CN112132661A - Information pushing method and device based on taxi taking preference of user - Google Patents
Information pushing method and device based on taxi taking preference of user Download PDFInfo
- Publication number
- CN112132661A CN112132661A CN202011033904.6A CN202011033904A CN112132661A CN 112132661 A CN112132661 A CN 112132661A CN 202011033904 A CN202011033904 A CN 202011033904A CN 112132661 A CN112132661 A CN 112132661A
- Authority
- CN
- China
- Prior art keywords
- taxi taking
- user
- taxi
- taking
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007418 data mining Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 40
- 238000007619 statistical method Methods 0.000 claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 9
- 238000007621 cluster analysis Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 80
- 238000005065 mining Methods 0.000 description 19
- 238000004364 calculation method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000009412 basement excavation Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003442 weekly effect Effects 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Fuzzy Systems (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Traffic Control Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an information pushing method based on taxi taking preference of a user, which comprises the following steps: collecting taxi taking behavior data samples from transaction detail data of taxi taking trips of a user; carrying out statistical analysis on the collected taxi taking behavior data samples based on a preset data mining algorithm, and determining taxi taking behavior preference of a user; the taxi taking behavior preference comprises a target taxi taking time period preferred by the user and a target taxi taking place preferred by the user in the target taxi taking time period; judging whether the current time hits a target taxi taking time period preferred by a user in real time; if the current time hits the target taxi taking time period preferred by the user, further judging whether the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period; if so, pushing first taxi taking prompt information corresponding to the target taxi taking place to the user client; and if not, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client so as to display the second taxi taking prompt information on a home page of the user at the client.
Description
Technical Field
The application relates to the field of computer application, in particular to an information pushing method and device based on taxi taking preference of a user.
Background
With the increasing popularity of mobile internet, O2O, big data, etc., it is very important to how to use good data to effectively support services, and more internet companies propose the concept of big data operation, and guide services by using data to make data really become an "oil field".
As a pay for help (Alipay) of a one-stop life service platform, one of the most intuitive and largest changes of the information interface of a user is to output a pull-down menu on a home page of the user. The daily behaviors of the user are understood through data analysis of a background, and various requirements of the user, which are passed through, concerned and interested in life, are directly pushed to the user in a 'life dynamic' plate of a user home page in the form of an information card; however, in practical application, because the offline requirements of users are various, how to push the information card to the home page of the user can meet various requirements of 'clothes and eating houses' in the basic life of the user in time, and the method has a very important meaning for improving the user experience.
Disclosure of Invention
The application provides an information pushing method based on taxi taking preference of a user, and the method comprises the following steps:
collecting taxi taking behavior data samples from transaction detail data of taxi taking trips of a user;
carrying out statistical analysis on the collected taxi taking behavior data samples based on a preset data mining algorithm so as to determine taxi taking behavior preference of a user; the taxi taking behavior preference comprises a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period;
judging whether the current time hits a target taxi taking time period preferred by a user in real time;
if the current time hits the target taxi taking time period preferred by the user, further judging whether the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period;
if so, pushing first taxi taking prompt information corresponding to the target taxi taking place to a user client; and if not, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client so as to display the second taxi taking prompt information on a user home page of the user client.
This application still provides an information push device based on user preference of taking a car, the device includes:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring taxi taking behavior data samples from transaction detail data of taxi taking trips of a user;
the analysis module is used for carrying out statistical analysis on the collected taxi taking behavior data samples based on a preset data mining algorithm so as to determine taxi taking behavior preference of a user; the taxi taking behavior preference comprises a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period;
the judging module is used for judging whether the current time hits the target taxi taking time period preferred by the user in real time; if the current time hits the target taxi taking time period preferred by the user, further judging whether the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period;
the pushing module is used for pushing first taxi taking prompt information corresponding to the target taxi taking place to a user client side if the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period; and if the current positioning position of the user does not hit the preferred target taxi taking place of the user in the target taxi taking time period, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client so as to display the second taxi taking prompt information on a user home page of the user client.
According to the method and the device, when the taxi taking requirement of the user is judged in real time based on taxi taking behavior preferences of the excavated user, corresponding taxi taking prompt information is timely pushed to the user client side, and the user home page of the user client side is displayed; meanwhile, different taxi taking prompt messages can be respectively pushed according to different taxi taking requirements of the user, so that the corresponding taxi taking prompt messages can be timely pushed to the user in a more natural pushing mode when the fact that the user has the taxi taking requirements is judged in advance, user experience can be optimized, and the utilization rate of the taxi taking of the user through a user client side is improved.
Drawings
Fig. 1 is a flowchart illustrating an information pushing method based on taxi taking preferences of a user according to an embodiment of the present application;
FIG. 2 is a process flow diagram illustrating a data mining algorithm for mining taxi taking time periods of user preferences in accordance with an embodiment of the subject application;
FIG. 3 is a logic block diagram of an information pushing apparatus based on taxi taking preferences of a user according to an embodiment of the present application;
fig. 4 is a hardware structure diagram of a server side that carries the information pushing apparatus based on the user taxi taking preference according to an embodiment of the present application.
Detailed Description
In the related art, when a user makes a taxi through a user client with a taxi taking function, usually when the user has a taxi taking requirement, the user manually triggers an entry option of a taxi taking interface provided by the user client to enter the taxi taking interface, then manually inputs a taxi taking destination in the taxi taking interface, and the user client generates a corresponding taxi taking order and submits the order to complete the taxi taking operation.
On one hand, most of the current user clients with taxi taking functions have deep entrances of taxi taking interfaces, are not intuitive enough and are difficult to find, so that the users may need to perform multiple operations to enter the taxi taking interfaces (for example, the users may need to click multiple menus to find the entrances of the taxi taking interfaces), and the user clients can complete the input of the destination of the taxi taking, the submission of orders and other operations.
On the other hand, most of the current user clients with taxi taking functions generally only add a few destination addresses used by the user in history in an address list in a taxi taking interface for the user to select, and do not actively mine taxi taking behavior preferences of the user and actively predict taxi taking requirements of the user.
Therefore, the existing user client carrying the taxi taking function has a deep taxi taking entrance, does not actively mine the taxi taking behavior preference of the user, and pre-judges the taxi taking requirement of the user, so that the utilization rate of the user when the user uses the client to take the taxi is low, and the user experience is poor.
