CN111966897A - Travel willingness sensing method and device, terminal and storage medium - Google Patents
Travel willingness sensing method and device, terminal and storage medium Download PDFInfo
- Publication number
- CN111966897A CN111966897A CN202010791316.2A CN202010791316A CN111966897A CN 111966897 A CN111966897 A CN 111966897A CN 202010791316 A CN202010791316 A CN 202010791316A CN 111966897 A CN111966897 A CN 111966897A
- Authority
- CN
- China
- Prior art keywords
- data
- behavior
- target user
- preset time
- historical
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (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 embodiment of the invention discloses a method, a device, a terminal and a storage medium for perceiving travel willingness. The method comprises the following steps: the method comprises the steps of obtaining car renting data of a target user within first preset time and behavior data of the target user within second preset time, and judging whether the user has first-direction behaviors or not by using a trained behavior discrimination model based on the car renting data and the behavior data; when the user has the first-direction behavior, acquiring vehicle browsing data of the user within a third preset time, and predicting the behavior intensity of the user by using the trained behavior intensity perception model and the vehicle browsing data; and acquiring vehicle interaction sequence data of the user within fourth preset time, and sensing the travel will of the user by using a trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity. The vehicle type meeting the travel will can be recommended to the user, the user experience is enhanced, the platform can also optimize the overall marketing strategy according to the vehicle type, and the matching efficiency of the sharing platform on the vehicle renting requirements of the user is improved.
Description
Technical Field
The embodiment of the invention relates to the field of deep learning, in particular to a method, a device, a terminal and a storage medium for perceiving travel willingness.
Background
With the increase of car renting demands of users, various car renting transaction platforms providing different services are continuously appeared.
In the prior art, a traditional trading platform generally performs regression prediction on the probability of subsequent trading of a single user and the trading scale of a partial or whole platform through historical trading information based on a machine learning or deep learning model. However, the method is mostly suitable for transaction platform scenes of high-frequency massive users, and relevant prediction is carried out on the basis of the assumption that the transaction preference of the users cannot be changed easily in a short period. However, car renting travel is a re-decision chain transaction behavior with low frequency and high unit price, car renting frequency of most users is once every several months, and willingness of specific car renting behaviors has a great relationship with car using scenes in different periods.
The problems of the prior art include at least: if the taxi renting trip intention of the user at every time cannot be well recognized, matching and recommendation of the vehicle are carried out only according to historical transaction information, the taxi renting intention of the user cannot be accurately sensed, user experience can be greatly reduced, and the demand matching efficiency of the sharing platform for the taxi renting of the user is reduced.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, a terminal and a storage medium for perceiving a travel intention, so as to recommend a vehicle type meeting the travel intention of a user with a strong intention to the user, enhance user experience, optimize an overall marketing strategy according to the vehicle type, and improve matching efficiency of a shared platform for the vehicle renting requirements of the user.
In a first aspect, an embodiment of the present invention provides a method for sensing a travel will, including:
the method comprises the steps of obtaining car renting data of a target user within first preset time and behavior data of the target user within second preset time, and judging whether the target user has first-direction behaviors or not by using a pre-trained behavior discrimination model based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time;
when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and acquiring vehicle interaction sequence data of the target user within fourth preset time, and sensing the travel will of the target user by using a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
Optionally, the training process of the behavior discrimination model includes:
acquiring behavior discrimination model training data of a sample user, wherein the behavior discrimination model training data comprises at least one of the following items: historical taxi renting data, historical chatting data and historical page series access data;
extracting historical order features of the historical taxi renting data;
extracting vehicle keywords in the historical chat data, and determining fully-connected word vectors based on the vehicle keywords;
performing statement on the historical page series access data to obtain a page access statement, and determining a behavior vector based on the page access statement;
and training by using the historical order features, the word vectors and the behavior vectors to obtain a second classifier which is used as the behavior discrimination model.
Optionally, the training process of the behavioral intensity perception model includes:
obtaining intensity perception model training data for a sample user, wherein the intensity perception model training data comprises at least one of: historical stay time data, historical vehicle access data and historical page access data;
and training by using the strength perception model training data to obtain a second classifier which is used as a behavior strength perception model.
Preferably, the training process of the behavior requirement model includes:
acquiring behavior demand model training data of a sample user, wherein the behavior demand model training data comprises historical car renting data and historical car interaction sequence data;
statement is carried out on the historical vehicle interaction sequence data to obtain historical vehicle interaction statements, and historical interaction vectors are determined by utilizing the historical vehicle interaction statements;
and training by using the historical taxi renting data and the historical interaction vector to obtain a plurality of classifiers serving as the behavior demand model.
Preferably, the acquiring of the behavior data of the target user includes:
obtaining chat data of the target user in a second preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in second preset time.
Preferably, the acquiring vehicle browsing data of the target user includes:
acquiring stay time data of the target user in a third preset time; and/or the presence of a gas in the gas,
acquiring vehicle access data of the target user within third preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in a third preset time.
Further, the determining, by using a pre-trained behavior discrimination model, whether the target user has a first directional behavior includes:
and when the target user does not have the first-direction behavior, storing the car renting data within the first preset time and/or the behavior data within the second preset time for updating and training the behavior discrimination model.
In a second aspect, an embodiment of the present invention further provides a device for sensing a trip intention, including:
a first direction behavior judgment module, configured to obtain car renting data of a target user within a first preset time and behavior data of the target user within a second preset time, and judge, based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time, whether the target user has a first direction behavior by using a pre-trained behavior judgment model
The behavior intensity prediction module is used for acquiring vehicle browsing data of the target user within a third preset time when the target user has the first-direction behavior, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and the intention demand perception module is used for acquiring vehicle interaction sequence data of the target user within fourth preset time, and perceiving the travel intention of the target user by utilizing a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
In a third aspect, an embodiment of the present invention further provides a terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the trip willingness sensing method according to any embodiment of the present application.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement a method for sensing a travel willingness, as provided in any embodiment of the present application.
According to the method, the device, the terminal and the storage medium for perceiving the travel will, vehicle renting data of a target user within a first preset time and behavior data of the target user within a second preset time are obtained, and whether the target user has a first-direction behavior or not is judged by using a pre-trained behavior discrimination model based on the vehicle renting data of the target user within the first preset time and the behavior data of the target user within the second preset time; when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time; and acquiring vehicle interaction sequence data of the target user within fourth preset time, and predicting the will vehicle type of the target user by using a pre-trained behavior demand model to sense the trip will of the user based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time. The vehicle type meeting the trip car renting intention of the user can be recommended to the user with a strong intention, the user experience is enhanced, the platform can also optimize the overall marketing strategy according to the vehicle type, and the matching efficiency of the shared platform to the car renting requirements of the user is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for sensing a trip intention according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a flow of perceiving a user's travel will according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for sensing a trip intention according to a second embodiment of the present invention;
fig. 4 is a block diagram of a device for sensing a trip intention according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a terminal according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through embodiments with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In the following embodiments, optional features and examples are provided in each embodiment, and various features described in the embodiments may be combined to form a plurality of alternatives, and each numbered embodiment should not be regarded as only one technical solution.
Example one
Fig. 1 is a schematic flow chart of a travel intention sensing method according to an embodiment of the present invention, and this embodiment is applicable to a situation of sensing a travel intention of a target user when a user rents a car on a car renting platform. The method may be executed by the apparatus for sensing travel will provided in the embodiment of the present invention, and the apparatus for sensing travel will may be configured in the terminal provided in the embodiment of the present invention, for example, may be configured in a computer device, and may also be configured in a mobile phone, which is not limited herein.
As shown in fig. 1, the method for sensing a trip will specifically includes the following steps:
s110, car renting data in first preset time and behavior data in second preset time of the target user are obtained, and whether the target user has first-direction behaviors or not is judged by using a pre-trained behavior judging model based on the car renting data in the first preset time and the behavior data in the second preset time.
The car renting data can be the model, the car renting time, the rent amount and the like of the car rented by the user within a first preset time, preferably, the first preset time can be one year, and exemplarily, the car renting data is the time at which the user rents which car, how long the car is rented, how much the rent amount is, and the like respectively within the last year; the behavior data refers to data obtained from behavior activities performed by the user on the platform application within a second preset time, preferably, the second preset time may be three months, and exemplarily, the behavior data may be data obtained according to the behavior activities performed each time the user enters the platform within approximately three months.
The first directional behavior may be that the trip will be positive feedback, that is, the user has a desire to rent a car for trip. And respectively extracting features of the car renting data in the first preset time and the behavior data in the second preset time, inputting the extracted features into a pre-trained behavior discrimination model, and judging whether the user has the willingness of renting the car to go out or not according to an output result. By acquiring multidimensional data of a user, the abnormal change of the trip willingness of renting the vehicle of the user can be more accurately identified by utilizing the neural network, and illustratively, the abnormal trip willingness can be that the vehicle is rented again for a short time after the vehicle is rented for a plurality of times at a fixed frequency, or the vehicle is rented for a plurality of times after the vehicle is rented for the vehicle type A, and the vehicle type B and the like.
Optionally, the acquiring the behavior data of the target user includes:
obtaining chat data of the target user in a second preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in second preset time.
The behavior data of the target user may be a chat record of the user in a second preset time, or may be page access data of the user, that is, a series of behavior data of a user access page generated according to a timeline every time the user enters the car rental platform in the second preset time, preferably, the user page access data includes all access data of different pages when the user enters the platform application every time in the second preset time, the second preset time may be within three months, exemplarily, the chat record of the user may be data acquired by the user according to a communication record with a car rental platform customer service in three months, or may be data acquired by a communication record of the user and a car owner, and the user page access data may include that the user opens a car rental application in nearly three months, first enters an application home page, and then searches for a vehicle of a certain vehicle type, the embodiment of the present invention does not specifically limit the contents of the car rental data within the first preset time and the contents of the behavior data within the second preset time.
Behavior data of the target user in the preset time is obtained, and whether the recent trip will of the user is judged conveniently.
And S120, when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time.
The vehicle browsing data refers to data determined according to behavior activities related to vehicle renting performed by a target user on the application platform. When the judgment result of the travel intention of the user by using the behavior judgment model is that the user has a first-direction behavior, namely the target user has the travel intention and wants to rent a car, at the moment, vehicle browsing data of the user in a third preset time of the platform application are obtained, data features extracted from the vehicle browsing data are input into the behavior intensity perception model, the travel intention intensity of the user is predicted, and the strength of the travel intention of the user is judged by using the output result. Preferably, the output of the behavior intensity perception model may be an intensity value of 0-1, a threshold value for determining the intensity of the user's travel will is set to be [0,1], the travel will is determined to be strong if the output is greater than or equal to the threshold value, and the travel will is determined to be weak if the output is less than the threshold value.
Optionally, the acquiring vehicle browsing data of the target user includes:
acquiring stay time data of the target user in a third preset time; and/or the presence of a gas in the gas,
acquiring vehicle access data of the target user within third preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in a third preset time.
The vehicle browsing data of the target user comprises the stay time length data of the user in a third preset time, which can be the stay time length when a plurality of vehicles are displayed on a certain page, the stay time length when a homepage of a certain vehicle is opened, or the total stay time length from entering the application platform to exiting; the vehicle browsing data may also include vehicle access data of the user within a third preset time, which type of vehicle the user has accessed, pictures, information, etc. of which vehicles the user has seen; the vehicle browsing data may further include page access data of the user within a third preset time, which may be the number of times and time of accessing a certain vehicle type, and may also be an access time interval of entering the platform application for multiple times, and preferably, the third preset time may be 3 to 5 days.
And vehicle browsing data in different aspects are obtained, so that the vehicle browsing data of the target user in the third preset time can be conveniently input into the behavior intensity perception model, and the willingness of the target user in the vehicle renting behavior can be predicted.
Optionally, the determining, by using a pre-trained behavior discrimination model, whether the target user has a first directional behavior includes:
and when the target user does not have the first-direction behavior, storing the car renting data within the first preset time and/or the behavior data within the second preset time for updating and training the behavior discrimination model.
When the travel intention judgment result of the behavior judgment model for the user is that the behavior does not have the first direction, namely the travel intention is negative feedback, the user can only browse at will at this time, or the user enters a platform application to see vehicle renting information such as vehicle returning time and the like during vehicle renting, and at this time, the acquired vehicle renting data of the user in the first preset time and the acquired behavior data in the second preset time can be stored so as to update a sample user data set for training the behavior judgment model and be used for updating and training the behavior judgment model.
The method and the device have the advantages that car renting data and behavior data of users without car renting intentions are stored, so that the sample user data set of the training behavior discrimination model can be expanded, and a data basis is provided for updating and training of the behavior discrimination model.
S130, vehicle interaction sequence data of the target user within fourth preset time are obtained, and the target user is subjected to travel willingness perception by means of a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
The vehicle interaction sequence data is data acquired according to a series of behaviors related to the vehicle performed by the target user within a fourth preset time, preferably, the fourth preset time can be three days, the vehicle interaction sequence data can be total data of interaction sequence data of different vehicles entering the platform application at different times within three days of the user, and exemplary interaction sequence data can be activities according to the following behaviors of the user: the user firstly enters all vehicle display pages, then clicks a detail page of a certain vehicle, shares information of the vehicle, or collects data acquired by vehicle information and the like.
And (3) performing feature vectorization on the vehicle interaction sequence data of the target user within the fourth preset time, inputting a result of the feature vectorization and the strength value of the vehicle renting intention of the user, which is obtained by predicting in the step (S120), into a pre-trained behavior demand model, and outputting to obtain a vehicle type meeting the vehicle renting intention of the user, namely realizing the perception of the trip intention of the target user.
All the operation behaviors of the user are converted into vectors, and the final taxi renting willingness requirement is judged by a bidirectional serialization method similar to a language text, so that the method has obvious advantages in a repeated comparison re-decision scene of taxi renting compared with the traditional one-way sequence structure model (such as a Markov chain model and an RNN model).
Referring to a perception flow diagram of the trip willingness of the user shown in fig. 2, car rental data of a target user in the last year and behavior data of the target user in the last 3 months are obtained, wherein the behavior data comprise IM chat data and page access data, and whether the target user has the trip willingness of car rental is judged by using a pre-trained behavior discrimination model based on the car rental data of the last year, the IM chat data of the last 3 months and the page access data of the last 3 months. If the user has the desire of renting the vehicle for traveling, vehicle browsing data of the user in nearly 3-5 days are obtained, the vehicle browsing data comprise the data of the stay time of the user in nearly 3-5 days, the data of vehicle access in nearly 3-5 days and the data of page access in nearly 3-5 days, and the behavior intensity of the user for renting the vehicle for traveling is predicted by utilizing a pre-trained behavior intensity perception model and the data of vehicle browsing in nearly 3-5 days. And acquiring vehicle interaction sequence data of the user in the last 3 days, and recommending a vehicle type meeting the travel will of the user to the user by using a pre-trained behavior demand model based on the vehicle interaction sequence data of the last 3 days and the predicted behavior intensity of the user.
If the user does not have the willingness of renting the vehicle to go out through the prediction of the behavior discrimination model, the user is judged to be only seen at will or the vehicle is renting and the user visits in the journey.
The trip willingness perception method provided by the embodiment of the invention comprises the steps of firstly obtaining car renting data in first preset time, chatting data in second preset time and page access data of a target user, and judging whether the target user has first-direction behaviors or not by using a pre-trained behavior discrimination model based on the car renting data in the first preset time and the chatting data and the page access data in the second preset time; when the target user has the first-direction behavior, obtaining stay time length data, vehicle access data and page access data of the target user within third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the stay time length data, the vehicle access data and the page access data within the third preset time; and acquiring vehicle interaction sequence data of the target user within fourth preset time, and predicting the will vehicle type of the target user by using a pre-trained behavior demand model to sense the trip will of the user based on the vehicle interaction sequence data within the fourth preset time and the predicted behavior intensity value. The vehicle type meeting the trip car renting intention of the user can be recommended to the user with a strong intention, the user experience is enhanced, the platform can also optimize the overall marketing strategy according to the vehicle type, and the matching efficiency of the shared platform to the car renting requirements of the user is improved.
Example two
Fig. 3 is a schematic flow chart of a travel will perception method according to a second embodiment of the present invention, and the present embodiment specifically explains training processes of a behavior discrimination model, a behavior intensity perception model, and a behavior demand model on the basis of the second embodiment. The embodiment of the invention and the method for sensing the travel will provided by the embodiment belong to the same inventive concept, and technical details which are not described in detail can be referred to the embodiment, and have the same technical effects.
As shown in fig. 3, the method for recommending vehicle data specifically includes the following steps:
s211, obtaining behavior discrimination model training data of the sample user, wherein the behavior discrimination model training data comprises at least one of the following items: historical car rental data, historical chat data, and historical page series access data.
Acquiring the stored historical data of all the sample users as training data of the behavior discrimination model, wherein the historical data of the sample users can comprise historical car renting data, historical chat data and historical page series access data of the sample users, and exemplarily, the historical car renting data can be car types and car renting time historically rented by the sample users, the method comprises the steps of obtaining total data such as car renting duration and rent, obtaining historical chat data from communication records of sample users and customer service, obtaining historical chat data from communication records of the sample users and car owners, obtaining historical page access data from the communication records of the sample users and car owners, and obtaining historical page access data from the historical page access data, wherein the historical page access data can be respectively determined according to series of behaviors of each sample user in a sample user group accessing a page each time.
And S221, extracting historical order features of historical car rental data.
The historical order characteristics refer to continuous and/or discrete variables which are extracted from historical car rental data of sample users and can represent historical car rental information, the continuous and/or discrete variables can be directly obtained from the historical car rental data, and can also be obtained by simply calculating and/or converting the historical car rental data.
S231, extracting vehicle keywords in the historical chat data, and determining a fully-connected word vector based on the vehicle keywords.
The historical chat data may be one or more sentences spoken by both chat parties, but the sentences include other words as sentence car rental components in addition to information of car rental related vehicles, so that text preprocessing needs to be performed on the historical chat data, vehicle keywords related to car rental are extracted, the vehicle keywords representing the vehicle information are represented as word vectors, and then the word vectors of all the keywords are fully connected.
S241, performing statement on the historical page series access data to obtain a page access statement, and determining a behavior vector based on the page access statement.
The historical page series access data is determined by the historical page series access records of the sample user, each step in the historical page series access process is subjected to statement to obtain a plurality of page access statements, and each statement is subjected to text vectorization to determine the behavior vector of the historical page access data. For example, the behavior vector may be determined by using a vector space model VSM, or may be determined by using a text distributed representation method, and the determination method of the behavior vector of the historical page series access data is not particularly limited in the embodiment of the present invention.
And S251, training by using the historical order features, the word vectors and the behavior vectors to obtain a second classifier which is used as a behavior discrimination model.
And inputting historical order features corresponding to historical car renting data of all sample users, word vectors expressed by car keywords in the historical chatting data and behavior vectors expressed by historical page access data into a convolutional neural network for training to obtain a two-classifier, and taking the two-classifier as a behavior discrimination model for judging whether the users have car renting intentions.
S212, obtaining strength perception model training data of the sample user, wherein the strength perception model training data comprises at least one of the following items: historical dwell time data, historical vehicle access data, and historical page access data.
The historical stay time data, the historical vehicle access data and the historical page access data of each access platform application of all sample users are obtained as the strength perception model training data set, the content of the stay time data, the historical vehicle access data and the historical page access data of the sample users can be the same as or different from the content of the vehicle browsing data of the target user in the third preset time in the step S120, and the historical stay time data, the historical vehicle access data and the historical page access data of the sample users are not specifically limited in the embodiment of the invention.
S222, training by using the strength perception model training data to obtain a second classifier which is used as a behavior strength perception model.
Inputting the historical stay time data, the historical vehicle access data and the historical page access data of all sample users into a classification model for performing classification training, and using the obtained classifier as a behavior intensity perception model to predict the vehicle renting behavior intensity of the target user. Illustratively, the behavior intensity perception model may be obtained by training using an XGBoost classification model.
Because car renting is a transaction behavior in a re-decision and medium-and-long-term decision process, decision periods of 3-5 days are respectively generated according to difference of weekdays and holidays, and because the re-decision enables part of users to continuously switch different car renting platforms for price comparison, the corresponding access times and stay time of the users are relatively fragmented, and therefore the two-classification behavior intensity perception model constructed through the characteristics can well represent the car renting willingness intensity of the users.
S232, acquiring behavior demand model training data of the sample user, wherein the behavior demand model training data comprises historical car renting data and historical car interaction sequence data.
The historical taxi renting data and the historical vehicle interaction sequence data of all sample users on the application platform are obtained to serve as a behavior demand model training data set, the historical taxi renting data of the sample users can be that the sample users rent a special car at a certain time, the content contained in the historical vehicle interaction sequence data can be the same as or different from the content contained in the vehicle interaction sequence data of the target users in the fourth preset time in the step S130, and the content of the historical taxi renting data and the content of the historical vehicle interaction sequence data of the sample users are not specifically limited.
And S242, performing statement on the historical vehicle interaction sequence data to obtain historical vehicle interaction statements, and determining historical interaction vectors by using the historical vehicle interaction statements.
The historical vehicle interaction sequence data is determined by the historical vehicle interaction records of the sample users, each step in each historical vehicle interaction record of each sample user is respectively statement, and the obtained interactive statements of all historical vehicles can obtain historical interaction vectors by using the text vectorization method in the step S241.
And S252, training by using the historical taxi renting data and the historical interaction vector to obtain a plurality of classifiers serving as behavior demand models.
Inputting the historical taxi renting data of the sample user and the historical interaction vector obtained in the step S242 into the deep learning model for training, and taking the obtained multiple classifiers as a behavior demand model, wherein actually, the historical taxi renting data of the sample user contains the taxi renting intention intensity of the sample user, if the sample user rents a taxi, the intention intensity is 1, and if the sample user does not rent a taxi, the intention intensity is 0, and preferably, the deep learning model can be a BERT deep learning model.
S260, obtaining car renting data of the target user within first preset time and behavior data of the target user within second preset time, and judging whether the target user has first-direction behaviors or not by using a pre-trained behavior discrimination model based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time.
And S270, when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time.
S280, vehicle interaction sequence data of the target user within fourth preset time are obtained, and the target user is subjected to travel willingness perception by means of a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
The embodiment of the invention does not specifically limit the training time sequences of the discrimination model, the strength perception model and the demand model.
The embodiment of the invention provides a method for perceiving travel willingness, which comprises the steps of obtaining historical taxi renting data, historical chat data and historical page series access data of a sample user as behavior discrimination model training data; extracting historical order features of historical car rental data; extracting vehicle keywords in the historical chat data, and determining fully-connected word vectors based on the vehicle keywords; performing statement on the historical page series access data to obtain a page access statement, and determining a behavior vector based on the page access statement; training by using the historical order features, the word vectors and the behavior vectors to obtain a second classifier which is used as a behavior discrimination model; acquiring historical stay time data, historical vehicle access data and historical page access data of a sample user as strength perception model training data; training by using the training data of the intensity perception model to obtain a second classifier as a behavior intensity perception model; acquiring historical taxi renting data and historical vehicle interaction sequence data of a sample user as behavior demand model training data; performing statement on the historical vehicle interaction sequence data to obtain historical vehicle interaction statements, and determining historical interaction vectors by using the historical vehicle interaction statements; and training by using historical car renting data and the historical interaction vectors to obtain a plurality of classifiers serving as the behavior demand model. The training processes of the behavior discrimination model, the behavior intensity perception model and the behavior demand model are respectively explained.
EXAMPLE III
Fig. 4 is a block diagram of a device for sensing a trip intention according to a third embodiment of the present invention, and this embodiment is applicable to a situation where a user performs a trip intention sensing on a target user when renting a car on a car renting platform. The method for sensing the travel will provided by any embodiment of the invention can be realized by applying the travel will sensing device. As shown in fig. 4, the device for sensing the willingness to travel includes:
the first direction behavior judgment module 310 is configured to obtain car renting data of a target user within first preset time and behavior data of the target user within second preset time, and judge whether the target user has a first direction behavior by using a pre-trained behavior judgment model based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time;
the behavior intensity prediction module 320 is configured to, when the target user has the first-direction behavior, obtain vehicle browsing data of the target user within a third preset time, and predict the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and the intention demand perception module 330 is configured to acquire vehicle interaction sequence data of the target user within a fourth preset time, and perceive an intention of the target user when the target user goes on a trip by using a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
Optionally, the acquiring the behavior data of the target user includes:
obtaining chat data of the target user in a second preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in second preset time.
Optionally, the acquiring vehicle browsing data of the target user includes:
acquiring stay time data of the target user in a third preset time; and/or the presence of a gas in the gas,
acquiring vehicle access data of the target user within third preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in a third preset time.
Optionally, the determining, by using a pre-trained behavior discrimination model, whether the target user has a first directional behavior includes:
and when the target user does not have the first-direction behavior, storing the car renting data within the first preset time and/or the behavior data within the second preset time for updating and training the behavior discrimination model.
Preferably, the training process of the behavior discrimination model includes:
acquiring behavior discrimination model training data of a sample user, wherein the behavior discrimination model training data comprises at least one of the following items: historical taxi renting data, historical chatting data and historical page series access data;
extracting historical order features of the historical taxi renting data;
extracting vehicle keywords in the historical chat data, and determining fully-connected word vectors based on the vehicle keywords;
performing statement on the historical page series access data to obtain a page access statement, and determining a behavior vector based on the page access statement;
and training by using the historical order features, the word vectors and the behavior vectors to obtain a second classifier which is used as the behavior discrimination model.
Preferably, the training process of the behavioral intensity perception model includes:
obtaining intensity perception model training data for a sample user, wherein the intensity perception model training data comprises at least one of: historical stay time data, historical vehicle access data and historical page access data;
and training by using the strength perception model training data to obtain a second classifier which is used as a behavior strength perception model.
Preferably, the training process of the behavior requirement model includes:
acquiring behavior demand model training data of a sample user, wherein the behavior demand model training data comprises historical car renting data and historical car interaction sequence data;
statement is carried out on the historical vehicle interaction sequence data to obtain historical vehicle interaction statements, and historical interaction vectors are determined by utilizing the historical vehicle interaction statements;
and training by using the historical taxi renting data and the historical interaction vector to obtain a plurality of classifiers serving as the behavior demand model.
The travel intention sensing device provided by the embodiment of the invention can execute the travel intention sensing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. The technical details that are not described in detail can be referred to a method for perceiving a travel intention provided by any embodiment of the present invention.
Example four
Fig. 5 is a schematic structural diagram of a terminal according to a fourth embodiment of the present invention. Fig. 5 illustrates a block diagram of an exemplary terminal 12 suitable for use in implementing any of the embodiments of the present invention. The terminal 12 shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention. The terminal 12 is typically a handset terminal that installs an application.
As shown in fig. 5, the terminal 12 is embodied in the form of a general purpose computing device. The components of the terminal 12 may include, but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 that couples the various components (including the memory 28 and the processing unit 16).
The terminal 12 typically includes a variety of computer readable media. Such media may be any available media that is accessible by terminal 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The terminal 12 may also communicate with one or more external devices 14 (e.g., keyboard, mouse, camera, etc., and display), one or more devices that enable a user to interact with the terminal 12, and/or any devices (e.g., network card, modem, etc.) that enable the terminal 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the terminal 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), and/or a public Network such as the internet) via the Network adapter 20. As shown, the network adapter 20 communicates with the other modules of the terminal 12 via the bus 18. It should be understood that although not shown in fig. 5, other hardware and/or software modules may be used in conjunction with the terminal 12, including but not limited to: microcode, device drivers, Redundant processing units, external disk drive Arrays, disk array (RAID) devices, tape drives, and data backup storage devices, to name a few.
The processor 16 executes various functional applications and data processing by executing programs stored in the memory 28, for example, implementing a method for perceiving travel will provided by the above-described embodiment of the present invention, the method including:
the method comprises the steps of obtaining car renting data of a target user within first preset time and behavior data of the target user within second preset time, and judging whether the target user has first-direction behaviors or not by using a pre-trained behavior discrimination model based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time;
when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and acquiring vehicle interaction sequence data of the target user within fourth preset time, and sensing the travel will of the target user by using a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
Of course, those skilled in the art will appreciate that the processor may also implement the method for perceiving the willingness to travel provided by any of the embodiments of the present invention.
EXAMPLE five
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for sensing travel willingness, the method including:
the method comprises the steps of obtaining car renting data of a target user within first preset time and behavior data of the target user within second preset time, and judging whether the target user has first-direction behaviors or not by using a pre-trained behavior discrimination model based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time;
when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and acquiring vehicle interaction sequence data of the target user within fourth preset time, and sensing the travel will of the target user by using a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
Of course, the computer program stored on the computer-readable storage medium provided in the embodiments of the present invention is not limited to the above method instructions, and may also execute the method for sensing a trip intention provided in any embodiment of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution apparatus, device, or apparatus.
