CN112241896A

CN112241896A - Information pushing method, device, equipment and computer readable medium

Info

Publication number: CN112241896A
Application number: CN201910649921.3A
Authority: CN
Inventors: 古宁; 李超; 汪双权; 孙启堂; 陈敏亮
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Baidu Online Network Technology Beijing Co Ltd; Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-07-18
Filing date: 2019-07-18
Publication date: 2021-01-19

Abstract

The invention provides an information pushing method, an information pushing device, information pushing equipment and a computer readable medium, wherein the method comprises the following steps: extracting characteristic data to be predicted from the collected motion data; inputting the characteristic data into a classification model, and outputting a behavior type by the classification model; and pushing corresponding information according to the behavior type. According to the embodiment of the invention, the current behavior type of the user can be judged by collecting the current motion data of the user, so that corresponding information can be pushed according to the behavior type of the user.

Description

Information pushing method, device, equipment and computer readable medium

Technical Field

The present invention relates to the field of internet technologies, and in particular, to an information pushing method, an information pushing device, information pushing equipment, and a computer readable medium.

Background

With the development of internet technology, information push technology has been greatly developed. Most of information push methods in the prior art push corresponding information to users based on search keywords, user tags and other modes for the users. However, the current information pushing method cannot push information according to the behavior of the user, and the real-time performance, click rate and conversion rate of the information are still not high enough.

Disclosure of Invention

Embodiments of the present invention provide an information pushing method, apparatus, device, and computer readable medium, so as to solve or alleviate one or more technical problems in the prior art.

In a first aspect, an embodiment of the present invention provides an information pushing method, including:

extracting characteristic data to be predicted from the collected motion data;

inputting the characteristic data into a classification model, and outputting a behavior type by the classification model;

and pushing corresponding information according to the behavior type.

In one embodiment, the motion data is motion data collected by a sensor.

In one embodiment, the motion data comprises: acceleration data of a three-dimensional vector.

In one embodiment, extracting feature data to be predicted from the acquired motion data includes:

preprocessing the motion data;

extracting sample data from the preprocessed motion data;

and extracting the time domain characteristics and the frequency domain characteristics of the sample data, and merging the extracted time domain characteristics and the extracted frequency domain characteristics to form the characteristic data.

In one embodiment, the method further comprises: training the classification model, wherein training the classification model comprises:

extracting feature data for training and carrying out label classification;

splitting the training characteristic data after label classification into training set data and test set data;

inputting the split training set data and test set data into the classification model for iterative training.

In one embodiment, pushing the corresponding information according to the behavior type includes:

inputting the behavior type as a characteristic parameter into a click rate estimation model;

obtaining the click probability of the model output information estimated by the click rate;

and pushing corresponding information according to the click probability.

In a second aspect, an embodiment of the present invention provides an information pushing apparatus, including:

the extraction module is used for extracting feature data to be predicted from the collected motion data;

the classification module is used for inputting the characteristic data into a classification model and outputting a behavior type by the classification model;

and the pushing module is used for pushing the corresponding information according to the behavior type.

In one embodiment, the motion data is motion data collected by a sensor.

In one embodiment, the motion data acquired in the acquisition module includes: acceleration data of a three-dimensional vector.

In one embodiment, the extraction module comprises:

the preprocessing submodule is used for preprocessing the motion data;

the sample extraction submodule is used for extracting sample data from the preprocessed motion data;

and the merging submodule is used for extracting the time domain characteristics and the frequency domain characteristics of the sample data and merging the extracted time domain characteristics and the frequency domain characteristics to form the characteristic data.

In one embodiment, the method further comprises a training module for training the classification model, wherein the training module comprises:

the label classification submodule is used for extracting feature data for training and performing label classification;

the splitting submodule is used for splitting the training characteristic data after the label classification into training set data and test set data;

and the iterative training submodule is used for inputting the split training set data and the test set data into the classification model for iterative training.

In one embodiment, the push module comprises:

the characteristic input submodule is used for inputting the behavior type as a characteristic parameter into a click rate estimation model;

the probability obtaining submodule is used for obtaining the click probability of the model output information estimated by the click rate;

and the pushing submodule is used for pushing corresponding information according to the click probability.

In a third aspect, an embodiment of the present invention provides an information pushing apparatus, where the apparatus includes:

one or more processors;

storage means for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the information push method of the first aspect described above.

In one possible design, the information pushing apparatus includes a processor and a memory, the memory is used for storing a program that supports the information pushing apparatus to execute the information pushing method in the first aspect, and the processor is configured to execute the program stored in the memory. The information pushing device may further comprise a communication interface for the information pushing device to communicate with other devices or a communication network.

In a fourth aspect, an embodiment of the present invention provides a computer-readable medium for storing computer software instructions for an information pushing apparatus, which includes a program for executing the information pushing method according to the first aspect.

In the above-mentioned solution, the embodiment of the present invention may determine the current behavior type of the user by collecting the current motion data of the user, so that the corresponding information may be pushed according to the behavior type of the user.

In another scheme, the current behavior type of the user is used as a characteristic parameter and input into the click rate estimation model, so that the accuracy of pushing information to the user can be improved.

The foregoing summary is provided for the purpose of description only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and following detailed description.

Drawings

In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.

FIG. 1 is a flowchart of an information pushing method according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating steps S120 according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating the steps of classification model training according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating steps S140 according to an embodiment of the present invention;

FIG. 5 is a block diagram of an information pushing apparatus according to an embodiment of the present invention;

FIG. 6 is a block diagram of the connection of the decimation module according to an embodiment of the present invention;

FIG. 7 is a connection block diagram of a training module according to an embodiment of the present invention;

FIG. 8 is a connection block diagram of a push module according to an embodiment of the invention;

fig. 9 is a block diagram of an information pushing apparatus according to another embodiment of the present invention.

Detailed Description

In the following, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive. The embodiment of the invention mainly provides a method and a device for pushing communication information, and the technical scheme is expanded and described through the following embodiments respectively.

The present invention provides an information pushing method and apparatus, and the following describes in detail a specific processing flow and principle of the information pushing method and apparatus according to the embodiments of the present invention.

Fig. 1 is a flowchart of an information pushing method according to an embodiment of the present invention. In an embodiment, an information pushing method according to an embodiment of the present invention may include the following steps:

s110: and extracting characteristic data to be predicted from the collected motion data.

The motion data is motion data collected by a sensor. In one embodiment, an acceleration sensor may be used for data acquisition, and the motion data includes: acceleration data of a three-dimensional vector. The acceleration of the three-dimensional vector is used to characterize the acceleration in three directions. When acquiring sensor data, different frequencies may be used for different scenarios, such as a sampling frequency of 100Hz, i.e. 100 pieces of raw sensor data per second. Wherein the scene may include: static, walking, running, public transit, subway, taxi, etc. For each scene, different types of mobile devices may be used for data acquisition. And each acquisition behavior can be within 2 minutes at the shortest and within 10 minutes at the longest, so that the diversity of the acquired data is ensured.

S120: inputting the characteristic data into a classification model, and outputting the behavior type by the classification model.

Inputting the extracted feature data into a trained classification model, and outputting behavior types corresponding to the feature data by the classification model, such as: stationary, running, sitting on a subway, etc.

S130: and pushing corresponding information according to the behavior type.

As shown in fig. 2, in one embodiment, the step S110 includes:

s1101: and preprocessing the motion data.

In one embodiment, if the data collected by different devices are checked to see whether the data collected by the devices have the condition of non-uniform data magnitude, and if so, the data are rejected.

S1102: sample data is extracted from the motion data after the preprocessing.

In most scenarios, the user's behavior does not need to employ high frequency sampled data. For example, when the user is in a stationary state, or on a subway or a car moving at a constant speed, the motion data does not change much, so that the data may be sampled at a frequency lower than 100Hz in the actual prediction of the user behavior. In one embodiment, three data sets of 50Hz, 20Hz, and 10Hz may be used to lower the sampling frequency of the data, which is equivalent to sampling every 2, 5, and 10 data sets of the original 100Hz collected data.

S1103: and extracting the time domain characteristics and the frequency domain characteristics of the sample data, and merging the extracted time domain characteristics and the extracted frequency domain characteristics to form characteristic data.

In one embodiment, when performing feature extraction on sample data, a batch of data is processed, and the batch of data is called a feature window (window). The feature window represents the number of accommodated feature data. Considering the continuity of user behaviors, the sampled feature windows need to be overlapped, namely, the previous window and the next window need to have repeated data. The size of the characteristic window and the sampling frequency have the following relationship: identifying a behavior requires time-the size of the feature window-the sampling frequency. The time required for the recognition behavior represents the time at which feature data is recognized. And respectively extracting time domain characteristics, such as maximum value, minimum value, average value and the like, of the sample data on one direction axis of one characteristic window. The direction axes represent three-dimensional directions of space, such as an x-axis direction, a y-axis direction, and a z-axis direction, which are perpendicular to each other. And simultaneously carrying out Fourier transform on the characteristic data, and then extracting the frequency domain characteristics on the frequency domain after the Fourier transform. Then, a plurality of time domain features and frequency domain features are respectively extracted from the three direction axes, and finally, the data of the three direction axes are combined into a piece of feature data.

As shown in fig. 3, in an embodiment, the classification model needs to be trained before being applied, and the specific training steps may include:

s210: and extracting feature data for training and performing label classification.

In one embodiment, after extracting the feature data to be predicted from the acquired motion data, a classification label is labeled for each feature data. Each behavior corresponds to a different classification label, for example, the label of the static behavior is labeled as 1, and the label of the walking behavior is labeled as 0.

S220: and splitting the training characteristic data after the label classification into training set data and test set data.

In one embodiment, a data set consisting of the entire feature data may be split into a training set and a test set, and then the model may be iteratively trained using different machine learning algorithms. For example, the training model may be a machine-learned multi-classification model, and when an input is a behavior feature, the behavior is output as to which of the above-mentioned classifications the behavior belongs. In one embodiment, the prediction results at different sampling frequencies, such as 10Hz, 20Hz, and 50Hz, can be tested separately to compare the accuracy of the results. Then, a compromise is made between high sampling frequency and accuracy, and the requirements of lower energy consumption and higher accuracy are met.

S230: inputting the split training set data and test set data into the classification model for iterative training.

In one embodiment, the motion data of the training set may be input into the classification model when training the classification model, and then learning training is performed according to the corresponding label classification. Then, the motion data of the test set can be input into the classification model, the classification accuracy is tested, and the training is sequentially iterated until the classification accuracy of the classification model reaches a preset threshold value, so that the training is completed.

In an embodiment, when pushing the corresponding information according to the behavior type in step S130, the predicted behavior type may be incorporated into the information targeting module, a user behavior targeting type is newly added to the targeting type of the quantitative delivery, and the type of the information targeted delivery is accepted. For example, when the acquired behavior type is running, the advertisement information of sports products such as running shoes and wristbands can be directionally pushed.

In addition, aiming at the estimation of the click rate of the bidding advertisement, the behavior type of the user can be introduced as a model characteristic parameter of the estimation of the click rate, so that the advertisement which is strongly related to the behavior type is recommended to the user according to the predicted behavior type, and the directional accuracy is improved. As shown in fig. 4, when the advertisement is pushed to the user through the click-through rate estimation model in step S130, the method may include:

s1301: and inputting the behavior type as a characteristic parameter into a click rate estimation model.

In one embodiment, the click through rate prediction model (CTR) may be any one of existing click through rate prediction models. The input parameters of the click rate prediction model may include: historical click rate, information location, time, user, etc. In one embodiment, the obtained behavior type may be input as a feature parameter into the click rate prediction model, and the click rate prediction model outputs a probability value of the clicked corresponding information.

S1302: and obtaining the click probability of the model output information estimated by the click rate.

S1303: and pushing corresponding information according to the click probability.

As shown in fig. 5, in an embodiment, the present invention further provides an information pushing apparatus, including:

and an acquisition module 110, configured to extract feature data to be predicted from the acquired motion data.

The motion data is motion data of the sensor. The motion data includes: acceleration data of a three-dimensional vector.

A classification module 120, configured to input the feature data into a classification model, and output a behavior type by the classification model.

And a pushing module 130, configured to push corresponding information according to the behavior type.

As shown in fig. 6, in one embodiment, the extraction module 110 includes:

the preprocessing submodule 1101 is configured to preprocess the motion data.

