CN111191834A - User behavior prediction method and device and server - Google Patents
User behavior prediction method and device and server Download PDFInfo
- Publication number
- CN111191834A CN111191834A CN201911364013.6A CN201911364013A CN111191834A CN 111191834 A CN111191834 A CN 111191834A CN 201911364013 A CN201911364013 A CN 201911364013A CN 111191834 A CN111191834 A CN 111191834A
- Authority
- CN
- China
- Prior art keywords
- period
- data
- user
- training sample
- riding
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims description 65
- 230000006399 behavior Effects 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 24
- 230000001351 cycling effect Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 9
- 238000007477 logistic regression Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 239000000835 fiber Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method and a device for predicting user behavior and a server. The method comprises the following steps: acquiring historical riding data of a target user; extracting feature data of a target user from historical riding data according to preset feature indexes; and inputting the characteristic data of the target user into a preset prediction model to obtain a corresponding prediction result, wherein the prediction result represents the riding times of the target user in a future setting period. The method can predict the riding requirement of the user in a future period of time according to the riding data of the user in the past period of time, and is beneficial to more scientifically and more specifically managing the vehicle and providing service for the user.
Description
Technical Field
The present invention relates to the technical field of vehicle management, and more particularly, to a method and an apparatus for predicting user behavior, and a server.
Background
At present, shared vehicles become important tools for people to go out. The healthy operation of the shared vehicle can not be managed and maintained by operators, for example, the operators can recover and maintain fault vehicles, and for example, the operators can adjust the number of vehicles thrown in different areas according to the use requirements and move the vehicles from a place with smaller demand to a place with larger demand.
The use of the shared vehicles by the users has certain randomness in time and space, which brings certain uncertain factors to the management of the shared vehicles and increases the difficulty of the management of the shared vehicles. If the riding behaviors of the users using the shared vehicle can be predicted, the method is beneficial for operators to manage the vehicle more scientifically and pertinently and provide services for the users.
Therefore, it is necessary to provide a new technical solution for predicting the usage behavior of the users of the shared vehicle.
Disclosure of Invention
The invention provides a new technical scheme for predicting the use behaviors of shared vehicle users.
According to a first aspect of the present invention, there is provided a method for predicting user behavior, comprising:
acquiring historical riding data of a target user;
extracting feature data of the target user from the historical riding data according to preset feature indexes;
and inputting the characteristic data of the target user into a preset prediction model to obtain a corresponding prediction result, wherein the prediction result represents the riding times of the target user in a future setting period.
Optionally, the prediction model is obtained by:
obtaining a training sample set, wherein the training sample set comprises a plurality of training samples, each training sample is cycling data of a user in a first period, and a label of each training sample is cycling times of the user in a second period, wherein the first period and the second period are adjacent to each other;
extracting feature data of each training sample according to the feature indexes;
and training a preset initial model by using the characteristic data and the label of each training sample through a machine learning method so as to adjust the parameters of the initial model and obtain the prediction model.
Optionally, the extracting, according to the feature index, feature data of each training sample includes:
extracting at least one of the following data to obtain the characteristic data:
the total number of rides in the first period;
the time interval from the last ride to the first period termination point in the first period;
the total amount of the riding orders in the first period.
Optionally, the initial model is a logistic regression model.
Optionally, the training a preset initial model by using the feature data and the label of each training sample through a machine learning method to adjust parameters of the initial model to obtain the prediction model includes:
substituting the characteristic data into the initial model to obtain a corresponding output result;
substituting the output result and the corresponding label into a preset loss function to obtain the loss of the output result, wherein the loss function is obtained based on the maximum likelihood estimation;
and updating the parameters of the initial model according to the loss to obtain the prediction model.
According to a second aspect of the present invention, there is provided an apparatus for predicting user behavior, comprising:
the historical data acquisition module is used for acquiring historical riding data of a target user;
the target user characteristic extraction module is used for extracting the characteristic data of the target user from the historical riding data according to preset characteristic indexes;
and the prediction module is used for inputting the characteristic data into a preset prediction model to obtain a corresponding prediction result, and the prediction result represents the riding times of the target user in a future setting period.