In view of the above, the application provides an information pushing method based on user taxi taking preference, which includes the steps of mining taxi taking behavior preferences such as a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period from transaction detail data of taxi taking outgoing of the user, timely pushing corresponding taxi taking prompt information to a user client when the fact that the user has taxi taking requirements is judged in real time based on the mined taxi taking behavior preferences of the user, and displaying the taxi taking prompt information on a user home page of the user client; meanwhile, different taxi taking prompt messages can be respectively pushed according to different taxi taking requirements of users;
on one hand, in the method and the device, the taxi taking behavior preference of the user can be actively mined based on the transaction detail data of the taxi taking trip of the user;
on the other hand, the taxi taking requirements of the users can be judged in advance based on the excavated taxi taking behavior preferences of the users, and corresponding taxi taking prompt messages can be pushed to the users in time in a more natural pushing mode when the users are judged to have taxi taking requirements in advance, and the taxi taking prompt messages are displayed on the home pages of the users at the user clients.
Therefore, whether the user has a taxi taking requirement or not can be judged in advance based on the excavated taxi taking behavior preference of the user; and can in time send the suggestion of taking a car to the user when judging in advance that the user has the demand of taking a car to user experience can be optimized, the rate of utilization that the user took a car through user client is promoted.
The present application is described below with reference to specific embodiments and specific application scenarios.
Referring to fig. 1, fig. 1 is a diagram illustrating an information push based on taxi taking preferences of a user, applied to a server, according to an embodiment of the present application, where the method performs the following steps:
the server may specifically be a server providing services for a user client, a server cluster, or a service platform built based on the server cluster. The user client specifically includes client software carrying a taxi taking function;
for example, the user client may be a pay bank APP, and an entry option of a third-party taxi-taking client may be loaded in the pay bank APP; the service end can be a service platform for providing payment treasures APP to the server.
In the method, the server can collect transaction detail data of daily taxi taking trips of each user, then collect corresponding information from the collected transaction detail data according to a fixed data format to generate taxi taking behavior data samples, and then perform statistical analysis on the collected taxi taking behavior data samples by combining a preset data mining algorithm to obtain taxi taking behavior preferences of each user.
In an embodiment, the data format of the taxi taking behavior data sample may be as shown in table 1:
user_id | user id |
city | City |
has_take_taxi | Whether to take a car or not |
time_date | Date |
time_hour | Hour(s) |
time_is_workday | Whether or not to work on a day |
time_week | … days on Monday and two weeks |
start_longitude | Longitude of origin |
start_latitude | Latitude of departure place |
end_address | Destination point |
TABLE 1
As can be seen from table 1, the data format of the taxi taking behavior data sample may include a user identification field, a taxi taking city field, a taxi taking date field, a taxi taking time period field, a work day field, a week field, a departure place longitude field, a departure place latitude field, and a destination place field. Of course, in practical application, the specific fields included in the taxi taking behavior data sample may be customized based on actual data mining requirements, and are not particularly limited in this application.
It should be noted that, in practical application, the unit time interval corresponding to the taxi taking time interval field (i.e., the time _ hour field shown in table 1) contained in the taxi taking behavior data sample shown in table 1 may be set to a smaller value;
for example, the unit time period shown in table 1 is 1 hour, that is, when the server collects data, the taxi taking data of the user in each hour time period may be collected respectively to generate one taxi taking data sample, so that each finally collected taxi taking data sample will contain taxi taking data of the user in the small time period respectively.
The value of the unit time interval corresponding to the taxi taking time interval field is set to be a smaller value, so that a smaller time interval of data mining can be kept when statistical analysis is carried out on collected taxi taking behavior data samples based on a data mining algorithm, and the accuracy of a final data mining result is improved.
Of course, in table 1, only the unit time period corresponding to the taxi taking period field is 1 hour as an example, and in practical application, the unit time period corresponding to the taxi taking time period may be customized based on actual requirements; for example, if the final data mining result is more demanding, the unit period corresponding to the taxi-taking time period may be set to a smaller unit period (e.g., 30 minutes) less than 1 hour.
It can be seen that data are collected in the standard format shown in table 1, and the data format of the taxi taking behavior data sample collected finally can be normalized, so that statistical analysis can be conveniently performed subsequently by combining a preset data mining algorithm.
102, carrying out statistical analysis on collected taxi taking behavior data samples based on a preset data mining algorithm to determine taxi taking behavior preference of a user; the taxi taking behavior preference comprises a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period;
for the taxi taking behavior data samples which are collected and classified according to the attributive cities, the server side can carry out statistical analysis and calculation based on a carried data mining algorithm, and then the taxi taking behavior preferences of the user in different cities are mined.
In this application, the taxi taking preference may specifically include a target taxi taking time period preferred by the user and a target taxi taking place preferred by the user in the target taxi taking time period.
The following describes the user's preferred target taxi taking time period and the mining process of the user's preferred target taxi taking place, respectively, with reference to specific examples.
1) Mining of user-preferred target taxi taking time period
Referring to fig. 2, fig. 2 is a process flow diagram of a data mining algorithm for mining taxi taking time periods preferred by users according to the present application.
The server side can sort the screened taxi taking behavior data samples in advance according to the sequence of taxi taking time before carrying out statistical analysis and calculation on the taxi taking behavior data samples screened from the collected taxi taking behavior data samples based on the data mining algorithm, and the preprocessing of the data samples to be calculated is completed.
As shown in fig. 2, when the preprocessing is completed, the server performs statistical analysis and calculation on taxi taking behavior data samples screened from collected taxi taking behavior data samples based on the data mining algorithm:
on one hand, the taxi taking times of the user in each first unit time period can be counted based on taxi taking behavior data samples, and the first unit time period in which the taxi taking times are larger than a first threshold value is searched;
on the other hand, the taxi taking times of the user in each second unit time interval can be counted on the basis of the taxi taking behavior data samples; wherein the second unit time interval consists of any two consecutive first unit time intervals in each first unit time interval;
for example, taking the unit time period corresponding to the taxi taking time period in the taxi taking behavior data sample as 1 hour as an example, the first unit time period may be 1 hour, and the second unit time period may be a 2-hour time period consisting of any two consecutive 1-hour time periods within each 1-hour time period; that is, for any one second unit period, it may be composed of two consecutive first unit periods; also, the first unit periods constituting the two second unit periods may intersect; for example, 1 point-2 points, 2 points-3 points, 3 points-4 points, and 4 points to 5 points may respectively constitute a first unit period; and 1 point to 3 points, 2 points to 4 points, and 3 points to 5 points may respectively constitute 3 second unit periods, and consecutive second unit periods may have an intersection in time.
After the taxi taking times of the user in each second unit time period are counted, the second unit time period in which the taxi taking times are greater than a second threshold value and the taxi taking times of the user in the first unit time period forming the second unit time period are greater than a third threshold value can be searched; wherein the second threshold is greater than the first threshold; the specific value of the third threshold is not particularly limited in this application, and may be smaller than the first threshold or larger than the first threshold; for example, in one example, the value of the third threshold may be 1.
