CN114139050A - Parking position recommendation method and device, storage medium and electronic device - Google Patents

Parking position recommendation method and device, storage medium and electronic device Download PDF

Info

Publication number
CN114139050A
CN114139050A CN202111381658.8A CN202111381658A CN114139050A CN 114139050 A CN114139050 A CN 114139050A CN 202111381658 A CN202111381658 A CN 202111381658A CN 114139050 A CN114139050 A CN 114139050A
Authority
CN
China
Prior art keywords
parking
data
parking position
user
recommendation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111381658.8A
Other languages
Chinese (zh)
Inventor
苗顺平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Ileja Tech Co ltd
Original Assignee
Beijing Ileja Tech Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Ileja Tech Co ltd filed Critical Beijing Ileja Tech Co ltd
Priority to CN202111381658.8A priority Critical patent/CN114139050A/en
Publication of CN114139050A publication Critical patent/CN114139050A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Remote Sensing (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application discloses a parking position recommendation method and device, a storage medium and an electronic device. The method comprises the steps of receiving a service data request, wherein the service data carries first position information of a user; acquiring map data provided by one or more map service providers and parking data of a user according to the first position information, wherein the map data and the parking data have an association relation; and obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model. The application solves the technical problem that the recommendation effect of the parking position is not good. The real-time performance and accuracy of the parking lot data are improved through the method and the device. In addition, the method and the device are also used for recommending the parking position such as the online appointment vehicle getting-on and getting-off position.

Description

Parking position recommendation method and device, storage medium and electronic device
Technical Field
The present application relates to the field, and in particular, to a parking position recommendation method and apparatus, a storage medium, and an electronic apparatus.
Background
The parking position mainly comprises the position of the parking lot where the current positioning position is located and the position of getting on or off the vehicle.
In the related technology, the data of the parking lot is not updated timely by mainly depending on the parking lot information in the map data; in addition, the generated parking data of a large number of users are not verified with the parking lot data on the map data.
Aiming at the problem of poor effect of recommending parking positions in the related art, no effective solution is provided at present.
Disclosure of Invention
The present disclosure is directed to a method and an apparatus for recommending a parking position, a storage medium, and an electronic apparatus, so as to solve the problem of poor effect of recommending a parking position.
In order to achieve the above object, according to one aspect of the present application, there is provided a parking position recommendation method.
The parking position recommendation method comprises the following steps: receiving a service data request, wherein the service data carries first position information of a user; acquiring map data provided by one or more map service providers and parking data of a user according to the first position information, wherein the map data and the parking data have an association relation; obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained through machine learning training by using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users comprises: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service; and determining the current parking position according to the recommendation result. It can be appreciated that data provided by multiple map service providers needs to be fused when the data is present.
Further, the pre-trained parking position recommendation model further includes: and obtaining a recommendation result of the parking position based on the navigation destination of the user, the time of the user estimated reaching the destination and the driving vehicle type of the user in the service data, wherein the parking data adopted by the user in the recommendation result is collected and used as the parking data of the user and used for training the pre-trained parking position recommendation model.
Further, the parking position includes at least one of: the destination of this navigation, the geographic location of the parking lot where the current parking location is located.
Further, the recommendation result of the parking position is obtained through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained through machine learning training by using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users includes: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service, comprising: and obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model and based on the navigation destination of the user, the time of the user to reach the destination and the driving vehicle type of the user in the service data.
Further, the obtaining, according to the first location information, map data provided by a plurality of map service providers and parking data of a user, where the map data and the parking data have an association relationship, includes: according to the first position information, if the distance between the navigation destination position in the map data and the parking position in the parking data is smaller than a preset range threshold, determining that the position near the navigation destination position is a valid parking position; according to the second position information of the user, matching the parking position data in the map data and marking the second position information as a new parking position; and if the distance between the second position information of the user and the effective parking position is smaller than a preset range threshold, determining the second position information as the parking position to be recommended.
Further, the obtaining of the recommendation result of the parking position through the pre-trained parking position recommendation model further includes: after a preset time period, acquiring violation information of the vehicle through a violation platform; if the violation information does not have the violation record of the current parking position within the preset time period, obtaining a recommendation result of the parking position; and confirming whether the current parking position in the recommended result of the parking position can provide parking service for the outside.
Further, the parking position recommendation model further includes: a parking position recommendation model established based on the user parking data; and the parking position recommendation model establishes a regression analysis model by taking the parking position of successful parking as a dependent variable according to the map data and the user parking data as independent variables.
In order to achieve the above object, according to another aspect of the present application, there is provided a parking position recommending apparatus.
The parking position recommendation device according to the application comprises: the receiving module is used for receiving a service data request, wherein the service data carries first position information of a user; the acquisition module is used for acquiring map data provided by a plurality of map service providers and parking data of a user according to the first position information, wherein the map data and the parking data have an incidence relation; the recommendation module is used for obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained through machine learning training by using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users comprises: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service; and the determining module is used for determining the current parking position according to the recommendation result.
In order to achieve the above object, according to another aspect of the present application, there is also provided a storage medium having a computer program stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.
In order to achieve the above object, according to yet another aspect of the present application, there is also provided an electronic device comprising a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
In the embodiment of the application, the parking position recommendation method and device, the storage medium and the electronic device adopt a mode of receiving a service data request, and the aims of obtaining the recommendation result of the parking position and determining the current parking position according to the recommendation result through a pre-trained parking position recommendation model by obtaining map data provided by a plurality of map service providers and parking data of a user according to the first position information are achieved, so that the technical effect of real-time and accurate parking position recommendation is achieved, and the technical problem of poor parking position recommendation effect is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
fig. 1 is a hardware configuration diagram of a parking position recommendation method according to an embodiment of the present application;
FIG. 2 is a flow chart of a parking position recommendation method according to an embodiment of the application;
FIG. 3 is a schematic structural diagram of a parking position recommendation device according to an embodiment of the application;
fig. 4 is a flowchart illustrating a parking position recommendation method according to an embodiment of the application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, a schematic hardware structure diagram of a parking position recommendation method in an embodiment of the present application includes: vehicle 100, backend server 200, map data server 300. The vehicle 100 is a vehicle that needs to be recommended to park and driven by a driver. The background server 200 is configured to receive the network request data of the driver and return a recommendation result. The map data server 300 mainly refers to a server maintained by a map service provider, and it can be understood that the map data server 300 includes map data provided by a plurality of map service providers.
As shown in fig. 2, the method includes steps S201 to S204 as follows:
step S201, receiving a service data request, wherein the service data carries first position information of a user;
step S202, according to the first position information, obtaining map data provided by a plurality of map service providers and parking data of a user, wherein the map data and the parking data have an incidence relation;
step S203, obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained through machine learning training by using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users comprises: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service;
and step S204, determining the current parking position according to the recommendation result.
From the above description, it can be seen that the following technical effects are achieved by the present application:
by adopting a mode of receiving a service data request and acquiring map data provided by one or more map service providers and parking data of a user according to the first position information, the aims of obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model and determining the current parking position according to the recommendation result are fulfilled, so that the technical effect of recommending the parking position accurately in real time is realized, and the technical problem of poor parking position recommendation effect is solved.
In step S201, the background server receives a service data request, where the service data request carries location information and user information for initiating a request.
As a preferred embodiment, the service data carries first location information of a user. The first position information may be the current position information of the vehicle.
As an alternative embodiment, the user information is decrypted data.
In the above step S202, the background server obtains map data provided by one or more map service providers and parking data of the user according to the first location information.
As an alternative embodiment, the map data and the parking data have a correlation with respect to a position.
As an alternative embodiment, the map data and the parking data have a cross-correlation relationship.
In step S203, the background server obtains a recommendation result of the parking position through a parking position recommendation model trained in advance.
Preferably, based on Deep Learning (Deep Learning), basic data (map data) and user parking data are used as input layers, parking lot data are converted into a continuous vector or One-Hot data through an Embedding neural network to be used as an output layer, and a neural network Learning model is established.
As an alternative, the background server may obtain a plurality of recommendation results through a pre-trained parking position recommendation model.
As an alternative embodiment, the pre-trained parking position recommendation model is obtained by machine learning training by using multiple groups of parking data of users and map data
As an optional implementation, each of the plurality of sets of user parking data includes: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service. That is, each set of data in the plurality of sets of map data is map data provided by one or more map service providers. Each set of data in the plurality of sets of user parking data includes: navigation destination and parking position information of the user. It is understood that the navigation destination of the user is related to the current position of the vehicle, and the parking position information refers to final parking position information determined based on the navigation destination of the user.
In the step S204, the background server finally determines the current parking position according to the recommendation result.
As an alternative embodiment, the determining of the current parking position includes, but is not limited to, information of a parking lot position where the parking position is located.
As an alternative embodiment, the determining of the current parking position includes, but is not limited to, information of the getting on/off position where the parking position is located.
As a preferable feature in this embodiment, the pre-trained parking position recommendation model further includes: and obtaining a recommendation result of the parking position based on the navigation destination of the user, the time of the user estimated reaching the destination and the driving vehicle type of the user in the service data, wherein the parking data adopted by the user in the recommendation result is collected and used as the parking data of the user and used for training the pre-trained parking position recommendation model.
In specific implementation, the pre-trained parking position recommendation model of the background server obtains the recommendation result of the parking position based on the navigation destination of the user, the time of the user to reach the destination, and the driving vehicle type of the user in the service data.
As an alternative embodiment, the parking data adopted by the user in the recommendation result is collected as the parking data of the user and used for training the pre-trained parking position recommendation model.
Preferably, in this embodiment, the parking position includes at least one of: the destination position of the navigation, and the geographic position of the parking lot where the current parking position is located.
In specific implementation, the destination position of the navigation can be determined through a parking position recommendation model in the background server.
The geographic position of the parking lot where the current parking position is located may also be determined by the parking position recommendation model in the backend server.
As a preferable example in this embodiment, the parking position recommendation result is obtained by a parking position recommendation model trained in advance, where the parking position recommendation model is obtained by machine learning training using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users includes: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service, comprising: and obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model and based on the navigation destination of the user, the time of the user to reach the destination and the driving vehicle type of the user in the service data.
In specific implementation, the background server obtains the recommendation result of the parking position through a pre-trained parking position recommendation model and based on the navigation destination of the user, the time for the user to expect to reach the destination and the driving vehicle type of the user in the service data.
It is noted that the navigation destination of the user, the time the user is expected to reach the destination, and the driving vehicle type of the user are based on the traffic data. And performing model prediction by using the pre-trained parking position recommendation model and using the destination, arrival time and vehicle type information of the user navigation as input conditions, wherein the parking lot recommended to the user is the parking lot position in the map data corresponding to the vehicle position information in the prediction result.
The driving vehicle type of the user includes but is not limited to distinguishing a special vehicle, such as an ultra-wide vehicle and the like.
As a preferable example in this embodiment, the obtaining, according to the first location information, map data provided by one or more map service providers and parking data of a user, where the map data and the parking data have an association relationship, includes: according to the first position information, if the distance between the navigation destination position in the map data and the parking position in the parking data is smaller than a preset range threshold, determining that the position near the navigation destination position is a valid parking position; according to the second position information of the user, matching the parking position data in the map data and marking the second position information as a new parking position; and if the distance between the second position information of the user and the effective parking position is smaller than a preset range threshold, determining the second position information as the parking position to be recommended.
In specific implementation, the background server determines that the vicinity of the navigation destination position is an effective parking position according to the first position information if the distance between the navigation destination position in the map data and the parking position in the parking data is smaller than a preset range threshold.
Further, the background server matches the parking position data in the map data according to second position information of the user and marks the second position information as a new parking position.
Further, the background server judges that the parking position to be recommended is determined if the distance between the second position information of the user and the effective parking position is smaller than a preset range threshold.
The background server collects navigation destination and parking position information of the user. If the distance between the navigation destination and the parking position is less than a certain range, for example, 1km, the parking position is considered to be an effective parking lot near the navigation destination, otherwise, the parking position is considered to be an ineffective parking position.
And the background server retrieves the existing parking lot data according to the final parking position, for example, the existing parking lot data can be obtained by a distance smaller than a threshold of 200m, and if the existing parking lot data cannot be retrieved, the parking place is marked as a new parking place.
As a preferable example in this embodiment, the obtaining of the recommendation result of the parking position through the pre-trained parking position recommendation model further includes: after a preset time period, acquiring violation information of the vehicle through a violation platform; if the violation information does not have the violation record of the current parking position within the preset time period, obtaining a recommendation result of the parking position; and confirming whether the current parking position in the recommended result of the parking position can provide parking service for the outside.
In specific implementation, vehicle information can be obtained through the violation platform after a preset time period, and if the violation record of the time period and the place does not exist, the parking lot is considered to be a recommended parking lot.
In addition, aiming at the newly added parking lot data, other confirmation methods can be matched to confirm whether the parking lot can provide parking service for the outside, such as eliminating the problems of some unit internal parking lots and the like.
As a preferable aspect of the present embodiment, the parking position recommendation model further includes: a parking position recommendation model established based on the user parking data; and the parking position recommendation model establishes a regression analysis model by taking the parking position of successful parking as a dependent variable according to the map data and the user parking data as independent variables.
In specific implementation, a parking lot recommendation model is established through the parking data of the user. And establishing a regression analysis model by taking basic data and user parking data, namely, position, time, vehicle type and the like as independent variables and taking a parking spot for successful parking as a dependent variable.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present application, there is also provided a parking position recommendation device for implementing the above method, as shown in fig. 3, the device including:
a receiving module 301, configured to receive a service data request, where the service data carries first location information of a user;
an obtaining module 302, configured to obtain map data provided by one or more map service providers and parking data of a user according to the first location information, where the map data and the parking data have an association relationship;
the recommending module 303 is configured to obtain a recommending result of the parking position through a parking position recommending model trained in advance, where the parking position recommending model is obtained through machine learning training by using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users includes: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service;
and the determining module 304 is configured to determine the current parking position according to the recommendation result.
The background server in the receiving module 301 receives a service data request, where the service data request carries location information and user information for initiating a request.
As a preferred embodiment, the service data carries first location information of a user. The first position information may be the current position information of the vehicle.
As an alternative embodiment, the user information is decrypted data.
In the aforementioned obtaining module 302, the background server obtains map data provided by one or more map service providers and parking data of the user according to the first location information.
As an alternative embodiment, the map data and the parking data have a correlation with respect to a position.
As an alternative embodiment, the map data and the parking data have a cross-correlation relationship.
The background server in the recommendation module 303 obtains the recommendation result of the parking position through a parking position recommendation model trained in advance.
Preferably, based on Deep Learning (Deep Learning), basic data (map data) and user parking data are used as input layers, parking lot data are converted into a continuous vector or One-Hot data through an Embedding neural network to be used as an output layer, and a neural network Learning model is established.
As an alternative, the background server may obtain a plurality of recommendation results through a pre-trained parking position recommendation model.
As an alternative embodiment, the pre-trained parking position recommendation model is derived by machine learning training using multiple sets of parking data of users and map data.
As an optional implementation, each of the plurality of sets of user parking data includes: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service. That is, each set of data in the plurality of sets of map data is map data provided by one or more map service providers. Each set of data in the plurality of sets of user parking data includes: navigation destination and parking position information of the user. It is understood that the navigation destination of the user is related to the current position of the vehicle, and the parking position information refers to final parking position information determined based on the navigation destination of the user.
The background server in the determination module 304 finally determines the current parking position according to the recommendation result.
As an alternative embodiment, the determining of the current parking position includes, but is not limited to, information of a parking lot position where the parking position is located.
As an alternative embodiment, the determining of the current parking position includes, but is not limited to, information of the getting on/off position where the parking position is located.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
In order to better understand the above method flow, the following explains the above technical solutions with reference to the preferred embodiments, but the technical solutions of the embodiments of the present invention are not limited.
The parking position recommending method in the embodiment of the application recommends the parking lot for the user on the basis of parking on the map, and acquires the final parking place data of the user. Meanwhile, after a certain amount of parking data exist, more accurate parking lot data can be provided for the user based on the collected parking data, and real-time performance and accuracy of the parking lot data are greatly improved.
As shown in fig. 4, the flowchart of the parking position recommendation method in the embodiment of the present application is schematic, and specifically includes the following steps:
step S401, receiving a service data request.
Step S402, obtaining map data provided by one or more map service providers and parking data of the user according to the first position information.
Basic parking lot data. And acquiring map data provided by one or more map service providers and parking data of a user according to the first position information, wherein the map data is mainly parking lot data in POI (Point of Interest) data fused with one or more map service providers. It is understood to include without limitation locations such as latitude and longitude or floors, capacity, hours of operation, service areas, supporting facilities and elevators, car wash services, height limits, width limits.
The basic data can be understood to be fused with a plurality of map service providers, so that the comprehensiveness of the data is ensured; meanwhile, the basic data is subjected to duplicate removal and comparison, and the latest data is reserved. In addition, the basic data is updated regularly or in other activation modes, and the real-time performance and the integrity of the basic data are ensured.
The parking data of the user refers to user data, and mainly comprises data such as license plate number, vehicle type, vehicle height, width and vehicle type, navigation destination and user parking behavior data, wherein the license plate number is mainly used for confirming whether to limit the vehicle, and the vehicle height, width and vehicle type are acquired through the vehicle type, and the parking behavior data comprises but is not limited to position information, time, duration and the like of a parking place.
And step S403, obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model.
The parking lot recommendation model comprises two parts, wherein one part is used for carrying out model training through the basic parking lot data and the user data; another part is to provide a recommended parking lot through data of a destination, a predicted arrival time, a vehicle type, etc. navigated by the user.
Further, after the recommendation model is recommended to the user, the last parking data of the user is collected into the user data for training the parking lot recommendation model.
And step S404, obtaining a recommendation result of the parking position based on the navigation destination of the user, the time of the user to reach the destination and the driving vehicle type of the user in the service data.
And step S405, establishing a parking position recommendation model based on the user parking data.
Step S406, the parking position recommendation model establishes a regression analysis model by taking the parking position of successful parking as a dependent variable according to the map data and the user parking data as independent variables.
Navigation destination and parking position information of the user is collected. If the distance between the navigation destination and the parking position is smaller than a certain range, the parking lot is considered to be an effective parking lot near the navigation destination, otherwise, the parking lot is considered to be an ineffective parking lot; retrieving the existing parking lot data according to the final parking position, and marking the parking position as a new parking lot or parking spot if the existing parking lot data cannot be retrieved;
further, after a period of time, for example, 1 month, vehicle information can be acquired through a violation platform, and if no violation record of the time period and the place exists, the parking lot is considered as a recommended parking lot; furthermore, aiming at the newly added parking lot data, other confirmation methods can be matched to confirm whether the parking lot can provide parking service for the outside.
If the distance between the parking position information of the user and the recommended parking lot is smaller than a certain threshold value, such as 200m, the recommended parking lot is considered to be correct; otherwise, marking the recommended record as failure;
and establishing a parking lot recommendation model through the parking data of the user. The regression analysis model is established by taking basic data and user parking data which can include but are not limited to positions, time, vehicle types and the like as independent variables and taking parking points for successful parking as dependent variables.
Optionally, based on Deep Learning (Deep Learning), the basic data and the user parking data are used as input layers, and the parking lot data is converted into a continuous vector or One-Hot data through an Embedding neural network to be used as an output layer, so as to establish a neural network model.
And performing model prediction by using the destination, arrival time and vehicle type information of the user navigation as input conditions through the parking lot recommendation model. The parking lot recommended to the user is the parking lot in the prediction result.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (10)

1. A parking position recommendation method, comprising:
receiving a service data request, wherein the service data carries first position information of a user;
acquiring map data provided by one or more map service providers and parking data of a user according to the first position information, wherein the map data and the parking data have an association relation;
obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained through machine learning training by using parking data and map data of multiple groups of users, and each group of data in the parking data of the multiple groups of users comprises: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service;
and determining the current parking position according to the recommendation result.
2. The method of claim 1, wherein the pre-trained parking location recommendation model further comprises:
and obtaining a recommendation result of the parking position based on the navigation destination of the user, the time of the user estimated reaching the destination and the driving vehicle type of the user in the service data, wherein the parking data adopted by the user in the recommendation result is collected and used as the parking data of the user and used for training the pre-trained parking position recommendation model.
3. The method of claim 2, wherein the parking location comprises at least one of: the destination of this navigation, the geographic location of the parking lot where the current parking location is located.
4. The method of claim 2, wherein the recommendation result of the parking position is obtained through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained through machine learning training by using parking data of a plurality of groups of users and map data, and each group of the parking data of the plurality of groups of users comprises: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service, comprising:
and obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model and based on the navigation destination of the user, the time of the user to reach the destination and the driving vehicle type of the user in the service data.
5. The method of claim 1, wherein obtaining map data provided by one or more map service providers and parking data of a user according to the first position information, wherein the map data and the parking data have an association relationship comprises:
according to the first position information, if the distance between the navigation destination position in the map data and the parking position in the parking data is smaller than a preset range threshold, determining that the position near the navigation destination position is a valid parking position;
according to the second position information of the user, matching the parking position data in the map data and marking the second position information as a new parking position;
and if the distance between the second position information of the user and the effective parking position is smaller than a preset range threshold, determining the second position information as the parking position to be recommended.
6. The method of claim 1, wherein obtaining the recommendation of the parking location through a pre-trained parking location recommendation model further comprises:
after a preset time period, acquiring violation information of the vehicle through a violation platform;
if the violation information does not have the violation record of the current parking position within the preset time period, obtaining a recommendation result of the parking position;
and confirming whether the current parking position in the recommended result of the parking position can provide parking service for the outside.
7. The method of claim 1, wherein the parking location recommendation model further comprises:
a parking position recommendation model established based on the user parking data;
and the parking position recommendation model establishes a regression analysis model by taking the parking position of successful parking as a dependent variable according to the map data and the user parking data as independent variables.
8. A parking position recommending device is characterized in that,
the receiving module is used for receiving a service data request, wherein the service data carries first position information of a user;
the acquisition module is used for acquiring map data provided by one or more map service providers and parking data of a user according to the first position information, wherein the map data and the parking data have an incidence relation;
the recommendation module is used for obtaining a recommendation result of the parking position through a pre-trained parking position recommendation model, wherein the parking position recommendation model is obtained by training parking data and map data of multiple groups of users through a machine learning or other regression analysis model, and each group of data in the parking data of the multiple groups of users comprises: the navigation destination and the parking position information of the user, and each group of data in the multiple groups of map data comprises: map data provided by at least one map service;
and the determining module is used for determining the current parking position according to the recommendation result.
9. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
CN202111381658.8A 2021-11-17 2021-11-17 Parking position recommendation method and device, storage medium and electronic device Pending CN114139050A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111381658.8A CN114139050A (en) 2021-11-17 2021-11-17 Parking position recommendation method and device, storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111381658.8A CN114139050A (en) 2021-11-17 2021-11-17 Parking position recommendation method and device, storage medium and electronic device

Publications (1)

Publication Number Publication Date
CN114139050A true CN114139050A (en) 2022-03-04

Family

ID=80390427

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111381658.8A Pending CN114139050A (en) 2021-11-17 2021-11-17 Parking position recommendation method and device, storage medium and electronic device

Country Status (1)

Country Link
CN (1) CN114139050A (en)

Similar Documents

Publication Publication Date Title
CN102027324B (en) Apparatus and method for determining parking information
CN106092113B (en) Pre- travel Prediction System, method, navigation client and server
CN109410623A (en) Parking navigation method and device
CN108230725A (en) Method and apparatus are recommended in parking
CN110118567B (en) Travel mode recommendation method and device
CN105931494A (en) System and method for accurately acquiring parking spaces
CN108960590A (en) Vehicle leasing method, apparatus, computer equipment and storage medium
US20070083326A1 (en) Optimal route calculation based upon cohort analysis
CN108120999B (en) Vehicle-mounted navigation equipment and parking lot guiding method
CN105046965A (en) Unauthorized vehicle detection
CN1530890A (en) Traffic information displaying device, applying method for running managing center
CN111105053B (en) Route recommendation method and get-on point recommendation method for passenger vehicle
WO2014117016A1 (en) Computer system and method for search of a parking spot
CN109389416A (en) Number mark control device, number mark control method and recording medium
CN116362370A (en) Smart city parking lot parking space state prediction method, internet of things system and device
CN109741621B (en) Parking space information processing method and system based on crowd sensing and computer device
CN108230720A (en) Parking management method and device
CN103593977B (en) Private car illegal operation detection method
CN112562388B (en) Vehicle connection management method and device and storage medium
CN204731993U (en) A kind of parking position reservation system
JP2016200984A (en) Shared vehicle management apparatus
Tsiaras et al. parkitsmart: Minimization of cruising for parking
JP5886671B2 (en) Parking lot fullness judging device, judging method and program therefor
JP7082555B2 (en) Vehicle use support system
JPWO2018179956A1 (en) Parking lot information management system, parking lot guidance system, parking lot information management program, and parking lot guidance program

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