CN111126653B - User position prediction method, device and storage medium - Google Patents
User position prediction method, device and storage medium Download PDFInfo
- Publication number
- CN111126653B CN111126653B CN201811295960.XA CN201811295960A CN111126653B CN 111126653 B CN111126653 B CN 111126653B CN 201811295960 A CN201811295960 A CN 201811295960A CN 111126653 B CN111126653 B CN 111126653B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- positioning
- point
- network connection
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device and a storage medium for predicting the position of a user. The prediction method provided by the invention determines the position of the user based on the training model, and has higher prediction accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of big data application, in particular to a method and a device for predicting the position of a user and a storage medium.
Background
With the advent of the big data era, more and more user data and more information quantity exist, how to effectively utilize the user data to obtain more accurate and more valuable data information, and the obtained valuable data information is presented in an effective labeling display mode, so that accurate user portrait is established, and the problem in the existing big data field is solved.
The technical difficulty in the field of user portrait is always to mine the occupation of the user, and the accuracy rate is difficult to reach the available level. For example, in the aspect of financial wind control, the workplace of the user represents the income level and the work stability of the user, and the method has great value for evaluating the credit level and reasonably granting credit to the user. For another example, in an internet information flow product, if the working place and the living place of the user are known, the user attribute and the hobbies and interests can be inferred, and the income of the information recommendation algorithm is greatly increased.
In the prior art, for mining of user places, a traditional method is to simply cluster positioning track data based on users, and analyze a time sequence relation of user positioning cluster points to identify the user places. However, the clustering result data is more noisy, and the accuracy of the labels is not high.
Disclosure of Invention
The user occupation prediction method, the user occupation prediction device and the storage medium provided by the invention have higher prediction accuracy because the user occupation prediction is carried out on the basis of the training model.
A first aspect of the present invention provides a method for predicting a place of employment of a user, including:
acquiring positioning basic data of a first user;
determining a resident cluster point of the first user according to the positioning basic data;
acquiring network connection characteristic data corresponding to the resident cluster point;
and inputting the network connection characteristic data into a user position prediction model to obtain a prediction result of the first user position.
In a possible implementation manner, the determining a cluster location where the first user resides according to the positioning basic data includes:
carrying out data preprocessing on the positioning basic data to obtain positioning track data of the first user;
and determining the resident cluster point of the first user according to the positioning track data.
In a possible implementation manner, the positioning track data includes position information and time information of a plurality of positioning points; the determining the cluster residing point of the first user according to the positioning track data includes:
determining the speed information of the positioning points according to the position information and the time information of the positioning points;
determining a dwell point of the first user according to the speed information;
and clustering the resident points to obtain the resident cluster points of the first user.
In a possible implementation manner, the acquiring the network connection feature data corresponding to the residing cluster point includes:
acquiring network connection data of the first user at the resident cluster point;
extracting time distribution characteristic data of the network connection data;
and taking the time distribution characteristic data as the network connection characteristic data.
In one possible implementation, the creating process of the user accommodation prediction model includes:
acquiring positioning basic data of a plurality of users, and preprocessing the positioning basic data to obtain positioning track data of the users;
determining resident cluster points of the plurality of users according to the positioning track data;
acquiring network connection characteristic data corresponding to the resident cluster points of the plurality of users;
associating the place sample data with the network connection characteristic data of the users to obtain the place data of the users;
and training the position data of the users by adopting a preset model to obtain the user position prediction model.
In a possible implementation manner, the training the place and place data of the plurality of users by using a preset model to obtain the user place and place prediction model includes:
and training the place data of the users by adopting an Xgboost model to obtain a user place prediction model.
In one possible implementation, the dwell points include the following types: a fixed point, a slow moving point and a detour point.
A second aspect of the present invention provides a user occupation prediction apparatus, including:
the acquisition module is used for acquiring positioning basic data of a first user;
a determining module, configured to determine a cluster point where the first user resides according to the positioning basic data;
the acquisition module is further configured to acquire network connection characteristic data corresponding to the resident cluster point;
the prediction module is used for inputting the network connection characteristic data into a user place classification model to obtain a prediction result of the first user place.
A third aspect of the present invention provides a user occupation prediction apparatus comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement a user occupation prediction method according to any one of the first aspect of the invention.
A fourth aspect of the invention provides a computer readable storage medium having stored thereon a computer program for execution by a processor to implement a method of user job site prediction according to any one of the first aspects of the invention.