Referring to fig. 2, when the server finds out a first time unit time in which the number of times of taxi taking is greater than a first threshold, finds out a second unit time in which the number of times of taxi taking is greater than a second threshold and the number of times of taxi taking in a first unit time period constituting the second unit time period is greater than a third threshold, the found first unit time period and the second unit time period may be subjected to time period splicing to generate a corresponding time period interval, and then the time period interval obtained by splicing is used as a target taxi taking time period preferred by the user.
In this example, after the target taxi taking time period preferred by the user is counted, the taxi taking probability of the target taxi taking time period can be further calculated based on the total taxi taking times in the target taxi taking time period.
For example, in one illustrated embodiment, a target ratio of the total number of taxi trips within the target taxi-taking period to the total number of days corresponding to the input taxi-taking activity data sample may be calculated, and then the target ratio may be determined as a taxi-taking probability corresponding to the target taxi-taking period.
For example, suppose that the service side screens out driving behavior data samples of a user in a city for about N days as input data of an algorithm, where a first threshold is threshold, a second threshold may be threshold +1, and a third threshold is 1; the unit time interval corresponding to the first unit time interval is 1 hour, and the corresponding taxi taking times are expressed by Ai; the second unit period is a 2 hour period and the corresponding number of hits is represented by Bi.
Step 1, the server can count the taxi taking times of the user in each first unit time interval and each second unit time interval respectively.
Assume that the statistics for the Ai period are as shown in the following table:
time period numbering | 1 | 2 | 3 | 4 | 5 |
Ai | 0 time | 1 time of | 2 times (one time) | 3 times of | 1 time of |
At this time, the statistical results of the Bi period will be shown in the following table:
and 2, the server can find out the high-frequency time period of the taxi taking times.
For Ai, the server looks up the first unit time period of all Ai > threshold.
For Bi, the server side finds out all Bi > threshold +1 and Bi corresponds to all Ai >1 in the second unit time period.
And 3, splicing the first unit time periods corresponding to Ai and the second unit time periods corresponding to Bi meeting the conditions into a time period interval by the server. Assuming that the taxi taking times in the time interval are m, the server can calculate the taxi taking probability according to the following formula:
step 4, after the calculation is completed, the server side can output the mining result of the time period preferred by the user, so that the taxi taking requirement of the user can be judged in advance based on the mining result in the following process; the mining result may specifically include a preferred time period and a taxi taking probability of the user, and the format is (user _ id, city, interval, probability). user _ id represents the identity of the user; city represents the city of the taxi; interval represents a time period of user preference; probability represents the probability of taxi taking.
In this example, the target taxi taking time period preferred by the user may be further subdivided into a weekday taxi taking time period preferred by the user, a weekend taxi taking time period preferred by the user, and a weekend taxi taking time period preferred by the user.
The taxi taking time period of the user on the preferred working day refers to the time period preferred by the user when the user takes a taxi on the daily working day; the time law of the user when the user drives the vehicle on the working day can be expressed in the preferred working day driving time period of the user; for example, assume that the user prefers a weekday period of 17:30-18:00, indicating that the user is accustomed to 17: getting the car at 30-18: 00.
The time period preferred by the user for taking the bus on the weekend is the time period preferred by the user for taking the bus on the daily weekend holiday; the time interval of the user's preferred weekend taxi taking can express the time law of the user's taxi taking on weekend holidays; for example, assume that the user prefers a weekend period of 12: 30-13:00, indicating that the user is accustomed to 12 pm on weekend weekdays: getting the car at 30-13: 00.
The week regular taxi taking time period preferred by the user refers to a periodic time law that the user takes taxi every week; the week-regular taxi taking time period preferred by the user can express that the user prefers to taxi in a specific time period in a specific natural day of each week; for example, assume a user preferred weekly regular taxi taking period of 12 on friday of the week: 30-13:00, then it indicates that the user is accustomed to 12 in the afternoon of every friday: getting the car at 30-13: 00.
It should be noted that, when the server performs statistical analysis and calculation on the collected taxi-taking behavior data samples based on the data mining algorithm shown in fig. 2, the type of the taxi-taking behavior data sample used may be determined based on a specific scenario of a target taxi-taking time period preferred by the user that the server finally needs to mine.
In an embodiment shown, in a scene of mining a taxi taking time period on a working day preferred by a user, if a server needs to mine a taxi taking time period preferred by the user in a certain target city, taxi taking behavior data samples corresponding to the working day time period and having taxi taking cities of the target city can be screened out from collected taxi taking behavior data samples; then, carrying out statistical analysis on the screened taxi taking behavior data samples based on a data mining algorithm shown in FIG. 2 to obtain taxi taking time periods preferred by the user in the target city;
for example, assuming that the user prefers to drive at 6:00-7:59 on weekdays, the final output mining results based on the data mining algorithm shown in FIG. 2 may be as shown in the following table:
user' s | Preference type | Whether or not to work on a day | City | Week | Time period | Probability of taxi taking |
XXX | Time preference | Is that | XX | null | 6:00-7:59 | XX |
Under the scene of excavating the weekend taxi taking time period preferred by the user, if the server needs to excavate the weekend taxi taking time period preferred by the user in a certain target city, taxi taking behavior data samples corresponding to the weekend time period and of which the taxi taking cities are the target city can be screened out from the collected taxi taking behavior data samples; then, statistical analysis is carried out on the screened taxi taking behavior data samples based on the data mining algorithm shown in fig. 2, so that the taxi taking time periods preferred by the user in the target city are obtained.
For example, assume that the user prefers 12 on the weekend: 00-12:30 taxi taking, the final output mining result based on the data mining algorithm shown in fig. 2 can be shown as the following table:
user' s | Preference type | Whether or not to work on a day | City | Week | Time period | Probability of taxi taking |
XXX | Time preference | Whether or not | XX | null | 12:00-12:30 | XX |
Under the scene of excavating the week regular taxi taking time periods preferred by the users, if the server needs to excavate the week regular taxi taking time periods preferred by the users in a certain target city, the respective natural days corresponding to the week time periods can be respectively screened out from the collected taxi taking behavior data samples, and the taxi taking cities are taxi taking behavior data samples of the target city;
for example, assuming that the periodic time law of the user taking a car every friday needs to be mined, car-taking behavior data samples of friday can be screened out in nearly N weeks, and statistical analysis is performed based on the data mining algorithm shown in fig. 2, so as to obtain a car-taking time period preferred by the user every friday.
Then, the screened taxi taking behavior data samples can be subjected to statistical analysis based on a data mining algorithm shown in fig. 2, so that the taxi taking time periods preferred by the user in the target city are obtained;
for example, assume that the user is accustomed to the 17: 00-17: 59 taxi taking, then according to the data mining algorithm shown in fig. 2, the final output mining result can be shown as the following table:
in addition, it should be noted that, when the server side mines the target taxi taking time period preferred by the user based on the data mining algorithm shown in fig. 2, parameters adopted by the data mining algorithm in different scenarios may be different from each other, and a person skilled in the art may assign values based on needs or in combination with engineering experience.
For example, in one illustrated implementation, the parameters for the three different scenarios shown above may be as shown in the following table:
of course, it should be noted that the parameters used by the data mining algorithm under different scenarios shown in the above table are only exemplary and are not used to limit the technical solution of the present application.
2) Mining of user-preferred target taxi taking places
In this example, the taxi taking places where the users are located are generally different for each taxi taking time period preferred by the users; for example, when a user drives a car in the morning of a weekday, the starting location may be home, and the destination location may be a company; when a user drives a car in the evening of a working day, the starting place can be a company, and the destination place can be a home; when a user drives a car every friday, the starting place can be a company, and the destination place can be a railway station; therefore, in the present application, the mining of the target taxi taking places preferred by the user is completed on the basis of mining the taxi taking time periods preferred by the user based on the data mining algorithm shown in fig. 2, and the server needs to further mine the target taxi taking places preferred by the user within the target taxi taking time periods for each of the target taxi taking time periods preferred by the user mined according to the data mining algorithm shown in fig. 2.
The taxi taking place of the target preferred by the user can be further subdivided into a taxi taking starting place preferred by the user, a taxi taking destination preferred by the user and a taxi taking position range preferred by the user.
When the server needs to further dig a preferred target taxi taking place of a user in a certain excavated target taxi taking time period, firstly, position information of all taxi taking starting places of the user in the target time period can be counted; for example, the longitude and latitude of the starting position of the taxi taking;
then, the server side can perform cluster analysis based on the counted position information of all taxi-taking departure places of the user in the target time period, and search the target clusters which contain the largest taxi-taking departure places and the number of the taxi-taking departure places larger than a preset threshold value based on the result of the cluster analysis.
Finally, the server can calculate the center point of the target cluster, and determine the target location corresponding to the center point of the target cluster as the taxi taking starting location preferred by the user; similarly, the server can further calculate the radius of the target cluster, and determine the position range corresponding to the radius of the target cluster as the taxi taking position range preferred by the user; and further counting the destination points with the highest use frequency in the taxi taking behavior data samples corresponding to the taxi taking starting points in the target class cluster, and determining the destination points as the taxi taking destination points preferred by the user.
After the calculation is completed, the server side can output the mining result of the target taxi taking place preferred by the user in the target taxi taking time period, so that the taxi taking requirement of the user can be pre-judged based on the mining result in the following process; the mining result may specifically include a preferred starting location of the user within the target taxi taking time period, a preferred taxi taking position range of the user, and a preferred taxi taking destination of the user.
For example, assuming that the longitude of the center point of the target cluster is 120.13, the latitude is 30.2, the radius of the target cluster is 110 meters, and the preferred destination of the user is west river east, the mining result of the preferred destination of the user in the target taxi taking time period, which is finally output, may be as shown in the following table:
103, judging whether the current time hits the target taxi taking time period preferred by the user in real time; if the current time hits the target taxi taking time period preferred by the user, further judging whether the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period;
in this example, the user client used by each user may upload the timestamp corresponding to the current time and the positioning location of the user (for example, based on longitude and latitude data of the user acquired by the GPS module) to the server in real time, and the server may finally dig the preferred taxi taking time period of the user based on the collected taxi taking behavior data sample of the user, and may determine whether the timestamp hits the target taxi taking time period preferred by the user of the user client based on the timestamp uploaded by the user client in real time after the preferred taxi taking place in the taxi taking time period.
If the timestamp hits the target taxi taking time period preferred by the user, whether the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period can be further judged based on the positioning position of the user uploaded by the user client;
for example, the latitude and longitude information of the location position of the user may be matched with the found latitude and longitude information of the start location preferred by the user and the driving position range preferred by the user, so as to determine whether the location position of the user hits the start location preferred by the user or whether the location position of the user is within the driving position range preferred by the user.
And 104, if the current positioning position of the user hits a target taxi taking place preferred by the user in the target taxi taking time period, pushing first taxi taking prompt information corresponding to the target taxi taking place to the user client so as to be displayed on a user home page of the user client.
And 105, if the current positioning position of the user does not hit a target taxi taking place preferred by the user in the target taxi taking time period, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client so as to display the second taxi taking prompt information on a user home page of the user client.
If the current positioning position of the user is confirmed and the user hits a preferred target taxi taking place within the target taxi taking time period, the server side judges that the taxi taking requirement of the user to the target taxi taking place possibly exists in the current time period; in this case, the first taxi-taking prompt information corresponding to the target taxi-taking place may be pushed to the user client.
Certainly, if the current positioning position of the user is confirmed and the user does not hit a preferred target taxi taking place of the user in the target taxi taking time period, the server side judges that the taxi taking requirement of the user possibly exists in the current time period in advance at the moment; at this time, second taxi taking prompt information corresponding to the target taxi taking time period can be pushed to the user client.
In practical applications, the first taxi-taking prompt message and the second taxi-taking prompt message correspond to different taxi-taking requirements of users respectively, so that the first taxi-taking prompt message and the second taxi-taking prompt message can correspond to different documents respectively based on the specific taxi-taking requirements of the users; after the user client receives the first taxi-taking prompt message or the second taxi-taking prompt message pushed by the server, the received taxi-taking prompt message can be displayed on a user home page;
for example, taking the user client as the pay bank client as an example, if the server pre-judges that the taxi taking requirement of the user is to take a taxi to home at 17:30-18:00 pm on a weekday, the document content of the first taxi taking prompt message that the server needs to push to the user client may be specifically "cheela next shift, call home bar home"; after receiving the first taxi-taking prompt message pushed by the server, the payment client can present a travel card with a file of 'cheering off duty, calling a taxi to go home bar' to the user in a 'dynamic life' plate of a user home page, so that the user can more visually check the taxi-taking requirement pre-judged by the server.
For another example, if the server pre-determines that the taxi taking requirement of the user is to take a taxi to a company at 8:30-9:00 am on a weekday, the file content of the first taxi taking prompt message that the server needs to push to the user client may be "good morning, called a taxi service bar"; after receiving the first taxi-taking prompt message pushed by the server, the payment client can present a travel card with a file of 'good morning, call a taxi-taking bar' to the user in a 'dynamic life' plate of a user home page, so that the user can more visually check the taxi-taking requirement pre-judged by the server.
It should be noted that, because the first taxi taking prompt message or the second taxi taking prompt message pushed by the server side to the user client reflects the pre-judgment result of the server side for the taxi taking requirement of the user to some extent, in order to further improve the accuracy of the pre-judgment result of the taxi taking requirement, the server side can further introduce the judgment of the taxi taking probability on the basis of the real-time judgment process of the taxi taking requirement of the user described above.
In this case, when the server determines that the timestamp uploaded by the client hits the preferred taxi taking time period of the user through the real-time determination process of the taxi taking demand, it may be further determined whether the taxi taking probability corresponding to the target taxi taking time period is greater than a preset threshold value; and if the taxi taking probability of the target taxi taking time period is greater than the preset threshold value, the server side pushes the first taxi taking prompt message or the second taxi taking prompt message to the user client side at the moment.
In this way, the server pre-judges that the user has a taxi taking requirement in the current time period, further introduces judgment of taxi taking probability before pushing the first taxi taking prompt message or the second taxi taking prompt message to the user client, and pushes the first taxi taking prompt message or the second taxi taking prompt message only when the taxi taking probability is greater than a preset threshold; and if the taxi taking probability is smaller than the preset threshold value, the taxi taking prompt message or the second taxi taking prompt message can be stopped from being output to the user client side, so that the misjudgment probability of the server side can be further reduced, and the prejudgment accuracy of taxi taking requirements can be improved.
In an embodiment shown in the above, the first driving prompt message and the second driving prompt message may be specifically entry options of a driving interface. After receiving the first taxi taking prompt message and the second taxi taking prompt message, the user client can display the entry options of the corresponding taxi taking interface in the user home page based on the received taxi taking prompt message and output the corresponding prompt document. At the moment, the user can directly start the entry option in the home page of the user and enter a taxi taking interface, so that the operations of inputting a destination point, generating and submitting a taxi taking order and the like can be completed quickly.
The first taxi-taking prompt message and the second taxi-taking prompt message correspond to different taxi-taking requirements respectively, so that contents displayed in the taxi-taking interface can be slightly different after a user triggers the first taxi-taking prompt message and the second taxi-taking prompt message.
In an embodiment shown, after a user triggers a first taxi driving prompt message displayed on a first page of the user, the user client may send a data acquisition request to a server; after receiving the data acquisition request, the server side can push page data corresponding to the taxi taking interface to the user client side; after receiving the page data, the user client can jump to a taxi taking interface based on the received page data.
In another embodiment shown, after the user triggers the second taxi taking prompt message displayed on the home page of the user, the user client may also send a data acquisition request to the server; after the server receives the data acquisition request, the server previously digs the preferred taxi taking destination of the user in the current time period, so that the page data corresponding to the taxi taking interface and the pre-digged preferred taxi taking destination of the user can be pushed to the user client; after receiving the page data and the taxi taking destination preferred by the user, the user client can jump to a taxi taking interface based on the received page data and output the taxi taking destination preferred by the user in a taxi taking destination list in the taxi taking interface;
for example, in one implementation, the destination points recommended to the user in the taxi-taking destination point list may be sorted, and then the taxi-taking destination point preferred by the user in the current time period is recommended to the user at the top of the sorting.
Therefore, by the method, when the server side judges that the user has a taxi taking demand for going to any one target place in the current time period in advance, the first place of the target place in the taxi taking target place list of the taxi taking interface can be recommended to the user, so that the user can conveniently and quickly select the target place as the target place of local taxi taking operation, and the taxi taking order is generated and submitted.
Certainly, in practical application, after the server side successfully pre-judges that the user has a taxi taking requirement in the current time period and the user client side outputs corresponding taxi taking prompt information to the user on the user home page, after a period of time, if the pre-judged taxi taking requirement of the user is overtime, the user still does not trigger the taxi taking prompt information to enter a taxi taking interface to complete taxi taking operation, and then the user client side can also clear the taxi taking prompt information displayed in the user home page.
By the method, the displayed taxi taking prompt information can be timely cleared away after the pre-judged taxi taking requirement of the user is overtime, so that the information displayed in the home page of the user can be optimized, and the user is prevented from viewing the taxi taking prompt information corresponding to the overdue taxi taking requirement and affecting the experience of the user.
The detailed process that the server side excavates the taxi taking behavior preference of the user based on the collected taxi taking behavior data sample of the user, and the server side pre-judges the taxi taking requirement of the user in real time based on the excavation result and pushes taxi taking prompt information to the user client side is described in detail above; it should be noted that, in another embodiment, after the server successfully excavates the taxi taking behavior preference of the user, the excavation result may also be pushed to the user client, so that the subsequent user client may autonomously pre-judge the taxi taking requirement of the user based on the local excavation result, and output the corresponding taxi taking prompt information through the user home page.
According to the embodiments, the method for pushing the information based on the taxi taking preference of the user is provided, the taxi taking behavior preference such as the target taxi taking time period preferred by the user and the target taxi taking place preferred by the user in the target taxi taking time period is excavated from the transaction detail data of the taxi taking trip of the user, and when the taxi taking behavior preference of the user is judged to be met, the corresponding taxi taking prompt information is timely pushed to the user client side and displayed on the user home page of the user client side; meanwhile, different taxi taking prompt messages can be respectively pushed according to different taxi taking requirements of users;
on one hand, in the method and the device, the taxi taking behavior preference of the user can be actively mined based on the transaction detail data of the taxi taking trip of the user;
on the other hand, the taxi taking requirements of the users can be judged in advance based on the excavated taxi taking behavior preferences of the users, and corresponding taxi taking prompt messages can be pushed to the users in time in a more natural pushing mode when the users are judged to have taxi taking requirements in advance, and the taxi taking prompt messages are displayed on the home pages of the users at the user clients.
Therefore, whether the user has a taxi taking requirement or not can be judged in advance based on the excavated taxi taking behavior preference of the user; and can in time send the suggestion of taking a car to the user when judging in advance that the user has the demand of taking a car to user experience can be optimized, the rate of utilization that the user took a car through user client is promoted.
Corresponding to the method embodiment, the application also provides an embodiment of the device.