A sample extraction sub-module 1102 for extracting sample data from the pre-processed motion data.

And a merging submodule 1103, configured to extract the time domain features and the frequency domain features of the sample data, and merge the extracted time domain features and the extracted frequency domain features to form the feature data.

As shown in fig. 7, in an embodiment, a training module 200 is further included for training the classification model, where the training module 200 includes:

and the label classification submodule 210 is used for extracting the feature data for training and performing label classification.

The splitting sub-module 220 is configured to split the training feature data after the label classification into training set data and test set data.

And the iterative training submodule 230 is configured to input the split training set data and test set data into the classification model for iterative training.

As shown in fig. 8, in one embodiment, the pushing module 130 includes:

and the characteristic input submodule 1301 is used for inputting the behavior type as a characteristic parameter into a click rate estimation model.

And the probability obtaining submodule 1302 is configured to obtain the click probability of the model output information estimated by the click rate.

And the pushing submodule 1303 is used for pushing corresponding information according to the click probability.

The principle of the information pushing apparatus of this embodiment is similar to that of the information pushing method of the above embodiment, and therefore, the detailed description thereof is omitted.

In another embodiment, the present invention further provides an information pushing apparatus, as shown in fig. 9, the apparatus including: a memory 510 and a processor 520, the memory 510 having stored therein computer programs that are executable on the processor 520. The processor 520, when executing the computer program, implements the information pushing method in the above embodiments. The number of the memory 510 and the processor 520 may be one or more.

The apparatus further comprises:

the communication interface 530 is used for communicating with an external device to perform data interactive transmission.

Memory 510 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

If the memory 510, the processor 520, and the communication interface 530 are implemented independently, the memory 510, the processor 520, and the communication interface 530 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 9, but this does not indicate only one bus or one type of bus.

Optionally, in an implementation, if the memory 510, the processor 520, and the communication interface 530 are integrated on a chip, the memory 510, the processor 520, and the communication interface 530 may complete communication with each other through an internal interface.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

The computer readable medium described in embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the two. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable storage medium may even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

In embodiments of the present invention, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, input method, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, Radio Frequency (RF), etc., or any suitable combination of the preceding.

It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are 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 separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.

According to the embodiment of the invention, the current behavior type of the user can be judged by collecting the current motion data of the user, so that corresponding information can be pushed according to the behavior type of the user. In addition, the embodiment of the invention takes the current behavior type of the user as the characteristic parameter to be input into the click rate estimation model, thereby improving the accuracy of pushing information to the user.

The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims

1. An information pushing method, comprising:

extracting characteristic data to be predicted from the collected motion data;

and pushing corresponding information according to the behavior type.

2. The method of claim 1, wherein the motion data is motion data collected by a sensor.

3. The method of claim 1, wherein the motion data comprises: acceleration data of a three-dimensional vector.

4. The method according to any one of claims 1 to 3, wherein extracting feature data to be predicted from the acquired motion data comprises:

preprocessing the motion data;

extracting sample data from the preprocessed motion data;

5. The method of any one of claims 1-3, further comprising: training the classification model, wherein training the classification model comprises:

extracting feature data for training and carrying out label classification;

6. The method according to any one of claims 1 to 3, wherein pushing the corresponding information according to the behavior type includes:

and pushing corresponding information according to the click probability.

7. An information pushing apparatus, comprising:

8. The apparatus of claim 7, wherein the motion data is motion data collected by a sensor.

9. The apparatus of claim 7, wherein the motion data collected in the collection module comprises: acceleration data of a three-dimensional vector.

10. The apparatus of any one of claims 7-9, wherein the extraction module comprises:

the preprocessing submodule is used for preprocessing the motion data;

11. The apparatus of any one of claims 7-9, further comprising a training module for training the classification model, the training module comprising:

12. The apparatus of any of claims 7-9, wherein the push module comprises:

the characteristic input submodule is used for inputting the behavior type as a characteristic parameter into a click rate pre-estimated model;

the probability obtaining submodule is used for obtaining the click probability of the information output by the click rate estimation model;

13. An information push apparatus, characterized in that the apparatus comprises:

one or more processors;

storage means for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the information push method of any of claims 1-6.

14. A computer-readable medium, in which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the information push method according to any one of claims 1 to 6.