CN106611017B

CN106611017B - User identity identification method and device

Info

Publication number: CN106611017B
Application number: CN201510708357.XA
Authority: CN
Inventors: 谭伟
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2015-10-27
Filing date: 2015-10-27
Publication date: 2021-06-29
Anticipated expiration: 2035-10-27
Also published as: CN106611017A

Abstract

The invention provides a user identity identification method and a device, wherein the method comprises the following steps: acquiring historical order data of User Equipment (UE) in a preset time period, and identifying POI categories of a departure place and a destination in the historical order data; dividing the historical order data according to cities, and determining resident cities and non-resident cities corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city; acquiring a first type POI in historical order data corresponding to the resident city and a second type POI in historical order data corresponding to the non-resident city; and identifying the identity of the user according to the first type POI and the second type POI. The device comprises an acquisition unit, a city division unit, a POI acquisition unit and an identity recognition unit. The invention can judge the user identity more accurately and quickly, thereby pushing personalized products or applications for users with different identities.

Description

User identity identification method and device

Technical Field

The invention relates to the technical field of computer processing, in particular to a user identity identification method and device.

Background

Along with the development of intelligent equipment and mobile internet technology, the popularization of service software brings great convenience to the life of people. Various service requirements are currently common requirements of people in all levels of society. However, the preference of users with different identities is greatly different, for example, business people, tourists, and the like, and many application scenarios need to push some personalized product services according to the identities of the users. It is important to identify the identity of the user.

Currently, there is no direct information in the distribution service class software that can characterize the identity of the user. Therefore, it is an urgent problem to find relevant information according to the order information in the distribution service software to determine the identity of the user.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a user identity identification method and device, which can judge the identity of a user more accurately according to historical order data.

In a first aspect, the present invention provides a method for identifying a user identity, the method comprising:

acquiring historical order data of User Equipment (UE) in a preset time period, and identifying POI (point of interest) categories of a departure place and a destination in the historical order data;

dividing the historical order data according to cities, and determining resident cities and non-resident cities corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city;

acquiring a first type POI in historical order data corresponding to the resident city and a second type POI in historical order data corresponding to the non-resident city;

and identifying the identity of the user according to the first type POI and the second type POI.

Preferably, the first type of POI comprises airports and train stations; the second type of POI includes a company, a sight, an airport, and a train station.

Preferably, the dividing the historical order data according to cities, and determining a resident city and a non-resident city corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city includes:

dividing the historical order data of the UE according to different cities to obtain historical order data corresponding to a plurality of cities;

obtaining historical order data corresponding to a city to which the mobile phone number of the UE belongs, and taking the city to which the mobile phone number belongs as a first candidate resident city;

counting a third type POI in historical order data corresponding to the rest cities except the city to which the mobile phone number belongs in the plurality of cities, and screening out a second candidate resident city from the rest cities according to the third type POI;

selecting the first candidate resident city or the second candidate resident city as the resident city corresponding to the UE according to the order number and the third type POI occurrence frequency in the historical order data corresponding to the first candidate resident city and the order number and the third type POI occurrence frequency in the historical order data corresponding to the second candidate resident city;

wherein the third type of POI comprises hotels and residential quarters.

Preferably, the screening out a second candidate city from the remaining cities according to the third type of POI comprises:

acquiring the number of orders, the number of times of hotel and the number of times of residence in the residential area in the historical order data corresponding to each city in the rest cities;

judging whether the occurrence frequency of the hotels in the historical order data corresponding to each city is less than the occurrence frequency of the residential buildings in the residential area;

if the number of times of occurrence of the hotel is less than the number of times of occurrence of the residential quarter, the city is taken as a candidate resident city;

and screening out the candidate resident city with the largest number of times of residential housing of the cell from all the candidate resident cities as a second candidate resident city.

Preferably, the selecting, according to the amount of orders and the number of times of occurrence of the third type of POI in the history order data corresponding to the first candidate residential city and the amount of orders and the number of times of occurrence of the third type of POI in the history order data corresponding to the second candidate residential city, the first candidate residential city or the second candidate residential city as the residential city corresponding to the UE includes:

judging whether the ratio of the amount of orders of the first candidate resident city to the amount of orders of the second candidate resident city is larger than or equal to a first threshold value, and if so, taking the first candidate resident city as a resident city corresponding to the UE;

otherwise, judging whether the number of times of occurrence of the cell residence of the first candidate resident city is smaller than that of the cell residence of the second candidate resident city, and if so, taking the second candidate resident city as the resident city corresponding to the UE;

otherwise, judging whether the hotel occurrence frequency of the first candidate resident city is greater than the hotel occurrence frequency of the second candidate resident city, and if so, taking the second candidate resident city as the resident city corresponding to the UE;

otherwise, the first candidate resident city is used as the resident city corresponding to the UE.