Referring to fig. 3, the present application provides an information pushing apparatus 30 based on taxi taking preference of a user, which is applied to a server; referring to fig. 4, the hardware architecture related to the server side for carrying the information pushing device 70 based on the user taxi taking preference generally includes a CPU, a memory, a nonvolatile memory, a network interface, an internal bus, and the like; taking a software implementation as an example, the information pushing device 30 based on the taxi taking preference of the user can be generally understood as a computer program loaded in a memory, and a logic device formed by combining software and hardware after running through a CPU, where the device 30 includes:
the acquisition module 301 acquires taxi taking behavior data samples from transaction detail data of taxi taking trips of a user;
the analysis module 302 is used for carrying out statistical analysis on the collected taxi taking behavior data samples based on a preset data mining algorithm so as to determine taxi taking behavior preference of the user; the taxi taking behavior preference comprises a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period;
the judging module 303 is used for judging whether the current time hits the target taxi taking time period preferred by the user in real time; if the current time hits the target taxi taking time period preferred by the user, further judging whether the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period;
the pushing module 304 is used for pushing first taxi taking prompt information corresponding to the target taxi taking place to a user client side if the current positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period; and if the current positioning position of the user does not hit the preferred target taxi taking place of the user in the target taxi taking time period, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client so as to display the second taxi taking prompt information on a user home page of the user client.
In this example, the taxi taking behavior data samples include:
a user identification field, a taxi-taking city field, a taxi-taking whether field, a taxi-taking date field, a taxi-taking period field, a work day field, a week field, a departure place longitude field, a departure place latitude field, and a destination place field.
In this example, the target taxi taking time period preferred by the user comprises a weekday taxi taking time period preferred by the user, a weekend taxi taking time period preferred by the user and a weekend taxi taking time period preferred by the user;
the analysis module 302:
screening taxi taking behavior data samples which correspond to the working day time period and are the same in taxi taking cities from the taxi taking behavior data samples, and performing statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm to obtain the working day taxi taking time period preferred by a user;
screening taxi taking behavior data samples which correspond to weekend taxi taking time periods and are the same as taxi taking cities from the taxi taking behavior data samples, and performing statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm to obtain the weekend taxi taking time periods preferred by users;
and respectively screening the taxi taking behavior data samples which correspond to the respective natural days in the week period and have the same taxi taking places, and carrying out statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm so as to obtain the week regular taxi taking time period preferred by the user.
In this example, the analysis module 302 further:
counting the taxi taking times of the user in each first unit time period based on the taxi taking behavior data samples, and searching the first unit time period in which the taxi taking times are greater than a first threshold value;
counting the taxi taking times of the user in each second unit time period based on the taxi taking behavior data samples, searching for the second unit time periods when the taxi taking times are greater than a second threshold value and the taxi taking times of the user in the first unit time periods forming the second unit time period are greater than a third threshold value; wherein the second unit period consists of any two consecutive first unit periods within each first unit period; the second threshold is greater than the first threshold;
and carrying out time interval splicing according to the searched first unit time interval and the second unit time interval to generate a target taxi taking time interval preferred by the user.
In this example, the analysis module 302 further:
calculating the total times of taxi taking in the target taxi taking time period, and determining the target ratio of the total days corresponding to the taxi taking behavior data samples as taxi taking probability corresponding to the target taxi taking time period.
The analysis module 302 further:
performing cluster analysis based on all taxi-taking departure places of the user in the target time period;
searching for target clusters which contain the largest number of taxi taking starting places and the number of taxi taking starting places larger than a preset threshold value based on the result of the cluster analysis;
calculating the center point of the target cluster, and determining a target location corresponding to the center point of the target cluster as a taxi taking starting location preferred by a user;
calculating the radius of the target cluster, and determining a position range corresponding to the radius of the target cluster as a taxi taking position range preferred by a user;
and counting the destination point with the highest use frequency in the taxi taking behavior data samples corresponding to the taxi taking place points in the target cluster, and determining the destination point as the taxi taking destination point preferred by the user.
In this example, the determining module 303 further:
before the pushing module 304 pushes the first taxi taking prompt message or the second taxi taking prompt message to the user client, judging whether the taxi taking probability corresponding to the target taxi taking time period is greater than a preset threshold value; if yes, the pushing module 304 pushes the first taxi driving prompt message or the second taxi driving prompt message to the user client.
In this example, the taxi taking prompt message is an entry option of a taxi taking interface;
the push module 304 further:
responding to a data acquisition request sent by the user client after detecting the triggering operation of the user for the first taxi taking prompt message, and pushing page data corresponding to a taxi taking interface to the user client so that the user client enters the taxi taking interface based on the page data;
and responding to a data acquisition request sent by the user client after detecting the triggering operation of the user for the second taxi taking prompt message, pushing page data corresponding to a taxi taking interface and a taxi taking destination preferred by the user to the user client, so that the user client enters the taxi taking interface based on the page data, and outputting the taxi taking destination preferred by the user in a taxi taking destination list in the taxi taking interface.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (18)
1. An information pushing method based on taxi taking preference of a user comprises the following steps:
collecting a taxi taking behavior data sample of a user;
carrying out statistical analysis on the collected taxi taking behavior data samples based on a preset data mining algorithm so as to determine a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period;
judging whether the current time hits a target taxi taking time period preferred by the user or not;
if the current time hits the target taxi taking time period preferred by the user, further judging whether the positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period;
and if the positioning position hits the target taxi taking place, pushing first taxi taking prompt information corresponding to the target taxi taking place to a user client.
2. The method of claim 1, further comprising:
and if the positioning position does not hit the target taxi taking place, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client.
3. The method of claim 2, the taxi taking activity data samples comprising:
a user identification field, a taxi-taking city field, a taxi-taking whether field, a taxi-taking date field, a taxi-taking period field, a work day field, a week field, a departure place longitude field, a departure place latitude field, and a destination place field.
4. The method of claim 2, the user preferred target taxi-taking periods comprising user preferred weekday taxi-taking periods, user preferred weekend taxi-taking periods, and user preferred weekend taxi-taking periods;
the statistical analysis is carried out on the collected taxi taking behavior data samples based on the preset data mining algorithm, and the statistical analysis comprises the following steps:
screening taxi taking behavior data samples which correspond to the working day time period and are the same in taxi taking cities from the taxi taking behavior data samples, and performing statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm to obtain the working day taxi taking time period preferred by a user;
screening taxi taking behavior data samples which correspond to weekend taxi taking time periods and are the same as taxi taking cities from the taxi taking behavior data samples, and performing statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm to obtain the weekend taxi taking time periods preferred by users;
and respectively screening the taxi taking behavior data samples which correspond to the respective natural days in the week period and have the same taxi taking places, and carrying out statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm so as to obtain the week regular taxi taking time period preferred by the user.
5. The method of claim 4, the pre-set data mining algorithm, comprising:
counting the taxi taking times of the user in each first unit time period based on the taxi taking behavior data samples, and searching the first unit time period in which the taxi taking times are greater than a first threshold value;
counting the taxi taking times of the user in each second unit time period based on the taxi taking behavior data samples, searching for the second unit time periods when the taxi taking times are greater than a second threshold value and the taxi taking times of the user in the first unit time periods forming the second unit time period are greater than a third threshold value; wherein the second unit period consists of any two consecutive first unit periods within each first unit period; the second threshold is greater than the first threshold;
and carrying out time interval splicing according to the searched first unit time interval and the second unit time interval to generate a target taxi taking time interval preferred by the user.
6. The method of claim 5, further comprising:
and calculating the total taxi taking times in the target taxi taking time period and the target ratio of the total days corresponding to the taxi taking behavior data samples, and determining the target ratio as the taxi taking probability corresponding to the target taxi taking time period.
7. The method of claim 5, the user preferred target taxi-taking location comprising a user preferred taxi-taking start location, a user preferred taxi-taking destination location, and a user preferred taxi-taking location range;
the method further comprises the following steps:
performing cluster analysis based on all taxi-taking departure places of the user in the target time period;
searching for target clusters which contain the largest number of taxi taking starting places and the number of taxi taking starting places larger than a preset threshold value based on the result of the cluster analysis;
calculating the center point of the target cluster, and determining a target location corresponding to the center point of the target cluster as a taxi taking starting location preferred by a user;
calculating the radius of the target cluster, and determining a position range corresponding to the radius of the target cluster as a taxi taking position range preferred by a user;
and counting the destination point with the highest use frequency in the taxi taking behavior data samples corresponding to the taxi taking place points in the target cluster, and determining the destination point as the taxi taking destination point preferred by the user.
8. The method of claim 6, prior to pushing the first or second taxi hiring prompt information to a user client, the method further comprising:
judging whether the taxi taking probability corresponding to the target taxi taking time period is greater than a preset threshold value or not;
if so, pushing the first taxi driving prompt message or the second taxi driving prompt message to a user client.
9. The method according to claim 2 or 8, wherein the taxi taking prompt message is an entry option of a taxi taking interface;
the method further comprises the following steps:
responding to a data acquisition request sent by the user client after detecting the triggering operation of the user for the first taxi taking prompt message, and pushing page data corresponding to a taxi taking interface to the user client so that the user client enters the taxi taking interface based on the page data;
and responding to a data acquisition request sent by the user client after detecting the triggering operation of the user for the second taxi taking prompt message, pushing page data corresponding to a taxi taking interface and a taxi taking destination preferred by the user to the user client, so that the user client enters the taxi taking interface based on the page data, and outputting the taxi taking destination preferred by the user in a taxi taking destination list in the taxi taking interface.
10. An information pushing device based on taxi taking preference of a user is characterized by comprising:
the acquisition module is used for acquiring a taxi taking behavior data sample of a user;
the analysis module is used for carrying out statistical analysis on the collected taxi taking behavior data samples based on a preset data mining algorithm so as to determine a target taxi taking time period preferred by a user and a target taxi taking place preferred by the user in the target taxi taking time period;
the judging module is used for judging whether the current time hits the target taxi taking time period preferred by the user; if the current time hits the target taxi taking time period preferred by the user, further judging whether the positioning position of the user hits the target taxi taking place preferred by the user in the target taxi taking time period;
and the pushing module is used for pushing first taxi taking prompt information corresponding to the target taxi taking place to a user client side if the positioning position hits the target taxi taking place.
11. The apparatus of claim 10, the push module further to: and if the positioning position does not hit the target taxi taking place, pushing second taxi taking prompt information corresponding to the target taxi taking time period to the user client.
12. The apparatus of claim 11, the taxi taking activity data samples comprising:
a user identification field, a taxi-taking city field, a taxi-taking whether field, a taxi-taking date field, a taxi-taking period field, a work day field, a week field, a departure place longitude field, a departure place latitude field, and a destination place field.
13. The apparatus of claim 11, the user preferred target taxi-taking periods comprising user preferred weekday taxi-taking periods, user preferred weekend taxi-taking periods, and user preferred weekend taxi-taking periods;
the analysis module:
screening taxi taking behavior data samples which correspond to the working day time period and are the same in taxi taking cities from the taxi taking behavior data samples, and performing statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm to obtain the working day taxi taking time period preferred by a user;
screening taxi taking behavior data samples which correspond to weekend taxi taking time periods and are the same as taxi taking cities from the taxi taking behavior data samples, and performing statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm to obtain the weekend taxi taking time periods preferred by users;
and respectively screening the taxi taking behavior data samples which correspond to the respective natural days in the week period and have the same taxi taking places, and carrying out statistical analysis on the screened taxi taking behavior data samples based on a preset data mining algorithm so as to obtain the week regular taxi taking time period preferred by the user.
14. The apparatus of claim 13, the analysis module further to:
counting the taxi taking times of the user in each first unit time period based on the taxi taking behavior data samples, and searching the first unit time period in which the taxi taking times are greater than a first threshold value;
counting the taxi taking times of the user in each second unit time period based on the taxi taking behavior data samples, searching for the second unit time periods when the taxi taking times are greater than a second threshold value and the taxi taking times of the user in the first unit time periods forming the second unit time period are greater than a third threshold value; wherein the second unit period consists of any two consecutive first unit periods within each first unit period; the second threshold is greater than the first threshold;
and carrying out time interval splicing according to the searched first unit time interval and the second unit time interval to generate a target taxi taking time interval preferred by the user.
15. The apparatus of claim 14, the analysis module further to:
and calculating the total taxi taking times in the target taxi taking time period and the target ratio of the total days corresponding to the taxi taking behavior data samples, and determining the target ratio as the taxi taking probability corresponding to the target taxi taking time period.
16. The apparatus of claim 14, the user preferred target taxi-taking location comprising a user preferred taxi-taking start location, a user preferred taxi-taking destination location, and a user preferred taxi-taking location range;
the analysis module further:
performing cluster analysis based on all taxi-taking departure places of the user in the target time period;
searching for target clusters which contain the largest number of taxi taking starting places and the number of taxi taking starting places larger than a preset threshold value based on the result of the cluster analysis;
calculating the center point of the target cluster, and determining a target location corresponding to the center point of the target cluster as a taxi taking starting location preferred by a user;
calculating the radius of the target cluster, and determining a position range corresponding to the radius of the target cluster as a taxi taking position range preferred by a user;
and counting the destination point with the highest use frequency in the taxi taking behavior data samples corresponding to the taxi taking place points in the target cluster, and determining the destination point as the taxi taking destination point preferred by the user.
17. The apparatus of claim 15, the determination module further to:
before the pushing module pushes the first taxi taking prompt message or the second taxi taking prompt message to the user client, judging whether the taxi taking probability corresponding to the target taxi taking time period is greater than a preset threshold value or not; if so, the pushing module pushes the first taxi driving prompt message or the second taxi driving prompt message to a user client.
18. The device of claim 11 or 17, wherein the taxi taking prompt message is an entry option of a taxi taking interface;
the push module further:
responding to a data acquisition request sent by the user client after detecting the triggering operation of the user for the first taxi taking prompt message, and pushing page data corresponding to a taxi taking interface to the user client so that the user client enters the taxi taking interface based on the page data;
and responding to a data acquisition request sent by the user client after detecting the triggering operation of the user for the second taxi taking prompt message, pushing page data corresponding to a taxi taking interface and a taxi taking destination preferred by the user to the user client, so that the user client enters the taxi taking interface based on the page data, and outputting the taxi taking destination preferred by the user in a taxi taking destination list in the taxi taking interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011033904.6A CN112132661A (en) | 2017-02-15 | 2017-02-15 | Information pushing method and device based on taxi taking preference of user |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710081798.0A CN107038620B (en) | 2017-02-15 | 2017-02-15 | Information pushing and device based on taxi taking preference of user |
CN202011033904.6A CN112132661A (en) | 2017-02-15 | 2017-02-15 | Information pushing method and device based on taxi taking preference of user |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710081798.0A Division CN107038620B (en) | 2017-02-15 | 2017-02-15 | Information pushing and device based on taxi taking preference of user |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112132661A true CN112132661A (en) | 2020-12-25 |
Family
ID=59534307
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011033904.6A Pending CN112132661A (en) | 2017-02-15 | 2017-02-15 | Information pushing method and device based on taxi taking preference of user |
CN201710081798.0A Active CN107038620B (en) | 2017-02-15 | 2017-02-15 | Information pushing and device based on taxi taking preference of user |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710081798.0A Active CN107038620B (en) | 2017-02-15 | 2017-02-15 | Information pushing and device based on taxi taking preference of user |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN112132661A (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108255997A (en) * | 2017-12-29 | 2018-07-06 | 武汉斑马快跑科技有限公司 | A kind of Forecasting Methodology and system of destination of calling a taxi |
CN108198346A (en) * | 2018-01-23 | 2018-06-22 | 北京小米移动软件有限公司 | The method and device of the shared bicycle of management |
CN108566618B (en) * | 2018-04-04 | 2020-07-28 | 广州杰赛科技股份有限公司 | Method, device, equipment and storage medium for acquiring user residence law |
US11429987B2 (en) * | 2018-05-09 | 2022-08-30 | Volvo Car Corporation | Data-driven method and system to forecast demand for mobility units in a predetermined area based on user group preferences |
CN110887498B (en) * | 2018-09-07 | 2022-11-22 | 北京搜狗科技发展有限公司 | Navigation route recommendation method and device, electronic equipment and readable storage medium |
CN110969449B (en) * | 2018-09-28 | 2023-12-05 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining tail number of vehicle |
CN111311295B (en) * | 2018-12-12 | 2023-10-13 | 北京嘀嘀无限科技发展有限公司 | Service mode determining method, device, electronic equipment and storage medium |
CN111652666B (en) * | 2019-11-18 | 2021-05-18 | 北京嘀嘀无限科技发展有限公司 | Travel order processing method and device |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130262222A1 (en) * | 2012-03-30 | 2013-10-03 | Xerox Corporation | Customer metrics driven traveler information system for multimodal public transporation systems |
WO2016019189A1 (en) * | 2014-07-30 | 2016-02-04 | Uber Technologies, Inc. | Arranging a transport service for multiple users |
CN104168380A (en) * | 2014-08-19 | 2014-11-26 | 英华达(南京)科技有限公司 | Schedule reminding method |
CN104899252B (en) * | 2015-05-12 | 2019-03-12 | 北京嘀嘀无限科技发展有限公司 | A kind of method and device of information push |
CN105138590A (en) * | 2015-07-31 | 2015-12-09 | 北京嘀嘀无限科技发展有限公司 | Trajectory prediction method and apparatus |
CN105547306B (en) * | 2015-08-11 | 2018-08-07 | 深圳大学 | A kind of route method for pushing and system |
CN105279957B (en) * | 2015-10-30 | 2018-03-06 | 小米科技有限责任公司 | Message prompt method and device |
-
2017
- 2017-02-15 CN CN202011033904.6A patent/CN112132661A/en active Pending
- 2017-02-15 CN CN201710081798.0A patent/CN107038620B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107038620A (en) | 2017-08-11 |
CN107038620B (en) | 2020-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107038620B (en) | Information pushing and device based on taxi taking preference of user | |
EP3471374B1 (en) | Method and device for identifying type of geographic location at where user is located | |
RU2612583C2 (en) | Marketplace for timely event data distribution | |
US8745133B2 (en) | System and method for optimizing the storage of data | |
CN104867065B (en) | Method and equipment for processing order | |
US20120143755A1 (en) | Collection and Distribution of Customer Service Metric Information | |
CN107087017B (en) | Method and device for service drainage | |
CN111368221A (en) | Information providing method, information acquiring method, device, server and storage medium | |
US20130315042A1 (en) | Geo-normalization of Calendar Items | |
US10049378B1 (en) | Push reporting | |
CN111148018B (en) | Method and device for identifying and positioning regional value based on communication data | |
CN110955838A (en) | House resource recommendation processing method and device, terminal and computer readable storage medium | |
CN112182295B (en) | Service processing method and device based on behavior prediction and electronic equipment | |
US9553838B1 (en) | Querying for devices based on location | |
CN115017400A (en) | Application APP recommendation method and electronic equipment | |
CN110262863B (en) | Method and device for displaying terminal main interface | |
US11651320B2 (en) | Presentation device and presentation method | |
CN110827123A (en) | Message pushing method and device, computer equipment and storage medium | |
CN112380443B (en) | Guide recommendation method, device, computer equipment and storage medium | |
CN112883291A (en) | Destination position recommendation method and device and server | |
US20160073228A1 (en) | System and method for generating expected geolocations of mobile computing devices | |
CN111861540A (en) | Information pushing method and device, computer equipment and storage medium | |
CN111242723A (en) | User child and child condition judgment method, server and computer readable storage medium | |
CN110852807A (en) | User determination method and device, computer equipment and storage medium | |
CN113569159A (en) | Recommendation method and device for enterprise stores 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 |