Optionally, the apparatus further comprises a model obtaining module, the model obtaining module comprising:
the training sample set comprises a plurality of training samples, each training sample is cycling data of a user in a first period, and a label of each training sample is cycling times of the user in a second period, wherein the first period and the second period are adjacent to each other;
the characteristic extraction unit is used for extracting characteristic data of each training sample according to the characteristic indexes;
and the training unit is used for training a preset initial model by using the characteristic data and the label of each training sample through a machine learning method so as to adjust the parameters of the initial model and obtain the prediction model.
According to a third aspect of the present invention, there is provided a server comprising:
a memory for storing executable commands;
a processor for performing the method of the first aspect of the invention under control of the executable command.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium storing executable instructions which, when executed by a processor, implement the method of the first aspect of the present invention.
According to the user behavior prediction method, the characteristic data are extracted from the historical riding data of the target user, the characteristic data are input into the pre-trained prediction model to obtain the prediction result, the riding requirement of the user in a future period can be predicted according to the riding data of the user in the past period, and the method is beneficial to more scientifically and more specifically managing vehicles and providing services for the user.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a schematic diagram of a shared vehicle system that may be used to implement an embodiment of the present invention.
FIG. 2 is a schematic diagram of an electronic device that may be used to implement an embodiment of the invention.
Fig. 3 is a flowchart of a prediction method of user behavior according to an embodiment of the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
< hardware configuration >
FIG. 1 is a block diagram of a hardware configuration of a shared vehicle system 100 that may be used to implement an embodiment of the invention.
As shown in fig. 1, the shared vehicle system 100 includes a server 1000, a terminal device 2000, a shared vehicle 3000, and a network 4000.
The server 1000 is used to provide management functions for sharing vehicles. The server 1000 may be a unitary server or a distributed server across multiple computers or computer data centers. In some embodiments, each server may include hardware, software, or embedded logic components or a combination of two or more such components for performing the appropriate functions supported or implemented by the server.
The terminal device 2000 is a terminal device for a user to send an unlocking request, and may be a mobile phone, a portable computer, a tablet computer, a palmtop computer, a wearable device, or the like.
The shared vehicle 3000 is a vehicle that can be used by a user, and the shared vehicle 3000 has a special device, such as an electronic lock, that controls the user's usage right in addition to the component structure of the unshared vehicle.
The network 4000 may be a wireless communication network or a wired communication network, and may be a local area network or a wide area network. In the shared vehicle system 100 shown in fig. 1, the terminal device 2000 and the server 1000, the shared vehicle 3000, and the server 1000 may each communicate via the network 4000.
In one embodiment, the server 1000 and the terminal device 2000 have the structure of the electronic device 1100 shown in fig. 2.
As shown in fig. 2, the electronic device 1100 includes a processor 1110, a memory 1120, an interface device 1130, a communication device 1140, an output device 1150, and an input device 1160. The processor 1110 is, for example, a central processing unit CPU, a microprocessor MCU, or the like. The memory 1120 is, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, or the like. The interface device 1130 is, for example, a USB interface, a headphone interface, or the like. The communication device 1140 is capable of wired or wireless communication, for example. The output device 1150 is, for example, a liquid crystal display, a touch panel, a speaker, or the like. The input device 1160 is, for example, a touch screen, a keyboard, a mouse, a microphone, or the like. In this embodiment, the terminal device 2000 further includes a positioning device, such as a GPS positioning module, which can be used to obtain the geographic location of the terminal device 2000.
Before using the shared vehicle, the user may send an unlocking request to the server 1000 through the terminal device 2000, the server 1000 verifies the unlocking request, for example, detects the user qualification, the vehicle use status, and the like, and if the verification passes, the server 100 sends an unlocking instruction to the shared vehicle 3000, and the shared vehicle 3000 unlocks in response to the unlocking instruction. Accordingly, after the use is finished, the user closes the electronic lock of the shared vehicle 3000, the shared vehicle 3000 reports lock closing information to the server 1000, and the server settles the current order according to the lock closing information and communicates with the terminal device 2000 to complete the deduction.
It should be understood that although fig. 1 shows only one server 1000, terminal device 2000, and shared vehicle 3000, the number of each is not meant to be limiting, and multiple servers 1000, multiple terminal devices 2000, and multiple shared vehicles 3000 may be included in the shared vehicle system 100.
The shared vehicle system 100 shown in FIG. 1 is illustrative only and is not intended to limit the invention, its application, or uses in any way.
< general idea >
The present specification provides a solution for predicting usage behavior of shared vehicle users. The scheme is based on the regularity of the user riding behaviors in a continuous time period, or the recent riding behaviors of the user and the future riding behaviors have strong correlation. Therefore, the scheme predicts the future riding requirements of the user based on the previous riding data of the user.
< method examples >
The present embodiment provides a method for predicting user behavior, for example, implemented by the server 1000 shown in fig. 1.
In this embodiment, before predicting the behavior of the target user, a prediction model for predicting the behavior of the user is trained.
The training process of the predictive model may be divided into the following steps S100-S300.
In step S100, a training sample set is obtained, where the training sample set includes a plurality of training samples, each training sample is cycling data of a user in a first period, and a label of each training sample is a cycling number of the user in a second period, where the first period and the second period are adjacent to each other.
In this embodiment, the server 1000 may obtain a training sample set according to historical cycling data of a large number of users. The above-mentioned historical riding data is stored in the server 1000, or in another storage server.
In this embodiment, each training sample is cycling data of a user in a first period, and the corresponding label is cycling times of the same user in a second period. Here, the first period and the second period are adjacent, and the first period precedes the second period. For example, the first period is the first three weeks of a month (assuming the month comprises four weeks), and the second period is the fourth week of the month. The lengths of the first period and the second period may be set on the scale of week, month, quarter, etc., according to the actual situation.
In this embodiment, the first period and the second period are connected first, and the ending point of the first period and the starting point of the second period can be regarded as the same time point and are also the reference points in the prediction problem. With respect to the reference point, the first period is a past period of time and the second period is a future period of time. Therefore, the training sample set can be used for predicting the riding times in a future period of time according to the riding data in the past period of time.
In this embodiment, the riding data refers to data related to the behavior of the user using the shared vehicle, and includes, for example, the date, duration, order amount, and the like of each riding. The riding data of the first period is data of all riding orders of the user in the first period. The number of rides during the second period, i.e., the total number of rides that the user has performed in their entirety during the second period. And taking the process of unlocking to locking each time as a riding process.
In one example, assume the value diRepresenting the riding data of the ith user in the first period (i is more than or equal to 1 and i is an integer), niRepresenting the number of times the ith user rides during the second period, the ith sample and its label may be denoted as { d }i，niCan represent the training sample set as
Where N represents the number of samples in the training sample set.
In step S200, feature data of each training sample is extracted according to a preset feature index.
In this embodiment, the characteristic index refers to an index that can describe a user behavior characteristic and predict a future riding demand of the user according to the user behavior characteristic among multiple indexes included in the riding data.
In one example, the characteristic index is set to at least one of the following indexes: total number of rides in the first period; the time interval from the last riding to the first period ending point in the first period; total amount of riding orders in the first period.
In this example, each time the process from unlocking to locking is taken as a riding process, and the total number of riding times in the first period can be calculated. It is easy to understand that the total number of rides in the first period can reflect the frequency of rides of the user, and the frequency of rides of the user has a trend of keeping stable in a period of time, so the total number of rides in the first period can be used as a characteristic index.
In this example, the time interval from the last ride to the end of the first period in the first period, i.e., the time interval from the last ride to the predicted reference point. The time interval is, for example, the number of days in the interval. It is understood that the time interval can also be used as a characteristic indicator.
In the example, the total amount of the riding orders in the first period is also taken as a characteristic index in consideration of the influence of economic factors on the future riding behaviors of the user.
The characteristic indexes can effectively represent the characteristics of the riding behaviors of the user, and are favorable for predicting the future riding requirements of the user.
In this embodiment, according to a preset characteristic index, the original riding data is analyzed and processed to obtain data corresponding to the characteristic index, that is, characteristic data.
In one example, assume that the preset characteristic indexes are l in sequence1、l2、l3Then the characteristic data l can be expressed as l ═ l (l)1l2，l3) Characteristic data l of the ith subscriberiCan be represented as li＝(l1 i，l2 i，l3 i) Wherein l isiFrom diIs obtained by extraction.
In step S300, a preset initial model is trained through a machine learning method using the feature data and the label of each training sample to adjust parameters of the initial model, so as to obtain a prediction model.
In this embodiment, the initial model is a logistic regression model. The logistic regression model is a generalized linear regression analysis model and can be used for the two-classification and multi-classification problems.
The following describes the modeling and training process in this embodiment by taking the case of two classes as an example. In this case, it is assumed that the output result of the model is zero or non-zero, that is, the predicted result is that the user will or will not ride the shared vehicle for a set period in the future (the period is the same as the second period in length).
First, the essence of the binary problem is to divide the sample points into two classes (positive and negative samples, corresponding to labels of zero and non-zero) by determining the boundary, where the equation is established as Eθ(X)＝θTX, where θ represents a model parameter and θ ═ θ (θ)0，θ1……θn)TN is not less than 1 and n is an integer, thetaTA transposed matrix representing θ, X represents a feature vector and X is (1, X)1，x2……xn)T. To make the boundary non-linear, the coordinates of the feature vector X may be the high power or product of the feature index, e.g., X1＝l1，x2＝l2，x3＝l3，x4＝l1×l1，x5＝l1×l2. It is readily understood that the decision boundary is to satisfy EθA set of points corresponding to a feature vector X where (X) ═ 0.
Secondly, E is addedθ(X) conversion of the function into a probability function, i.e. Eθ(X) carry-in sigmoid function
Obtaining a logistic regression model
Next, a loss function of the logistic regression model is established. In the embodiment, the loss function is obtained by adopting maximum likelihood estimation, so that the accuracy of the output result of the logistic regression model can be accurately measured. By hθThe value of (X) represents the probability of a positive sample, with y-1 representing a positive sample and y-0 representing a negative sample, then:
P(y＝1|X；θ)＝hθ(X)；
P(y＝0|X；θ)＝1-hθ(X)。
combining the above two formulas, with P (y | X; theta) ═ hθ(X))y(1-(hθ(X))1-y. For m samples (m ≧ 1 and m is an integer), the maximum likelihood estimate is solved:
the final loss function is obtained by taking the logarithm of the above equation and deforming:
training the model based on the logistic regression model and the loss function, and comprising the following steps of: substituting the characteristic data into the initial model to obtain a corresponding output result; substituting the output result and the corresponding label into a preset loss function to obtain the loss of the output result, wherein the loss function is obtained based on the maximum likelihood estimation; the parameters of the initial model are updated according to the loss.
And updating the model parameters for multiple times based on a gradient descent method according to the characteristic data and the labels of the multiple samples until the result is converged, thereby obtaining the trained prediction model.
The model training process described above is directed to a two-class case, which can be decomposed into multiple two-class problems for a multiple-class case (the output of the model is a non-negative integer, i.e., the predicted result is the number of times the user rides the shared vehicle during the future setup), or the two-class problem is transitioned to the multiple-class problem using the softmax function.
The user behavior is predicted based on the prediction model, and the method comprises the following steps of S1100-S1300.
In step S1100, the historical cycling data of the target user is acquired.
In this embodiment, the time range involved by the historical riding data of the target user is greater than or equal to the length of the first period in the foregoing. The historical cycling data of the target user is stored in the server 1000 or in another storage server.
In step S1200. And extracting the characteristic data of the target user from the historical riding data according to the preset characteristic indexes.
In this embodiment, the feature index is consistent with the feature index in the previous model training phase, and is not described here again.
In step S1300, the feature data of the target user is input into the prediction model described above, and a corresponding prediction result is obtained, where the prediction result represents the number of riding times of the target user in the future setting period.
In this embodiment, the future setting period is the same as the second period described above.
According to the user behavior prediction method, the characteristic data are extracted from the historical riding data of the target user, the characteristic data are input into the pre-trained prediction model to obtain the prediction result, the riding requirement of the user in a future period can be predicted according to the riding data of the user in the past period, and the method is beneficial to more scientifically and more specifically managing vehicles and providing services for the user.
< apparatus embodiment >
The embodiment provides a user behavior prediction device which comprises a historical data acquisition module, a target user feature extraction module and a prediction module.
And the historical data acquisition module is used for acquiring the historical riding data of the target user.
And the target user characteristic extraction module is used for extracting the characteristic data of the target user from the historical riding data according to the preset characteristic indexes.
And the prediction module is used for inputting the characteristic data into a preset prediction model to obtain a corresponding prediction result, and the prediction result represents the riding times of the target user in a future setting period.
In one example, the apparatus for predicting user behavior further includes a model obtaining module, which includes a sample obtaining unit, a feature extracting unit, and a training unit.
The training sample set comprises a plurality of training samples, each training sample is cycling data of a user in a first period, and a label of each training sample is cycling times of the user in a second period, wherein the first period and the second period are adjacent.
And the characteristic extraction unit is used for extracting the characteristic data of each training sample according to the characteristic indexes.
And the training unit is used for training a preset initial model by using the characteristic data and the label of each training sample through a machine learning method so as to adjust the parameters of the initial model and obtain the prediction model.
In one example, the feature extraction unit is to: extracting at least one of the following data to obtain characteristic data: total number of rides in the first period; the time interval from the last riding to the first period ending point in the first period; total amount of riding orders in the first period.
In one example, the initial model is a logistic regression model.
In one example, the training unit is to: substituting the characteristic data into the initial model to obtain a corresponding output result; substituting the output result and the corresponding label into a preset loss function to obtain the loss of the output result, wherein the loss function is obtained based on the maximum likelihood estimation; and updating the parameters of the initial model according to the loss to obtain a prediction model.
< Server embodiment >
The embodiment provides a server which comprises a memory and a processor. The memory is used for storing executable commands. The processor is used for executing the prediction method of the user behavior described in the embodiment of the method under the control of the executable command.
< computer-readable storage Medium embodiment >
The present embodiment provides a computer-readable storage medium, in which an executable command is stored, and when the executable command is executed by a processor, the method for predicting user behavior described in the method embodiment of the present invention is implemented.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (9)
1. A method of predicting user behavior, comprising:
acquiring historical riding data of a target user;
extracting feature data of the target user from the historical riding data according to preset feature indexes;
and inputting the characteristic data of the target user into a preset prediction model to obtain a corresponding prediction result, wherein the prediction result represents the riding times of the target user in a future setting period.
2. The method of claim 1, wherein the predictive model is obtained by:
obtaining a training sample set, wherein the training sample set comprises a plurality of training samples, each training sample is cycling data of a user in a first period, and a label of each training sample is cycling times of the user in a second period, wherein the first period and the second period are adjacent to each other;
extracting feature data of each training sample according to the feature indexes;
and training a preset initial model by using the characteristic data and the label of each training sample through a machine learning method so as to adjust the parameters of the initial model and obtain the prediction model.
3. The method of claim 1, wherein said extracting feature data of each of the training samples according to the feature index comprises:
extracting at least one of the following data to obtain the characteristic data:
the total number of rides in the first period;
the time interval from the last ride to the first period termination point in the first period;
the total amount of the riding orders in the first period.
4. The method of claim 2, wherein the initial model is a logistic regression model.
5. The method of claim 4, wherein the training a preset initial model by a machine learning method using the feature data and the labels of each training sample to adjust parameters of the initial model to obtain the prediction model comprises:
substituting the characteristic data into the initial model to obtain a corresponding output result;
substituting the output result and the corresponding label into a preset loss function to obtain the loss of the output result, wherein the loss function is obtained based on the maximum likelihood estimation;
and updating the parameters of the initial model according to the loss to obtain the prediction model.
6. An apparatus for predicting user behavior, comprising:
the historical data acquisition module is used for acquiring historical riding data of a target user;
the target user characteristic extraction module is used for extracting the characteristic data of the target user from the historical riding data according to preset characteristic indexes;
and the prediction module is used for inputting the characteristic data into a preset prediction model to obtain a corresponding prediction result, and the prediction result represents the riding times of the target user in a future setting period.
7. The apparatus of claim 6, wherein the apparatus further comprises a model acquisition module comprising:
the training sample set comprises a plurality of training samples, each training sample is cycling data of a user in a first period, and a label of each training sample is cycling times of the user in a second period, wherein the first period and the second period are adjacent to each other;
the characteristic extraction unit is used for extracting characteristic data of each training sample according to the characteristic indexes;
and the training unit is used for training a preset initial model by using the characteristic data and the label of each training sample through a machine learning method so as to adjust the parameters of the initial model and obtain the prediction model.
8. A server, comprising:
a memory for storing executable commands;
a processor for performing the method of any one of claims 1-5 under the control of the executable command.
9. A computer-readable storage medium storing executable instructions that, when executed by a processor, implement the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911364013.6A CN111191834A (en) | 2019-12-26 | 2019-12-26 | User behavior prediction method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911364013.6A CN111191834A (en) | 2019-12-26 | 2019-12-26 | User behavior prediction method and device and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111191834A true CN111191834A (en) | 2020-05-22 |
Family
ID=70709395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911364013.6A Withdrawn CN111191834A (en) | 2019-12-26 | 2019-12-26 | User behavior prediction method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191834A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116397A (en) * | 2020-09-25 | 2020-12-22 | 贝壳技术有限公司 | User behavior characteristic real-time processing method and device, storage medium and electronic equipment |
| CN112184939A (en) * | 2020-09-03 | 2021-01-05 | 珠海格力电器股份有限公司 | Method and device for judging employee attendance, storage medium and electronic equipment |
| CN112418569A (en) * | 2021-01-25 | 2021-02-26 | 北京云真信科技有限公司 | User portrait determination method, electronic equipment and computer readable storage medium |
| CN113112309A (en) * | 2021-05-08 | 2021-07-13 | 上海钧正网络科技有限公司 | User management method, device, electronic equipment and medium |
| CN113822709A (en) * | 2021-09-15 | 2021-12-21 | 摩拜(北京)信息技术有限公司 | Travel data processing method and device and server |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919996A (en) * | 2015-12-25 | 2017-07-04 | 滴滴（中国）科技有限公司 | A kind of destination Forecasting Methodology and device |
| CN107578294A (en) * | 2017-09-28 | 2018-01-12 | 北京小度信息科技有限公司 | User's behavior prediction method, apparatus and electronic equipment |
| CN109003157A (en) * | 2018-06-22 | 2018-12-14 | 北京摩拜科技有限公司 | Vehicles management method, device, server and system |
| CN109636446A (en) * | 2018-11-16 | 2019-04-16 | 北京奇虎科技有限公司 | Customer churn prediction technique, device and electronic equipment |
| CN110097193A (en) * | 2019-04-28 | 2019-08-06 | 第四范式（北京）技术有限公司 | The method and system of training pattern and the method and system of forecasting sequence data |
| CN110502336A (en) * | 2019-07-05 | 2019-11-26 | 深圳壹账通智能科技有限公司 | A kind of starting method, apparatus, equipment and the readable storage medium storing program for executing of server |
| CN110555714A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | method and apparatus for outputting information |
| CN112329986A (en) * | 2020-10-13 | 2021-02-05 | 厦门市交通研究中心 | Parking management method, device and equipment for shared bicycle |
| CN113191560A (en) * | 2021-05-08 | 2021-07-30 | 北京工业大学 | Sharing bicycle short-time demand prediction method and system for improving SGM (1,1) model |
| CN113822709A (en) * | 2021-09-15 | 2021-12-21 | 摩拜(北京)信息技术有限公司 | Travel data processing method and device and server |
-
2019
- 2019-12-26 CN CN201911364013.6A patent/CN111191834A/en not_active Withdrawn
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919996A (en) * | 2015-12-25 | 2017-07-04 | 滴滴（中国）科技有限公司 | A kind of destination Forecasting Methodology and device |
| CN107578294A (en) * | 2017-09-28 | 2018-01-12 | 北京小度信息科技有限公司 | User's behavior prediction method, apparatus and electronic equipment |
| CN110555714A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术（北京）有限公司 | method and apparatus for outputting information |
| CN109003157A (en) * | 2018-06-22 | 2018-12-14 | 北京摩拜科技有限公司 | Vehicles management method, device, server and system |
| CN109636446A (en) * | 2018-11-16 | 2019-04-16 | 北京奇虎科技有限公司 | Customer churn prediction technique, device and electronic equipment |
| CN110097193A (en) * | 2019-04-28 | 2019-08-06 | 第四范式（北京）技术有限公司 | The method and system of training pattern and the method and system of forecasting sequence data |
| CN110502336A (en) * | 2019-07-05 | 2019-11-26 | 深圳壹账通智能科技有限公司 | A kind of starting method, apparatus, equipment and the readable storage medium storing program for executing of server |
| CN112329986A (en) * | 2020-10-13 | 2021-02-05 | 厦门市交通研究中心 | Parking management method, device and equipment for shared bicycle |
| CN113191560A (en) * | 2021-05-08 | 2021-07-30 | 北京工业大学 | Sharing bicycle short-time demand prediction method and system for improving SGM (1,1) model |
| CN113822709A (en) * | 2021-09-15 | 2021-12-21 | 摩拜(北京)信息技术有限公司 | Travel data processing method and device and server |
Non-Patent Citations (2)
| Title |
|---|
| 苏影: "基于数据分析的共享单车动态调配优化研究" * |
| 韩震等: "基于共享单车出行数据的用户行为分析" * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184939A (en) * | 2020-09-03 | 2021-01-05 | 珠海格力电器股份有限公司 | Method and device for judging employee attendance, storage medium and electronic equipment |
| CN112184939B (en) * | 2020-09-03 | 2022-03-18 | 珠海格力电器股份有限公司 | Method and device for judging employee attendance, storage medium and electronic equipment |
| CN112116397A (en) * | 2020-09-25 | 2020-12-22 | 贝壳技术有限公司 | User behavior characteristic real-time processing method and device, storage medium and electronic equipment |
| CN112418569A (en) * | 2021-01-25 | 2021-02-26 | 北京云真信科技有限公司 | User portrait determination method, electronic equipment and computer readable storage medium |
| CN113112309A (en) * | 2021-05-08 | 2021-07-13 | 上海钧正网络科技有限公司 | User management method, device, electronic equipment and medium |
| CN113822709A (en) * | 2021-09-15 | 2021-12-21 | 摩拜(北京)信息技术有限公司 | Travel data processing method and device and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191834A (en) | User behavior prediction method and device and server | |
| EP3446260B1 (en) | Memory-efficient backpropagation through time | |
| US20190370659A1 (en) | Optimizing neural network architectures | |
| US11915123B2 (en) | Fusing multimodal data using recurrent neural networks | |
| CN107040397B (en) | Service parameter acquisition method and device | |
| CN107103036B (en) | Method and equipment for acquiring application downloading probability and programmable equipment | |
| CN110807515A (en) | Model generation method and device | |
| CN106407381B (en) | A kind of method and apparatus of the pushed information based on artificial intelligence | |
| CN108769125B (en) | Application recommendation method and device, storage medium and computer equipment | |
| CN111027707A (en) | Model optimization method and device and electronic equipment | |
| CN113326991A (en) | Automatic authorization method, device, computer equipment and storage medium | |
| CN111311030A (en) | User credit risk prediction method and device based on influence factor detection | |
| CN111275205A (en) | Virtual sample generation method, terminal device and storage medium | |
| CN112182281B (en) | Audio recommendation method, device and storage medium | |
| CN111104874A (en) | Face age prediction method, training method and device of model and electronic equipment | |
| CN113256390A (en) | Product recommendation method and device, computer equipment and storage medium | |
| WO2023077989A1 (en) | Incremental machine learning for a parametric machine learning model | |
| CN114639072A (en) | People flow information generation method and device, electronic equipment and computer readable medium | |
| CN114328995A (en) | Content recommendation method, device, equipment and storage medium | |
| CN111767290B (en) | Method and apparatus for updating user portraits | |
| Prashanth et al. | Simultaneous perturbation methods for adaptive labor staffing in service systems | |
| US10997535B1 (en) | System, method, and computer program for predicting delays in delivering a project to a customer | |
| CN110942306A (en) | Data processing method and device and electronic equipment | |
| CN114637560B (en) | Device management method, electronic device, and computer program product | |
| CN115129838B (en) | Model training and dialogue data processing method, device, equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201215 Address after: Room 168, building 6, 741 Hangzhou Road, Yangpu District, Shanghai 200090 Applicant after: HANHAI INFORMATION TECHNOLOGY SHANGHAI Co.,Ltd. Address before: Room Bnan 1231, 2 bungalows, No. 5 Road, College, Haidian District, Beijing, 100191 Applicant before: BEIJING MOBIKE TECHNOLOGY Co.,Ltd. |
|
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200522 |