Preferably, the identifying the identity of the user according to the first type of POI and the second type of POI includes:

counting the occurrence times of a first type POI in the historical order data corresponding to the resident city and the occurrence times of a second type POI in the historical order data corresponding to the non-resident city;

and judging that the user is a business person or a tourist person according to the occurrence times of the first type POI and the second type POI.

Preferably, the determining that the user is a business person or a tourist according to the number of occurrences of the first type POI and the number of occurrences of the second type POI includes:

initializing a first characteristic value and a second characteristic value;

accumulating corresponding numerical values for the first characteristic value and the second characteristic value respectively according to the occurrence times of the first type POI and the second type POI;

when the first characteristic value is larger than a second threshold value, judging that the user is a business person;

and when the second characteristic value is larger than a third threshold value, determining that the user is a tourist person.

Preferably, the accumulating corresponding values for the first characteristic value and the second characteristic value according to the number of occurrences of the first-type POI and the number of occurrences of the second-type POI respectively includes:

counting the number of times of airport appearance in historical order data corresponding to the resident city, and respectively adding a first preset value to the first characteristic value and the second characteristic value when the airport appears once;

counting the occurrence times of the railway stations in the historical order data corresponding to the resident city, and adding a second preset value to the first characteristic value and the second characteristic value respectively when the railway stations occur once;

counting the occurrence times of companies in the historical order data corresponding to the non-resident city, and adding a third preset value to the first characteristic value every time a company occurs;

counting the occurrence times of the scenic spots in the historical order data corresponding to the non-resident city, and adding a fourth preset value to the second characteristic value every time the scenic spots appear;

counting the number of times of airport appearance in historical order data corresponding to the non-resident city, and adding a fifth preset value to the first characteristic value and the second characteristic value respectively when the airport appears once;

counting the number of times of airport appearance in the historical order data corresponding to the non-resident city, and adding a sixth preset value to the first characteristic value and the second characteristic value respectively every time the airport appears.

In a second aspect, the present invention provides a user identification apparatus, including:

the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring historical order data of User Equipment (UE) in a preset time period and identifying POI (point of interest) categories of a departure place and a destination in the historical order data;

the city dividing unit is used for dividing the historical order data according to cities and determining a resident city and a non-resident city corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city;

the POI acquisition unit is used for acquiring a first type POI in historical order data corresponding to the resident city and a second type POI in historical order data corresponding to the non-resident city;

and the identity recognition unit is used for recognizing the identity of the user according to the first type POI and the second type POI.

Preferably, the city dividing unit is configured to:

wherein the third type of POI comprises hotels and residential quarters.

Preferably, the city dividing unit is further configured to:

Preferably, the identification unit is configured to:

Preferably, the identity recognition unit is further configured to:

initializing a first characteristic value and a second characteristic value;

Preferably, the identity recognition unit is further configured to:

According to the technical scheme, the invention provides the user identity identification method and the user identity identification device, the permanent location of the user can be judged according to the departure point POI type and the destination POI type in the historical order data, and the identity of the user can be judged according to the orders, related to business trip and travel trip, of the user in the resident city and the non-resident city.

Drawings

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic flowchart of a user identification method according to an embodiment of the present disclosure;

fig. 2 is a schematic flow chart illustrating a process of screening user resident cities according to another embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of a user identification apparatus according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

Some words mentioned in the embodiments of the present disclosure are exemplified below.

It will be understood by those skilled in the art that a User Equipment (UE) referred to in embodiments of the present disclosure refers to any terminal installed with a service class software passenger end, is a call service party, and may include any type of User Equipment, such as a handheld computer, a Personal Digital Assistant (PDA), a cellular phone, a network appliance, a smart phone, an Enhanced General Packet Radio Service (EGPRS) mobile phone, a media player, a navigation device, or a combination of any two or more of these or other data processing devices.

It should be understood by those skilled in the art that the executing subject and the user identification device of the user identification method in the embodiments of the present disclosure may be servers, and the servers may represent a single server such as a computer server or multiple servers working together to execute functions, such as a cloud server hadoop.

Fig. 1 shows a schematic flow chart of a user identity identification method provided in an embodiment of the present disclosure, and as shown in fig. 1, the method includes the following steps:

s1: the method comprises the steps of obtaining historical order data of User Equipment (UE) in a preset time period, and identifying the types of points of Interest (POI for short) of a departure place and a destination in the historical order data.

S2: dividing the historical order data according to cities, and determining resident cities and non-resident cities corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city.

Specifically, rules are defined by using the POI category corresponding to the departure place and the POI category corresponding to the destination in the historical order data to identify the resident city and the non-resident city corresponding to the UE.

For example, in an order in a non-resident city, a hotel is mostly present at the departure place and the destination, and in an order in a resident city, a residential housing is mostly present at the departure place and the destination. Therefore, the rule is defined according to the aspect of "live" in the POI category, and the resident city is identified.

S3: and acquiring a first type POI in the historical order data corresponding to the resident city and a second type POI in the historical order data corresponding to the non-resident city.

Specifically, in this step, the orders related to business trip and travel trip are selected from the historical orders corresponding to the resident city and the non-resident city. For example, the first type of POI includes transportation transit points such as airports and train stations; the second type of POI includes company, attraction, airport, train station, and the like.

S4: and identifying the identity of the user according to the first type POI and the second type POI.

In the step, corresponding scores can be formulated according to different POI categories, an integral form is adopted, and finally the identities of business persons and tourist persons are judged according to the integral value.

Therefore, the method can judge the identity of the user accurately and quickly according to the departure point POI category and the destination point POI category in the historical order data, and judge the identity of the user according to orders related to business trip and travel of the user in the resident city and the non-resident city, so that different personalized products or applications can be pushed for users with different identities.

In this embodiment, step S2 may be specifically implemented by the following steps:

s21: and dividing the historical order data of the UE according to different cities to obtain the historical order data corresponding to a plurality of cities.

For example, as shown in fig. 2, passenger orders are divided into cities to obtain historical order data of city 1, city 2, and … …, city n, and the city to which the mobile phone number belongs, and statistics is performed to obtain the number of orders, the number of times of residential housing and the number of times of hotel (i.e., the number of times of POI occurrence) in each historical order data of cities.

S22: and obtaining historical order data corresponding to the city to which the mobile phone number of the UE belongs, and taking the city to which the mobile phone number belongs as a first candidate resident city.

S23: and counting a third type POI in historical order data corresponding to the rest cities except the city to which the mobile phone number belongs from the plurality of cities, and screening out a second candidate resident city from the rest cities according to the third type POI.

Wherein the third type of POI comprises hotels and residential quarters.

For example, as shown in FIG. 2, according to the number of times of occurrence of residential houses and the number of times of occurrence of hotels (i.e., the number of times of occurrence of POIs of the third type), a city x (x is a positive integer, and 1 ≦ x ≦ n) may be screened as a second candidate city.

S24: and selecting the first candidate resident city or the second candidate resident city as the resident city corresponding to the UE according to the order number and the third type POI occurrence frequency in the historical order data corresponding to the first candidate resident city and the order number and the third type POI occurrence frequency in the historical order data corresponding to the second candidate resident city.

Specifically, as shown in fig. 2, according to the order number of the city to which the mobile phone number belongs, the number of times of occurrence of the cell house, and the number of times of occurrence of the hotel (that is, the number of times of occurrence of the third-type POI), and the number of orders of the city x, the number of times of occurrence of the cell house, and the number of times of occurrence of the hotel (that is, the number of times of occurrence of the third-type POI), one of them is selected as the resident city of the user by using.

Further, the step S23 of screening out a second candidate city from the remaining cities according to the third type POI specifically includes:

a01, obtaining the number of orders, the number of times of hotel and the number of times of residence in the residential area in the historical order data corresponding to each city in the rest cities;

as shown in fig. 2, the remaining cities include city 1, city 2, … …, and city n.

A02, judging whether the number of occurrences of the hotel in the historical order data corresponding to each city is less than the number of occurrences of the residential district;

a03, if the number of times of hotel is less than the number of times of residence in the community, the city is taken as a candidate resident city;

understandably, if the number of times of hotel and hotel is more than or equal to the number of times of residence in the cell, the city is not a resident city, otherwise, the city is used as a candidate city of the resident city.

And A04, screening out the candidate resident city with the largest number of times of residential housing from all the candidate resident cities as a second candidate resident city.

It should be noted that, if the user only has a travel record in the city to which the telephone number belongs, the city to which the telephone number belongs may be used as the resident city of the user; if the user does not have a travel record in the phone number home city, the second candidate resident city selected in steps a01 to a04 is only required to be the most resident city of the user.

Further, the step S24 specifically includes the following sub-steps:

b01: judging whether the ratio of the amount of orders of the first candidate resident city to the amount of orders of the second candidate resident city is larger than or equal to a first threshold value, and if so, taking the first candidate resident city as a resident city corresponding to the UE;

for example, it is determined whether the order number of the first candidate city (i.e., the city where the mobile phone number belongs) and the order number of the second candidate city are greater than or equal to 0.4, if yes, it is determined that the first candidate city is the city, otherwise, the process goes to step B02.

B02: otherwise, judging whether the number of times of occurrence of the cell residence of the first candidate resident city is smaller than that of the cell residence of the second candidate resident city, and if so, taking the second candidate resident city as the resident city corresponding to the UE;

understandably, if the number of times of occurrence of the cell residence of the first candidate residential city is greater than or equal to the number of times of occurrence of the cell residence of the second candidate residential city, the process goes to step B03.

B03: otherwise, judging whether the hotel occurrence frequency of the first candidate resident city is greater than the hotel occurrence frequency of the second candidate resident city, and if so, taking the second candidate resident city as the resident city corresponding to the UE;

understandably, when none of the above conditions is satisfied, go to step B04.

B04: otherwise, the first candidate resident city is used as the resident city corresponding to the UE.

It can be seen that the identification method of the resident city is mainly started from the POI related to the user's "live", such as: residential houses, hotels and guest houses. Since the mobile phone number attribution is a factor which is most likely to be a permanent place, the mobile phone number attribution city needs to be separated from a plurality of cities of the order as a main candidate city. And then selecting a city which is most likely to be a resident city from cities except the city to which the mobile phone number belongs and the city to which the mobile phone number belongs to perform rule calculation, and finally, identifying the resident city of the passenger by one alternative.

Furthermore, the user identity needs to be identified, and the identification of the business and tourist people is mainly based on the POI orders of the passengers related to airports and railway stations in the orders of resident cities and the POIs related to business buildings and tourist attractions in the orders of non-resident cities. If the passenger frequently visits tourist attractions in a non-resident city, the passenger is considered to be related to the identity of the tourist, and if the passenger frequently visits a business building or a business enterprise, the passenger is considered to be related to the identity of the business person. Of course a passenger may be identified as either a business person or a tourist person.

In this embodiment, the step S4 of recognizing the identity of the user according to the first type of POI and the second type of POI includes the following sub-steps:

s41: counting the occurrence times of a first type POI in the historical order data corresponding to the resident city and the occurrence times of a second type POI in the historical order data corresponding to the non-resident city;

s42: and judging that the user is a business person or a tourist person according to the occurrence times of the first type POI and the second type POI.

Wherein the first type POI comprises an airport and a railway station; the second type of POI includes a company, a sight, an airport, and a train station. The business person or tourist can be accurately judged according to the times of the user going to airports and railway stations in the resident city and the times of the user going to companies (business buildings), scenic spots, airports and railway stations in the non-resident city. For example, if there are more visits to a sight spot in a very stationary city, the user is more likely to be a tourist.

Specifically, step S41 can be implemented by the following steps:

c01, initializing a first characteristic value and a second characteristic value;

c02, accumulating corresponding numerical values for the first characteristic value and the second characteristic value respectively according to the occurrence times of the first type POI and the second type POI;

c03, when the first characteristic value is larger than a second threshold value, determining that the user is a business person;

and C04, when the second characteristic value is larger than a third threshold value, determining that the user is a tourist person.

Therefore, corresponding scores can be formulated according to different POI categories, an integral value form is adopted, and finally the identities of business persons and tourist persons are judged according to the integral value.

The step C02 can be implemented according to the following rules:

(1) counting the number of times of airport appearance in historical order data corresponding to the resident city, and respectively adding a first preset value to the first characteristic value and the second characteristic value when the airport appears once;

(2) counting the occurrence times of the railway stations in the historical order data corresponding to the resident city, and adding a second preset value to the first characteristic value and the second characteristic value respectively when the railway stations occur once;

(3) counting the occurrence times of companies in the historical order data corresponding to the non-resident city, and adding a third preset value to the first characteristic value every time a company occurs;

(4) counting the occurrence times of the scenic spots in the historical order data corresponding to the non-resident city, and adding a fourth preset value to the second characteristic value every time the scenic spots appear;

(5) counting the number of times of airport appearance in historical order data corresponding to the non-resident city, and adding a fifth preset value to the first characteristic value and the second characteristic value respectively when the airport appears once;

(6) counting the number of times of airport appearance in the historical order data corresponding to the non-resident city, and adding a sixth preset value to the first characteristic value and the second characteristic value respectively every time the airport appears.

For example, in a standing premises order, there are the following POI categories in the starting or ending point, with the respective score accumulated once each occurrence:

airport: +2 (Business, travel)

A railway station: +1 (Business, travel)

Not adding points if there is no order of airport and railway station

In the very-resident order, the following POI categories exist in the starting point or the ending point, and the corresponding scores are accumulated once each POI category appears:

company: +5 (Business)

Scenic spots: +5 (traveling)

Airport: +2 (Business, travel)

A railway station: +1 (Business, travel)

And others: +0.1 (Business, travel)

Thus, points are respectively added to two variables, the score related to business is only added to the variable related to business persons, the score related to tourism is only added to the variable related to tourism persons, and other items are added to the two variables. The business person and the tourist can be identified by screening the two variables through a threshold value.

In order to more clearly illustrate the technical solution of the present disclosure, a user identification method is described below by a specific embodiment:

table 1 shows the order records of passenger P1 in the last 6 months, the data volume is large, and only partial detailed order data of each city are listed

TABLE 1 passenger P1 order record

From table 1 above, it can be seen that passenger P1 has a phone number belonging to city 29, and passenger P1 has a record of orders for making cars in cities 1, 29, and 4, and the resident city of the passenger and the business and tourist identities of the passenger are identified from these records. The process is as follows:

first, resident city identification:

1. the number of times of hotel occurrence, the number of times of residential housing and the total number of orders of each city are counted (as shown in table 2).

TABLE 2 order data statistics per city

City number	Number of hotels	Number of residence in district	Total number of orders
				1	6	9	56
4	1	20	46
				29	0	1	1

2. Except the mobile phone number belonging city 29, filtering city 1, wherein the number of times 6 of going to hotels is less than the number of times 9 of residential houses, and then the city 1 is a candidate city of a resident city; the city 4 is filtered, the number of times 1 of going to hotels is less than the number of times 20 of residential housing, and then the city 4 is also a candidate city of a resident city.

3. From candidate cities 1 and 4, one with the largest number of cell residences is selected as the city most likely to be the resident city except the city to which the mobile phone number belongs, i.e., 20 cities 4 with the largest number of cell residences are selected as candidate cities.

4. Either city 4 or 29 is used as the resident city:

judging a first scene: the number of orders for city 29 to which the telephone number belongs divided by the number of orders for city 4: 1/46<0.4, no resident city can be determined

Then scenario two is interpreted next: if the number of houses 20 in the city 4 is greater than the number of houses 1 in the city 29, that is, if the condition is satisfied, the city 4 is regarded as a resident city, and the determination is terminated.

Secondly, identifying business and tourist people:

the resident city of the passenger is identified to be 4 through the last step, then the order in the city 4 belongs to the resident city order, 1 and 29 belong to the off-site city order, and the integration is carried out according to the integration rule:

1. in the order of resident city 4, the train station appears 2 times, the airport 9 times,

the business score for this step is 2 x 9+1 x 2-20 and the travel score is 2 x 9+1 x 2-20.

2. In the orders for the off-site cities 29 and 1, the train station appears 0 times, the airport 1 times, the company 36 times, the scenic spots 0 times, and the others 72 times.

The business score for this step is 36 × 5+1 × 2+72 × 0.1 ═ 189.2, and the travel score is 1 × 2+72 × 0.1 ═ 9.2.

3. The final business score is: 20+ 189.2-209.2, and the travel point is 20+ 7.2-27.2.

And (4) conclusion: indicating that passenger P1 is more in line with the identity of business persons and not in line with the identity of tourist persons.

Fig. 3 is a schematic structural diagram of a user identification apparatus according to an embodiment of the present disclosure, where the apparatus includes an obtaining unit 301, a city dividing unit 302, a POI obtaining unit 303, and an identification unit 304. Wherein:

an obtaining unit 301, configured to obtain historical order data of a user equipment UE in a preset time period, and identify a POI category of a departure place and a destination in the historical order data;

a city dividing unit 302, configured to divide the historical order data according to cities, and determine a resident city and a non-resident city corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city;

a POI obtaining unit 303, configured to obtain a first type POI in the historical order data corresponding to the resident city and a second type POI in the historical order data corresponding to the non-resident city;

an identity recognition unit 304, configured to recognize an identity of a user according to the first type of POI and the second type of POI;

the first type POI comprises a transit point of a transportation facility such as an airport and a railway station; the second type of POI includes company, attraction, airport, train station, and the like.

In this embodiment, the city dividing unit 302 is configured to:

wherein the third type of POI comprises hotels and residential quarters.

In this embodiment, the city dividing unit is further configured to:

In this embodiment, the identity recognizing unit is configured to:

In this embodiment, the identity recognizing unit is further configured to:

initializing a first characteristic value and a second characteristic value;

In this embodiment, the identity recognizing unit is further configured to:

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

It should be noted that, in the respective components of the system of the present disclosure, the components therein are logically divided according to the functions to be implemented, but the present disclosure is not limited thereto, and the respective components may be re-divided or combined as needed, for example, some components may be combined into a single component, or some components may be further decomposed into more sub-components.

Various component embodiments of the disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in a system according to embodiments of the present disclosure. The present disclosure may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present disclosure may be stored on a computer-readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

The above embodiments are only suitable for illustrating the present disclosure, and not limiting the present disclosure, and those skilled in the relevant art can make various changes and modifications without departing from the spirit and scope of the present disclosure, so that all equivalent technical solutions also belong to the scope of the present disclosure, and the scope of the present disclosure should be defined by the claims.

Claims

1. A user identification method is characterized by comprising the following steps:

identifying the identity of a user according to the first type POI and the second type POI;

the dividing the historical order data according to cities, and determining resident cities and non-resident cities corresponding to the UE according to POI categories of a departure place and a destination in the historical order data corresponding to each city, comprises:

and if the user only has travel records in the mobile phone number attributive city, taking the mobile phone number attributive city as the resident city of the user.

2. The method of claim 1, wherein the POIs of the first type include airports and train stations; the second type of POI includes a company, a sight, an airport, and a train station.

3. The method of claim 1, wherein the historical order data is divided into cities, and a resident city and a non-resident city corresponding to the UE are determined according to POI categories of a departure place and a destination in the historical order data corresponding to each city, further comprising:

wherein the third type of POI comprises hotels and residential quarters.

4. The method of claim 3, wherein said screening out a second candidate city from said remaining cities according to said third type of POI comprises:

5. The method of claim 3, wherein the selecting the first candidate resident city or the second candidate resident city as the resident city corresponding to the UE according to the number of orders and the number of times of occurrence of the third type POI in the historical order data corresponding to the first candidate resident city and the number of orders and the number of times of occurrence of the third type POI in the historical order data corresponding to the second candidate resident city comprises:

6. The method of claim 2, wherein said identifying the identity of the user based on the first type of POI and the second type of POI comprises:

7. The method as claimed in claim 6, wherein said determining whether the user is a business person or a tourist person according to the number of occurrences of the first type of POI and the number of occurrences of the second type of POI comprises:

initializing a first characteristic value and a second characteristic value;

8. The method of claim 7, wherein accumulating the first and second eigenvalues with corresponding values based on the number of occurrences of the first-type POI and the number of occurrences of the second-type POI, respectively, comprises:

and counting the occurrence times of the railway stations in the historical order data corresponding to the non-resident city, and adding a sixth preset value to the first characteristic value and the second characteristic value respectively every time the railway stations occur.

9. An apparatus for identifying a user, the apparatus comprising:

the identity recognition unit is used for recognizing the identity of the user according to the first type POI and the second type POI;

10. The apparatus of claim 9, wherein the POIs of the first type comprise airports and train stations; the second type of POI includes a company, a sight, an airport, and a train station.

11. The apparatus of claim 9, wherein the city dividing unit is configured to:

wherein the third type of POI comprises hotels and residential quarters.

12. The apparatus of claim 11, wherein the city dividing unit is further configured to:

13. The apparatus of claim 11, wherein the city dividing unit is further configured to:

14. The apparatus of claim 10, wherein the identification unit is configured to:

15. The apparatus of claim 14, wherein the identification unit is further configured to:

initializing a first characteristic value and a second characteristic value;

16. The apparatus of claim 15, wherein the identification unit is further configured to: