CN116258267A - Method and device for setting boarding point, storage medium and computer equipment - Google Patents

Method and device for setting boarding point, storage medium and computer equipment Download PDF

Info

Publication number
CN116258267A
CN116258267A CN202310245901.6A CN202310245901A CN116258267A CN 116258267 A CN116258267 A CN 116258267A CN 202310245901 A CN202310245901 A CN 202310245901A CN 116258267 A CN116258267 A CN 116258267A
Authority
CN
China
Prior art keywords
point
predicted
position information
user
preset
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
CN202310245901.6A
Other languages
Chinese (zh)
Inventor
曾干
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.)
Ping An E Wallet Electronic Commerce Co Ltd
Original Assignee
Ping An E Wallet Electronic Commerce 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 Ping An E Wallet Electronic Commerce Co Ltd filed Critical Ping An E Wallet Electronic Commerce Co Ltd
Priority to CN202310245901.6A priority Critical patent/CN116258267A/en
Publication of CN116258267A publication Critical patent/CN116258267A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0645—Rental transactions; Leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Accounting & Taxation (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method, a device, a storage medium and computer equipment for setting a boarding point, which relate to the technical field of information and financial science and technology and mainly are capable of improving the setting precision and the setting efficiency of the boarding point and improving the driving experience of a user. The method comprises the following steps: responding to a get-on point setting instruction sent by a getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; and if the predicted position information corresponding to the predicted getting-on point is correct, determining the predicted getting-on point as the target getting-on point corresponding to the getting-on user.

Description

Method and device for setting boarding point, storage medium and computer equipment
Technical Field
The present invention relates to the field of information technologies, and in particular, to a method and apparatus for setting a boarding point, a storage medium, and a computer device.
Background
With the development of society, more and more taxi taking software is presented, and taxi taking software of most companies, a taxi taking point is an index for measuring the competitiveness of taxi taking services.
Currently, a position manually input by a user is generally used as a get-on point. This way of manually entering the entry point by the user, however, results in a lower efficiency of setting the entry point, while at the same time the entry point manually entered by the user is not a place where parking is possible, e.g. the entry point set by the user is within a building, the driver parking spot and the get-on spot are offset, so that the setting precision of the get-on spot is lower, and meanwhile, under the condition that the offset exists between the get-on spot and the parking spot, a user needs to carry out telephone communication with a master driver to determine the actual get-on spot, and the driving experience of the user is reduced.
Disclosure of Invention
The invention provides a method, a device, a storage medium and computer equipment for setting a boarding point, which mainly can improve the setting precision and the setting efficiency of the boarding point and improve the driving experience of a user.
According to a first aspect of the present invention, there is provided a method for setting a boarding point, including:
responding to a get-on point setting instruction sent by a getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user;
inputting the position information and the characteristic data into a preset get-on point prediction model to predict a get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user;
responding to a trigger signal of the taxi taking user on the predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point;
judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the preset map;
and if the predicted position information corresponding to the predicted get-on point is correct, determining the predicted get-on point as the target get-on point corresponding to the taxi taking user.
Preferably, before the position information and the feature data are input into a preset get-on point prediction model to perform get-on point prediction, and the predicted get-on point corresponding to the taxi taking user is obtained, the method further includes:
constructing at least one preset initial get-on point prediction model;
Acquiring sample position information and sample characteristic data corresponding to a sample taxi taking user and a corresponding sample actual taxi taking point;
constructing a training set based on the sample position information, the sample characteristic data and the corresponding sample actual vehicle points;
and constructing the preset get-on point prediction model according to the training set.
Preferably, the constructing the preset get-on point prediction model according to the training set includes:
dividing the training set into a plurality of groups of training data and corresponding test data according to the number of preset initial get-on point prediction models;
training a corresponding preset initial get-on point prediction model by utilizing each group of training data to obtain each trained preset initial get-on point prediction model;
sample position information and sample characteristic data corresponding to the same sample taxi taking user in each group of test data are input into a corresponding trained preset initial taxi taking point prediction model to conduct taxi taking point prediction, and a predicted sample taxi taking point is obtained;
determining a backtracking value corresponding to each trained preset initial get-on point prediction model based on an actual sample get-on point and a predicted sample get-on point corresponding to the same sample get-on user, wherein the backtracking value is used for representing a prediction error of the corresponding preset initial get-on point prediction model;
And filtering each trained preset initial get-on point prediction model according to the backtracking value to obtain the preset get-on point prediction model.
Preferably, the inputting the position information and the feature data into a preset get-on point prediction model to predict a get-on point, to obtain a predicted get-on point corresponding to the taxi taking user, includes:
determining a first characteristic vector corresponding to the position information and a second characteristic vector corresponding to the characteristic data;
fusing the first feature vector and the second feature vector to obtain a taxi taking fusion feature vector;
and inputting the taxi taking fusion feature vector into a preset taxi taking point prediction model to predict a taxi taking point, and obtaining a predicted taxi taking point corresponding to the taxi taking user.
Preferably, the determining, based on the preset map, whether the predicted position information corresponding to the predicted on-coming point is correct includes:
determining the same target point as the predicted on-vehicle point in the preset map, displaying position information corresponding to the target point layer by layer, and determining map position information displayed to the tail end in the position information displayed layer by layer;
and judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the predicted position information and the map position information.
Preferably, the determining whether the predicted position information corresponding to the predicted on-coming point is correct based on the predicted position information and the map position information includes:
determining a third feature vector corresponding to the predicted position information and determining a fourth feature vector corresponding to the map position information;
calculating cosine similarity between the predicted position information and the map position information based on the third feature vector and the fourth feature vector;
judging whether the cosine similarity is larger than a preset similarity threshold value or not;
if the predicted position information is larger than the preset similarity threshold value, judging whether the predicted position information is the position information which can be parked;
and if the predicted position information is the position information capable of stopping, judging that the predicted position information corresponding to the predicted boarding point is accurate.
Preferably, after the determining, based on the preset map, whether the predicted position information corresponding to the predicted on-coming point is correct, the method further includes:
if the predicted position information corresponding to the predicted get-on point is incorrect, correcting the predicted position information corresponding to the predicted get-on point based on the position information corresponding to the point which is the same as the predicted get-on point in the preset map, and determining the predicted get-on point after correcting the position information as the target get-on point corresponding to the taxi taking user.
According to a second aspect of the present invention, there is provided a setting device of a boarding point, comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for responding to a get-on point setting instruction sent by a getting-on user and acquiring position information and characteristic data corresponding to the getting-on user;
the prediction unit is used for inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user;
the display unit is used for responding to the trigger signal of the taxi taking user on the predicted taxi taking point and displaying a preset map within a preset range where the predicted taxi taking point is located;
the judging unit is used for judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the preset map;
and the determining unit is used for determining the predicted get-on point as the target get-on point corresponding to the getting-on user if the predicted position information corresponding to the predicted get-on point is correct.
According to a third aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above step of setting a get-on point.
According to a fourth aspect of the present invention there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above set-up steps for the drive-up points when executing the program.
According to the method, the device, the storage medium and the computer equipment for setting the get-on point, compared with the mode of manually inputting the get-on point at present, the method and the device for setting the get-on point acquire the position information and the characteristic data corresponding to the get-on user by responding to the get-on point setting instruction sent by the get-on user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to a get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; if the predicted position information corresponding to the get-on point is correct, the predicted get-on point is determined to be the target get-on point corresponding to the get-on user, so that the get-on point is predicted by inputting the position information and the characteristic data of the get-on user into a preset get-on point prediction model, the time consumed by manually inputting the get-on point is avoided, the setting efficiency of the get-on point is improved, the situation that the get-on point is set incorrectly due to negligence of the user can be avoided by the magnetic shoe, the setting accuracy of the get-on point is improved, and meanwhile, the get-on point predicted by the model is compared with the point at the same position in the map, and the setting accuracy of the get-on point is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
fig. 1 shows a flow chart of a method for setting a get-on point according to an embodiment of the present invention;
FIG. 2 shows a flowchart of another method for setting a get-on point according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for setting a boarding point according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of another device for setting a boarding point according to an embodiment of the present invention;
fig. 5 shows a schematic physical structure of a computer device according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the drawings in conjunction with embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
At present, the mode of manually inputting the get-on point leads to lower setting efficiency of the get-on point, and meanwhile, due to the fact that the get-on point is set incorrectly by the negligence of a user, the setting accuracy of the get-on point is lower.
In order to solve the above problem, an embodiment of the present invention provides a method for setting a get-on point, as shown in fig. 1, where the method includes:
101. and responding to a get-on point setting instruction sent by a getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user.
The position information is longitude and latitude information of a taxi taking user when sending a taxi taking instruction, and the characteristic data comprises information such as the position information of historical taxi taking points of the taxi taking user, the age, occupation, interests and hobbies of the user, used taxi taking equipment, signals corresponding to the equipment and the like.
For the embodiment of the invention, when the user clicks the search area in the browsing page of the taxi taking software, namely, the taxi taking point setting instruction is triggered, after the server corresponding to the taxi taking software receives the search instruction, the information such as the position information and the characteristic data of the user is acquired, the position information and the characteristic data can be input into the preset taxi taking point prediction model to conduct taxi taking point prediction, the predicted taxi taking point is obtained, the time consumed by manually inputting the taxi taking point is avoided, and therefore, the taxi taking point setting efficiency is improved, and meanwhile, the condition that the user inadvertently causes the taxi taking point to be set in error is avoided, so that the taxi taking point setting accuracy is improved.
The location information and the feature data of the taxi taking user acquired in the embodiment are not personal privacy data of the dispatcher, but data (non-personal privacy data) related to the taxi taking user, which are available in the taxi taking management platform.
102. And inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user.
The preset get-on point prediction model may be a neural network model, such as a preset multi-layer sensor. After the position information and the characteristic data of a taxi taking user are obtained, the position information and the characteristic data are input into a preset taxi taking point prediction model together for taxi taking point prediction, a taxi taking point corresponding to the taxi taking user can be predicted through the model, then the taxi taking point is displayed to the user, the user can firstly check whether the taxi taking point is a required taxi taking point or not, if the taxi taking point is not the required taxi taking point, the user can click a deletion mark at the preset position of the taxi taking point, the deletion mark can be a symbol mark or a character mark, the deletion mark is not limited specifically, the user clicks the deletion mark and then displays the predicted taxi taking point to the user, at the moment, the user can input the taxi taking point at the corresponding position or call a map, and the corresponding taxi taking point is selected in the map, wherein in order to avoid the situation that the taxi taking point is too many in the history corresponding to the user, the map is displayed, the deletion mark can be a symbol mark or a character mark, the map is displayed in a messy way, the preset position can be displayed on the map, the map is not broken, the user can feel the map is more easily, the map is displayed on the map, the map is not is touched, the user has a plurality of the map is required by the map, and the user is enabled to have a plurality of the map.
103. Responding to a trigger signal of the taxi taking user on the predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point.
The preset map may be a satellite map. The preset range can be set according to actual conditions, and the preset range can be the city range of the taxi taking user; or a round range with a preset length as a radius and the like by taking the position of the taxi taking user as the center.
For the embodiment of the invention, after the get-on point meeting the requirement of the user is predicted by using the preset get-on point prediction model, the get-on point is displayed to the user, and can be particularly displayed to the user in a popup window mode, if the get-on point can meet the requirement of the user, the user clicks the get-on point to trigger a confirmation signal of the get-on point, after the confirmation signal of the predicted get-on point is received, a preset map corresponding to the predicted get-on point is displayed, and by displaying the preset map, on one hand, the user can intuitively feel the position information of the predicted get-on point displayed in the popup window, on the other hand, the system can determine the map position information corresponding to the same point as the predicted get-on point in the map, and compare the map position information with the position information corresponding to the predicted get-on point to judge the accuracy of the position information of the predicted get-on point, and if the position information of the predicted get-on point is accurate, the position information of the predicted get-on point is directly displayed at a blank position corresponding to the departure point, so that the setting accuracy of the get-on point is improved. Meanwhile, if the get-on point required by the user is not the get-on point displayed in the popup window, the user can click the deletion mark in the popup window, at this time, the predicted get-on point disappears along with the popup window, the corresponding position of the departure point is still blank, at this time, the user can manually input the get-on point, or select the get-on point by calling the map.
104. And judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the preset map.
After the user triggers the predicted get-on point displayed in the popup window, the server corresponding to the get-on software automatically determines map position information corresponding to the predicted get-on point in a preset map after receiving the trigger signal, and matches the map position information with position information corresponding to the get-on point, if the map position information can be matched, the position information corresponding to the get-on point is determined to be accurate, meanwhile, because the map position information can accurately display longitude and latitude information corresponding to the get-on point, the server can accurately display the longitude and latitude information corresponding to the get-on point in a building, the server can accurately confirm whether the predicted get-on point is a point at which a driver can park, when the predicted get-on point is determined to be a point at which the driver can park, and the predicted get-on point is matched with the map position information, the predicted get-on point is determined to be accurate, and the predicted get-on point is set at a blank position corresponding to the start point, so that the setting of the get-on point is completed, and the like can be accurately displayed in the building, and the user can not feel the park on the car, and the telephone charge is further avoided, and the user is further prevented from being set up the telephone charge between the driver and the driver.
105. And if the predicted position information corresponding to the predicted get-on point is correct, determining the predicted get-on point as the target get-on point corresponding to the taxi taking user.
The target get-on point is a stop point for a driver to receive a user. For the embodiment of the invention, after the predicted position information corresponding to the boarding point predicted by the model is checked by using the preset map, if the predicted position information corresponding to the boarding point is completely consistent with the map position information in the map and is not a point which cannot be parked in a building or the like, the predicted position information corresponding to the predicted boarding point is determined to be accurate, and at the moment, the predicted position information corresponding to the predicted boarding point can be displayed at a blank position corresponding to the departure point on the departure software. Therefore, the prediction efficiency and the prediction accuracy of the get-on point can be improved by predicting the get-on point by using the preset get-on point prediction model, and meanwhile, the predicted get-on point can be further checked by comparing the map position information displayed in the map with the position information corresponding to the predicted get-on point, so that the setting precision of the get-on point is improved, the getting-on experience of a user is improved, and the communication cost and the communication time between a getting-on user and a driver are saved.
According to the method for setting the get-on point, compared with the mode of manually inputting the get-on point at present, the method for setting the get-on point acquires the position information and the characteristic data corresponding to the get-on user by responding to the get-on point setting instruction sent by the get-on user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to a get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; if the predicted position information corresponding to the get-on point is correct, the predicted get-on point is determined to be the target get-on point corresponding to the get-on user, so that the get-on point is predicted by inputting the position information and the characteristic data of the get-on user into a preset get-on point prediction model, the time consumed by manually inputting the get-on point is avoided, the setting efficiency of the get-on point is improved, the situation that the get-on point is set incorrectly due to negligence of the user can be avoided by the magnetic shoe, the setting accuracy of the get-on point is improved, and meanwhile, the get-on point predicted by the model is compared with the point at the same position in the map, and the setting accuracy of the get-on point is further improved.
Further, in order to better illustrate the above process of setting the get-on point, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another method for setting the get-on point, as shown in fig. 2, where the method includes:
201. and responding to a get-on point setting instruction sent by the getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user.
Specifically, when a taxi taking user opens taxi taking software, position information and characteristic data of the user can be obtained, or when the taxi taking user opens taxi taking software, and clicks in a search area of a main interface of the taxi taking software, the position information and the characteristic data of the user are obtained, wherein the position information is longitude and latitude information of the taxi taking user when opening the taxi taking software, the position information can be positioned in a certain building, the position information and the characteristic data are input into a preset taxi taking point prediction model for taxi taking point prediction, a predicted taxi taking point output by the model is obtained, and the model outputs a taxi taking point through running of address information, such as an east door of a XX street XX district in XX district in XX city of XX province.
202. And determining a first characteristic vector corresponding to the position information and a second characteristic vector corresponding to the characteristic data.
Specifically, after obtaining position information and feature data of a taxi taking user, in order to improve prediction accuracy of a model, a first feature vector corresponding to the position information and a second feature vector corresponding to the feature data need to be determined. And then, the first feature vector and the second feature vector are input into a preset get-on point prediction model together to predict the get-on point, so that a predicted get-on point is obtained, and the predicted get-on point is recommended to a user, so that the situation that the get-on point is set incorrectly due to manual setting of the get-on point according to experience is avoided, and the setting accuracy of the get-on point is improved.
203. And fusing the first feature vector and the second feature vector to obtain a taxi taking fusion feature vector.
Specifically, after determining the first feature vector corresponding to the position information and the second feature vector corresponding to the feature data, in order to fuse the first feature vector and the second feature vector, the first feature vector and the second feature vector need to be fused, and specifically, a preset fusion function (such as a sort function) may be used to fuse the first feature vector and the second feature vector to obtain a taxi taking fusion feature vector, for example, the first feature vector is (1, 2, 3), the second feature vector is (5, 6), and then fuse the first feature vector and the second feature vector to obtain a fusion feature vector is (1, 2,3,5, 6).
204. And inputting the taxi taking fusion feature vector into a preset taxi taking point prediction model to predict a taxi taking point, so as to obtain a predicted taxi taking point corresponding to a taxi taking user.
Specifically, in order to predict a get-on point by using a preset get-on point prediction model, a preset get-on point prediction model needs to be constructed first, and based on this, the method includes: constructing at least one preset initial get-on point prediction model; acquiring sample position information and sample characteristic data corresponding to a sample taxi taking user and a corresponding sample actual taxi taking point; based on sample position information, sample characteristic data and corresponding actual sample vehicle points, a training set is constructed; and constructing a preset get-on point prediction model according to the training set. The method for constructing the preset get-on point prediction model according to the training set comprises the following steps: dividing the training set into a plurality of groups of training data and corresponding test data according to the number of the preset initial on-board point prediction models; training a corresponding preset initial get-on point prediction model by utilizing each group of training data to obtain each trained preset initial get-on point prediction model; sample position information and sample characteristic data corresponding to the same sample taxi taking user in each group of test data are input into a corresponding trained preset initial taxi taking point prediction model to conduct taxi taking point prediction, and a predicted sample taxi taking point is obtained; determining a backtracking value corresponding to each trained preset initial get-on point prediction model based on an actual sample get-on point and a predicted sample get-on point corresponding to the same sample get-on user, wherein the backtracking value is used for representing a prediction error of the corresponding preset initial get-on point prediction model; and filtering the trained preset initial get-on point prediction models according to the backtracking values to obtain preset get-on point prediction models.
The trace-back value is the absolute difference between the real data value of the same sample data and the sample prediction result. The preset initial order conversion rate prediction model is a numerical prediction model constructed based on a neural network.
Specifically, a plurality of preset initial get-on point prediction models are pre-built, sample position information and sample characteristic data of a sample get-on user are obtained, the sample get-on points corresponding to the sample get-on user are obtained, the data are determined to be a training set, then the training set is divided into a plurality of groups of training data and a plurality of groups of test data according to the number of the models, the corresponding preset initial get-on point prediction models are trained by the aid of the plurality of groups of training data, each trained preset initial get-on point prediction model is obtained, the test data are used for testing the corresponding trained preset initial get-on point prediction models, firstly, feature vectors corresponding to the sample position information of the sample get-on user in the test data and feature vectors corresponding to the sample characteristic data are determined, fusion feature vectors are obtained based on the feature vectors, then the sample get-on fusion feature vectors are input into the corresponding trained preset initial get-on point prediction models, the get-on points are predicted, then the actual sample get-on points corresponding to the same sample get-on point prediction models are determined, the corresponding actual sample get-on points corresponding to the same sample get-on point prediction models, the corresponding initial error values are traced to the corresponding initial error values, and the corresponding error values are determined. Further, after determining the backtracking value corresponding to each preset initial get-on point prediction model, determining the minimum backtracking value in each backtracking value, determining the preset initial get-on point prediction model corresponding to the minimum backtracking value as a preset get-on point prediction model, and predicting the get-on point of the user by using the established preset get-on point prediction model.
Further, the preset get-on point prediction model may specifically be a multi-layer sensor, which is a neural network model and includes an input layer, a hidden layer and an output layer.
For the embodiment of the present invention, after determining the taxi taking fusion feature vector, the feature vector may be input into a preset taxi taking point prediction model to perform taxi taking point prediction, based on which step 204 specifically includes: inputting the taxi taking fusion feature vector to the multilayer perceptron, and extracting the feature output by the last full-connection layer in the multilayer perceptron; and inputting the characteristics output by the last full-connection layer into a softmax layer in the multi-layer sensor to obtain the predicted get-on point corresponding to the taxi taking user.
Specifically, the taxi taking fusion feature vector is input to the hidden layer through the input layer of the multi-layer perceptron model, and the result output through the hidden layer is as follows:
f(W 1 x+b 1 )
wherein the output junctionThe result is the feature that the taxi taking fusion feature vector is output after the full connection of the preset taxi taking point prediction model, x is the taxi taking fusion feature vector, and w 1 B, as the weight of the hidden layer, is also the connection coefficient of the multi-layer sensor 1 For the bias factor of the hidden layer, the f-function may generally be a sigmoid function or a tanh function, as follows:
sigmoid(x)＝1/(1+e -x )
tanh(x)＝(e x -e -x )/(e 1 +e -x )
Further, after the taxi taking fusion feature vector is input to the hidden layer through the input layer of the multi-layer perceptron model to obtain a result output by the hidden layer, the result is input to the output layer, namely a softmax layer of the multi-layer perceptron, and taxi taking point prediction is carried out through the output layer, so that the obtained prediction result is as follows:
softmax(W 2 f(W 1 x+b 1 )+b 2 )
wherein W is 2 B is the weight coefficient of the output layer 2 And outputting a predicted get-on point corresponding to the taxi taking user through the output layer of the multi-layer perceptron model as the bias coefficient of the output layer.
205. And responding to a trigger signal of the taxi taking user on the predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point.
Specifically, after a predicted get-on point of a getting-on user is predicted by using a preset get-on point prediction model, the predicted get-on point is displayed to the user, if the user approves the predicted get-on point, the get-on point is clicked, and then a preset map corresponding to the get-on point is displayed.
206. And determining the same target point as the predicted upper vehicle point in the preset map, displaying the position information corresponding to the target point layer by layer, and determining the map position information displayed to the tail end in the position information displayed layer by layer.
Specifically, a point with the same position as the predicted position information is found in the map, wherein, in order to ensure the clear display of the map, each position on the map is displayed in the form of simple identification information, for example, after the target point with the same predicted position information is determined, the target point is displayed in the form of a highlight dot in the preset map, the user clicks layer by layer, the detailed position information (map position information) corresponding to the target point is displayed all the time, the user waits for a driver according to the displayed map position information to arrive at the corresponding position, and meanwhile, in order to display the accurate get-on position information to the driver, the system compares the map position information corresponding to the target point with the predicted position information to judge the accuracy of the predicted position information corresponding to the predicted get-on point.
207. Based on the map position information, whether the predicted position information corresponding to the predicted on-coming point is correct or not is judged.
For the embodiment of the invention, after determining the same target point as the predicted on-coming point in the preset map, it is necessary to determine whether the predicted position information corresponding to the predicted on-coming point is accurate based on the predicted position information corresponding to the preset on-coming point and the map position information corresponding to the target point, based on which the method comprises: determining a third feature vector corresponding to the predicted position information and a fourth feature vector corresponding to the map position information; calculating cosine similarity between the predicted position information and the map position information based on the third feature vector and the fourth feature vector; judging whether the cosine similarity is larger than a preset similarity threshold value or not; if the predicted position information is larger than the preset similarity threshold value, judging whether the predicted position information is the position information capable of stopping; if the predicted position information is the position information capable of stopping, the predicted position information corresponding to the predicted getting-on point is determined to be accurate.
The preset similarity threshold is set according to actual conditions, and the preset similarity threshold is a critical value at which a driver can quickly and accurately reach a boarding point of a passenger. Specifically, each first character contained in the predicted position information is determined, each second character contained in the map position information is determined, then embedding processing is carried out on each first character by using methods such as preset word embedding to obtain a third feature vector corresponding to the predicted position information, embedding processing is carried out on each second character by using a preset word embedding method to obtain a fourth feature vector corresponding to the map position information, and then cosine similarity between the predicted position information and the map position information is calculated based on the third feature vector and the fourth feature vector, wherein a specific calculation formula is as follows:
Figure BDA0004126370140000131
Wherein cos (θ) represents cosine similarity between predicted position information and map position information, x i Representing a third eigenvector, y, corresponding to the predicted position information i And the fourth feature vector corresponding to the map position information is represented, and the cosine similarity between the predicted position center and the map position information can be calculated according to the formula. Then judging whether the cosine similarity is larger than a preset similarity threshold value, if so, judging whether the predicted position information is a boarding point capable of being parked, if the position information is the stop-enabling point, the predicted position information is determined to be incorrect, and the predicted position information needs to be modified into the stop-enabling position information closest to the predicted position information according to the map information. If the predicted getting-on point is a getting-on point capable of being parked, the predicted position information is determined to be correct, and meanwhile, if the cosine similarity is smaller than or equal to a preset similarity threshold value, the predicted position information and the map position information are determined to have larger deviation, so that the parking point of a driver and the getting-on point waiting by a passenger are not located at the same position. Further, if the preset position information is a stop-enabling stop point, the cosine similarity between the predicted position information and the map position information is smaller than or equal to the preset similarity The threshold value is required to be corrected for the predicted position information corresponding to the predicted get-on point, and based on the threshold value, the method comprises the following steps: if the predicted position information corresponding to the predicted getting-on point is incorrect, correcting the predicted position information corresponding to the predicted getting-on point based on the position information corresponding to the point which is the same as the predicted getting-on point in the preset map, and determining the predicted getting-on point after correcting the position information as the target getting-on point corresponding to the getting-on user. And the taxi taking user reaches a taxi taking point according to the corrected position information.
Specifically, if the predicted position information corresponding to the on-vehicle point is different from the map position information corresponding to the corresponding point in the map, the predicted position information needs to be corrected according to the map position information, that is, the predicted position information is modified into the map position information, the corrected predicted position information is finally displayed at the blank position corresponding to the departure point, a taxi taking order is initiated, and after the driver receives the order, the taxi taking user is received at the corresponding position according to the predicted position information corresponding to the departure point.
208. And if the predicted position information corresponding to the predicted getting-on point is correct, determining the predicted getting-on point as the target getting-on point corresponding to the getting-on user.
Specifically, if the position information corresponding to the predicted get-on point is the same as the map position information, and the predicted get-on point is the get-on point capable of stopping, the predicted position information corresponding to the predicted get-on point is determined to be accurate, and the predicted position information corresponding to the predicted get-on point is directly displayed at a blank position corresponding to the departure point in the get-on order, so that a get-on user and a driver all go to the get-on point according to the same accurate position information, the problem that the get-on user and the driver reach different positions to cause the need of telephone communication with the junction again is avoided, the communication cost is avoided, and the get-on experience of the user is improved.
According to the setting method of the get-on point, compared with the mode of manually inputting the get-on point at present, the setting method of the get-on point obtains the position information and the characteristic data corresponding to the get-on user by responding to the get-on point setting instruction sent by the get-on user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to a get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; if the predicted position information corresponding to the get-on point is correct, the predicted get-on point is determined to be the target get-on point corresponding to the get-on user, so that the get-on point is predicted by inputting the position information and the characteristic data of the get-on user into a preset get-on point prediction model, the time consumed by manually inputting the get-on point is avoided, the setting efficiency of the get-on point is improved, the situation that the get-on point is set incorrectly due to negligence of the user can be avoided by the magnetic shoe, the setting accuracy of the get-on point is improved, and meanwhile, the get-on point predicted by the model is compared with the point at the same position in the map, and the setting accuracy of the get-on point is further improved.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides a device for setting a boarding point, as shown in fig. 3, where the device includes: an acquisition unit 31, a prediction unit 32, a presentation unit 33, a judgment unit 34, and a determination unit 35.
The acquisition unit 31. The method can be used for responding to the get-on point setting instruction sent by the getting-on user and obtaining the position information and the characteristic data corresponding to the getting-on user.
The prediction unit 32 may be configured to input the location information and the feature data into a preset get-on point prediction model to perform get-on point prediction, obtain a predicted get-on point corresponding to the getting-on user, and display the predicted get-on point to the getting-on user.
The display unit 33 may be configured to display a preset map within a preset range where the predicted get-on point is located, in response to a trigger signal of the get-on user to the predicted get-on point.
The judging unit 34 may be configured to judge whether the predicted position information corresponding to the predicted on-coming point is correct based on the preset map.
The determining unit 35 may be configured to determine the predicted get-on point as the target get-on point corresponding to the taxi taking user if the predicted position information corresponding to the predicted get-on point is correct.
In a specific application scenario, in order to construct a preset get-on point prediction model, as shown in fig. 4, the apparatus further includes: a construction unit 36.
The construction unit 36 may be configured to construct at least one preset initial get-on point prediction model.
The obtaining unit 31 may be further configured to obtain sample position information and sample feature data corresponding to a sample taxi taking user, and a sample actual taxi point corresponding to the sample position information and the sample feature data.
The construction unit 36 may be further configured to construct a training set based on the sample position information and sample feature data and the corresponding actual points of the sample.
The construction unit 36 may be specifically configured to construct the preset get-on point prediction model according to the training set.
In a specific application scenario, in order to construct a preset get-on point prediction model, the construction unit 36 includes a grouping module 361, a training module 362, a first prediction module 363, a first determination module 364, and a filtering module 365.
The grouping module 361 may be configured to divide the training set into a plurality of sets of training data and corresponding test data according to a number of preset initial driving point prediction models.
The training module 362 may be configured to train the corresponding preset initial driving point prediction model with each set of training data, to obtain each trained preset initial driving point prediction model.
The first prediction module 363 may be configured to input sample position information and sample feature data corresponding to the same sample taxi taking user in each set of test data into a corresponding trained preset initial taxi taking point prediction model to perform taxi taking point prediction, so as to obtain a predicted sample taxi taking point.
The first determining module 364 may be configured to determine a backtracking value corresponding to each trained preset initial on-coming point prediction model based on an actual on-coming point and a predicted on-coming point corresponding to the same sample on-coming user, where the backtracking value is used to characterize a prediction error of the corresponding preset initial on-coming point prediction model.
The filtering module 365 may be configured to filter each trained preset initial get-on-coming-point prediction model according to the backtracking value, to obtain the preset get-on-coming-point prediction model.
In a specific application scenario, in order to predict the get-on point for the taxi taking user, the prediction unit 32 includes a second determination module 321, a feature fusion module 322, and a second prediction module 323.
The second determining module 321 may be configured to determine a first feature vector corresponding to the location information and a second feature vector corresponding to the feature data.
The feature fusion module 322 may be configured to fuse the first feature vector and the second feature vector to obtain a taxi taking fusion feature vector.
The second prediction module 323 may be configured to input the taxi taking fusion feature vector into a preset taxi taking point prediction model to perform taxi taking point prediction, so as to obtain a predicted taxi taking point corresponding to the taxi taking user.
In a specific application scenario, in order to determine whether the predicted position information corresponding to the predicted on-coming point is correct, the determining unit 34 includes a third determining module 341 and a determining module 342.
The third determining module 341 may be configured to determine, in the preset map, a target point that is the same as the predicted upper vehicle point position, display, layer by layer, position information corresponding to the target point, and determine, in the position information displayed layer by layer, position information of the map displayed to the end.
The determining module 342 may be configured to determine whether the predicted position information corresponding to the predicted on-coming point is correct based on the predicted position information and the map position information.
In a specific application scenario, in order to determine whether the predicted position information corresponding to the predicted on-coming point is correct, the determining module 342 includes a determining sub-module, a calculating sub-module, a determining sub-module, and a determining sub-module.
The determining submodule may be used for determining a third feature vector corresponding to the predicted position information and determining a fourth feature vector corresponding to the map position information.
The calculating submodule may be used for calculating cosine similarity between the predicted position information and the map position information based on the third feature vector and the fourth feature vector.
The judging sub-module may be configured to judge whether the cosine similarity is greater than a preset similarity threshold.
The judging sub-module may be specifically configured to judge whether the predicted position information is position information that can be parked if the predicted position information is greater than the preset similarity threshold.
The judging submodule can be used for judging that the predicted position information corresponding to the predicted boarding point is accurate if the predicted position information is the position information capable of being parked.
In a specific application scenario, if the predicted position information corresponding to the predicted get-on point is incorrect, in order to correct the predicted position information, the apparatus further includes: a correction unit 37.
The correction unit 37 may be configured to correct the predicted position information corresponding to the predicted on-coming point based on the position information corresponding to the same point as the predicted on-coming point in the preset map if the predicted position information corresponding to the predicted on-coming point is incorrect, and determine the predicted on-coming point after the position information is corrected as the target on-coming point corresponding to the taxi-taking user.
It should be noted that, other corresponding descriptions of each functional module related to the setting device of the get-on point provided by the embodiment of the present invention may refer to corresponding descriptions of the method shown in fig. 1, which are not repeated herein.
Based on the above method as shown in fig. 1, correspondingly, the embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the following steps: responding to a get-on point setting instruction sent by a getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; and if the predicted position information corresponding to the predicted getting-on point is correct, determining the predicted getting-on point as the target getting-on point corresponding to the getting-on user.
Based on the embodiment of the method shown in fig. 1 and the device shown in fig. 3, the embodiment of the invention further provides a physical structure diagram of a computer device, as shown in fig. 5, where the computer device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, the processor 41 performing the following steps when said program is executed: responding to a get-on point setting instruction sent by a getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; and if the predicted position information corresponding to the predicted getting-on point is correct, determining the predicted getting-on point as the target getting-on point corresponding to the getting-on user.
According to the technical scheme, the method and the device acquire the position information and the characteristic data corresponding to the taxi taking user by responding to the taxi taking point setting instruction sent by the taxi taking user; inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to a get-on user, and displaying the predicted get-on point to the get-on user; responding to a trigger signal of a taxi taking user on a predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point; judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on a preset map; if the predicted position information corresponding to the get-on point is correct, the predicted get-on point is determined to be the target get-on point corresponding to the get-on user, so that the get-on point is predicted by inputting the position information and the characteristic data of the get-on user into a preset get-on point prediction model, the time consumed by manually inputting the get-on point is avoided, the setting efficiency of the get-on point is improved, the situation that the get-on point is set incorrectly due to negligence of the user can be avoided by the magnetic shoe, the setting accuracy of the get-on point is improved, and meanwhile, the get-on point predicted by the model is compared with the point at the same position in the map, and the setting accuracy of the get-on point is further improved.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a memory device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. The method for setting the boarding point is characterized by comprising the following steps:
Responding to a get-on point setting instruction sent by a getting-on user, and acquiring position information and characteristic data corresponding to the getting-on user;
inputting the position information and the characteristic data into a preset get-on point prediction model to predict a get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user;
responding to a trigger signal of the taxi taking user on the predicted taxi taking point, and displaying a preset map within a preset range of the predicted taxi taking point;
judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the preset map;
and if the predicted position information corresponding to the predicted get-on point is correct, determining the predicted get-on point as the target get-on point corresponding to the taxi taking user.
2. The method according to claim 1, wherein before the inputting the position information and the feature data into a preset get-on point prediction model to perform get-on point prediction, the method further comprises:
constructing at least one preset initial get-on point prediction model;
acquiring sample position information and sample characteristic data corresponding to a sample taxi taking user and a corresponding sample actual taxi taking point;
Constructing a training set based on the sample position information, the sample characteristic data and the corresponding sample actual vehicle points;
and constructing the preset get-on point prediction model according to the training set.
3. The method of claim 2, wherein constructing the preset get-on point prediction model from the training set comprises:
dividing the training set into a plurality of groups of training data and corresponding test data according to the number of preset initial get-on point prediction models;
training a corresponding preset initial get-on point prediction model by utilizing each group of training data to obtain each trained preset initial get-on point prediction model;
sample position information and sample characteristic data corresponding to the same sample taxi taking user in each group of test data are input into a corresponding trained preset initial taxi taking point prediction model to conduct taxi taking point prediction, and a predicted sample taxi taking point is obtained;
determining a backtracking value corresponding to each trained preset initial get-on point prediction model based on an actual sample get-on point and a predicted sample get-on point corresponding to the same sample get-on user, wherein the backtracking value is used for representing a prediction error of the corresponding preset initial get-on point prediction model;
And filtering each trained preset initial get-on point prediction model according to the backtracking value to obtain the preset get-on point prediction model.
4. The method of claim 1, wherein the inputting the location information and the feature data into a preset get-on point prediction model to predict a get-on point, and obtaining a predicted get-on point corresponding to the getting-on user comprises:
determining a first characteristic vector corresponding to the position information and a second characteristic vector corresponding to the characteristic data;
fusing the first feature vector and the second feature vector to obtain a taxi taking fusion feature vector;
and inputting the taxi taking fusion feature vector into a preset taxi taking point prediction model to predict a taxi taking point, and obtaining a predicted taxi taking point corresponding to the taxi taking user.
5. The method according to claim 1, wherein the determining whether the predicted position information corresponding to the predicted on-coming point is correct based on the preset map includes:
determining the same target point as the predicted on-vehicle point in the preset map, displaying position information corresponding to the target point layer by layer, and determining map position information displayed to the tail end in the position information displayed layer by layer;
And judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the map position information.
6. The method of claim 5, wherein determining whether the predicted location information corresponding to the predicted on-coming point is correct based on the predicted location information and the map location information comprises:
determining a third feature vector corresponding to the predicted position information and determining a fourth feature vector corresponding to the map position information;
calculating cosine similarity between the predicted position information and the map position information based on the third feature vector and the fourth feature vector;
judging whether the cosine similarity is larger than a preset similarity threshold value or not;
if the predicted position information is larger than the preset similarity threshold value, judging whether the predicted position information is the position information which can be parked;
and if the predicted position information is the position information capable of stopping, judging that the predicted position information corresponding to the predicted boarding point is accurate.
7. The method according to claim 1, wherein after the determining whether the predicted position information corresponding to the predicted on-coming point is correct based on the preset map, the method further comprises:
If the predicted position information corresponding to the predicted get-on point is incorrect, correcting the predicted position information corresponding to the predicted get-on point based on the position information corresponding to the point which is the same as the predicted get-on point in the preset map, and determining the predicted get-on point after correcting the position information as the target get-on point corresponding to the taxi taking user.
8. The setting device of get on a car the some, characterized by comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for responding to a get-on point setting instruction sent by a getting-on user and acquiring position information and characteristic data corresponding to the getting-on user;
the prediction unit is used for inputting the position information and the characteristic data into a preset get-on point prediction model to predict the get-on point, obtaining a predicted get-on point corresponding to the get-on user, and displaying the predicted get-on point to the get-on user;
the display unit is used for responding to the trigger signal of the taxi taking user on the predicted taxi taking point and displaying a preset map within a preset range where the predicted taxi taking point is located;
the judging unit is used for judging whether the predicted position information corresponding to the predicted get-on point is correct or not based on the preset map;
And the determining unit is used for determining the predicted get-on point as the target get-on point corresponding to the getting-on user if the predicted position information corresponding to the predicted get-on point is correct.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method according to any one of claims 1 to 7.
CN202310245901.6A 2023-03-06 2023-03-06 Method and device for setting boarding point, storage medium and computer equipment Pending CN116258267A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310245901.6A CN116258267A (en) 2023-03-06 2023-03-06 Method and device for setting boarding point, storage medium and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310245901.6A CN116258267A (en) 2023-03-06 2023-03-06 Method and device for setting boarding point, storage medium and computer equipment

Publications (1)

Publication Number Publication Date
CN116258267A true CN116258267A (en) 2023-06-13

Family

ID=86680777

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310245901.6A Pending CN116258267A (en) 2023-03-06 2023-03-06 Method and device for setting boarding point, storage medium and computer equipment

Country Status (1)

Country Link
CN (1) CN116258267A (en)

Similar Documents

Publication Publication Date Title
KR102414456B1 (en) Dialogue processing apparatus, vehicle having the same and accident information processing method
US20070276586A1 (en) Method of setting a navigation terminal for a destination and an apparatus therefor
CN106815574B (en) Method and device for establishing detection model and detecting behavior of connecting and calling mobile phone
CN110726417B (en) Vehicle yaw identification method, device, terminal and storage medium
CN108230720A (en) Parking management method and device
CN111750882B (en) Method and device for correcting vehicle pose during initialization of navigation map
CN111091215B (en) Vehicle identification method, device, computer equipment and storage medium
CN114022973B (en) Method, device, equipment and storage medium for processing vehicle faults
US11951976B2 (en) Method for automated parking, device, and storage medium
CN109215368B (en) Driving assistance method, device, equipment and computer storage medium
US10896676B2 (en) Server system, information system, and in-vehicle apparatus
CN116258267A (en) Method and device for setting boarding point, storage medium and computer equipment
CN113139139A (en) Method, apparatus, electronic device, and medium for determining boarding point
CN113449687A (en) Identification method and device for point of interest entrance and exit and electronic equipment
CN111527377A (en) Verification of digital maps
CN113066284A (en) Data processing method and data processing device
CN109270566B (en) Navigation method, navigation effect testing method, device, equipment and medium
CN113052397B (en) Method and device for determining boarding information, electronic equipment and storage medium
CN115209374B (en) Motor vehicle alarm system based on third party call center
US20220261942A1 (en) Method, information processing device, and system
CN108088449B (en) Method for planning navigation path and navigation equipment
CN116432067A (en) Automatic driving test scene extraction method and equipment based on deep embedded clustering
CN114166234A (en) System, method, device, processor and computer storage medium for selecting navigation route and road damage identification early warning based on road damage measurement
CN115062240A (en) Parking lot sorting method and device, electronic equipment and storage medium
CN108398702B (en) Parking environment identification method and device

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