A computer readable signal medium may include 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 apparatus, device, or apparatus.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out instructions of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code 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).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for perceiving travel will is characterized by comprising the following steps:
the method comprises the steps of obtaining car renting data of a target user within first preset time and behavior data of the target user within second preset time, and judging whether the target user has first-direction behaviors or not by using a pre-trained behavior discrimination model based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time;
when the target user has the first-direction behavior, acquiring vehicle browsing data of the target user within a third preset time, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and acquiring vehicle interaction sequence data of the target user within fourth preset time, and sensing the travel will of the target user by using a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
2. The method of claim 1, wherein the behavior discriminant model training process comprises:
acquiring behavior discrimination model training data of a sample user, wherein the behavior discrimination model training data comprises at least one of the following items: historical taxi renting data, historical chatting data and historical page series access data;
extracting historical order features of the historical taxi renting data;
extracting vehicle keywords in the historical chat data, and determining fully-connected word vectors based on the vehicle keywords;
performing statement on the historical page series access data to obtain a page access statement, and determining a behavior vector based on the page access statement;
and training by using the historical order features, the word vectors and the behavior vectors to obtain a second classifier which is used as the behavior discrimination model.
3. The method of claim 1, wherein the behavioral intensity perception model training process comprises:
obtaining intensity perception model training data for a sample user, wherein the intensity perception model training data comprises at least one of: historical stay time data, historical vehicle access data and historical page access data;
and training by using the strength perception model training data to obtain a second classifier which is used as a behavior strength perception model.
4. The method of claim 1, wherein the training process of the behavioral need model comprises:
acquiring behavior demand model training data of a sample user, wherein the behavior demand model training data comprises historical car renting data and historical car interaction sequence data;
statement is carried out on the historical vehicle interaction sequence data to obtain historical vehicle interaction statements, and historical interaction vectors are determined by utilizing the historical vehicle interaction statements;
and training by using the historical taxi renting data and the historical interaction vector to obtain a plurality of classifiers serving as the behavior demand model.
5. The method according to any one of claim 1, wherein the obtaining behavior data of the target user comprises:
obtaining chat data of the target user in a second preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in second preset time.
6. The method of claim 1, wherein the obtaining vehicle browsing data of the target user comprises:
acquiring stay time data of the target user in a third preset time; and/or the presence of a gas in the gas,
acquiring vehicle access data of the target user within third preset time; and/or the presence of a gas in the gas,
and acquiring page access data of the target user in a third preset time.
7. The method of claim 1, wherein the determining whether the target user has a first directional behavior using a pre-trained behavior discrimination model comprises:
and when the target user does not have the first-direction behavior, storing the car renting data within the first preset time and/or the behavior data within the second preset time for updating and training the behavior discrimination model.
8. A device for sensing a desire to travel, comprising:
a first direction behavior judgment module, configured to obtain car renting data of a target user within a first preset time and behavior data of the target user within a second preset time, and judge, based on the car renting data of the target user within the first preset time and the behavior data of the target user within the second preset time, whether the target user has a first direction behavior by using a pre-trained behavior judgment model
The behavior intensity prediction module is used for acquiring vehicle browsing data of the target user within a third preset time when the target user has the first-direction behavior, and predicting the behavior intensity of the target user by using a pre-trained behavior intensity perception model and the vehicle browsing data within the third preset time;
and the intention demand perception module is used for acquiring vehicle interaction sequence data of the target user within fourth preset time, and perceiving the travel intention of the target user by utilizing a pre-trained behavior demand model based on the vehicle interaction sequence data and the behavior intensity within the fourth preset time.
9. A terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for perceiving a travel willingness according to any one of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a method of perceiving a willingness to travel as set forth in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010791316.2A CN111966897B (en) | 2020-08-07 | 2020-08-07 | Method, device, terminal and storage medium for sensing travel willingness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010791316.2A CN111966897B (en) | 2020-08-07 | 2020-08-07 | Method, device, terminal and storage medium for sensing travel willingness |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111966897A true CN111966897A (en) | 2020-11-20 |
| CN111966897B CN111966897B (en) | 2023-07-21 |
Family
ID=73364853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010791316.2A Active CN111966897B (en) | 2020-08-07 | 2020-08-07 | Method, device, terminal and storage medium for sensing travel willingness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111966897B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493002A (en) * | 2022-01-26 | 2022-05-13 | 北京百度网讯科技有限公司 | Production intention prediction method and device and electronic equipment |
| CN114997590A (en) * | 2022-05-06 | 2022-09-02 | 上海增融信息科技有限公司 | Method and device for vehicle schedule management, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2372625A1 (en) * | 2010-03-30 | 2011-10-05 | Sap Ag | Method for allocating trip sharing |
| WO2016145547A1 (en) * | 2015-03-13 | 2016-09-22 | Xiaoou Tang | Apparatus and system for vehicle classification and verification |
| CN106875066A (en) * | 2017-02-28 | 2017-06-20 | 百度在线网络技术（北京）有限公司 | With the Forecasting Methodology of car travel behaviour, device, server and storage medium |
| US20180012141A1 (en) * | 2016-07-11 | 2018-01-11 | Conduent Business Services, Llc | Method of trip prediction by leveraging trip histories from neighboring users |
| US20180025292A1 (en) * | 2016-07-19 | 2018-01-25 | Mastercard International Incorporated | Systems and methods for optimizing travel bookings |
| CN110458664A (en) * | 2019-08-06 | 2019-11-15 | 上海新共赢信息科技有限公司 | A kind of user's trip information prediction technique, device, equipment and storage medium |
| CN110491124A (en) * | 2019-08-19 | 2019-11-22 | 上海新共赢信息科技有限公司 | A kind of vehicle flow prediction technique, device, equipment and storage medium |
-
2020
- 2020-08-07 CN CN202010791316.2A patent/CN111966897B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2372625A1 (en) * | 2010-03-30 | 2011-10-05 | Sap Ag | Method for allocating trip sharing |
| WO2016145547A1 (en) * | 2015-03-13 | 2016-09-22 | Xiaoou Tang | Apparatus and system for vehicle classification and verification |
| US20180012141A1 (en) * | 2016-07-11 | 2018-01-11 | Conduent Business Services, Llc | Method of trip prediction by leveraging trip histories from neighboring users |
| US20180025292A1 (en) * | 2016-07-19 | 2018-01-25 | Mastercard International Incorporated | Systems and methods for optimizing travel bookings |
| CN106875066A (en) * | 2017-02-28 | 2017-06-20 | 百度在线网络技术（北京）有限公司 | With the Forecasting Methodology of car travel behaviour, device, server and storage medium |
| CN110458664A (en) * | 2019-08-06 | 2019-11-15 | 上海新共赢信息科技有限公司 | A kind of user's trip information prediction technique, device, equipment and storage medium |
| CN110491124A (en) * | 2019-08-19 | 2019-11-22 | 上海新共赢信息科技有限公司 | A kind of vehicle flow prediction technique, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 吴钉捷;李晓露;: "基于实时出行需求和交通路况的电动汽车充电负荷预测", 电力建设, no. 08 * |
| 钱岳;丁效;刘挺;陈毅恒;: "聊天机器人中用户出行消费意图识别方法", 中国科学:信息科学, no. 08 * |
| 韩震;杨丽;徐小凡;: "基于共享单车出行数据的用户行为分析", 大连海事大学学报, no. 04 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493002A (en) * | 2022-01-26 | 2022-05-13 | 北京百度网讯科技有限公司 | Production intention prediction method and device and electronic equipment |
| CN114997590A (en) * | 2022-05-06 | 2022-09-02 | 上海增融信息科技有限公司 | Method and device for vehicle schedule management, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111966897B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135901A (en) | A kind of enterprise customer draws a portrait construction method, system, medium and electronic equipment | |
| CN109034203B (en) | Method, device, equipment and medium for training expression recommendation model and recommending expression | |
| CN107862339B (en) | Method and apparatus for outputting information | |
| CN114417174B (en) | Content recommendation method, device, equipment and computer storage medium | |
| CN117217284A (en) | A data processing method and its device | |
| CN119904786B (en) | Method, device and apparatus for generating event description text based on video data | |
| WO2025016416A1 (en) | Data processing method and related apparatus | |
| CN114880565B (en) | Information recommendation method, model training method and related device | |
| CN116204709A (en) | Data processing method and related device | |
| CN118095269B (en) | Dialogue information extraction method, device, equipment, medium and program product | |
| CN111966897B (en) | Method, device, terminal and storage medium for sensing travel willingness | |
| CN114328915A (en) | Corpus tag acquisition method, device and computer equipment | |
| CN116821298A (en) | Keyword automatic identification method applied to application information and related equipment | |
| CN117251632A (en) | Training method of information recommendation model, information recommendation method and device | |
| CN116362790A (en) | Client type prediction method, client type prediction device, electronic device, medium and program product | |
| CN111444335B (en) | Method and device for extracting central word | |
| CN116091249A (en) | Transaction risk assessment method, device, electronic equipment and medium | |
| CN114547308A (en) | Text processing method and device, electronic equipment and storage medium | |
| CN111177493B (en) | Data processing method, device, server and storage medium | |
| CN120163632A (en) | Product recommendation strategy generation method, device, computer equipment and storage medium | |
| CN119691281A (en) | Information pushing method, device, equipment, medium and program product | |
| CN119625421A (en) | Scene graph generation method, device, equipment, storage medium and program product based on graph semantic understanding | |
| CN112825075A (en) | Dialog text processing method and related equipment | |
| CN117591734A (en) | Training methods and devices for click rate prediction models, and item recommendation methods and devices | |
| CN117556917A (en) | A data processing method and its device |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030 Applicant after: Shanghai Lexiang Sijin Technology Co.,Ltd. Address before: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030 Applicant before: Shanghai xinwin Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230403 Address after: 2406, Building 1, Tongji Science and Technology Plaza, No. 2 Hushan Road, Changshu High and New Technology Industrial Development Zone, Suzhou City, Jiangsu Province, 215500 Applicant after: Concavoconvex Lexiang (Suzhou) Information Technology Co.,Ltd. Address before: Room 587, building 3, 333 Hongqiao Road, Xuhui District, Shanghai 200030 Applicant before: Shanghai Lexiang Sijin Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |