CN105701123A - Passenger-vehicle relationship identification method and apparatus - Google Patents
Passenger-vehicle relationship identification method and apparatus Download PDFInfo
- Publication number
- CN105701123A CN105701123A CN201410710170.9A CN201410710170A CN105701123A CN 105701123 A CN105701123 A CN 105701123A CN 201410710170 A CN201410710170 A CN 201410710170A CN 105701123 A CN105701123 A CN 105701123A
- Authority
- CN
- China
- Prior art keywords
- car
- people
- man
- space
- time data
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a passenger-vehicle relationship identification method and apparatus. The passenger-vehicle relationship identification method comprises the steps of according to time-space data of a passenger and time-space data of a vehicle, calculating a correlation coefficient of each passenger-vehicle combination; traversing each passenger-vehicle combination and judging whether the correlation coefficient is greater than or equal to a correlation coefficient threshold or not; if yes, taking the passenger-vehicle combination as a to-be-identified passenger-vehicle relationship; and by adopting a preset rule, identifying the to-be-identified passenger-vehicle relationship as a passenger-vehicle relationship between one vehicle and one passenger or between one vehicle and multiple passengers. With the adoption of the method provided by the invention, the passenger-vehicle relationship can be identified as the passenger-vehicle relationship between one vehicle and one passenger or between one vehicle and multiple passengers according to the time-space data of the passenger and the time-space data of the vehicle; and the data coverage range of the collected time-space data of the passenger and the vehicle is wide, so that a relatively wide passenger-vehicle relationship can be identified.
Description
Technical field
The application relates to Data Mining, is specifically related to recognition methods and the device of a kind of man-vehicle interface。
Background technology
At present, all trades and professions are all collecting user data widely, and are searched out from substantial amounts of data be hidden in useful information therein by algorithm, it may be assumed that data mining。How to utilize limited data, as much as possible also original subscriber scene, catch the real demand of user more accurately and have become as the important research problem in industry-by-industry, field。
The problems referred to above, in automobile consumption field, are presented as and how to utilize limited data, also the scene of protoplast's car association, the problem identifying man-vehicle interface。In datumization operation, assets assessment, it is often necessary to judge whether someone has car。Existing people's car recognition methods mainly includes following two:
1) it is identified based on people's car register information。
This type of information is the most accurate, just can register because only that user really has vehicle。With it, the relation that can directly obtain between User Identity, vehicles identifications。But, this type of information only has vehicle administration office, sale of automobile website, automobile 4s to service shop and be only possible to, owing to information is more sensitive, it is difficult to the open other industry that is shared with uses, for instance: the electricity industry such as business, social platform。
2) it is identified in the Automobile Products consumer record of electricity business's platform based on people。
The user of Automobile Products is bought, it is more likely that having automobile, this type of information also is able to relatively accurately identify the relation of people, car, it might even be possible to according to the Automobile Products bought, identify the model of automobile at electricity business's platform。But, due to the difference of buying habit, a lot of people buy Automobile Products not by electricity business's platform, and service shop to the automobile 4s under line and buy, and therefore, the shortcoming of the method is that people, car data coverage are wideless。
In sum, on the one hand, vehicle administration office, sale of automobile website, automobile 4s service shop and have the data of people's car association, but data sensitive is seldom open, can not be more that other industry high-volume uses。On the other hand, owing to people, car are independent entities, and the on-line systems such as electricity business's platform, social platform are when collecting data, can only obtain the data of very limited amount of people's car association。
Therefore, prior art existence can only according to the problem of people's car associated data identification man-vehicle interface a limited number of, real。
Summary of the invention
The application provides recognition methods and the device of a kind of man-vehicle interface, with solve prior art exist can only according to the problem of people's car associated data identification man-vehicle interface a limited number of, real。
The application provides the recognition methods of a kind of man-vehicle interface, including:
Space-time data according to people and the space-time data of car, calculate the relative coefficient of each individual's car combination；
Travel through each individual's car combination, it is judged that whether described relative coefficient is be more than or equal to relative coefficient threshold value；If so, then described people's car is combined as man-vehicle interface to be identified；
Adopt preset rule, described man-vehicle interface to be identified is designated a car to a people or a car man-vehicle interface to many people。
Optionally, at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
Obtain the space-time data of described people and the space-time data of car。
Optionally, the space-time data of described people includes identity, longitude, latitude and time；The space-time data of described car includes navigator mark, longitude, latitude and time；Described relative coefficient refers to the number of times that between people and Che, the time is all identical with geographical position。
Optionally, at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
Longitude described in every a pair of the space-time data of the space-time data of described people and car and latitude data are converted to the character string of geohash coding。
Optionally, the figure place of described geohash coding is adjustable。
Optionally, the space-time data of described people and the space-time data of car, refer to the average geographic location within the scope of default interval。
Optionally, at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
POI data according to the map, by the space-time data of described people and the data deletion relevant to specific geographic position in the space-time data of car；Described map POI data includes title, classification, longitude and latitude。
Optionally, the space-time data of the described space-time data according to people and car, the relative coefficient calculating each individual's car combination includes:
Space-time data according to people and the space-time data of car, generate everyone car combination；
Travel through each individual's car combination, obtain the space-time data with described people's car combination space-time data of relevant people and car, and the space-time data according to the space-time data of described relevant people and car, calculate the relative coefficient of described people's car combination。
Optionally, the rule that described employing is preset, described man-vehicle interface to be identified is designated a car man-vehicle interface of many people is included by one people or a car:
If the people in described man-vehicle interface to be identified only and a car there is man-vehicle interface, and only there is man-vehicle interface with a people in the car in described man-vehicle interface to be identified, then judge that described man-vehicle interface to be identified is as the car man-vehicle interface to a people；
If respectively and there is man-vehicle interface to be identified between many cars in the people in described man-vehicle interface to be identified, or the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge that the maximum man-vehicle interface to be identified of described relative coefficient is as the car man-vehicle interface to a people；
If the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge between this car and the plurality of people as the car man-vehicle interface to many people。
Optionally, described relative coefficient threshold value adopts following steps to generate:
In the space-time data of described people, that chooses the first predetermined number has car and the people of mobile equipment, as the first sample；
According to described first sample, in the space-time data of described people and the space-time data of car, obtain the space-time data of the car that the space-time data of everyone described people and this people have in described first sample, as the first data to be calculated；
Calculate everyone in described first data to be calculated with the relative coefficient of each car；
Calculate everyone in described first data to be calculated with the meansigma methods of the relative coefficient of each car, as described relative coefficient threshold value。
Optionally, described relative coefficient threshold value adopts following steps to generate:
In the space-time data of described people, that chooses the first predetermined number has car and the people of mobile equipment, as the first sample；
According to described first sample, in the space-time data of described people and the space-time data of car, obtain the space-time data of the car that the space-time data of everyone described people and this people have in described first sample, as the first data to be calculated；
Calculate everyone in described first data to be calculated with the relative coefficient of each car；
Calculate everyone in described first data to be calculated with the meansigma methods of the relative coefficient of each car, as the first average correlation coefficient；
In the space-time data of described people, choose the second predetermined number only there is mobile equipment and not there is the people of car, as the second sample；
According to described second sample, in the space-time data of described people, obtain the space-time data of everyone described people in described second sample, using its space-time data with described car as the second data to be calculated；
Calculate everyone in described second data to be calculated with the relative coefficient of each car；
In described second data to be calculated everyone with in the relative coefficient of each car, choose the relative coefficient of the highest preset ratio of relative coefficient, as relative coefficient to be calculated；And the meansigma methods of described relative coefficient to be calculated is added the 3rd predetermined number, as the second average correlation coefficient；
Choose the maximum in described first average correlation coefficient and the second average correlation coefficient, as described relative coefficient threshold value。
Optionally, the space-time data of described car also includes vehicle model and the number-plate number。
The application also provides for the identification device of a kind of man-vehicle interface, including:
Computing unit, for the space-time data of the space-time data according to people and car, calculates the relative coefficient of each individual's car combination；
Judging unit, is used for traveling through each individual's car combination, it is judged that whether described relative coefficient is be more than or equal to relative coefficient threshold value；If so, then described people's car is combined as man-vehicle interface to be identified；
Mark unit, for adopting default rule, described man-vehicle interface to be identified is designated a car to a people or a car man-vehicle interface to many people。
Optionally, also include:
Acquiring unit, for obtaining the space-time data of described people and the space-time data of car。
Optionally, also include:
Transcoding units, for being converted to the character string of geohash coding by every a pair longitude of the space-time data of the space-time data of described people and car and latitude data。
Optionally, also include:
Delete unit, for POI data according to the map, by the space-time data of described people and the data deletion relevant to specific geographic position in the space-time data of car；Described map POI data includes title, classification, longitude and latitude。
Optionally, described computing unit includes:
Combination subelement, for the space-time data of the space-time data according to people and car, generates everyone car combination；
Computation subunit, is used for traveling through each individual's car combination, obtains the space-time data of the space-time data with described people's car combination relevant people and car, and the space-time data according to the space-time data of described relevant people and car, calculates the relative coefficient of described people's car combination。
Optionally, described mark unit includes:
First mark subelement, if only there is man-vehicle interface with a car for the people in described man-vehicle interface to be identified, and the car in described man-vehicle interface to be identified only exists man-vehicle interface with a people, then judge that described man-vehicle interface to be identified is as the car man-vehicle interface to a people；
Second mark subelement, if respectively and there is man-vehicle interface to be identified between many cars for the people in described man-vehicle interface to be identified, or the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge that the maximum man-vehicle interface to be identified of described relative coefficient is as the car man-vehicle interface to a people；
3rd mark subelement, if respectively and there is man-vehicle interface to be identified between many individuals for the car in described man-vehicle interface to be identified, then judges between this car and the plurality of people as the car man-vehicle interface to many people。
Compared with prior art, the application has the advantage that
The recognition methods of the man-vehicle interface that the application provides and device, by the positional information of collector, car respectively, based on the identification of space-time, obtain the relation of people and car。
The recognition methods of the man-vehicle interface that the application provides and device, the space-time data of people and the space-time data of car are carried out data mining, by calculating the relative coefficient of each individual's car combination, and each relative coefficient and relative coefficient threshold value are compared, default rule can be adopted, by relative coefficient be more than or equal to the man-vehicle interface of relative coefficient threshold value be designated a car to a people or a car man-vehicle interface to many people, owing to the data cover of the space-time data of people collected and the space-time data of car is wide such that it is able to identify the man-vehicle interface that comparison is wide。
Accompanying drawing explanation
Fig. 1 is the flow chart of the recognition methods embodiment of the man-vehicle interface of the application；
Fig. 2 be the man-vehicle interface of the application recognition methods embodiment in generate the particular flow sheet of space-time data of people；
Fig. 3 be the man-vehicle interface of the application recognition methods embodiment in the particular flow sheet of step S101；
Fig. 4 be the man-vehicle interface of the application recognition methods embodiment in generate relative coefficient threshold value particular flow sheet；
Fig. 5 be the man-vehicle interface of the application recognition methods embodiment in the particular flow sheet of step S103；
Fig. 6 is the schematic diagram identifying device embodiment of the man-vehicle interface of the application。
Detailed description of the invention
Elaborate a lot of detail in the following description so that fully understanding the present invention。But the present invention can implement being much different from alternate manner described here, and those skilled in the art can do similar popularization when without prejudice to intension of the present invention, therefore the present invention is by the following public restriction being embodied as。
In this application, it is provided that the recognition methods of a kind of man-vehicle interface and device。It is described in detail one by one in the following embodiments。
Refer to Fig. 1, it is the flow chart of recognition methods embodiment of man-vehicle interface of the application。Described method comprises the steps:
Step S101: the space-time data according to the space-time data of people and car, calculates the relative coefficient of each individual's car combination。
Existing man-vehicle interface information or use can not be shared due to too sensitive, or can not be widely used owing to coverage rate is little。The recognition methods of the man-vehicle interface that the application provides, it is possible to according to substantial amounts of people truck position information, carry out the identification of man-vehicle interface, supplement existing man-vehicle interface data from the angle of data mining。
Data mining (DataMining, DM) being the hot issue of current artificial intelligence and data base's area research, so-called data mining refers to the non-trivial process being disclosed information that is implicit, not previously known and that have potential value from the mass data of data base by algorithm。Data mining is a kind of decision support processes, it is based primarily upon artificial intelligence, machine learning, pattern recognition, statistics, data base, visualization technique etc., analyze the data of enterprise increasingly automatedly, make the reasoning of inductive, therefrom excavate potential pattern, aid decision making person adjusts market strategy, reduces risks, and makes correct decision-making。
Knowledge Discovery process was made up of the three below stage: the preparation of (1) data, (2) data mining, (3) results expression and explanation。Data mining can be mutual with user or knowledge base。Data mining is by analyzing each data, finds the technology of its rule from mass data, mainly has data preparation, rule to find and rule represents 3 steps。It is choose required data from relevant data source and be integrated into the data set for data mining that data prepare；It is with the rule contained by data set being found out someway that rule is found；Rule represents it is the rule found out showed in the intelligible mode of user (such as visualization) as far as possible。
The relevant analysis of task of data mining, cluster analysis, classification analysis, anomaly analysis, special cohort analysis and evolution analysis etc.。The recognition methods of man-vehicle interface that the application provides, is a kind of method of typical data mining, and its task is according to substantial amounts of people truck position information, is associated people and Che analyzing, thus obtain a people to a car or a car man-vehicle interface to many people。
In the present embodiment, at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
Step S100: obtain the space-time data of described people and the space-time data of car。
For implementing the recognition methods of the man-vehicle interface that the application provides, it is necessary first to carry out Data Preparation, obtain the object of data mining, it may be assumed that the data set of the space-time data of people and the space-time data of car。
The space-time data of the people described in the embodiment of the present application is mainly derived from smart mobile phone。The coverage of smart mobile phone has been covered with the whole world, because smart mobile phone has outstanding operating system, can freely install this three big characteristic of full touch screen type operation sense of all kinds of software, complete large-size screen monitors, so the keyboard-type mobile phone several years ago that terminated completely。At present, most people are owned by smart mobile phone。Along with the development of mobile Internet, the application based on mobile Internet is also increasing, for instance: network finance, mobile shopping, social media, ecommerce, instant messaging etc., the application of various mobile phones has provided the user colourful service。Wherein, the client of some application program of mobile phone can collect the positional information of people, for instance, user's geographical location information all can be collected by Tencent QQ, Taobao。Along with the extensive use of smart mobile phone and becoming increasingly abundant of mobile phone application, people have got used to using smart mobile phone to carry out doing shopping, chatting whenever and wherever possible, client is all at the positional information recording user incessantly, such as, when user drives, client background is also at the positional information that record user dumbly。Therefore, the original position-information of substantial amounts of people can be collected by smart mobile phone。These original position-information include but not limited to the information such as device number or User Identity, longitude, the latitude of mobile phone, and time。
After collecting the original position-information of people, for performing the recognition methods of the man-vehicle interface that the embodiment of the present application provides, in addition it is also necessary to the original position-information of people is carried out data compilation work, in order to obtain normalized data set。Such as, if what collect is not User Identity, but cell phone apparatus number (being specifically as follows international mobile subscriber identity or ad identifier), then can identify system by user, identify people corresponding to this equipment User Identity in corresponding application program of mobile phone, for instance: Taobao user id, Alipay user id etc.。According to the User Identity obtained, generate the positional information of normalized people。The positional information of normalized people is designated as user [userID, lat, log, time], and the implication of its expression is: user is in the information of the longitude residing for certain concrete time and latitude。
In the present embodiment, the space-time data of described people includes identity, longitude, latitude and time。Refer to Fig. 2, its be the application man-vehicle interface recognition methods embodiment in generate the particular flow sheet of space-time data of people, the space-time data of described people adopts following steps to generate:
Step S201: gather the space-time data of original people；The space-time data of described original people includes the device number of mobile terminal and at least one of the User Identity of application program and longitude, latitude and time。
Step S202: judge whether the space-time data of described original people includes the User Identity of described application program。
Step S203: if it is not, then device number according to described mobile terminal, and the device number of mobile terminal and the incidence relation of the User Identity of application program, obtain the User Identity of the application program associated with the device number of described mobile terminal。
Step S204: the User Identity according to the space-time data of described original people and the application program of described association, generates the space-time data of described people。
Step S205: store the space-time data of described people。
In the present embodiment, the space-time data of described car includes navigator mark, longitude, latitude and time。The space-time data of the car described in the embodiment of the present application is mainly derived from automobile navigation instrument。Owing to most private car is all configured with navigator, in vehicle traveling process, if employ navigation way or at crossing, important monitoring section etc. all can record the log information of travel route。Such as: the navigation of high moral can collect the daily record data in vehicle traveling process, owing to navigator is built in automobile, so navigation can be similar to and be equal to automobile, navigator mark is approximate is equal to automobile logo。The automobile log information collected by navigator includes but not limited to navigator mark, longitude, latitude and time, it is designated as car [carID, lat, log, time], the implication of its expression is: automobile is in the information of the longitude residing for certain concrete time and latitude。
The recognition methods of the man-vehicle interface that the embodiment of the present application provides, by the equipment such as smart mobile phone and automobile navigation instrument, it is possible to obtain the positional information of substantial amounts of people, car。Data cover owing to collecting is wide, it is possible to identify the man-vehicle interface data that comparison is wide, thus compensate in prior art the defect that people's car data coverage rate that the on-line systems such as electricity business's platform, social platform collect is little。
When carrying out Data Preparation, it is necessary to noting the ageing of data, the effectiveness of the ageing same data of data is the same, decides the analysis result of data mining。In actual applications, it is necessary to confirm the ageing of data according to different demands, even if out-of-date thing has been analyzed out produces impact without on decision-making。For man-vehicle interface, this ageing it is critical that, the industries such as reason is in that the relation between people and car it may happen that change, electricity business need the space-time data according to the people collected and Che quickly to analyze effective result, thus bring bigger interests could to electricity business。Therefore, performing the recognition methods of the man-vehicle interface that the embodiment of the present application provides, the time range of the space-time data of described people and the space-time data of car is adjustable, for instance, the data of the nearest 365 days object as data mining can be taken, in order to quickly recognize real man-vehicle interface effectively。
Got the space-time data of people and the space-time data of car by step S100, step S101 can be performed, the space-time data according to the space-time data of people and car, calculate the relative coefficient of each individual's car combination。Relative coefficient described herein refers to the number of times that between people and Che, the time is all identical with geographical position, i.e. the space-time registration of people and Che。For obtaining man-vehicle interface, it is necessary to the combination to every a pair people and Che, calculate the relative coefficient between them respectively。When calculating relative coefficient, it is necessary to people and the time of Che, geographical position are compared。
Geographical location information in the space-time data of people directly obtained respectively by smart mobile phone and navigator and the space-time data of car is longitude and latitude data。The recognition methods of the man-vehicle interface that the embodiment of the present application provides, both can directly longitude and latitude data be contrasted, different coded systems can also be adopted first to transfer longitude and latitude data to can represent geographical position one-dimensional character string after, then more one-dimensional character string is contrasted, it is thus possible to be more efficiently calculated, obtain the relative coefficient of people's car combination。It is for instance possible to use geohash coded system, after first transferring longitude and latitude data to one-dimensional character string, more one-dimensional character string is contrasted。These different calculations above-mentioned, are all the change of detailed description of the invention, all without departing from the core of the application, therefore all within the protection domain of the application。
Based on above-mentioned analysis, for reaching higher calculating speed, in the present embodiment, space-time data at the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include: longitude described in every a pair of the space-time data of the space-time data of described people and car and latitude data are converted to the character string of geohash coding。
Geohash is the algorithm that the longitude and latitude of two dimension converts to one-dimensional character string, and each character string represents a certain rectangular area。The simplest explanation of geohash is exactly: by a latitude and longitude information, converts a string encoding that can sort, can compare to。This algorithm is currently mainly used in the address searching of map, and applying this algorithm can be that the address in data base indexes, and greatly improves the speed of map data retrieval。The figure place of geohash coding is adjustable, and the figure place of character string is more many, and the rectangular area of its representative is more little, thus the geographical position represented is more accurate。In the present embodiment, owing to automobile moves soon, encode (about 0.34 sq-km) with 6 geohash and represent a region, as minimum mikey。
The people in each geographical position and the space-time data of Che can be gathered at any time by navigator and smart mobile phone, including: parking lot, bustling business block。The business block of parking lot and prosperity is all the region that wagon flow is crowded, the data in these regions are relatively difficult to navigate to concrete car, people, such as: the man-vehicle interface gone out according to the data analysis in these places be a people to many cars or a car relation to many people, and practical situation is really not so。Therefore, for the analysis of man-vehicle interface, it is regarded as interference data, or claims noise data。For this, it is possible to POI (PointofInterest) coordinate according to the map, the positional information relating to the block of parking lot, prosperity in the space-time data of people and Che is weeded out, in order to avoid the effectiveness of impact analysis result。
In the present embodiment, space-time data at the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include: POI data according to the map, by the space-time data of described people and the data deletion relevant to specific geographic position in the space-time data of car。
In GIS-Geographic Information System, a POI can be a house, retail shop, mailbox, a bus station etc.。Each POI comprises four directions surface information, title, classification, longitude, latitude。Therefore, the space-time data of a very important person and the geographical position in the space-time data of car overlap with the specific geographic position of map POI coordinates logo, can these data be rejected。Classification information by map POI, it is possible to specify specific geographic position, for instance: classification is the POI of parking lot, bustling block。
Refer to Fig. 3, its be the application man-vehicle interface recognition methods embodiment in the particular flow sheet of step S101。In the present embodiment, the space-time data of the described space-time data according to people and car, the relative coefficient calculating each individual's car combination includes:
Step S1011: the space-time data according to the space-time data of people and car, generates everyone car combination。
In step S1011, the first space-time data according to the space-time data of people and car, obtain all people and all of car in data set, then people and Che are combined one by one, generate the combination of all people's car。Such as: if the number of people is M, the number of car is N, then the number of people's car combination is M*N。
Step S1012: travel through each individual's car combination, obtains the space-time data with described people's car combination space-time data of relevant people and car, and the space-time data according to the space-time data of described relevant people and car, calculates the relative coefficient of described people's car combination。
In step S1012, for above-mentioned every a pair people's car combination, the space-time data of people and the space-time data of car are inquired about, thus obtaining all space-time datas of people in the combination of people's car and all space-time datas of car, and calculate the number of times that between this people and this car, time and geographical position are all identical, obtain relative coefficient。
The recognition methods of the man-vehicle interface that the embodiment of the present application provides, is the combination calculation relative coefficient to each individual's car, and therefore computation complexity is O (M*N), and wherein M is the data volume of the space-time data of people, and N is the data volume of the space-time data of car。The space-time data of the people of original collection and the space-time data of car, depend on the application client of smart mobile phone and the record set of time option of navigator, and open the time of application client and navigator。Therefore, the space-time data of the people of original collection and the space-time data of car equally distributed data in non-temporal, the time of a part of data is likely to very intensive, and the time of another part data is likely to loosen very much。The more important thing is, original data volume is great。Therefore, if according to initial data calculates the relative coefficient of people's car, huge amount of calculation will be caused, and take system resource more。Consider the movement characteristic of people and Che, except being calculated relative coefficient except the space-time data of the above-mentioned people according to original collection and the space-time data of car, can also be calculated according to the space-time data of the space-time data of the people of the average geographic location within the scope of default interval and car, so that minimizing amount of calculation, improve and calculate speed, and the space-time data of the space-time data of the people of the average geographic location within the scope of the interval rationally arranged and car can the movement locus of representative and Che。These different calculations above-mentioned, are all the change of detailed description of the invention, all without departing from the core of the application, therefore all within the protection domain of the application。
In the present embodiment, for every a pair people's car combination, the space-time data according to the space-time data of the people of the average geographic location within the scope of default interval and car, the number of times that between this people and this car, time and geographical position are all identical is calculated。Particularly as follows: by the time using 10 minutes as minimum unit of time, calculate the mean place obtaining people's car appearance in every 10 minutes, including two steps: according to default interval, split by the space-time data of the space-time data of the people of original collection and car；Calculate the average geographic location of the every a part of initial data after segmentation。When calculating mean place, it is possible to use the string representation position of geohash coding, then calculation result data is car [carID, geohash6, timeID], user [userID, geohash6, timeID], represents an event of car and people respectively。
Step S102: travel through each individual's car combination, it is judged that whether described relative coefficient is be more than or equal to relative coefficient threshold value；If so, then described people's car is combined as man-vehicle interface to be identified。
Relative coefficient described herein, refers to the number between people's car with identical event, and the numerical value of relative coefficient is more big, then the dependency of people's car is more big。Relative coefficient threshold value described herein is the threshold value of the acquired relative coefficient of a large amount of regression training of process, this threshold value table is leted others have a look at the minima of the relative coefficient between car, that is: when the relative coefficient between people's car is be more than or equal to relative coefficient threshold value, it is determined that people's car is correlated with；When relative coefficient between people's car is less than or equal to relative coefficient threshold value, then judge that people's car is unrelated。Relevant people's car be probably a car to a people, a car to a people or a car to many people。In specific implementation process, reasonably assessment relative coefficient threshold value is very crucial。When obtaining relative coefficient threshold value by regression training, feasible regression training mode includes the regression training mode of linear model, i.e. linear regression algorithm。
The recognition methods of the man-vehicle interface that the embodiment of the present application provides, adopts following steps to generate relative coefficient threshold value: in the space-time data of described people, and that chooses the first predetermined number has car and the people of mobile equipment, as the first sample；According to described first sample, in the space-time data of described people and the space-time data of car, obtain the space-time data of the car that the space-time data of everyone described people and this people have in described first sample, as the first data to be calculated；Calculate everyone in described first data to be calculated with the relative coefficient of each car；Calculate everyone in described first data to be calculated with the meansigma methods of the relative coefficient of each car, as described relative coefficient threshold value。
The recognition methods of man-vehicle interface that the embodiment of the present application provides, when generating relative coefficient threshold value, everyone in the first sample chosen has car or smart mobile phone, it may be assumed that calculate relative coefficient threshold value from the angle estimator in front。The number of the first sample should be sufficiently large, and the number of sample is more many, and the relative coefficient threshold value obtained is more accurate, for instance: the number of the first sample is more than 100。Based on the consideration of data age, the data that the present embodiment chooses the people in the first sample data, car data is nearest 365 days, it may be assumed that the first data to be calculated are specially the data in preset time range。By step S401 to step S404, it is possible to obtain the average correlation coefficient that not only there is car but also have people's car of smart mobile phone to combine, using the meansigma methods of relative coefficient as relative coefficient threshold value。
When assessing relative coefficient threshold value, for obtaining assessment result more accurately, it is preferred that assessment mode is for carry out comprehensive assessment from two angles of obverse and reverse。Refer to Fig. 4, its be the application man-vehicle interface recognition methods embodiment in generate relative coefficient threshold value particular flow sheet。In the present embodiment, described relative coefficient threshold value adopts following steps to generate:
Step S401: in the space-time data of described people, that chooses the first predetermined number has car and the people of mobile equipment, as the first sample。
Step S402: according to described first sample, in the space-time data of described people and the space-time data of car, obtains the space-time data of the car that the space-time data of everyone described people and this people have in described first sample, as the first data to be calculated。
Step S403: calculate everyone in described first data to be calculated with the relative coefficient of each car。
Step S404: calculate everyone in described first data to be calculated with the meansigma methods of the relative coefficient of each car, as the first average correlation coefficient。
First average correlation coefficient described herein, refers to the meansigma methods of the relative coefficient of people and the car having car。In the present embodiment, being first estimated from front calculating, everyone in the first sample has car, smart mobile phone。By step S401 to step S404, it is possible to obtain the average correlation coefficient that not only there is car but also have people's car of smart mobile phone to combine。Such as: choosing 100 people really having car as the first sample, the meansigma methods of these people relative coefficient respectively and between its car having is 10 times。
Step S405: in the space-time data of described people, chooses only the having mobile equipment of the second predetermined number and does not have the people of car, as the second sample。
Step S406: according to described second sample, in the space-time data of described people, obtains the space-time data of everyone described people in described second sample, using its space-time data with described car as the second data to be calculated。
Step S407: calculate everyone in described second data to be calculated with the relative coefficient of each car。
Step S408: in described second data to be calculated everyone with in the relative coefficient of each car, choose the relative coefficient of the highest preset ratio of relative coefficient, as relative coefficient to be calculated；And the meansigma methods of described relative coefficient to be calculated is added the 3rd predetermined number, as the second average correlation coefficient。
Step S405 to step S408 is estimated calculating from the negative, does not have car per capita, but have smart mobile phone in the second sample chosen。In proprietary space-time data, obtain the part data belonging to people in the second sample, and the space-time data of the data of collection Yu whole cars is carried out relative coefficient calculating, obtain the relative coefficient of each individual's car combination of the second sample。In the present embodiment, choose the relative coefficient of people's car of numerical value the highest 20%, calculate the meansigma methods of these relative coefficients, and using meansigma methods plus the 3rd predetermined number as the second average correlation coefficient。Such as: choose 100 people not having car as the second sample, calculate these people relative coefficient respectively and between car, to relative coefficient the highest 20% the relative coefficient of people's car, averaged is 7 times, if the 3rd predetermined number is 1, then the second average correlation coefficient is 8 times。
In the present embodiment, the number of first, second sample should be sufficiently large, and the number of sample is more many, and the relative coefficient threshold value obtained is more accurate, for instance: the number of first, second sample is all higher than 100。
Based on the consideration of data age, the data that the present embodiment chooses the people in first, second sample data, car data is nearest 365 days, it may be assumed that first, second data to be calculated are specially the data in preset time range。
The 3rd predetermined number described in the embodiment of the present application, refers to if the relative coefficient between a people and a car is less than or equal to the meansigma methods of described relative coefficient to be calculated, is then absent from man-vehicle interface between this people and this car；If the relative coefficient between a people and a car is be more than or equal to meansigma methods and the 3rd predetermined number sum of described relative coefficient to be calculated, then there is man-vehicle interface between this people and this car。3rd predetermined number is adjustable, it is possible to take the integer more than 0, for instance: the 3rd predetermined number is set as 1 or 2 etc.。
Step S409: choose the maximum in described first average correlation coefficient and the second average correlation coefficient, as described relative coefficient threshold value。
The first average correlation coefficient is obtained from front assessment, assessment obtains the second average correlation coefficient from the negative, minima due to the relative coefficient that relative coefficient threshold value table is leted others have a look between car, therefore the maximum in the first average correlation coefficient and the second average correlation coefficient should be chosen, as relative coefficient threshold value。Such as: the first average correlation coefficient is 10, the second average correlation coefficient is 8, then relative coefficient threshold value is 10。
Step S103: adopt preset rule, described man-vehicle interface to be identified is designated a car to a people or a car man-vehicle interface to many people。
By step S102, obtain relative coefficient in everyone car combination to combine be more than or equal to people's car of relative coefficient threshold value, the relation of these people's cars combination includes a car to a people, a car to many people, and the various different man-vehicle interface that many cars are to a people, described in detail below:
1) car man-vehicle interface to a people: the people in these man-vehicle interfaces is only corresponding with a car, in turn, the car in these man-vehicle interfaces is also only corresponding with a people, it may be assumed that be man-to-man relation between people and Che。Therefore, it is determined that such man-vehicle interface is the car man-vehicle interface to a people。
2) car man-vehicle interface to many people: same car in these man-vehicle interfaces is corresponding with many individuals, it may be assumed that be many-to-one relation between people and Che。Therefore, it can merge into such man-vehicle interface one new man-vehicle interface, the artificial how individual in new man-vehicle interface, car is the car that these people have, and new man-vehicle interface is judged to the car man-vehicle interface to many people。Owing to very eurypalynous car services for public trip, for instance: regular bus, school bus, officer's car etc., therefore there will be the situation of the corresponding same car of many individuals。
In actual applications, can also be as the case may be, the man-vehicle interface of many people is further segmented by one car, a portion man-vehicle interface is judged to the car man-vehicle interface to many people, and another part man-vehicle interface is judged to the car man-vehicle interface to a people。Particularly as follows: first to any one car, search whether there is N number of above people's property coefficient associated therewith be more than or equal to relative coefficient threshold value, N can set according to practical situation, adopt N in the present embodiment >=5, if there is N number of above people, it is possible to these man-vehicle interfaces are judged to the car man-vehicle interface to many people；If the only people less than N, then choose this car and the maximum in everyone relative coefficient, and the people related to by maximal correlation property coefficient and Che are judged to the car man-vehicle interface to a people。Such as, three people in one family own a car together, then judge to have between the people of this car most-often used and this car man-to-man man-vehicle interface。These different judgment rules above-mentioned, are all the change of detailed description of the invention, all without departing from the core of the application, therefore all within the protection domain of the application。
3) many cars man-vehicle interface to a people: the same person in these man-vehicle interfaces is corresponding with multiple cars, it may be assumed that be the relation of one-to-many between people and Che。Therefore, it can merge into such man-vehicle interface one new man-vehicle interface, the artificial people in new man-vehicle interface, car is many cars that this people has, and new man-vehicle interface is judged to many cars man-vehicle interface to a people。In the present embodiment, it is a region due to geohash character string identification, it is possible to the car that can recognize this region is all someone, both the corresponding people of many cars, these part data are actual is " dirty data ", it is possible to according to concrete time and position, find out this part data, and rejected。Such as: in the same time, the data of the corresponding multiple cars of someone are " dirty data "。
Owing to many cars are complex to the situation of a people, for instance: when a people is when unit, it is possible to obtain the situation of its corresponding many cars, these are not real many cars man-vehicle interfaces to a people。Therefore, the recognition methods of the man-vehicle interface that the embodiment of the present application provides, the man-vehicle interface of a people is not carried out concrete identification by many cars。
In sum, it is necessary to as the case may be, pre-establish some judgment rules, various man-vehicle interfaces are identified。Refer to Fig. 5, its be the application man-vehicle interface recognition methods embodiment in the particular flow sheet of step S103。In the present embodiment, the rule that described employing is preset, described man-vehicle interface to be identified is designated a car man-vehicle interface of many people is included by one people or a car:
Step S1031: if the people in described man-vehicle interface to be identified only exists man-vehicle interface with a car, and the car in described man-vehicle interface to be identified only exists man-vehicle interface with a people, then judge that described man-vehicle interface to be identified is as the car man-vehicle interface to a people。
Step S1032: if the people in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many cars, or respectively and there is man-vehicle interface to be identified between many individuals in the car in described man-vehicle interface to be identified, it is determined that the maximum man-vehicle interface to be identified of described relative coefficient is the car man-vehicle interface to a people。
Step S1033: if the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge between this car and the plurality of people as the car man-vehicle interface to many people。
In the present embodiment, the space-time data of the described car obtained by navigator also includes vehicle model and the number-plate number。The recognition methods of the man-vehicle interface that the electricity industry such as business provides according to the application, after obtaining the relation of people's car, is possible not only to carry out, according to man-vehicle interface, shopping guide's business of being correlated with, it is also possible to carry out the activities such as the sales promotion be correlated with further according to vehicle model and the number-plate number。
The recognition methods of the man-vehicle interface that the application provides, the space-time data of people and the space-time data of car are carried out data mining, by calculating the relative coefficient of each individual's car combination, and each relative coefficient and relative coefficient threshold value are compared, default rule can be adopted, by relative coefficient be more than or equal to the man-vehicle interface of relative coefficient threshold value be designated a car to a people or a car man-vehicle interface to many people, owing to the data cover of the space-time data of people collected and the space-time data of car is wide such that it is able to identify the man-vehicle interface that comparison is wide。
In the above-described embodiment, it is provided that the recognition methods of a kind of man-vehicle interface, corresponding, the application also provides for the identification device of a kind of man-vehicle interface。Refer to Fig. 5, its be the application man-vehicle interface identify device embodiment schematic diagram。Owing to device embodiment is substantially similar to embodiment of the method, so describing fairly simple, relevant part illustrates referring to the part of embodiment of the method。Device embodiment described below is merely schematic。
A kind of identification device of the man-vehicle interface of the present embodiment, including:
Computing unit 101, for the space-time data of the space-time data according to people and car, calculates the relative coefficient judging unit 102 of each individual's car combination, is used for traveling through each individual's car combination, it is judged that whether described relative coefficient is be more than or equal to relative coefficient threshold value；If so, then described people's car is combined as man-vehicle interface to be identified；Mark unit 103, for adopting default rule, described man-vehicle interface to be identified is designated a car to a people or a car man-vehicle interface to many people。
Optionally, also include:
Acquiring unit, for obtaining the space-time data of described people and the space-time data of car。
Optionally, also include:
Transcoding units, for being converted to the character string of geohash coding by every a pair longitude of the space-time data of the space-time data of described people and car and latitude data。
Optionally, also include:
Delete unit, for POI data according to the map, by the space-time data of described people and the data deletion relevant to specific geographic position in the space-time data of car；Described map POI data includes title, classification, longitude and latitude。
Optionally, described computing unit 101 includes:
Combination subelement, for the space-time data of the space-time data according to people and car, generates everyone car combination；
Computation subunit, is used for traveling through each individual's car combination, obtains the space-time data of the space-time data with described people's car combination relevant people and car, and the space-time data according to the space-time data of described relevant people and car, calculates the relative coefficient of described people's car combination。
Optionally, described mark unit 103 includes:
First mark subelement, if only there is man-vehicle interface with a car for the people in described man-vehicle interface to be identified, and the car in described man-vehicle interface to be identified only exists man-vehicle interface with a people, then judge that described man-vehicle interface to be identified is as the car man-vehicle interface to a people；
Second mark subelement, if respectively and there is man-vehicle interface to be identified between many cars for the people in described man-vehicle interface to be identified, or the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge that the maximum man-vehicle interface to be identified of described relative coefficient is as the car man-vehicle interface to a people；
3rd mark subelement, if respectively and there is man-vehicle interface to be identified between many individuals for the car in described man-vehicle interface to be identified, then judges between this car and the plurality of people as the car man-vehicle interface to many people。
Although the present invention is with preferred embodiment openly as above; but it is not for limiting the present invention; any those skilled in the art are without departing from the spirit and scope of the present invention; can making possible variation and amendment, therefore protection scope of the present invention should be as the criterion with the scope that the claims in the present invention define。
In a typical configuration, computing equipment includes one or more processor (CPU), input/output interface, network interface and internal memory。
Internal memory potentially includes the forms such as the volatile memory in computer-readable medium, random access memory (RAM) and/or Nonvolatile memory, such as read only memory (ROM) or flash memory (flashRAM)。Internal memory is the example of computer-readable medium。
1, computer-readable medium includes permanent and impermanency, removable and non-removable media can by any method or technology to realize information storage。Information can be computer-readable instruction, data structure, the module of program or other data。The example of the storage medium of computer includes, but it is not limited to phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read only memory (ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus or any other non-transmission medium, can be used for the information that storage can be accessed by a computing device。According to defining herein, computer-readable medium does not include non-temporary computer readable media (transitorymedia), such as data signal and the carrier wave of modulation。
2, it will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program。Therefore, the application can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect。And, the application can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code。
Claims (18)
1. the recognition methods of a man-vehicle interface, it is characterised in that including:
Space-time data according to people and the space-time data of car, calculate the relative coefficient of each individual's car combination；
Travel through each individual's car combination, it is judged that whether described relative coefficient is be more than or equal to relative coefficient threshold value；If so, then described people's car is combined as man-vehicle interface to be identified；
Adopt preset rule, described man-vehicle interface to be identified is designated a car to a people or a car man-vehicle interface to many people。
2. the recognition methods of man-vehicle interface according to claim 1, it is characterised in that at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
Obtain the space-time data of described people and the space-time data of car。
3. the recognition methods of man-vehicle interface according to claim 1, it is characterised in that the space-time data of described people includes identity, longitude, latitude and time；The space-time data of described car includes navigator mark, longitude, latitude and time；Described relative coefficient refers to the number of times that between people and Che, the time is all identical with geographical position。
4. the recognition methods of man-vehicle interface according to claim 2, it is characterised in that at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
Longitude described in every a pair of the space-time data of the space-time data of described people and car and latitude data are converted to the character string of geohash coding。
5. the recognition methods of man-vehicle interface according to claim 4, it is characterised in that the figure place of described geohash coding is adjustable。
6. the recognition methods of man-vehicle interface according to claim 4, it is characterised in that the space-time data of described people and the space-time data of car, refers to the average geographic location within the scope of default interval。
