CN117786239A

CN117786239A - Position name generation method and device, electronic equipment and storage medium

Info

Publication number: CN117786239A
Application number: CN202311866471.6A
Authority: CN
Inventors: 李欣雨
Original assignee: Nanjing Leading Technology Co Ltd
Current assignee: Nanjing Leading Technology Co Ltd
Priority date: 2023-12-29
Filing date: 2023-12-29
Publication date: 2024-03-29

Abstract

The application relates to the technical field of network taxi taking, in particular to a method, a device, electronic equipment and a storage medium for generating a position name, which are used for solving the problem of poor travel efficiency and user experience, and the method comprises the following steps: acquiring travel demands including the current position and travel time of a user, screening out each reference POI in a preset range from historical behavior data of the user based on recommended boarding points, wherein any reference POI is a POI which is searched by the user in a historical mode or used by a historical order; generating names of boarding points according to travel demands, user behavior characteristics corresponding to each reference POI and POI heat characteristics; any user behavior feature characterizes the preference degree of the user on the reference POI corresponding to the user behavior feature; the POI heat characteristic is obtained by extracting heat characteristics of each POI in historical data based on the historical data of each user in a preset time period; so as to improve travel efficiency and user experience.

Description

Position name generation method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the technical field of network about vehicles, and in particular, to a method and an apparatus for generating a location name, an electronic device, and a storage medium.

Background

With the development of internet technology, more and more application programs realize the recommendation of the position coordinates to users by displaying specific position coordinates, for example, in a network taxi-taking scene, when users open clients of travel application programs, the travel application programs often show recommended taxi-taking points around the current positioning points, and the users can utilize the recommended taxi-taking points to perform network taxi-taking order placing operation; for another example, when the user waits for receiving the order, the user can display all the recommended boarding points around the user along with the real-time position of the user, and the user can select any recommended boarding point as the receiving driving position of the current travel requirement.

At present, names of conventional points of departure are generally generated by a single rule, such as static generation of names of points of departure (Point of Interest, POI) data or road network data, such as "east side of XX building", "south door of YY mall", etc., according to points of interest (Point of Interest, POI) data or road network data, which are near the current location of the user. Because the single rule adopted by the traditional method has fewer factors, the problems of wrong and inconspicuous names of boarding points, even naming by using indoor POIs and the like often occur, so that a user cannot find the boarding point selected by the user, and the travel efficiency and the user experience are reduced.

Disclosure of Invention

The embodiment of the application provides a method, a device, electronic equipment and a storage medium for generating a position name, which are used for dynamically generating the name of a get-on point for a user according to historical behavior data and real-time positions of the user, so that the name can meet different habits of different users, the time for the user to find the get-on point is reduced, and the travel efficiency and the user satisfaction are improved.

The specific technical scheme provided by the embodiment of the application is as follows:

in a first aspect, an embodiment of the present application provides a method for generating a location name, including:

acquiring a travel demand of a user, wherein the travel demand comprises the current position and travel time of the user;

screening out POIs (point of interest) within a preset range from historical behavior data of the user based on the get-on points of travel demand, wherein the get-on points are recommended to the user through a preset get-on point recommendation rule based on the current position, and any one of the POIs is a POI which is searched for by the user in a historical mode or used by a historical order;

generating the name of the boarding point according to the travel demand, the user behavior characteristics corresponding to each reference POI and the POI heat characteristics;

Wherein, any user behavior feature characterizes the preference degree of the user to the reference POI corresponding to the any user behavior feature; the POI heat characteristics are obtained by extracting heat characteristics of each POI in the historical data based on the historical data of each user in a preset time period, and the historical data comprise search log data and historical order data.

By adopting the method for generating the position name, the name of the boarding point can be dynamically generated for the user according to the user behavior characteristics corresponding to each reference POI in the user's historical behavior data, the current position and the travel time of the user included in the travel demand, and the POI heat characteristics obtained by extracting the heat characteristics of each POI in the historical data based on the historical data of each user in a preset time period, wherein any one of the reference POIs is the POI used by the historical search or the historical order of the user; therefore, the get-on roll call considers the behavior characteristics of the user and the POI heat characteristics corresponding to each candidate POI in the historical data, so that the generated get-on roll call can meet different habits of different users, the time for the users to find the get-on roll call is reduced, and the travel efficiency and the user satisfaction are improved.

In a possible implementation manner, the generating the name of the boarding point according to the travel requirement, the user behavior feature corresponding to each reference POI, and the POI heat feature includes:

inputting the travel demand, the user behavior characteristics corresponding to each reference POI, the get-on point, the distance and the relative position relation between the get-on point and the user, and the POI heat characteristic into a preset get-on roll name generation model;

screening target POIs from each reference POI and each POI in the historical data based on the travel requirement, the user behavior characteristics corresponding to each reference POI, the boarding points, the distance and relative position relation and the POI heat characteristics through the boarding roll name generation model;

and generating the name of the get-on point based on the name of the target POI and the position relation between the target POI and the current position.

According to the method, the on-coming roll call generation model is trained in advance, so that the model has personalized behavior characteristics of different users and global POI heat characteristics, and the on-coming roll call name generated based on the on-coming roll call generation model can be dynamically changed according to the user characteristics, so that thousands of people and thousands of faces are achieved.

In a possible implementation manner, before the generating the name of the boarding point according to the travel requirement, the user behavior feature corresponding to each reference POI, and the POI heat feature, the method further includes:

determining the distance between the user and the get-on point based on the get-on point and the current position;

and judging whether a road exists between the user and the get-on point or not by utilizing road network data based on the get-on point and the current position, and obtaining the relative position relationship between the user and the get-on point based on a judging result.

In one possible implementation manner, the user behavior feature corresponding to any one of the reference POIs is obtained by the following manner:

based on the historical behavior data, counting the searching accumulated times of any reference POI in the historical behavior data, and counting the starting point accumulated times of any reference POI serving as a starting point;

and taking the accumulated searching times of any reference POI and the accumulated starting point times as user behavior characteristics corresponding to any reference POI.

According to the method, the user behavior characteristics corresponding to each reference POI are obtained based on the historical behavior data of the user, so that the behavior characteristics of the user are considered when the names of the boarding points are generated, the thousands of people and thousands of faces of the names of the boarding points are generated, the habit of the user can be met, the time for finding the boarding points is shortened, and the travel efficiency and the user satisfaction are improved.

In one possible implementation, the POI heat feature is obtained by:

based on the historical data of each user, counting to obtain first heat characteristics corresponding to each starting point POI and second heat characteristics corresponding to each terminal point POI in the historical data;

screening out cross-city order data from the historical order data, counting and obtaining the accumulated use times of all terminal POIs in the cross-city order data based on the cross-city order data, and respectively determining the ratio of the accumulated use times of all terminal POIs to the total number of orders of the cross-city order data;

and determining each first heat characteristic, each second heat characteristic, each accumulated use time and each cross-city POI ratio as the POI heat characteristic.

According to the method, the global POI specificity characteristics are obtained based on the historical data of each user, so that the global POI heat characteristics are considered when the names of the getting-on points are generated, the generated getting-on point names have wider cognition and significance, the time for finding the getting-on points is reduced, and the trip efficiency and the user satisfaction are improved.

In one possible implementation manner, based on the historical data of each user, a first heat feature corresponding to each start point POI and a second heat feature corresponding to each end point POI in the historical data are obtained through statistics, including:

Based on the historical data, adopting a first time period, a second time period and a third time period in a preset POI heat characteristic extraction rule to respectively count the accumulated times corresponding to each starting point POI and the accumulated times corresponding to each terminal point POI in the historical data;

the following operations are executed for each starting point POI in the starting point POIs: based on any accumulated times of any starting point POI in the starting point POIs, adopting a feature extraction rule in the POI heat feature extraction rule to obtain first sub heat features of a time period corresponding to any accumulated times of any starting point POI, and taking each first sub heat feature as a first heat feature corresponding to any starting point POI;

the following operations are performed for each of the end point POIs: and based on any accumulated times of any one of the terminal POIs, obtaining second sub-heat characteristics of a time period corresponding to any accumulated times of any one terminal POI by adopting a characteristic extraction rule in the POI heat characteristic extraction rule, and taking each second sub-heat characteristic as a second heat characteristic corresponding to any one terminal POI.

In a possible implementation manner, after the current position of the user and the travel requirement are obtained, before the getting-on point based on the travel requirement filters out each reference point of interest POI in a preset range from the historical behavior data of the user, the method further includes:

And recommending the get-on point aiming at the travel requirement for the user based on the current position and the get-on point recommendation rule.

In a second aspect, an embodiment of the present application provides a location name generating device, including:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring the travel demand of a user, and the travel demand comprises the current position and travel time of the user;

the screening module is used for screening out POIs (point of interest) in a preset range from historical behavior data of the user based on the boarding points of the travel demands, wherein the boarding points are recommended to the user through preset boarding point recommendation rules based on the current position, and any one of the POIs is a POI which is searched for by the user in a historical mode or used by a historical order;

the position name generation module is used for generating the name of the boarding point according to the travel requirement, the user behavior characteristics corresponding to each reference POI and the POI heat characteristics;

In one possible implementation manner, the location name generation module is specifically configured to:

In one possible implementation manner, before the generating the name of the boarding point according to the travel requirement, the user behavior feature corresponding to each reference POI, and the POI popularity feature, the location name generating module is further configured to:

In one possible implementation manner, the location name generating module is configured to obtain a user behavior feature corresponding to any one of the reference POIs by:

In one possible implementation manner, the location name generation module is configured to obtain the POI popularity feature by:

In a possible implementation manner, after the current position of the user and the travel requirement are obtained, before the getting-on point based on the travel requirement filters out each reference point of interest POI in a preset range from the historical behavior data of the user, the obtaining module is further configured to:

In a third aspect, an embodiment of the present application provides an electronic device, including:

a memory for storing a computer program or instructions;

a processor for executing a computer program or instructions in the memory such that the method according to any of the first aspects is performed.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which when executed by a processor, causes the processor to perform the method of any one of the first aspects.

In a fifth aspect, embodiments of the present application provide a computer program product comprising: computer program code which, when run on a computer, causes the computer to perform the method of any of the first aspects.

In addition, the technical effects caused by any implementation manner of the second aspect to the fifth aspect may refer to the technical effects caused by different implementation manners of the first aspect, which are not described herein.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

Fig. 1 is an application scenario schematic diagram of an alternative method for generating a location name in an embodiment of the present application;

fig. 2A is a schematic diagram of a display interface of a get-on point name in an embodiment of the present application;

FIG. 2B is a schematic diagram of another display interface for the name of the get-on point according to an embodiment of the present application;

fig. 3 is a flow chart of a method for generating a get-on point name in the embodiment of the present application;

FIG. 4 is a schematic diagram of each recommended get-on point for a current location of a user according to an embodiment of the present application;

FIG. 5 is a flow chart of a method for determining a distance and a relative positional relationship between a user and a get-on point according to an embodiment of the present application;

FIG. 6 is a flow chart of a method for generating a get-on point name based on a get-on point name generation model according to an embodiment of the present application;

FIG. 7 is a flowchart illustrating a method for determining user behavior characteristics according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a network architecture of an RNN according to an embodiment of the present disclosure;

fig. 9 is a flowchart of a method for determining heat characteristics corresponding to historical data in an embodiment of the present application;

FIG. 10 is a flowchart of a method for determining a first heat characteristic and a second heat characteristic according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a logic architecture of a location name generating device according to an embodiment of the present application;

fig. 12 is a schematic diagram of an entity architecture of an electronic device in an embodiment of the application.

Detailed Description

The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

It should be noted that the terms "first," "second," "third," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be capable of being practiced otherwise than as specifically illustrated and described.

In the embodiment of the application, in order to solve the problem that the on-board roll names generated under the traditional technology cause poor travel efficiency and user experience, the travel requirements of the user are acquired, wherein the travel requirements comprise the current position and travel time of the user; screening out all reference POIs in a preset range from historical behavior data of a user based on a get-on point of travel demand, wherein the get-on point is recommended to the user through a preset get-on point recommendation rule based on the current position, and any one of the reference POIs is a POI which is searched for by the user in a historical mode or used by a historical order; generating names of boarding points according to travel demands, user behavior characteristics corresponding to each reference POI and POI heat characteristics; any user behavior feature characterizes the preference degree of the user on the reference POI corresponding to the user behavior feature; the POI heat characteristic is obtained by extracting heat characteristics of each POI in the historical data based on the historical data of each user in a preset time period, wherein the historical data comprises search log data and historical order data.

By adopting the method for generating the position name, the names of the boarding points can be dynamically generated for the users according to the user behavior characteristics corresponding to each reference POI which is searched for by the user in the history behavior data of the users and/or used by the history orders, the current position and the travel time of the users which are included in the travel demands, and the POI heat characteristics obtained by extracting the heat characteristics of each POI in the history data based on the history data of each user in a preset time period.

The preferred embodiments of the present application will be described in further detail below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation only, and are not intended to limit the present application, and the features of the embodiments and examples of the present application may be combined with each other without conflict.

Fig. 1 is a schematic view of an application scenario in an embodiment of the present application. The application scenario includes the user terminal 10, the server 20 and the vehicle-mounted terminal 30, wherein the user terminal 10 is connected with the server 20 through a wired network or a wireless network, and the vehicle-mounted terminal 30 is also connected with the server 20 through the wired network or the wireless network.

It should be noted that the positions of the in-vehicle terminal 30 in fig. 1 are only for example, and the positions of both are specifically shown in the drawings, and are not as fixed positions actually installed in the vehicle. The position of the in-vehicle terminal 30 may be at other positions of the vehicle, such as where the in-vehicle terminal 30 is mounted at a door, between front seats, and the like.

In the network taxi taking Application scenario shown in fig. 1, referring to fig. 2A, when a user opens a client of a trip Application (APP), the trip Application often displays a recommended taxi taking point around a current positioning point, and the user can perform a network taxi taking order placing operation by using the recommended taxi taking point.

Still referring to the network taxi-taking application scenario shown in fig. 1, referring to fig. 2B, when a user waits for receiving a taxi, a trip-class application program often follows the real-time position of the user, displays each recommended taxi-taking point around the user, and the user can select any recommended taxi-taking point as the receiving position of the current trip requirement.

Of course, the method provided in the embodiment of the present application is not limited to the application scenario shown in fig. 1, fig. 2A, and fig. 2B, but may be used in other possible application scenarios, which is not limited in the embodiment of the present application.

It is to be understood that the method for generating the location name in the embodiment of the present application is applicable to any application scenario in which the generation of the get-on roll name for the get-on point is required. In the following embodiments, only the starting trip class APP is taken as an example to display the boarding point for detailed description.

After introducing the application scenario of the embodiment of the present application, referring to fig. 3, in the embodiment of the present application, a method for generating a location name is provided, where a specific flow of the method is as follows:

step 300: and acquiring the travel demand of the user, wherein the travel demand comprises the current position and travel time of the user.

In this embodiment, referring to fig. 2A, a user opens a client of a trip application program, and a user terminal starts the trip application program in response to starting of the trip application program triggered by the user in a preset manner, and step 300 is executed, where the acquired trip requirement includes a current position and trip time of the user, and the preset manner includes clicking operation, sliding operation or voice data control.

In some possible embodiments, when the user is not satisfied with the displayed boarding point, the position of the user is generally adjusted by drawing or searching, and at this time, the user terminal responds to the above operation of the user to obtain the travel requirement of the user, and step 300 is performed.

In this embodiment of the present application, after the travel requirement is obtained in the execution step 300, the get-on point for the travel requirement is recommended to the user based on the current position in the travel requirement and the get-on point recommendation rule, where the get-on point recommendation rule may be any get-on point recommendation mode in the prior art, and the application is not specifically limited.

In practical application, three or more get-on points are recommended for a travel requirement, as shown in fig. 4, when the current position of the user is at the point a, three get-on points are recommended for the user, namely a get-on point 1, a get-on point 2 and a get-on point 3, wherein the get-on point 1 is located at the road edge of the right road of the user, the get-on point 2 is located at the road edge of the front road of the user, and the get-on point 3 is located at the road edge opposite to the front road of the user.

After obtaining the get-on point of the travel requirement by adopting the preset get-on point recommendation rule, before executing step 310, referring to fig. 5, the following steps are further executed:

Step 500: and determining the distance between the user and the get-on point based on the get-on point and the current position.

Step 510: based on the get-on point and the current position, judging whether a road exists between the user and the get-on point by utilizing road network data, and obtaining the relative position relationship between the user and the get-on point based on the judging result.

In this embodiment, if a plurality of boarding points are recommended for the user, when executing steps 500-510, the distance and the relative positional relationship between each boarding point and the user are obtained respectively, which is not described herein.

In this way, by executing steps 500-510, the distance between the user and each get-on point and the relative position relationship are obtained, so that the get-on point name generated for naming the get-on point based on the distance and the relative position relationship can be better reflected, and the travel efficiency of the user is improved.

Step 310: screening out all reference POIs in a preset range from historical behavior data of a user based on a trip requirement, wherein the trip point is recommended to the user through a preset trip point recommendation rule based on the current position, and any one of the reference POIs is a POI which is searched for by the user in a historical mode or used by a historical order.

Under the related technology, the log in the user terminal records POIs which are clicked by the user in the history search and used by the history order in the travel class APP. In the embodiment of the application, the historical behavior data of the user is the log of the user. In specific implementation, when step 310 is executed, based on the log of the user, each POI that is searched for by the user and used by the historical order is obtained, and then, based on the boarding point of the travel requirement, each reference POI in a preset range is screened out from each POI that is searched for by the user and used by the historical order, wherein in the embodiment of the application, the preset range can be selected as 30m near the boarding point.

Step 320: generating names of boarding points according to travel demands, user behavior characteristics corresponding to each reference POI and POI heat characteristics; any user behavior feature characterizes the preference degree of the user on the reference POI corresponding to the user behavior feature; the POI heat characteristic is obtained by extracting heat characteristics of each POI in the historical data based on the historical data of each user in a preset time period, wherein the historical data comprises search log data and historical order data.

In implementation, in executing step 320, referring to fig. 6, the following steps are specifically executed:

Step 3201: and inputting travel requirements, user behavior characteristics corresponding to each reference POI, get-on points, distance and relative position relations between the get-on points and the users, and POI heat characteristics into a preset get-on roll name generation model.

In this embodiment, after step 310 is performed, referring to fig. 7, the following steps are performed to obtain the user behavior feature corresponding to any one of the reference POIs:

step 700: based on the historical behavior data, statistics is made of the cumulative number of searches for the reference POI in the historical behavior data, and statistics is made of the cumulative number of starting points of the reference POI as starting points.

Step 710: and taking the accumulated searching times and the accumulated starting point times of the reference POI as user behavior characteristics corresponding to the reference POI.

In this way, through the steps 700-710, the preference degree of the user for each reference POI can be obtained, so that when the step 320 is executed, the get-on point name which is more fit with the preference of the user is generated, thereby reducing the time for the user to find the get-on point and improving the travel efficiency.

In the embodiment of the present application, the timing of obtaining the user behavior feature corresponding to each POI in the historical behavior data based on the statistics of the historical behavior data is not limited, and it can be understood that the timing may be obtained by statistics in advance, or may be based on the statistics of the historical behavior data in executing the above-mentioned method for generating the location name.

In this embodiment, when step 3201 is executed, the travel requirement, the user behavior feature corresponding to each reference POI, the get-on point, the distance between the get-on point and the user, and the relative positional relationship, these real-time features, and the POI heat feature (historical heat feature) are input together to a pre-trained get-on roll name generation model to obtain the name of the get-on point, where the get-on roll name generation model is obtained by training the POI heat feature, and the historical order data and the historical behavior data (i.e. the historical search log) of each user.

The model training process of the roll-up name generation model is summarized below. Before training the model, collecting a plurality of training samples, each training sample being derived based on historical order data and historical behavior data of a sample user, wherein each training sample includes, but is not limited to, the following information:

information 1, sample user id;

information 2, cumulative number of times of each poi_a in a history search log of the sample user's history 90 days, wherein three dimensions of working day and non-working day are distinguished, and working day and non-working day are not distinguished;

information 3, the cumulative number of times each poi_a in the historical 90-day historical order data of the sample user is used as a starting point, wherein three dimensions of working days and non-working days are distinguished, and the working days and the non-working days are not distinguished;

Information 4, poi_a heat characteristics, which are global characteristics, are not distinguished from users, and are detailed in the subsequent determining process;

information 5, judging whether the road crossing between the sample user and the boarding point is carried out: judging whether a road exists between the current position of the user and the boarding point, if so, determining that the road is a crossing (which can be represented by '1'), and if not, determining that the road is not a crossing (which can be represented by '0');

information 6, the distance between the boarding point and the sample user;

information 7, sampling travel time in the historical order data of the user;

information 8, names of boarding points in historical order data of sample users, namely boarding point name labels.

After the above information of each training sample in the training sample set is obtained, a training sample set for training the on-coming roll-call generation model to be trained is obtained, then, based on the training sample set, iterative training is carried out on the on-coming roll-call generation model to be trained, and after convergence conditions (for example, the error between the name of the on-coming roll-call output by the on-coming roll-call generation model to be trained and the corresponding on-coming roll-call label is smaller than an error threshold value, etc.), the on-coming roll-call generation model after the training is completed is obtained, and then, the on-coming roll-call generation model used in the implementation process is obtained. In the embodiments of the present application, the content of the model training method, the model parameter adjustment method, the training super-parameter, and the like is not limited.

In the embodiment of the application, one get-on point is preferably named by relying on 3 POIs. In specific implementation, all POIs are acquired in the vicinity of the boarding point 30m, and 3 POIs are collected from the 30m and screened out, wherein two POIs can be the highest and next highest search accumulation number selected based on historical behavior data of a user, namely, the highest search accumulation number is the hottest for the user, and one POI can be the hottest not for any user.

Then, the names of the three POIs are spliced by using preset symbols, such as SEP symbols, wherein null values are filled with 0, the three names (in the form of words) are mapped into numbers through a preset dictionary, and the numbers obtained by mapping and the information 1-7 are spliced into a 64-dimensional vector which is used as input of a roll-in name generation model to be trained.

In the embodiment of the application, the roll call generation model is preferably constructed by a cyclic neural network (Recurrent Neural Network, RNN), and the network architecture of the cyclic neural network is shown in fig. 8. Referring to fig. 8, the spliced vectors (the vector obtained by receiving the training samples is 64-dimensional) are input into the RNN, and the name of the boarding point is obtained by mapping the numbers into texts through a softmax layer.

In this embodiment, referring to fig. 9, the foregoing POI heat characteristics in the training process and in the implementation project are obtained by:

step 900: based on the historical data of each user, the first heat characteristics corresponding to each starting point POI and the second heat characteristics corresponding to each terminal point POI in the historical data are obtained through statistics.

In the embodiment of the application, the historical data in each user is collected in advance, wherein the historical data comprises search log data and historical order data, and the historical order data preferably refers to historical completion data.

In implementation, in executing step 900, referring to fig. 10, the following steps are specifically executed:

step 9001: based on the historical data, adopting a first time period, a second time period and a third time period in a preset POI heat characteristic extraction rule to respectively count the accumulated times corresponding to each starting point POI and the accumulated times corresponding to each terminal point POI in the historical data.

Step 9002: the following is performed for each of the starting point POIs: and based on any accumulated times of any starting point POI in the starting point POIs, obtaining first sub-heat characteristics of a time period corresponding to any accumulated times of the starting point POIs by adopting a characteristic extraction rule in a POI heat characteristic extraction rule, and taking each first sub-heat characteristic as a first heat characteristic corresponding to the starting point POI.

Step 9003: the following is performed for each of the end point POIs: and based on any accumulated times of any one of the terminal POIs, obtaining second sub-heat characteristics of the terminal POIs in a time period corresponding to any accumulated times of the terminal POIs by adopting a characteristic extraction rule in a POI heat characteristic extraction rule, and taking each second sub-heat characteristic as the second heat characteristic corresponding to the terminal POI.

In this embodiment of the present application, if the history data is the search log data, in executing step 9001, according to the search log data, the cumulative number of times corresponding to each start POI and the cumulative number of times corresponding to each end POI in the search log data in a first period (e.g. 90 days of history), the cumulative number of times corresponding to each start POI and the cumulative number of times corresponding to each end POI in the search log data in a second period (e.g. 60 days of history), and the cumulative number of times corresponding to each start POI and the cumulative number of times corresponding to each end POI in the search log data in a third period (e.g. 30 days of history) are counted respectively; and searching the accumulated times of distinguishing working days and non-working days corresponding to the starting point POIs and the accumulated times of distinguishing working days and non-working days corresponding to the end point POIs in log data in a first time period (such as 90 days).

Then, when step 9002 is executed, the following formula is adopted to calculate and obtain the first sub-heat feature/the second sub-heat feature of each time period corresponding to each start point/end point POI, where the start point POI/the end point POI is marked as a historical POI, and the first sub-heat feature/the second sub-heat feature is marked as POI search heat:

POI search heat = log ₂ (1+cumulative times of historical POIs)

In this embodiment, if the historical data is historical order data, in executing step 9001, according to the historical order data, the cumulative number of times corresponding to each start POI and the cumulative number of times corresponding to each end POI in the historical order data in a first period (e.g. 90 days of history), the cumulative number of times corresponding to each start POI and the cumulative number of times corresponding to each end POI in the historical order data in a second period (e.g. 60 days of history), and the cumulative number of times corresponding to each start POI and the cumulative number of times corresponding to each end POI in the historical order data in a third period (e.g. 30 days of history) are counted respectively; and the cumulative number of distinguishing working days and non-working days corresponding to each starting point POI and the cumulative number of distinguishing working days and non-working days corresponding to each terminal point POI in the historical order data in the first time period (such as 90 days).

Then, when step 9002 is executed, the first sub-heat feature/second sub-heat feature of each time period corresponding to each start point/end point POI is calculated by the following formula, namely, the start point/end point POI order heat:

start POI order heat = log ₂ (1 + cumulative times of historical order origin POI)

Endpoint POI order heat = log ₂ (1+cumulative times of historical order Point of sale)

Step 910: and screening out cross-city order data from the historical order data, counting and obtaining the accumulated use times of all terminal POIs in the cross-city order data based on the cross-city order data, and respectively determining the ratio of the accumulated use times of all terminal POIs to the total number of orders of the cross-city order data.

In this embodiment, when executing step 910, first, cross-city order data is screened from historical order data, where a starting point and an ending point in the cross-city order data are respectively in different cities; then, based on the cross-city order data, the cumulative use times of the terminal POI in the cross-city order data in the first time period (such as 90 days in history) are obtained through statistics, and the cross-city POI ratio of the cumulative use times of the terminal POI to the total amount of orders of the cross-city order data is obtained, which can be expressed by the following formula:

Aggregate number of uses of destination POI in cross city order =cross city POI heat

Cross metropolitan POI ratio = cumulative number of uses of endpoint POI in cross metropolitan order/total number of orders for cross metropolitan order

Step 920: and determining each first heat characteristic, each second heat characteristic, each accumulated use time and each cross-city POI ratio as POI heat characteristics.

In this way, the POI popularity feature is obtained and is used as a historical benchmark feature so as to facilitate the knowledge of popular POIs.

In this embodiment, when step 3201 is executed, travel requirements, user behavior features corresponding to each reference POI, get-on points, distances and relative positional relationships between get-on points and users, these real-time features, and POI heat features (historical heat features) are also mapped and spliced according to a mapping manner and a splicing manner adopted in the training process of the model, and then, the spliced vectors are input into the get-on point name generation model before the travel requirements, the user behavior features corresponding to each reference POI, the distances and relative positional relationships between the get-on points, the get-on points and the users, and POI heat features (historical heat features) are input into the get-on point name generation model.

Step 3202: and screening out target POIs from each reference POI and each POI in the historical data based on travel requirements, user behavior characteristics corresponding to each reference POI, boarding points, distances, relative position relations and POI heat characteristics through the boarding point name generation model.

Step 3203: and generating the name of the get-on point based on the name of the target POI and the position relation between the target POI and the current position.

In this embodiment of the present application, after the name of the get-on point is obtained in step 320, user behavior data associated with the current trip requirement, such as a get-on point selected by a user, is recorded, and a POI database (the POI database is used for storing basic information of all POIs, such as names, user ids, addresses, cities, longitude and latitude, heat, etc.) in the historical data associated with the POI heat feature of the user is updated, so that by continuously updating the user historical behavior database and the POI database, data iteration can be performed according to user behaviors and market changes, and the recommendation accuracy is improved, so that the naming accuracy of the get-on point name is improved.

In this way, by the method for generating the location name in the embodiment of the application, according to the user behavior characteristics corresponding to each reference POI which is searched for by the history of the user and/or used by the history order, the current location and travel time of the user which are included in the travel requirement, and the POI heat characteristics which are obtained by extracting the heat characteristics of each POI in the history data based on the history data of each user in a preset time period, the name of the boarding point is dynamically generated for the user.

Further, by adopting the method in the embodiment of the application, the position information of the boarding point can be dynamically changed according to the characteristics of the user, so that thousands of people and thousands of sides are realized, namely, the boarding point names displayed in the application interfaces of different people are different for the same boarding point.

Based on the same inventive concept, referring to fig. 11, in an embodiment of the present application, a location name generating device is provided, including:

an obtaining module 1110, configured to obtain a travel requirement of a user, where the travel requirement includes a current location and a travel time of the user;

the screening module 1120 is configured to screen out, from historical behavior data of the user, each reference point of interest POI within a preset range based on the get-on point of the travel requirement, where the get-on point is recommended to the user by a preset get-on point recommendation rule based on the current position, and any one of the reference POI is a POI that has been historically searched or used by a historical order of the user;

the location name generating module 1130 is configured to generate a name of the boarding point according to the travel requirement, the user behavior feature corresponding to each reference POI, and the POI heat feature;

In one possible implementation, the location name generation module 1130 is specifically configured to:

In a possible implementation manner, before the generating the name of the boarding point according to the travel requirement, the user behavior feature corresponding to each reference POI, and the POI popularity feature, the location name generating module 1130 is further configured to:

In a possible implementation manner, the location name generating module 1130 is configured to obtain a user behavior feature corresponding to any one of the reference POIs by:

In one possible implementation, the location name generating module 1130 is configured to obtain the POI popularity feature by:

In a possible implementation manner, after the current location and the trip requirement of the user are obtained, before the getting-on point based on the trip requirement filters out each reference point of interest POI in a preset range from the historical behavior data of the user, the obtaining module 1110 is further configured to:

Based on the same inventive concept, an electronic device is provided in the embodiment of the present application, and an electronic device 120 according to this embodiment of the present application is described below with reference to fig. 12. The electronic device 120 shown in fig. 12 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments herein.

As shown in fig. 12, the electronic device 120 is in the form of a general-purpose electronic device. Components of electronic device 120 may include, but are not limited to: the at least one processor 121, the at least one memory 122, and a bus 123 that connects the various system components, including the memory 122 and the processor 121.

Bus 123 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, and a local bus using any of a variety of bus architectures.

Memory 122 may include readable media in the form of volatile memory, such as Random Access Memory (RAM) 1221 and/or cache memory 1222, and may further include Read Only Memory (ROM) 1223.

Memory 122 may also include a program/utility 1225 having a set (at least one) of program modules 1224, such program modules 1224 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

The electronic device 120 may also communicate with one or more external devices 124 (e.g., keyboard, pointing device, etc.), one or more devices that enable a user to interact with the electronic device 120, and/or any device (e.g., router, modem, etc.) that enables the electronic device 120 to communicate with one or more other electronic devices. Such communication may occur through an input/output (I/O) interface 125. Also, the electronic device 90 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 126. As shown, network adapter 126 communicates with other modules for electronic device 120 over bus 123. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 120, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

Based on the same inventive concept, embodiments of the present application provide a computer-readable storage medium, which when executed by a processor, causes the processor to perform the method of any one of the above. Since the principle of solving the problem by the computer readable storage medium is similar to that of generating the location name, implementation of the computer readable storage medium may refer to implementation of the method, and the repetition is not repeated.

Based on the same inventive concept, embodiments of the present application also provide a computer program product comprising: computer program code which, when run on a computer, causes the computer to perform the method as any of the preceding discussion. Since the principle of solving the problem by the computer program product is similar to that of generating the location name, the implementation of the computer program product may refer to the implementation of the method, and the repetition is omitted.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart block or blocks and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. A method for generating a location name, comprising:

2. The method of claim 1, wherein the generating the name of the boarding point according to the travel demand, the user behavior feature corresponding to each reference POI, and the POI popularity feature comprises:

3. The method of claim 2, wherein before generating the name of the boarding point according to the travel requirement, the user behavior feature corresponding to each reference POI, and the POI popularity feature, further comprises:

4. A method according to any one of claims 1-3, wherein the user behavior characteristics corresponding to any one of the reference POIs are obtained by:

5. A method according to any one of claims 1 to 3, wherein the POI heat signature is obtained by:

6. The method of claim 5, wherein statistically obtaining a first heat characteristic corresponding to each start point POI and a second heat characteristic corresponding to each end point POI in the history data based on the history data of each user, comprising:

7. The method as set forth in any one of claims 1 to 3, wherein after the obtaining the current location and the travel requirement of the user, before the getting-on point based on the travel requirement and screening out the POI of each reference interest point in a preset range from the historical behavior data of the user, the method further includes:

8. A position name generating apparatus, comprising:

the generation module is used for generating the name of the boarding point according to the travel requirement, the user behavior characteristics corresponding to each reference POI and the POI heat characteristics;

9. An electronic device, comprising:

a memory for storing a computer program or instructions;

a processor for executing a computer program or instructions in the memory, such that the method of any of claims 1-7 is performed.

10. A computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor, enable the processor to perform the method of any one of claims 1-7.

11. A computer program product, the computer program product comprising: computer program code which, when run on a computer, causes the computer to perform the method of any of the preceding claims 1-7.