state, the environment state and the like. For example, the scenario modeling layer may construct a key value model, a pattern identification model, a graph model, an entity relation model, an object-oriented model, and the like according to the features extracted by the feature extraction layer.
And as the highest layer of the panoramic perception architecture, the intelligent service layer is used for providing intelligent services according to the model constructed by the scene modeling layer. For example, the intelligent service layer may provide basic application services for the user, may perform system intelligent optimization services for the electronic device, and may also provide personalized intelligent services for the user.
In addition, the panoramic sensing architecture further comprises an algorithm library, and the algorithm library comprises, but is not limited to, algorithms such as a markov algorithm, a hidden dirichlet distribution algorithm, a bayesian classification algorithm, a support vector machine, a K-means clustering algorithm, a K-nearest neighbor algorithm, a conditional random field, a residual error network, a long-short term memory network, a convolutional neural network, a cyclic neural network and the like.
Based on the panoramic sensing architecture provided by the embodiment of the present application, the embodiment of the present application provides a behavior prediction method, and an execution subject of the behavior prediction method may be a behavior prediction apparatus provided by the embodiment of the present application, or an electronic device integrated with the behavior prediction apparatus, where the behavior prediction apparatus may be implemented in a hardware or software manner. The electronic device may be a device with processing capability configured with a processor, such as a smart phone, a tablet computer, a palm computer, a notebook computer, or a desktop computer.
Based on the behavior prediction method provided by the embodiment of the application, the information perception layer acquires a time sequence data sequence of the corresponding electronic equipment from the acquired panoramic data and provides a data processing layer; the data processing layer extracts the data of the time sequence data sequence according to the sliding time windows with different durations to obtain window data corresponding to each sliding time window, and the window data are provided for the characteristic extraction layer; the characteristic extraction layer is used for extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window; the scene modeling layer models according to the characteristics corresponding to each sliding time window, namely, the scene modeling layer predicts the behavior of the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result, and the prediction result is provided for the intelligent service layer; the intelligent service layer provides personalized services for the user according to the prediction result of the scene modeling layer, namely the predicted user behavior, such as recommending a route when the user goes home, recommending a restaurant when the user has a meal, and the like.
Referring to fig. 2, fig. 2 is a flowchart illustrating a behavior prediction method according to an embodiment of the present disclosure. As shown in fig. 2, a flow of the behavior prediction method provided in the embodiment of the present application may be as follows:
in 101, a time series data sequence of a corresponding electronic device is obtained, wherein the time series data sequence comprises a plurality of preset types of data corresponding to different time points.
In the embodiment of the application, as shown in fig. 3, the electronic device uses the current time point as a starting point, obtains a plurality of pieces of preset type data corresponding to different time points in the forward direction, and forms a time sequence data sequence corresponding to the electronic device by using the obtained plurality of pieces of preset type data corresponding to different time points. For example, the electronic device may obtain the preset type data of the N time points forward with the current time point as a starting point, where the intervals of the two adjacent time points are the same.
It should be noted that the preset type data acquired in the embodiment of the present application includes external environment related data, such as temperature, light, place, sound, weather, and the like, user state related data, such as posture, speed, usage habits of the mobile phone, personal basic information, and the like, and electronic device state related data, such as power consumption, resource usage status, network status, and the like.
At 102, data extraction is performed on the time sequence data sequence according to the sliding time windows with different durations, so as to obtain window data corresponding to each sliding time window.
In the embodiment of the application, after the time sequence data sequence is obtained, the electronic device further extracts the obtained time sequence data sequence according to a preset number of sliding time windows with different durations, wherein each sliding time window obtains a plurality of window data, and each window data comprises preset type data of a plurality of time points. Any window data reflects the behavior of the user in the time interval corresponding to the window data, such as getting up, working, sitting on a subway, driving, sitting on a bus, and the like.
It should be noted that, when the electronic device performs data extraction according to each sliding time window, the starting time points of the data extraction may be the same or different. For example, the electronic device extracts data of the acquired time series data sequence by using the current time point as a common starting time point according to a sliding time window a with a time length of t +1 time points, a sliding time window B with a time length of 3/2t +1 time points, and a sliding time window C with a time length of 5t +1 time points, where the sliding time window a extracts X window data (including preset type data of t +1 time points), the sliding time window B extracts Y window data (including preset type data of 3/2t +1 time points), and the sliding time window C extracts Z window data (including preset type data of 5t +1 time points), and it can be seen that X > Y > Z.
In 103, feature extraction is performed on the window data corresponding to each sliding time window to obtain features corresponding to each sliding time window.
In the embodiment of the application, after extracting the window data corresponding to each sliding time window, the electronic device further performs feature extraction on the window data corresponding to each sliding time window by using a preset feature extraction technology, so as to obtain features corresponding to each sliding time window. It should be noted that, in the embodiment of the present application, there is no specific limitation on what kind of feature extraction technology is used for feature extraction, and a person having ordinary skill in the art may select the feature extraction technology according to actual needs, for example, the feature extraction technology may be used in a neural network manner.
And 104, performing behavior prediction on the user according to the characteristics corresponding to the sliding time windows and a pre-trained behavior prediction model to obtain a prediction result.
In the embodiment of the application, a behavior prediction model for predicting the behavior of the user is also trained in advance, wherein the behavior prediction model can be stored locally in the electronic device or stored in a remote server. In this way, after the electronic device performs feature extraction on the window data corresponding to each sliding time window to obtain the features corresponding to each sliding time window, the electronic device further obtains a behavior prediction model for predicting the behavior of the user from the local, or obtains a behavior prediction model for predicting the behavior of the user from a remote server.
After the pre-trained behavior prediction model is obtained, the electronic device performs behavior prediction on the user according to the characteristics corresponding to each sliding time window and the pre-trained behavior prediction model to obtain a prediction result, namely, the upcoming behavior of the user is predicted according to the historical behavior sequence of the user under different duration scales.
After obtaining the prediction result of the user, the electronic device may further perform an intelligent service for the user according to the prediction result, for example, if the obtained prediction result is that the user is going to "go home", a route to go home may be recommended to the user, or if the obtained prediction result is that the user is going to "eat", a nearby restaurant may be recommended to the user.
As can be seen from the above, in the embodiment of the present application, the electronic device may first obtain a time series data sequence corresponding to the electronic device, where the time series data sequence includes multiple preset types of data corresponding to different time points, then perform data extraction on the time series data sequence according to sliding time windows of different durations to obtain window data corresponding to each sliding time window, then perform feature extraction on the window data corresponding to each sliding time window to obtain features corresponding to each sliding time window, and finally perform behavior prediction on a user according to the features corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result. Therefore, the user behavior is predicted, and intelligent service can be better provided for the user.
In an embodiment, "data extraction is performed on a time series data sequence according to sliding time windows of different durations", including:
and according to different starting time points, performing data extraction on the time sequence data sequence according to each sliding time window.
In the embodiment of the application, when the electronic device extracts data of the time sequence data sequence, different starting time points are adopted among the sliding time windows, so that the window data extracted by the different sliding time windows are crossed.
For example, in the embodiment of the present application, a sliding time window a with a duration of t +1 time points, a sliding time window B with a duration of 3/2t +1 time points, and a sliding time window C with a duration of 5t +1 time points are provided, where the sliding time window a takes the current time point as a start time point of data extraction, the sliding time window B takes the t/2 time point before the current time point as a start time point of data extraction, and the sliding time window C takes the t time point before the current time period as a start time point of data extraction, as shown in fig. 4.
In one embodiment, "acquiring a time series data sequence of a corresponding electronic device" includes:
(1) judging whether preset type data corresponding to the time point exists or not;
(2) if so, acquiring preset type data corresponding to the time point;
(3) if not, acquiring the preset type data closest to the time point as the preset type data corresponding to the time point.
According to the above description of the embodiments, it can be understood by those skilled in the art that the time-series data sequence is composed of preset type data corresponding to a plurality of time points in time series. In the following, how to obtain the time series data sequence of the corresponding electronic device is described by taking the example of obtaining the preset type data corresponding to one time point.
It should be noted that, for the external environment-related data, the user state-related data, and the electronic device state-related data included in the preset type of data, the return frequencies of the types of data may not be consistent, for example, the return frequencies of the acceleration sensor data and the gyroscope sensor data in the user state-related data are not consistent, so that the acceleration sensor data is collected but the gyroscope sensor data is not collected, or the gyroscope sensor data is collected but the acceleration sensor data is not collected at a certain time point. Therefore, in the embodiment of the application, when acquiring the preset type data of a time point, the electronic device first determines whether the preset type data corresponding to the time point exists, if the preset type data corresponding to the time point exists, the preset type data corresponding to the time point is acquired, and if the preset type data corresponding to the time point does not exist, the preset type data closest to the time point (which may be before or after) is acquired as the preset type data corresponding to the time point.
For example, when the electronic device acquires acceleration sensor data at a time point, the electronic device directly acquires the acceleration sensor data corresponding to the time point if the acceleration sensor data corresponding to the time point exists, and when the electronic device acquires gyro sensor data at the time point, the electronic device acquires gyro sensor data closest to the time point if the gyro sensor data corresponding to the time point does not exist.
In an embodiment, "performing feature extraction on window data corresponding to each sliding time window" includes:
and inputting window data corresponding to each sliding time window into different encoder neural networks for feature extraction, wherein the number of features output by the different encoder neural networks for feature extraction is the same.
In the embodiment of the application, corresponding to different sliding time windows, the encoder neural network for extracting the characteristics of the window data extracted by the encoder neural network is trained in advance, and when the encoder neural network is trained, the quantity of the characteristics output by the different encoder neural networks for extracting the characteristics is the same through parameter setting.
For example, assuming that a sliding time window a, an encoder neural network a corresponding to the sliding time window a, a sliding time window B, an encoder neural network B corresponding to the sliding time window B, and a sliding time window C, an encoder neural network C corresponding to the sliding time window C are preset, wherein the electronic device inputs window data extracted by the sliding time window a into the encoder neural network a for feature extraction, inputs window data extracted by the sliding time window B into the encoder neural network B for feature extraction, and inputs window data extracted by the sliding time window C into the encoder neural network C for feature extraction, the encoder neural network a, the encoder neural network B, and the encoder neural network C have different "lengths" of window data input thereto, but the encoder neural network a, the encoder neural network B, and the encoder neural network C have different "lengths" of window data input thereto, The encoder neural network B and the encoder neural network C extract features of the input window data, and the number of the output features is the same.
It should be noted that, in this embodiment of the application, specific models and topology structures of each encoder neural network are not limited, a single-layer recurrent neural network may be used for training to obtain the encoder neural network, a multi-layer recurrent neural network may be used for training to obtain the encoder neural network, and a convolutional neural network, or a variant thereof, or a neural network with other network structures may be used for training to obtain the encoder neural network. For example, in the embodiment of the present application, a recurrent neural network may be used to train and obtain an encoder neural network.
In an embodiment, before "acquiring the time-series data sequence of the corresponding electronic device", the method further includes:
(1) acquiring a time sequence data sequence sample, wherein the time sequence data sequence sample is a historical time sequence data sequence of corresponding electronic equipment;
(2) performing data extraction on the time sequence data sequence samples according to the sliding time windows to obtain window data samples corresponding to the sliding time windows;
(3) extracting the characteristics of the window data samples corresponding to the sliding time windows to obtain characteristic samples corresponding to the sliding time windows;
(4) and performing model training according to the characteristic samples corresponding to the sliding windows to obtain a behavior prediction model.
In the embodiment of the application, the electronic equipment is trained in advance to obtain the behavior prediction model. The electronic equipment firstly acquires a historical time sequence data sequence corresponding to the electronic equipment as a time sequence data sequence sample of a training behavior prediction model.
After the time sequence data sequence samples are obtained, the electronic equipment further extracts the obtained time sequence data sequence samples according to a preset number of sliding time windows with different durations, each sliding time window obtains a plurality of window data samples, and each window data sample comprises preset type data of a plurality of historical time points. Any window data sample reflects the behavior of the user in the historical time interval corresponding to the window data sample, such as getting up, going to work, sitting on a subway, driving, sitting on a bus, and the like. It should be noted that, the manner of data extraction performed on the time series data sequence samples by the electronic device is the same as the manner of data extraction performed on the time series data sequence, and details are not repeated here, and reference may be specifically made to the above related description.
After the window data samples corresponding to the sliding time windows are extracted, a preset feature extraction technology is further adopted to perform feature extraction on the window data samples corresponding to the sliding time windows, and therefore the feature samples corresponding to the sliding time windows are obtained. It should be noted that, a manner of performing feature extraction on the window data sample by the electronic device is the same as that of performing feature extraction on the window data, and details are not repeated here, and reference may be specifically made to the above related description.
After the feature samples corresponding to the sliding time windows are obtained, the electronic device can perform model training according to the feature samples corresponding to the sliding time windows and a preset training algorithm, so as to obtain a behavior prediction model for predicting the behavior of the user through training.
In an embodiment, "performing model training according to the feature samples corresponding to the sliding windows" includes:
(1) constructing a recurrent neural network and constructing a loss function corresponding to the recurrent neural network;
(2) inputting the characteristic sample corresponding to each sliding window into the recurrent neural network, obtaining the loss value of the recurrent neural network according to the loss function, and reversely transmitting the loss value to the recurrent neural network.
In the embodiment of the application, when model training is performed according to the feature samples corresponding to the sliding windows, the electronic device first constructs a recurrent neural network, and further constructs a loss function of the correspondingly constructed recurrent neural network according to a preset training target and the configuration of the constructed recurrent neural network.
The configuration of the constructed recurrent neural network and the type of the loss function are not specifically limited in the embodiment of the present application, and can be preset by a person of ordinary skill in the art according to actual needs, for example, a LSTM (long short-Term Memory) recurrent neural network model is constructed, and a cross entropy loss function corresponding to the LSTM recurrent neural network model is constructed.
In addition, the electronic equipment also receives the user behaviors which are manually calibrated and correspond to the characteristic samples corresponding to the sliding windows, and the user behaviors are used as output labels of the training recurrent neural network.
Then, the electronic device initializes the parameters of the recurrent neural network, inputs the feature samples corresponding to the sliding windows into the recurrent neural network, obtains the loss value of the recurrent neural network according to the actual output of the recurrent neural network, the corresponding output labels and the constructed loss function, reversely propagates the obtained loss value to the recurrent neural network, and updates the parameters of the recurrent neural network. And continuously and iteratively inputting the characteristic samples corresponding to the sliding windows to the recurrent neural network, training the recurrent neural network until a preset training target is met, terminating the training, and taking the trained recurrent neural network as a behavior prediction model for predicting the user behavior.
It should be noted that training the recurrent neural network only changes the parameters of the recurrent neural network, but does not change the configuration of the recurrent neural network, for example, the constructed recurrent neural network is still the recurrent neural network after completing the training, but the parameter initialization parameters of the recurrent neural network are changed.
In an embodiment, before inputting the feature sample corresponding to each sliding window into the recurrent neural network, "the method further includes:
and carrying out regularization processing on the loss function.
In the embodiment of the application, before the electronic device starts to train the recurrent neural network, the electronic device performs regularization processing on the constructed loss function, so as to prevent overfitting.
For example, the electronic device may add an L1 regular term, an L2 regular term, or other types of regular terms to the constructed loss function to implement the regularization processing on the aforementioned loss function.
Referring to fig. 5, fig. 5 is another flow chart of a behavior prediction method according to an embodiment of the present disclosure. The behavior prediction method can be applied to the electronic device, and the flow of the behavior prediction method can include:
in 201, an electronic device acquires a time series data sequence corresponding to the electronic device, where the time series data sequence includes a plurality of preset types of data corresponding to different time points.
In the embodiment of the application, as shown in fig. 3, the electronic device uses the current time point as a starting point, obtains a plurality of pieces of preset type data corresponding to different time points in the forward direction, and forms a time sequence data sequence corresponding to the electronic device by using the obtained plurality of pieces of preset type data corresponding to different time points. For example, the electronic device may obtain the preset type data of the N time points forward with the current time point as a starting point, where the intervals of the two adjacent time points are the same.
It should be noted that the preset type data acquired in the embodiment of the present application includes external environment related data, such as temperature, light, place, sound, weather, and the like, user state related data, such as posture, speed, usage habits of the mobile phone, personal basic information, and the like, and electronic device state related data, such as power consumption, resource usage status, network status, and the like.
In 202, the electronic device performs data extraction on the time series data sequence according to different starting time points and sliding time windows with different durations to obtain window data corresponding to each sliding time window.
In the embodiment of the application, after the time sequence data sequence is obtained, the electronic device further extracts the obtained time sequence data sequence according to a preset number of sliding time windows with different durations, wherein each sliding time window obtains a plurality of window data, and each window data comprises preset type data of a plurality of time points. Any window data reflects the behavior of the user in the time interval corresponding to the window data, such as getting up, working, sitting on a subway, driving, sitting on a bus, and the like.
It should be noted that, when the electronic device performs data extraction according to each sliding time window, the starting time points of the data extraction are different. For example, in the embodiment of the present application, a sliding time window a with a duration of t +1 time points, a sliding time window B with a duration of 3/2t +1 time points, and a sliding time window C with a duration of 5t +1 time points are provided, where the sliding time window a takes the current time point as a start time point of data extraction, the sliding time window B takes the t/2 time point before the current time point as a start time point of data extraction, and the sliding time window C takes the t time point before the current time period as a start time point of data extraction, as shown in fig. 4. The sliding time window a extracts X window data (including t +1 time point preset type data), the sliding time window B extracts Y window data (including 3/2t +1 time point preset type data), and the sliding time window C extracts Z window data (including 5t +1 time point preset type data), so that X > Y > Z.
At 203, the electronic device inputs the window data corresponding to each sliding time window into different encoder neural networks for feature extraction, so as to obtain features corresponding to each sliding time window, wherein the number of features output by the different encoder neural networks for feature extraction is the same.
In the embodiment of the application, corresponding to different sliding time windows, the encoder neural network for extracting the characteristics of the window data extracted by the encoder neural network is trained in advance, and when the encoder neural network is trained, the quantity of the characteristics output by the different encoder neural networks for extracting the characteristics is the same through parameter setting.
In the embodiment of the application, after extracting the window data corresponding to each sliding time window, the electronic device further inputs the window data corresponding to each sliding time window into different encoder neural networks for feature extraction, so as to obtain the features corresponding to each sliding time window.
For example, assuming that a sliding time window a, an encoder neural network a corresponding to the sliding time window a, a sliding time window B, an encoder neural network B corresponding to the sliding time window B, and a sliding time window C, an encoder neural network C corresponding to the sliding time window C are preset, wherein the electronic device inputs window data extracted by the sliding time window a into the encoder neural network a for feature extraction, inputs window data extracted by the sliding time window B into the encoder neural network B for feature extraction, and inputs window data extracted by the sliding time window C into the encoder neural network C for feature extraction, the encoder neural network a, the encoder neural network B, and the encoder neural network C have different "lengths" of window data input thereto, but the encoder neural network a, the encoder neural network B, and the encoder neural network C have different "lengths" of window data input thereto, The encoder neural network B and the encoder neural network C extract features of the input window data, and the number of the output features is the same.
It should be noted that, in this embodiment of the application, specific models and topology structures of each encoder neural network are not limited, a single-layer recurrent neural network may be used for training to obtain the encoder neural network, a multi-layer recurrent neural network may be used for training to obtain the encoder neural network, and a convolutional neural network, or a variant thereof, or a neural network with other network structures may be used for training to obtain the encoder neural network. For example, in the embodiment of the present application, a recurrent neural network may be used to train and obtain an encoder neural network
At 204, the electronic device performs behavior prediction on the user according to the features corresponding to the sliding time windows and a pre-trained behavior prediction model to obtain a prediction result.
In the embodiment of the application, a behavior prediction model for predicting the behavior of the user is also trained in advance, wherein the behavior prediction model can be stored locally in the electronic device or stored in a remote server. In this way, after the electronic device performs feature extraction on the window data corresponding to each sliding time window to obtain the features corresponding to each sliding time window, the electronic device further obtains a behavior prediction model for predicting the behavior of the user from the local, or obtains a behavior prediction model for predicting the behavior of the user from a remote server.
After the pre-trained behavior prediction model is obtained, the electronic device performs behavior prediction on the user according to the characteristics corresponding to each sliding time window and the pre-trained behavior prediction model to obtain a prediction result, namely, the upcoming behavior of the user is predicted according to the historical behavior sequence of the user under different duration scales.
After obtaining the prediction result of the user, the electronic device may further perform an intelligent service for the user according to the prediction result, for example, if the obtained prediction result is that the user is going to "go home", a route to go home may be recommended to the user, or if the obtained prediction result is that the user is going to "eat", a nearby restaurant may be recommended to the user.
The embodiment of the application also provides a behavior prediction device. Referring to fig. 6, fig. 6 is a schematic structural diagram of a behavior prediction apparatus according to an embodiment of the present disclosure. The behavior prediction device is applied to an electronic device, and includes a data acquisition module 301, a data extraction module 302, a feature extraction module 303, and a behavior prediction module 304, as follows:
the data acquisition module 301 is configured to acquire a time sequence data sequence corresponding to the electronic device, where the time sequence data sequence includes multiple preset types of data corresponding to different time points;
the data extraction module 302 is configured to perform data extraction on the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
a feature extraction module 303, configured to perform feature extraction on the window data corresponding to each sliding time window to obtain features corresponding to each sliding time window;
and the behavior prediction module 304 is configured to perform behavior prediction on the user according to the features corresponding to the sliding time windows and a pre-trained behavior prediction model to obtain a prediction result.
In an embodiment, when performing data extraction on the time series data sequence according to sliding time windows of different durations, the data extraction module 302 may be configured to:
and according to different starting time points, performing data extraction on the time sequence data sequence according to each sliding time window.
In an embodiment, when acquiring a time series data sequence of a corresponding electronic device, the data acquisition module 301 may be configured to:
judging whether preset type data corresponding to the time point exists or not;
if so, acquiring preset type data corresponding to the time point;
if not, acquiring the preset type data closest to the time point as the preset type data corresponding to the time point.
In an embodiment, when performing feature extraction on the window data corresponding to each sliding time window, the feature extraction module 303 may be configured to:
and inputting window data corresponding to each sliding time window into different encoder neural networks for feature extraction, wherein the number of features output by the different encoder neural networks for feature extraction is the same.
In one embodiment, the behavior prediction apparatus further includes a model training module, which, before acquiring the time-series data sequence of the corresponding electronic device,
the data obtaining module 301 is further configured to obtain a time series data sequence sample, where the time series data sequence sample is a historical time series data sequence of the corresponding electronic device;
the data extraction module 302 is further configured to perform data extraction on the time sequence data sequence samples according to each sliding time window to obtain window data samples corresponding to each sliding time window;
the feature extraction module 303 is further configured to perform feature extraction on the window data samples corresponding to each sliding time window to obtain feature samples corresponding to each sliding time window;
and the model training module is used for carrying out model training according to the characteristic samples corresponding to the sliding windows to obtain a behavior prediction model.
In an embodiment, when performing model training according to the feature samples corresponding to the sliding windows, the model training module may be configured to:
constructing a recurrent neural network and constructing a loss function corresponding to the recurrent neural network;
inputting the characteristic sample corresponding to each sliding window into the recurrent neural network, obtaining the loss value of the recurrent neural network according to the loss function, and reversely transmitting the loss value to the recurrent neural network.
In an embodiment, before inputting the feature samples corresponding to each sliding window into the recurrent neural network, the model training module is further configured to:
and carrying out regularization processing on the loss function.
It should be noted that the behavior prediction apparatus provided in the embodiment of the present application and the behavior prediction method in the foregoing embodiment belong to the same concept, and any method provided in the behavior prediction method embodiment may be run on the behavior prediction apparatus, and a specific implementation process thereof is described in detail in the behavior prediction method embodiment and is not described here again.
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program stored in the storage medium is executed on a computer, the computer is caused to execute the steps in the behavior prediction method provided in this embodiment. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
The embodiment of the present application further provides an electronic device, which includes a memory and a processor, where the processor executes the steps in the behavior prediction method provided in this embodiment by calling a computer program stored in the memory.
In an embodiment, an electronic device is also provided. Referring to fig. 7, the electronic device includes a processor 401 and a memory 402. The processor 401 is electrically connected to the memory 402.
The processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device and processes data by running or loading a computer program stored in the memory 402 and calling data stored in the memory 402.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the computer programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.
In this embodiment, the processor 401 in the electronic device loads instructions corresponding to one or more processes of the computer program into the memory 402 according to the following steps, and the processor 401 runs the computer program stored in the memory 402, so as to implement various functions, as follows:
acquiring a time sequence data sequence corresponding to the electronic equipment, wherein the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points;
performing data extraction on the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window;
and performing behavior prediction on the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result.
Referring to fig. 8, fig. 8 is another schematic structural diagram of the electronic device according to the embodiment of the present disclosure, and the difference from the electronic device shown in fig. 7 is that the electronic device further includes components such as an input unit 403 and an output unit 404.
The input unit 403 may be used for receiving input numbers, character information, or user characteristic information (such as fingerprints), and generating a keyboard, a mouse, a joystick, an optical or trackball signal input, etc., related to user setting and function control, among others.
The output unit 404 may be used to display information input by the user or information provided to the user, such as a screen.
In this embodiment, the processor 401 in the electronic device loads instructions corresponding to one or more processes of the computer program into the memory 402 according to the following steps, and the processor 401 runs the computer program stored in the memory 402, so as to implement various functions, as follows:
acquiring a time sequence data sequence corresponding to the electronic equipment, wherein the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points;
performing data extraction on the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window;
and performing behavior prediction on the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result.
In an embodiment, when performing data extraction on the time series data according to sliding time windows of different durations, the processor 401 may perform:
and according to different starting time points, performing data extraction on the time sequence data sequence according to each sliding time window.
In an embodiment, in acquiring the time series data sequence of the corresponding electronic device, the processor 401 may perform:
judging whether preset type data corresponding to the time point exists or not;
if so, acquiring preset type data corresponding to the time point;
if not, acquiring the preset type data closest to the time point as the preset type data corresponding to the time point.
In an embodiment, when performing feature extraction on window data corresponding to each sliding time window, the processor 401 may perform:
and inputting window data corresponding to each sliding time window into different encoder neural networks for feature extraction, wherein the number of features output by the different encoder neural networks for feature extraction is the same.
In an embodiment, before acquiring the time series data sequence of the corresponding electronic device, the processor 401 may perform:
acquiring a time sequence data sequence sample, wherein the time sequence data sequence sample is a historical time sequence data sequence of corresponding electronic equipment;
performing data extraction on the time sequence data sequence samples according to the sliding time windows to obtain window data samples corresponding to the sliding time windows;
extracting the characteristics of the window data samples corresponding to the sliding time windows to obtain characteristic samples corresponding to the sliding time windows;
and performing model training according to the characteristic samples corresponding to the sliding windows to obtain a behavior prediction model.
In an embodiment, when performing model training according to the feature samples corresponding to the sliding windows, the processor 401 may perform:
constructing a recurrent neural network and constructing a loss function corresponding to the recurrent neural network;
inputting the characteristic sample corresponding to each sliding window into the recurrent neural network, obtaining the loss value of the recurrent neural network according to the loss function, and reversely transmitting the loss value to the recurrent neural network.
In an embodiment, before inputting the feature samples corresponding to each sliding window into the recurrent neural network, the processor 401 may perform:
and carrying out regularization processing on the loss function.
It should be noted that the electronic device provided in the embodiment of the present application and the behavior prediction method in the foregoing embodiment belong to the same concept, and any method provided in the behavior prediction method embodiment may be executed on the electronic device, and a specific implementation process thereof is described in detail in the behavior prediction method embodiment, and is not described here again.
It should be noted that, for the behavior prediction method of the embodiment of the present application, it can be understood by those skilled in the art that all or part of the process of implementing the behavior prediction method of the embodiment of the present application can be implemented by controlling the relevant hardware through a computer program, where the computer program can be stored in a computer readable storage medium, such as a memory of an electronic device, and executed by at least one processor in the electronic device, and during the execution process, the process of the embodiment of the behavior prediction method can be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.
In the behavior prediction apparatus according to the embodiment of the present application, each functional module may be integrated into one processing chip, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.
The behavior prediction method, the behavior prediction device, the storage medium, and the electronic device provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A behavior prediction method applied to electronic equipment is characterized by comprising the following steps:
acquiring a time sequence data sequence corresponding to the electronic equipment, wherein the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points;
performing data extraction on the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window;
and performing behavior prediction on the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result.
2. The behavior prediction method according to claim 1, wherein the data extraction of the time series data sequence according to the sliding time windows with different durations comprises:
and according to different starting time points, performing data extraction on the time sequence data sequence according to each sliding time window.
3. The behavior prediction method according to claim 1, wherein the obtaining of the time series data sequence corresponding to the electronic device comprises:
judging whether preset type data corresponding to the time point exists or not;
if so, acquiring preset type data corresponding to the time point;
if not, acquiring the preset type data closest to the time point as the preset type data corresponding to the time point.
4. The behavior prediction method according to claim 1, wherein the performing feature extraction on the window data corresponding to each sliding time window includes:
and inputting window data corresponding to each sliding time window into different encoder neural networks for feature extraction, wherein the number of features output by the different encoder neural networks for feature extraction is the same.
5. The behavior prediction method according to any one of claims 1 to 4, wherein before the obtaining the time series data sequence corresponding to the electronic device, further comprising:
acquiring a time sequence data sequence sample, wherein the time sequence data sequence sample is a historical time sequence data sequence corresponding to the electronic equipment;
performing data extraction on the time sequence data sequence samples according to the sliding time windows to obtain window data samples corresponding to the sliding time windows;
extracting the characteristics of the window data samples corresponding to the sliding time windows to obtain characteristic samples corresponding to the sliding time windows;
and performing model training according to the characteristic samples corresponding to the sliding windows to obtain the behavior prediction model.
6. The behavior prediction method according to claim 5, wherein performing model training according to the feature samples corresponding to the sliding windows comprises:
constructing a recurrent neural network and constructing a loss function corresponding to the recurrent neural network;
inputting the characteristic samples corresponding to the sliding windows into the recurrent neural network, obtaining the loss value of the recurrent neural network according to the loss function, and reversely transmitting the loss value to the recurrent neural network.
7. The behavior prediction method according to claim 6, wherein before inputting the feature samples corresponding to the sliding windows into the recurrent neural network, the method further comprises:
and carrying out regularization processing on the loss function.
8. A behavior prediction device applied to an electronic device includes:
the data acquisition module is used for acquiring a time sequence data sequence corresponding to the electronic equipment, and the time sequence data sequence comprises a plurality of preset types of data corresponding to different time points;
the data extraction module is used for extracting data of the time sequence data sequence according to sliding time windows with different durations to obtain window data corresponding to each sliding time window;
the characteristic extraction module is used for extracting the characteristics of the window data corresponding to each sliding time window to obtain the characteristics corresponding to each sliding time window;
and the behavior prediction module is used for predicting the behavior of the user according to the characteristics corresponding to each sliding time window and a pre-trained behavior prediction model to obtain a prediction result.
9. A storage medium having stored thereon a computer program, characterized in that, when the computer program is run on a computer, it causes the computer to execute the behavior prediction method according to any one of claims 1 to 7.
10. An electronic device comprising a processor and a memory, the memory storing a computer program, wherein the processor is configured to perform the behavior prediction method of any one of claims 1 to 7 by invoking the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910282131.6A CN111798018A (en) | 2019-04-09 | 2019-04-09 | Behavior prediction method, behavior prediction device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910282131.6A CN111798018A (en) | 2019-04-09 | 2019-04-09 | Behavior prediction method, behavior prediction device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111798018A true CN111798018A (en) | 2020-10-20 |
Family
ID=72805370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910282131.6A Pending CN111798018A (en) | 2019-04-09 | 2019-04-09 | Behavior prediction method, behavior prediction device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111798018A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113077292A (en) * | 2021-04-20 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | User classification method and device, storage medium and electronic equipment |
| CN113341919A (en) * | 2021-05-31 | 2021-09-03 | 中国科学院重庆绿色智能技术研究院 | Computing system fault prediction method based on time sequence data length optimization |
| CN113409135A (en) * | 2021-06-30 | 2021-09-17 | 中国工商银行股份有限公司 | Model training method and device, behavior prediction method and device, equipment and medium |
| CN113469142A (en) * | 2021-03-12 | 2021-10-01 | 山西长河科技股份有限公司 | Classification method, device and terminal for monitoring video time-space information fusion |
| CN113971478A (en) * | 2021-09-28 | 2022-01-25 | 北京百度网讯科技有限公司 | Subway running state prediction method and device, electronic equipment and storage medium |
| CN114647853A (en) * | 2022-03-01 | 2022-06-21 | 深圳开源互联网安全技术有限公司 | Method and system for improving distributed application program vulnerability detection accuracy |
| CN114663691A (en) * | 2022-05-24 | 2022-06-24 | 浙江大华技术股份有限公司 | Method and device for positioning foothold and electronic equipment |
| CN115049015A (en) * | 2022-07-14 | 2022-09-13 | 北京中科心研科技有限公司 | Method, device and equipment for aligning time sequence data after sliding window and storage medium |
| CN115422264A (en) * | 2022-11-02 | 2022-12-02 | 苏州浪潮智能科技有限公司 | Time sequence data processing method, device and equipment and readable storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007223494A (en) * | 2006-02-24 | 2007-09-06 | Fuji Heavy Ind Ltd | Vehicle behavior estimation and prediction device and vehicle stabilization control system |
| GB201603472D0 (en) * | 2016-02-29 | 2016-04-13 | Fujitsu Ltd | Method and apparatus for generating time series data sets for predictive analysis |
| CN106529721A (en) * | 2016-11-08 | 2017-03-22 | 安徽大学 | Advertisement click-through rate predication system based on deep characteristic extraction and predication method thereof |
| CN106651030A (en) * | 2016-12-21 | 2017-05-10 | 重庆邮电大学 | Method for predicting user participation behavior of hot topic by improved RBF neural network |
| US20180041536A1 (en) * | 2016-08-02 | 2018-02-08 | Invincea, Inc. | Methods and apparatus for detecting and identifying malware by mapping feature data into a semantic space |
| GB201800841D0 (en) * | 2017-04-07 | 2018-03-07 | Adobe Systems Inc | Forecasting multiple poses based on a graphical image |
| CN108076224A (en) * | 2017-12-21 | 2018-05-25 | 广东欧珀移动通信有限公司 | application control method, device and storage medium and mobile terminal |
| CN108196998A (en) * | 2018-01-02 | 2018-06-22 | 联想(北京)有限公司 | A kind of state identification method, mobile equipment and server |
| CN108615096A (en) * | 2018-05-10 | 2018-10-02 | 平安科技（深圳）有限公司 | Server, the processing method of Financial Time Series and storage medium |
| WO2019007253A1 (en) * | 2017-07-06 | 2019-01-10 | 阿里巴巴集团控股有限公司 | Image recognition method, apparatus and device, and readable medium |
| CN109241946A (en) * | 2018-10-11 | 2019-01-18 | 平安科技（深圳）有限公司 | Abnormal behaviour monitoring method, device, computer equipment and storage medium |
| CN109242207A (en) * | 2018-10-10 | 2019-01-18 | 中山大学 | A kind of Financial Time Series prediction technique based on deeply study |
| US20190034937A1 (en) * | 2016-03-31 | 2019-01-31 | Alibaba Group Holding Limited | Problem Prediction Method and System |
| CN109299812A (en) * | 2018-08-23 | 2019-02-01 | 河海大学 | A kind of Forecasting Flood method based on deep learning model and KNN real time correction |
| US20190075123A1 (en) * | 2017-09-06 | 2019-03-07 | Rank Software Inc. | Systems and methods for cyber intrusion detection and prevention |
-
2019
- 2019-04-09 CN CN201910282131.6A patent/CN111798018A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007223494A (en) * | 2006-02-24 | 2007-09-06 | Fuji Heavy Ind Ltd | Vehicle behavior estimation and prediction device and vehicle stabilization control system |
| GB201603472D0 (en) * | 2016-02-29 | 2016-04-13 | Fujitsu Ltd | Method and apparatus for generating time series data sets for predictive analysis |
| US20190034937A1 (en) * | 2016-03-31 | 2019-01-31 | Alibaba Group Holding Limited | Problem Prediction Method and System |
| US20180041536A1 (en) * | 2016-08-02 | 2018-02-08 | Invincea, Inc. | Methods and apparatus for detecting and identifying malware by mapping feature data into a semantic space |
| CN106529721A (en) * | 2016-11-08 | 2017-03-22 | 安徽大学 | Advertisement click-through rate predication system based on deep characteristic extraction and predication method thereof |
| CN106651030A (en) * | 2016-12-21 | 2017-05-10 | 重庆邮电大学 | Method for predicting user participation behavior of hot topic by improved RBF neural network |
| GB201800841D0 (en) * | 2017-04-07 | 2018-03-07 | Adobe Systems Inc | Forecasting multiple poses based on a graphical image |
| WO2019007253A1 (en) * | 2017-07-06 | 2019-01-10 | 阿里巴巴集团控股有限公司 | Image recognition method, apparatus and device, and readable medium |
| US20190075123A1 (en) * | 2017-09-06 | 2019-03-07 | Rank Software Inc. | Systems and methods for cyber intrusion detection and prevention |
| CN108076224A (en) * | 2017-12-21 | 2018-05-25 | 广东欧珀移动通信有限公司 | application control method, device and storage medium and mobile terminal |
| CN108196998A (en) * | 2018-01-02 | 2018-06-22 | 联想(北京)有限公司 | A kind of state identification method, mobile equipment and server |
| CN108615096A (en) * | 2018-05-10 | 2018-10-02 | 平安科技（深圳）有限公司 | Server, the processing method of Financial Time Series and storage medium |
| CN109299812A (en) * | 2018-08-23 | 2019-02-01 | 河海大学 | A kind of Forecasting Flood method based on deep learning model and KNN real time correction |
| CN109242207A (en) * | 2018-10-10 | 2019-01-18 | 中山大学 | A kind of Financial Time Series prediction technique based on deeply study |
| CN109241946A (en) * | 2018-10-11 | 2019-01-18 | 平安科技（深圳）有限公司 | Abnormal behaviour monitoring method, device, computer equipment and storage medium |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469142A (en) * | 2021-03-12 | 2021-10-01 | 山西长河科技股份有限公司 | Classification method, device and terminal for monitoring video time-space information fusion |
| CN113469142B (en) * | 2021-03-12 | 2022-01-14 | 山西长河科技股份有限公司 | Classification method, device and terminal for monitoring video time-space information fusion |
| CN113077292A (en) * | 2021-04-20 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | User classification method and device, storage medium and electronic equipment |
| CN113341919A (en) * | 2021-05-31 | 2021-09-03 | 中国科学院重庆绿色智能技术研究院 | Computing system fault prediction method based on time sequence data length optimization |
| CN113409135A (en) * | 2021-06-30 | 2021-09-17 | 中国工商银行股份有限公司 | Model training method and device, behavior prediction method and device, equipment and medium |
| CN113971478B (en) * | 2021-09-28 | 2023-11-21 | 北京百度网讯科技有限公司 | Subway running state prediction method and device, electronic equipment and storage medium |
| CN113971478A (en) * | 2021-09-28 | 2022-01-25 | 北京百度网讯科技有限公司 | Subway running state prediction method and device, electronic equipment and storage medium |
| CN114647853A (en) * | 2022-03-01 | 2022-06-21 | 深圳开源互联网安全技术有限公司 | Method and system for improving distributed application program vulnerability detection accuracy |
| CN114647853B (en) * | 2022-03-01 | 2023-06-23 | 深圳开源互联网安全技术有限公司 | Method and system for improving vulnerability detection accuracy of distributed application program |
| CN114663691A (en) * | 2022-05-24 | 2022-06-24 | 浙江大华技术股份有限公司 | Method and device for positioning foothold and electronic equipment |
| CN115049015A (en) * | 2022-07-14 | 2022-09-13 | 北京中科心研科技有限公司 | Method, device and equipment for aligning time sequence data after sliding window and storage medium |
| CN115049015B (en) * | 2022-07-14 | 2023-04-18 | 北京中科心研科技有限公司 | Method, device and equipment for aligning time sequence data after sliding window and storage medium |
| CN115422264A (en) * | 2022-11-02 | 2022-12-02 | 苏州浪潮智能科技有限公司 | Time sequence data processing method, device and equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111798018A (en) | Behavior prediction method, behavior prediction device, storage medium and electronic equipment | |
| CN111813532B (en) | Image management method and device based on multitask machine learning model | |
| CN111797858A (en) | Model training method, behavior prediction method, device, storage medium and equipment | |
| CN111797288A (en) | Data screening method and device, storage medium and electronic equipment | |
| CN111797302A (en) | Model processing method and device, storage medium and electronic equipment | |
| CN111798259A (en) | Application recommendation method and device, storage medium and electronic equipment | |
| CN111797861A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| KR20180132493A (en) | System and method for determinig input character based on swipe input | |
| CN111797870A (en) | Optimization method and device of algorithm model, storage medium and electronic equipment | |
| CN111797854A (en) | Scene model establishing method and device, storage medium and electronic equipment | |
| CN111800445B (en) | Message pushing method and device, storage medium and electronic equipment | |
| CN111797874B (en) | Behavior prediction method and device, storage medium and electronic equipment | |
| CN111796925A (en) | Method and device for screening algorithm model, storage medium and electronic equipment | |
| CN111798019B (en) | Intention prediction method, intention prediction device, storage medium and electronic equipment | |
| CN111797867A (en) | System resource optimization method and device, storage medium and electronic equipment | |
| CN111797289A (en) | Model processing method and device, storage medium and electronic equipment | |
| CN111797261A (en) | Feature extraction method and device, storage medium and electronic equipment | |
| CN111797986A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN111796663B (en) | Scene recognition model updating method and device, storage medium and electronic equipment | |
| CN111796992B (en) | Behavior preference determination method and apparatus, storage medium and electronic device | |
| CN111797299A (en) | Model training method, webpage classification method, device, storage medium and equipment | |
| CN111797301A (en) | Activity prediction method, activity prediction device, storage medium and electronic equipment | |
| CN111797878A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN111797075A (en) | Data recovery method and device, storage medium and electronic equipment | |
| CN111797863A (en) | Model training method, data processing method, device, storage medium and 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 |