7. the recognition methods of man-vehicle interface according to claim 1, it is characterised in that at the space-time data of the described space-time data according to people and car, before calculating the relative coefficient of each individual's car combination, also include:
POI data according to the map, by the space-time data of described people and the data deletion relevant to specific geographic position in the space-time data of car；Described map POI data includes title, classification, longitude and latitude。
8. the recognition methods of man-vehicle interface according to claim 1, it is characterised in that the space-time data of the described space-time data according to people and car, the relative coefficient calculating each individual's car combination includes:
Space-time data according to people and the space-time data of car, generate everyone car combination；
Travel through each individual's car combination, obtain the space-time data with described people's car combination space-time data of relevant people and car, and the space-time data according to the space-time data of described relevant people and car, calculate the relative coefficient of described people's car combination。
9. the recognition methods of man-vehicle interface according to claim 1, it is characterised in that the rule that described employing is preset, is designated a car by described man-vehicle interface to be identified and the man-vehicle interface of many people is included by one people or a car:
If the people in described man-vehicle interface to be identified only and a car there is man-vehicle interface, and only there is man-vehicle interface with a people in the car in described man-vehicle interface to be identified, then judge that described man-vehicle interface to be identified is as the car man-vehicle interface to a people；
If respectively and there is man-vehicle interface to be identified between many cars in the people in described man-vehicle interface to be identified, or the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge that the maximum man-vehicle interface to be identified of described relative coefficient is as the car man-vehicle interface to a people；
If the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge between this car and the plurality of people as the car man-vehicle interface to many people。
10. the recognition methods of the man-vehicle interface according to any one of claim 1-9, it is characterised in that described relative coefficient threshold value adopts following steps to generate:
In the space-time data of described people, that chooses the first predetermined number has car and the people of mobile equipment, as the first sample；
According to described first sample, in the space-time data of described people and the space-time data of car, obtain the space-time data of the car that the space-time data of everyone described people and this people have in described first sample, as the first data to be calculated；
Calculate everyone in described first data to be calculated with the relative coefficient of each car；
Calculate everyone in described first data to be calculated with the meansigma methods of the relative coefficient of each car, as described relative coefficient threshold value。
11. the recognition methods of the man-vehicle interface according to any one of claim 1-9, it is characterised in that described relative coefficient threshold value adopts following steps to generate:
In the space-time data of described people, that chooses the first predetermined number has car and the people of mobile equipment, as the first sample；
According to described first sample, in the space-time data of described people and the space-time data of car, obtain the space-time data of the car that the space-time data of everyone described people and this people have in described first sample, as the first data to be calculated；
Calculate everyone in described first data to be calculated with the relative coefficient of each car；
Calculate everyone in described first data to be calculated with the meansigma methods of the relative coefficient of each car, as the first average correlation coefficient；
In the space-time data of described people, choose the second predetermined number only there is mobile equipment and not there is the people of car, as the second sample；
According to described second sample, in the space-time data of described people, obtain the space-time data of everyone described people in described second sample, using its space-time data with described car as the second data to be calculated；
Calculate everyone in described second data to be calculated with the relative coefficient of each car；
In described second data to be calculated everyone with in the relative coefficient of each car, choose the relative coefficient of the highest preset ratio of relative coefficient, as relative coefficient to be calculated；And the meansigma methods of described relative coefficient to be calculated is added the 3rd predetermined number, as the second average correlation coefficient；
Choose the maximum in described first average correlation coefficient and the second average correlation coefficient, as described relative coefficient threshold value。
12. the recognition methods of the man-vehicle interface according to any one of claim 1-9, it is characterised in that the space-time data of described car also includes vehicle model and the number-plate number。
13. the identification device of the man-vehicle interface of a kind, it is characterised in that including:
Computing unit, for the space-time data of the space-time data according to people and car, calculates the relative coefficient of each individual's car combination；
Judging unit, is used for traveling through each individual's car combination, it is judged that whether described relative coefficient is be more than or equal to relative coefficient threshold value；If so, then described people's car is combined as man-vehicle interface to be identified；
Mark unit, for adopting default rule, described man-vehicle interface to be identified is designated a car to a people or a car man-vehicle interface to many people。
14. the identification device of man-vehicle interface according to claim 13, it is characterised in that also include:
Acquiring unit, for obtaining the space-time data of described people and the space-time data of car。
15. the identification device of man-vehicle interface according to claim 13, it is characterised in that also include:
Transcoding units, for being converted to the character string of geohash coding by every a pair longitude of the space-time data of the space-time data of described people and car and latitude data。
16. the identification device of man-vehicle interface according to claim 13, it is characterised in that also include:
Delete unit, for POI data according to the map, by the space-time data of described people and the data deletion relevant to specific geographic position in the space-time data of car；Described map POI data includes title, classification, longitude and latitude。
17. the identification device of man-vehicle interface according to claim 13, it is characterised in that described computing unit includes:
Combination subelement, for the space-time data of the space-time data according to people and car, generates everyone car combination；
Computation subunit, is used for traveling through each individual's car combination, obtains the space-time data of the space-time data with described people's car combination relevant people and car, and the space-time data according to the space-time data of described relevant people and car, calculates the relative coefficient of described people's car combination。
18. the identification device of man-vehicle interface according to claim 13, it is characterised in that described mark unit includes:
First mark subelement, if only there is man-vehicle interface with a car for the people in described man-vehicle interface to be identified, and the car in described man-vehicle interface to be identified only exists man-vehicle interface with a people, then judge that described man-vehicle interface to be identified is as the car man-vehicle interface to a people；
Second mark subelement, if respectively and there is man-vehicle interface to be identified between many cars for the people in described man-vehicle interface to be identified, or the car in described man-vehicle interface to be identified respectively and exists man-vehicle interface to be identified between many individuals, then judge that the maximum man-vehicle interface to be identified of described relative coefficient is as the car man-vehicle interface to a people；
3rd mark subelement, if respectively and there is man-vehicle interface to be identified between many individuals for the car in described man-vehicle interface to be identified, then judges between this car and the plurality of people as the car man-vehicle interface to many people。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410710170.9A CN105701123B (en) | 2014-11-27 | 2014-11-27 | The recognition methods of man-vehicle interface and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410710170.9A CN105701123B (en) | 2014-11-27 | 2014-11-27 | The recognition methods of man-vehicle interface and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105701123A true CN105701123A (en) | 2016-06-22 |
| CN105701123B CN105701123B (en) | 2019-07-16 |
Family
ID=56230955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410710170.9A Active CN105701123B (en) | 2014-11-27 | 2014-11-27 | The recognition methods of man-vehicle interface and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701123B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106303962A (en) * | 2016-08-17 | 2017-01-04 | 公安部道路交通安全研究中心 | A kind of method and system realizing people's car information association |
| CN107330466A (en) * | 2017-06-30 | 2017-11-07 | 上海连尚网络科技有限公司 | Very fast geographical GeoHash clustering methods |
| CN107559944A (en) * | 2017-09-22 | 2018-01-09 | 天津大学 | Method for identifying regulation mode of central heating system |
| CN107944031A (en) * | 2017-12-13 | 2018-04-20 | 福建省汽车工业集团云度新能源汽车股份有限公司 | The collecting method and automobile of automobile based on different user |
| CN108346289A (en) * | 2018-02-13 | 2018-07-31 | 重庆交通大学 | A kind of highway people vehicle interconnected system and method |
| CN108763331A (en) * | 2018-05-09 | 2018-11-06 | 泉州市三川通讯技术有限公司 | A kind of relevant open service application system in integrated position |
| CN108848460A (en) * | 2018-05-31 | 2018-11-20 | 重庆市城投金卡信息产业股份有限公司 | People's vehicle correlating method based on RFID and GPS data |
| CN109344773A (en) * | 2018-10-06 | 2019-02-15 | 广州智体科技有限公司 | A kind of taxi driver's face identification system method and device |
| CN109413074A (en) * | 2018-11-02 | 2019-03-01 | 上海博泰悦臻网络技术服务有限公司 | Driver and the multipair multi-account management method of vehicle, server-side and client |
| CN110517500A (en) * | 2018-05-21 | 2019-11-29 | 上海大唐移动通信设备有限公司 | A kind of people's vehicle association process method and device |
| CN110544378A (en) * | 2019-09-02 | 2019-12-06 | 上海评驾科技有限公司 | method for judging traffic jam condition of mobile phone user |
| CN110618997A (en) * | 2019-08-13 | 2019-12-27 | 深圳市天彦通信股份有限公司 | Identity data unifying method and related device |
| CN110825785A (en) * | 2019-11-05 | 2020-02-21 | 佳都新太科技股份有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN110888884A (en) * | 2019-11-26 | 2020-03-17 | 杭州三汇数字信息技术有限公司 | Vehicle code fitting method and system based on geohash matching |
| CN111177487A (en) * | 2019-12-19 | 2020-05-19 | 北京明略软件***有限公司 | Incidence relation determining method and device, electronic equipment and storage medium |
| CN111801667A (en) * | 2017-11-17 | 2020-10-20 | 日产自动车株式会社 | Vehicle operation assisting device |
| CN114817273A (en) * | 2022-07-01 | 2022-07-29 | 湖南智警公共安全技术研究院有限公司 | Data identification method and system for high-frequency man-vehicle association abnormity |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4990757A (en) * | 1988-12-22 | 1991-02-05 | Valet Parking Associates, Inc. | Method and apparatus for vehicle storage and retrieval |
| US20100138104A1 (en) * | 1999-12-15 | 2010-06-03 | Yacht Watchman International, Inc. | Marine vessel monitoring system |
| CN102831769A (en) * | 2012-08-29 | 2012-12-19 | 申屠祖军 | Caller and taxi matching method for taxi service system |
| CN103079169A (en) * | 2013-01-17 | 2013-05-01 | 成都美璞科技有限公司 | Intelligent taxi hailing system and method based on web page |
| CN103164954A (en) * | 2011-12-11 | 2013-06-19 | 方文淋 | System and method for remote inquiry and call of idle taxi |
| CN103680128A (en) * | 2013-11-26 | 2014-03-26 | 上海交通大学 | Intelligent taxi scheduling system |
| CN203580878U (en) * | 2013-10-22 | 2014-05-07 | 上海派特贵金属有限公司 | Man-vehicle matching safety management equipment |
| CN103856532A (en) * | 2012-12-05 | 2014-06-11 | 深圳先进技术研究院 | Intelligent car sharing cloud service method and system |
-
2014
- 2014-11-27 CN CN201410710170.9A patent/CN105701123B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4990757A (en) * | 1988-12-22 | 1991-02-05 | Valet Parking Associates, Inc. | Method and apparatus for vehicle storage and retrieval |
| US20100138104A1 (en) * | 1999-12-15 | 2010-06-03 | Yacht Watchman International, Inc. | Marine vessel monitoring system |
| CN103164954A (en) * | 2011-12-11 | 2013-06-19 | 方文淋 | System and method for remote inquiry and call of idle taxi |
| CN102831769A (en) * | 2012-08-29 | 2012-12-19 | 申屠祖军 | Caller and taxi matching method for taxi service system |
| CN103856532A (en) * | 2012-12-05 | 2014-06-11 | 深圳先进技术研究院 | Intelligent car sharing cloud service method and system |
| CN103079169A (en) * | 2013-01-17 | 2013-05-01 | 成都美璞科技有限公司 | Intelligent taxi hailing system and method based on web page |
| CN203580878U (en) * | 2013-10-22 | 2014-05-07 | 上海派特贵金属有限公司 | Man-vehicle matching safety management equipment |
| CN103680128A (en) * | 2013-11-26 | 2014-03-26 | 上海交通大学 | Intelligent taxi scheduling system |
Non-Patent Citations (2)
| Title |
|---|
| 何菲: ""嘀嘀打车：等来的商机"", 《IT 经理世界·CEOCIO》 * |
| 张艺娜 等: ""出租车与乘客即时运输交互信息***的可行性研究"", 《电子世界》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106303962A (en) * | 2016-08-17 | 2017-01-04 | 公安部道路交通安全研究中心 | A kind of method and system realizing people's car information association |
| CN107330466A (en) * | 2017-06-30 | 2017-11-07 | 上海连尚网络科技有限公司 | Very fast geographical GeoHash clustering methods |
| CN107559944B (en) * | 2017-09-22 | 2019-11-19 | 天津大学 | A method of identification central heating system shaping modes |
| CN107559944A (en) * | 2017-09-22 | 2018-01-09 | 天津大学 | Method for identifying regulation mode of central heating system |
| CN111801667B (en) * | 2017-11-17 | 2024-04-02 | 日产自动车株式会社 | Vehicle operation support device and vehicle operation support method |
| CN111801667A (en) * | 2017-11-17 | 2020-10-20 | 日产自动车株式会社 | Vehicle operation assisting device |
| CN107944031A (en) * | 2017-12-13 | 2018-04-20 | 福建省汽车工业集团云度新能源汽车股份有限公司 | The collecting method and automobile of automobile based on different user |
| CN108346289A (en) * | 2018-02-13 | 2018-07-31 | 重庆交通大学 | A kind of highway people vehicle interconnected system and method |
| CN108763331A (en) * | 2018-05-09 | 2018-11-06 | 泉州市三川通讯技术有限公司 | A kind of relevant open service application system in integrated position |
| CN110517500A (en) * | 2018-05-21 | 2019-11-29 | 上海大唐移动通信设备有限公司 | A kind of people's vehicle association process method and device |
| CN108848460A (en) * | 2018-05-31 | 2018-11-20 | 重庆市城投金卡信息产业股份有限公司 | People's vehicle correlating method based on RFID and GPS data |
| CN109344773A (en) * | 2018-10-06 | 2019-02-15 | 广州智体科技有限公司 | A kind of taxi driver's face identification system method and device |
| CN109413074A (en) * | 2018-11-02 | 2019-03-01 | 上海博泰悦臻网络技术服务有限公司 | Driver and the multipair multi-account management method of vehicle, server-side and client |
| CN110618997A (en) * | 2019-08-13 | 2019-12-27 | 深圳市天彦通信股份有限公司 | Identity data unifying method and related device |
| CN110618997B (en) * | 2019-08-13 | 2022-07-26 | 深圳市天彦通信股份有限公司 | Identity data unifying method and related device |
| CN110544378B (en) * | 2019-09-02 | 2020-11-03 | 上海评驾科技有限公司 | Method for judging traffic jam condition of mobile phone user |
| CN110544378A (en) * | 2019-09-02 | 2019-12-06 | 上海评驾科技有限公司 | method for judging traffic jam condition of mobile phone user |
| CN110825785A (en) * | 2019-11-05 | 2020-02-21 | 佳都新太科技股份有限公司 | Data mining method and device, electronic equipment and storage medium |
| CN110888884B (en) * | 2019-11-26 | 2022-08-23 | 杭州三汇数字信息技术有限公司 | Vehicle code fitting method and system based on geohash matching |
| CN110888884A (en) * | 2019-11-26 | 2020-03-17 | 杭州三汇数字信息技术有限公司 | Vehicle code fitting method and system based on geohash matching |
| CN111177487A (en) * | 2019-12-19 | 2020-05-19 | 北京明略软件***有限公司 | Incidence relation determining method and device, electronic equipment and storage medium |
| CN114817273A (en) * | 2022-07-01 | 2022-07-29 | 湖南智警公共安全技术研究院有限公司 | Data identification method and system for high-frequency man-vehicle association abnormity |
| CN114817273B (en) * | 2022-07-01 | 2022-09-27 | 湖南智警公共安全技术研究院有限公司 | Data identification method and system for high-frequency man-vehicle association abnormity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105701123B (en) | 2019-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105701123A (en) | Passenger-vehicle relationship identification method and apparatus | |
| US11669864B2 (en) | Determining locations of interest based on user visits | |
| AU2017399729B2 (en) | Trajectory analysis with mode of transport analysis | |
| Ahas et al. | Using mobile positioning data to model locations meaningful to users of mobile phones | |
| CN105528359B (en) | For storing the method and system of travel track | |
| CN106936806A (en) | A kind of recognition methods of account abnormal login and device | |
| US11255678B2 (en) | Classifying entities in digital maps using discrete non-trace positioning data | |
| US20210172759A1 (en) | Map Matching and Trajectory Analysis | |
| WO2018150228A1 (en) | Mobility gene for visit data | |
| Malmi et al. | Checking in or checked in: comparing large-scale manual and automatic location disclosure patterns | |
| WO2021191685A2 (en) | System and method for vehicle event data processing for identifying parking areas | |
| Li et al. | Metagraph-based life pattern clustering with big human mobility data | |
| WO2018151672A1 (en) | Trajectory analysis through fusion of multiple data sources | |
| Eum et al. | Vehicle detection from airborne LiDAR point clouds based on a decision tree algorithm with horizontal and vertical features | |
| WO2020167945A1 (en) | Systems and methods for route computing for destination-oriented navigation | |
| CN114007186B (en) | Positioning method and related product | |
| Panahandeh et al. | Clustering driving destinations using a modified dbscan algorithm with locally-defined map-based thresholds | |
| KR101201932B1 (en) | Apparatus for selecting of bus number in smart phone and method thereof | |
| Li et al. | Effective metagraph-based life pattern clustering with big human mobility data | |
| Zhao et al. | Efficient semantic enrichment process for spatiotemporal trajectories | |
| Xu et al. | Location prediction in social media based on contents and graphs | |
| Comito | Mining pattern similarity for mobility prediction in location-based social networks | |
| Prakash et al. | Exploiting trajectory data to improve smart city services | |
| Salnikov et al. | The geography and carbon footprint of mobile phone use in Côte d’Ivoire | |
| Phattanarat et al. | Detecting New Points of Interest Using Taxi GPS Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1225830 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211117 Address after: Room 202-47, Tianren building, No. 188, Liyi Road, ningwei street, Xiaoshan District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou xiaomanlu Intelligent Technology Co.,Ltd. Address before: Box 847, four, Grand Cayman capital, Cayman Islands, UK Patentee before: ALIBABA GROUP HOLDING Ltd. |