The embodiment of the invention provides a method, a device and a storage medium for predicting the position of a user. The prediction method provided by the embodiment determines the place of employment of the user based on the training model, and has high prediction accuracy.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic flowchart of a method for predicting a place of employment of a user according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a process of creating a user occupation prediction model according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a user occupation prediction apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a hardware structure of a user occupation prediction apparatus according to an embodiment of the present invention.
With the above figures, certain embodiments of the invention have been illustrated and described in more detail below. The drawings and the description are not intended to limit the scope of the inventive concept in any way, but rather to illustrate it by those skilled in the art with reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terms "comprising" and "having," and any variations thereof, in the description and claims of this invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference throughout this specification to "one embodiment" or "another embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in some embodiments" or "in the present embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The method for predicting the user place of employment provided by the embodiment is based on a pre-trained user place of employment prediction model, and network connection characteristic data corresponding to the resident cluster point determined according to the user positioning basic data is input into the user place of employment prediction model, so that a prediction result of the user place of employment is obtained. The user occupational region prediction model is obtained by training occupational region data of a plurality of users by adopting an Xgboost model, and has higher prediction accuracy compared with the current implementation scheme.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 1 is a flowchart illustrating a method for predicting a user's occupation area according to an embodiment of the present invention, where the method may be implemented by any device that performs the method, and the device may be implemented by software and/or hardware. As shown in fig. 1, the method for predicting the employment location of the user provided in this embodiment includes the following steps:
s101, acquiring positioning basic data of a first user;
in the present embodiment, the positioning basic data of the first user is derived from a positioning Software Development Kit (SDK). And aggregating the positioning basic data of different first users by taking the users as units so as to predict the occupational areas according to the aggregated positioning basic data of the different first users.
S102, determining a resident cluster point of a first user according to the positioning basic data;
specifically, the aggregated positioning basic data of the first user is preprocessed to obtain positioning track data of the first user. Wherein the data preprocessing of the positioning basis data comprises removing noisy data. And determining the resident cluster point of the first user according to the positioning track data of the first user.
In this embodiment, the positioning track data includes position information and time information of a plurality of positioning points of the first user, and the speed information of the plurality of positioning points is determined according to the position information and the time information of the plurality of positioning points of the first user; determining a resident point of a first user according to the speed information of a plurality of positioning points; and clustering the plurality of resident points to obtain the resident cluster point of the first user.
It should be noted that in this embodiment, the anchor point is first subjected to speed calculation, and the type of the anchor point is marked, where the type of the anchor point includes a stationary point, a slow moving point, a detour point, and a normal moving point. And secondly, determining a residence point according to the type of the positioning point, wherein the positioning points except the normal moving point are used as the residence point of the first user, and correspondingly, the type of the residence point comprises a fixed point, a slow moving point and a circuitous point. And finally, clustering the plurality of resident points to obtain the resident cluster point of the first user, specifically, clustering based on the time sequence relation of the plurality of resident points, determining a resident cluster point from the plurality of resident points in the preset range, and taking the central point of the plurality of resident points in the preset range as the resident cluster point.
Determining a resident cluster point of the first user through a preprocessing process of positioning basic data of the first user, wherein the resident cluster point is a resident point of a physical geographic position of the first user in a time dimension. After the resident cluster point is determined, the place of employment of the first user is further predicted according to the network connection characteristic data of the first user at the resident cluster point, see specifically S103 and S104.
S103, acquiring network connection characteristic data corresponding to the resident cluster point;
in this embodiment, after determining a cluster point where a first user resides, network connection data of the first user at the cluster point where the first user resides is obtained, where the network connection data includes at least one of wifi connection data and mobile network connection data.
Specifically, wifi connection data of the first user at the resident cluster point is obtained, wherein the wifi connection data comprises wifi access point data and wifi connection request data. The wifi access point data specifically comprises at least one of SSID, MAC address, geographic position, place name and access duration of wifi. The wifi connection request data specifically includes website information, access content and the like accessed by the first user.
Specifically, mobile network connection data of the first user at the resident cluster point is obtained, wherein the mobile network connection data includes mobile network access point data and mobile network connection request data. The mobile network access point data specifically includes at least one of access base station information and access duration. The mobile network connection request data specifically includes website information, access content, and the like accessed by the first user.
Extracting first time distribution characteristic data of wifi connection data, wherein the first time distribution characteristic data is statistical analysis data of wifi internet data of a first user in a time dimension, and the first time distribution characteristic data is used as network connection characteristic data.
And/or the presence of a gas in the gas,
and extracting second time distribution characteristic data of the mobile network data, wherein the second time distribution characteristic data is statistical analysis data of the mobile network surfing data of the first user in a time dimension, and the second time distribution characteristic data is used as network connection characteristic data.
And S104, inputting the network connection characteristic data into the user place prediction model to obtain a prediction result of the first user place.
In this embodiment, the user place and place prediction model is obtained by training place and place data of a large number of users, and the model adds network connection characteristic data of each user at different resident cluster points, so that the prediction accuracy is high.
And inputting the network connection characteristic data of the first user into a user place prediction model, and outputting a prediction result of a place corresponding to the first user by the model. Wherein the place of employment of the first user includes a place of employment and a place of residence of the first user.
Optionally, after determining the position of the first user, the user attributes (income level, work stability, purchasing power, etc.), hobbies and interests, etc. may be inferred according to big data analysis, and push information may be sent to the first user in a targeted manner.
According to the method for predicting the position of the user, provided by the embodiment of the invention, the positioning basic data of the first user are obtained, the resident cluster point of the first user is determined according to the positioning basic data, the network connection characteristic data corresponding to the resident cluster point is obtained, and the network connection characteristic data is input into a pre-trained user position prediction model to obtain the prediction result of the position of the first user. The prediction method provided by the embodiment determines the place of employment of the user based on the training model, and has high prediction accuracy.
On the basis of the above embodiment, the embodiment provides a method for establishing a user position and residence prediction model, where the prediction model is obtained by training position data of multiple users through an Xgboost model, and network connection characteristic data of each user at different resident cluster points is added to the model, so that the obtained user position and residence prediction model has a more accurate prediction effect.
The following describes in detail a process of creating the user accommodation prediction model according to this embodiment with reference to the drawings.
Fig. 2 is a schematic flow chart of a process of creating a user job place prediction model according to an embodiment of the present invention, and as shown in fig. 2, the method for establishing a user job place prediction model according to the embodiment specifically includes the following steps:
s201, acquiring positioning basic data of a plurality of users;
s202, preprocessing positioning basic data to obtain positioning track data of a plurality of users;
in this embodiment, the positioning basic data of a plurality of users are respectively obtained, the positioning basic data of different users are aggregated by taking the user as a unit, and the aggregated positioning basic data of the users are preprocessed to obtain the positioning track data of each user.
Wherein the data preprocessing of the positioning basis data comprises removing noisy data.
S203, determining resident cluster points of a plurality of users according to the positioning track data;
in this embodiment, the positioning track data includes position information and time information of a plurality of positioning points of the user, and the speed information of the plurality of positioning points is determined according to the position information and the time information of the plurality of positioning points of the user; determining a resident point of a user according to the speed information of a plurality of positioning points; and clustering the plurality of resident points to obtain the resident cluster points of the user.
In this embodiment, the type of the anchor point is marked by calculating the speed of the anchor point, and the type of the anchor point includes a stationary point, a slow moving point, a detour point, and a normal moving point. And secondly, determining a residence point according to the type of the positioning point, wherein the positioning points except the normal moving point are used as the residence point of the user, and correspondingly, the type of the residence point comprises a fixed point, a slow moving point and a circuitous point. And finally clustering the plurality of resident points to obtain the resident cluster points of the user, specifically, clustering based on the time sequence relation of the plurality of resident points, determining a resident cluster point from the plurality of resident points in the preset range, and taking the central point of the plurality of resident points in the preset range as the resident cluster point.
S204, acquiring network connection characteristic data corresponding to the resident cluster points of a plurality of users;
after the resident cluster point of each user is determined, network connection data of each user at the resident cluster point of each user are obtained, wherein the network connection data comprise at least one of wifi connection data and mobile network connection data.
Specifically, wifi connection data of a user at a resident cluster point is obtained, wherein the wifi connection data comprises wifi access point data and wifi connection request data. The wifi access point data specifically comprises at least one of SSID, MAC address, geographic position, place name and access duration of wifi. The wifi connection request data specifically includes website information and access content accessed by the user.
Specifically, mobile network connection data of a user at a resident cluster point is obtained, wherein the mobile network connection data includes mobile network access point data and mobile network connection request data. The mobile network access point data specifically includes at least one of access base station information and access duration. The mobile network connection request data specifically includes website information, access content, and the like accessed by the user.
Extracting first time distribution characteristic data of wifi connection data, wherein the first time distribution characteristic data is statistical analysis data of wifi internet data of a user in a time dimension, and the first time distribution characteristic data is used as network connection characteristic data.
And/or the presence of a gas in the gas,
and extracting second time distribution characteristic data of the mobile network data, wherein the second time distribution characteristic data is statistical analysis data of the user mobile network internet data in a time dimension, and the second time distribution characteristic data is used as network connection characteristic data.
S205, associating the occupational site sample data with the network connection characteristic data of the users to obtain occupational site data of the users;
the sample data of the place of employment of the embodiment includes the tag data of all places of residence and places of employment in the area where the user is located, the number of the sample data of the place of employment is associated with the network connection characteristic data of each user, and the place of employment data of each user is determined, that is, the place of residence data and the place of employment data of each user with the highest matching degree are determined in the sample data of the place of employment according to the network connection characteristic data of each user.
S206, training the place data of the users by adopting a preset model to obtain a user place prediction model.
Specifically, the Xgboost model is adopted to train the place data of each user determined in S205 to obtain a user place prediction model, and the prediction model is trained based on the place data of a large number of users, so that the prediction accuracy is high.
The user job site prediction model provided by the embodiment of the invention is created by acquiring the positioning track data of a plurality of users, determining the resident cluster points of the plurality of users according to the positioning track data, acquiring the network connection characteristic data corresponding to the resident cluster points of the plurality of users, associating the job site sample data with the network connection characteristic data of the plurality of users to obtain the job site data of the plurality of users, and training the job site data of the plurality of users by adopting a preset model to obtain the user job site prediction model. The user occupation prediction model obtained based on the establishing method is embedded with network connection characteristic data corresponding to the resident cluster points of different users and matching data of the occupation places of different users, and training data of the model is continuously updated through machine learning, so that the user occupation prediction model has a more accurate prediction effect.
Fig. 3 is a schematic structural diagram of a user occupation prediction apparatus according to an embodiment of the present invention, and as shown in fig. 3, a user occupation prediction apparatus 30 according to this embodiment includes:
an obtaining module 31, configured to obtain positioning basic data of a first user;
a determining module 32, configured to determine a cluster location of the first user according to the positioning basic data;
the obtaining module 31 is further configured to obtain network connection feature data corresponding to the resident cluster point;
and the prediction module 33 is configured to input the network connection feature data into a user place classification model to obtain a prediction result of the first user place.
The user occupation prediction device provided by the embodiment of the invention comprises an acquisition module, a determination module and a prediction module, wherein the acquisition module is used for acquiring positioning basic data of a first user, the determination module is used for determining a resident cluster point of the first user according to the positioning basic data, the acquisition module is also used for acquiring network connection characteristic data corresponding to the resident cluster point, and the prediction module is used for inputting the network connection characteristic data into a user occupation classification model to obtain a prediction result of the occupation of the first user. The user place prediction device determines the user place based on the built-in training model and has high prediction accuracy.
Optionally, the determining module 32 is specifically configured to:
carrying out data preprocessing on the positioning basic data to obtain positioning track data of the first user;
and determining the resident cluster point of the first user according to the positioning track data.
Optionally, the positioning track data includes position information and time information of a plurality of positioning points; the determining module 32 is specifically configured to:
determining the speed information of the positioning points according to the position information and the time information of the positioning points;
determining a dwell point of the first user according to the speed information;
and clustering the resident points to obtain the resident cluster points of the first user.
Optionally, the obtaining module 31 is specifically configured to:
acquiring wifi connection data of the first user at the resident cluster point;
extracting time distribution characteristic data of the wifi connection data;
and taking the time distribution characteristic data as the network connection characteristic data.
Optionally, the process of creating the user accommodation prediction model includes:
acquiring positioning track data of a plurality of users;
determining resident cluster points of the plurality of users according to the positioning track data;
acquiring network connection characteristic data corresponding to the resident cluster points of the plurality of users;
associating the place sample data with the network connection characteristic data of the users to obtain the place data of the users;
and training the position data of the users by adopting a preset model to obtain the user position prediction model.
Optionally, the training the place and place data of the multiple users by using a preset model to obtain the user place and place prediction model includes:
and training the place data of the users by adopting an Xgboost model to obtain a user place prediction model.
Optionally, the residence point includes the following types: a stationary point, a slow moving point and a detour point.
The device for predicting the position of the user may implement the technical solution of the method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 4 shows a user occupation prediction apparatus, which is provided in the embodiment of the present invention, and the embodiment of the present invention is only described with reference to fig. 4 as an example, which does not mean that the present invention is limited thereto.
Fig. 4 is a schematic diagram of a hardware structure of a user occupation prediction apparatus according to an embodiment of the present invention, and as shown in fig. 4, the user occupation prediction apparatus 40 according to the embodiment includes:
a memory 41;
a processor 42; and
a computer program;
wherein the computer program is stored in the memory 41 and configured to be executed by the processor 42 to implement the technical solution of any one of the foregoing method embodiments, and the implementation principle and technical effect are similar, which are not described herein again.
Alternatively, the memory 41 may be separate or integrated with the processor 42.
When the memory 41 is a device independent from the processor 42, the user position prediction apparatus 40 further includes:
a bus 43 for connecting the memory 41 and the processor 42.
Embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program for execution by the processor 42 to perform the steps performed by the user occupation prediction apparatus 40 in the above method embodiments.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the spirit of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for predicting a place of employment of a user, comprising:
acquiring positioning basic data of a first user;
determining a resident cluster point of the first user according to the positioning basic data;
acquiring network connection data of the first user at the resident cluster point;
extracting time distribution characteristic data of the network connection data;
taking the time distribution characteristic data as network connection characteristic data;
and inputting the network connection characteristic data into a user position prediction model to obtain a prediction result of the first user position.
2. The method of claim 1, wherein the determining the cluster point of residence for the first user according to the positioning base data comprises:
carrying out data preprocessing on the positioning basic data to obtain positioning track data of the first user;
and determining the resident cluster point of the first user according to the positioning track data.
3. The method of claim 2, wherein the positioning track data comprises position information of a plurality of positioning points and time information; the determining the cluster residing point of the first user according to the positioning track data includes:
determining the speed information of the positioning points according to the position information and the time information of the positioning points;
determining a dwell point of the first user according to the speed information;
and clustering the resident points to obtain the resident cluster points of the first user.
4. The method according to any one of claims 1 to 3, wherein the creation process of the user position prediction model comprises:
acquiring positioning basic data of a plurality of users, and preprocessing the positioning basic data to obtain positioning track data of the users;
determining resident cluster points of the plurality of users according to the positioning track data;
acquiring network connection characteristic data corresponding to the resident cluster points of the plurality of users;
associating the place sample data with the network connection characteristic data of the users to obtain the place data of the users;
and training the position data of the users by adopting a preset model to obtain the user position prediction model.
5. The method of claim 4, wherein training the position data of the plurality of users using a predetermined model to obtain the user position prediction model comprises:
and training the place data of the users by adopting an Xgboost model to obtain a user place prediction model.
6. The method of claim 3, wherein the residence points comprise the following types: a stationary point, a slow moving point and a detour point.
7. A user occupation prediction apparatus, comprising:
the acquisition module is used for acquiring positioning basic data of a first user;
a determining module, configured to determine a cluster point where the first user resides according to the positioning basic data;
the obtaining module is further configured to obtain network connection data of the first user at the residing cluster point;
extracting time distribution characteristic data of the network connection data;
taking the time distribution characteristic data as network connection characteristic data;
and the prediction module is used for inputting the network connection characteristic data into a user place classification model to obtain a prediction result of the first user place.
8. A user occupation prediction apparatus, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the user position prediction method as claimed in any one of claims 1 to 6.
9. A computer-readable storage medium, having stored thereon a computer program for execution by a processor to implement a method of user job site prediction according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811295960.XA CN111126653B (en) | 2018-11-01 | 2018-11-01 | User position prediction method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811295960.XA CN111126653B (en) | 2018-11-01 | 2018-11-01 | User position prediction method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111126653A CN111126653A (en) | 2020-05-08 |
| CN111126653B true CN111126653B (en) | 2022-06-17 |
Family
ID=70494126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811295960.XA Active CN111126653B (en) | 2018-11-01 | 2018-11-01 | User position prediction method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126653B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488384B (en) * | 2020-11-27 | 2021-08-31 | 香港理工大学深圳研究院 | Method, terminal and storage medium for predicting target area based on social media sign-in |
| CN112685659B (en) * | 2021-03-19 | 2021-06-18 | 上海钐昆网络科技有限公司 | Target location determination method and device, electronic equipment and computer storage medium |
| CN118590832A (en) * | 2023-03-02 | 2024-09-03 | 蔚来移动科技有限公司 | User job place identification method, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636354A (en) * | 2013-11-07 | 2015-05-20 | 华为技术有限公司 | Position point of interest clustering method and related device |
| CN104965876A (en) * | 2015-06-12 | 2015-10-07 | 微梦创科网络科技（中国）有限公司 | Method and apparatus for carrying out mining on work units of users on basis of position information |
| CN105978722A (en) * | 2016-05-11 | 2016-09-28 | 腾讯科技（深圳）有限公司 | User attribute mining method and device |
| CN106557942A (en) * | 2015-09-30 | 2017-04-05 | 百度在线网络技术（北京）有限公司 | A kind of recognition methodss of customer relationship and device |
| CN106792514A (en) * | 2016-11-30 | 2017-05-31 | 南京华苏科技有限公司 | User's duty residence analysis method based on signaling data |
| CN106790468A (en) * | 2016-12-10 | 2017-05-31 | 武汉白虹软件科技有限公司 | A kind of distributed implementation method for analyzing user's WiFi event trace rules |
| CN108650632A (en) * | 2018-04-28 | 2018-10-12 | 广州市交通规划研究院 | It is a kind of based on duty live correspondence and when space kernel clustering stationary point judgment method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9930494B2 (en) * | 2015-10-13 | 2018-03-27 | Cisco Technology, Inc. | Leveraging location data from mobile devices for user classification |
-
2018
- 2018-11-01 CN CN201811295960.XA patent/CN111126653B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636354A (en) * | 2013-11-07 | 2015-05-20 | 华为技术有限公司 | Position point of interest clustering method and related device |
| CN104965876A (en) * | 2015-06-12 | 2015-10-07 | 微梦创科网络科技（中国）有限公司 | Method and apparatus for carrying out mining on work units of users on basis of position information |
| CN106557942A (en) * | 2015-09-30 | 2017-04-05 | 百度在线网络技术（北京）有限公司 | A kind of recognition methodss of customer relationship and device |
| CN105978722A (en) * | 2016-05-11 | 2016-09-28 | 腾讯科技（深圳）有限公司 | User attribute mining method and device |
| CN106792514A (en) * | 2016-11-30 | 2017-05-31 | 南京华苏科技有限公司 | User's duty residence analysis method based on signaling data |
| CN106790468A (en) * | 2016-12-10 | 2017-05-31 | 武汉白虹软件科技有限公司 | A kind of distributed implementation method for analyzing user's WiFi event trace rules |
| CN108650632A (en) * | 2018-04-28 | 2018-10-12 | 广州市交通规划研究院 | It is a kind of based on duty live correspondence and when space kernel clustering stationary point judgment method |
Non-Patent Citations (1)
| Title |
|---|
| 基于手机信令数据的数据清洗挖掘与居民职住空间分析;苗壮;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20170715(第7期);第I138-557页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111126653A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102260554B1 (en) | Method for generating learning contents | |
| KR101999471B1 (en) | Information recommendation methods and devices | |
| CN110825957B (en) | Deep learning-based information recommendation method, device, equipment and storage medium | |
| CN107657048B (en) | User identification method and device | |
| CN110826006B (en) | Abnormal collection behavior identification method and device based on privacy data protection | |
| CN107330459B (en) | Data processing method and device and electronic equipment | |
| CN111126653B (en) | User position prediction method, device and storage medium | |
| CN109167816B (en) | Information pushing method, device, equipment and storage medium | |
| CN107798557A (en) | Electronic installation, the service location based on LBS data recommend method and storage medium | |
| CN109086377B (en) | Equipment portrait generation method and device and computing equipment | |
| CN108090211B (en) | Hot news pushing method and device | |
| CN110674208B (en) | Method and device for determining position information of user | |
| CN108563680A (en) | Resource recommendation method and device | |
| CN112184290A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111460327B (en) | Method and device for searching for interest, storage medium and computer equipment | |
| CN108921587B (en) | Data processing method and device and server | |
| CN108182253A (en) | For generating the method and apparatus of information | |
| CN106650433A (en) | Detecting method and system for abnormal behavior | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN116361552A (en) | Campus book retrieval method, device, equipment and readable storage medium | |
| CN105408894A (en) | Method and device for determining user identity category | |
| CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
| CN110717094A (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN108804917B (en) | File detection method and device, electronic equipment and storage medium | |
| CN110598090A (en) | Interest tag generation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |