WO2022116522A1 - Trip fusion method and apparatus, and vehicle - Google Patents

Abstract

A trip fusion method and apparatus, and a vehicle. Said method comprises: acquiring a trip to be fused, and on the basis of said trip, acquiring a time interval between a first time point and a second time point (S110), the first time point being the start time corresponding to said trip, and the second time point being the stop time corresponding to a previous trip to be fused; determining whether the time interval is less than a first time threshold (S120); if the time interval is less than the first time threshold, determining that said trip is a temporary trip (S130); fusing said trip with the previous trip, so as to obtain a target trip (S140); and storing the target trip (S150). According to the trip fusion method, it is determined whether a time interval is less than a first time threshold, so as to determine whether to fuse a trip to be fused with a previous trip, such that the accuracy of target trip acquisition can be improved to a certain extent.

Description

Trip fusion method, device, and vehicle

cross reference

The present application claims the priority of the prior application with the application number 202011398906.5 filed on December 1, 2020 and entitled "Travel Fusion Method, Device and Vehicle", the contents of which are incorporated into this text by way of reference .

technical field

The present invention relates to the technical field of electric vehicles, in particular to a method, device and vehicle for fusion of journeys.

Background technique

At present, in some business scenarios, users have the need to obtain vehicle itineraries, and when displaying relevant vehicle data to users, the data with the itinerary as the dimension is usually one of the most frequently appeared information, and the daily number of trips is also a user One of the more interesting information. Therefore, how to better obtain the itinerary information, so as to meet the different needs of the user through the itinerary information, is an urgent problem to be solved.

SUMMARY OF THE INVENTION

In view of the above problems, embodiments of the present invention provide a method, device and vehicle for itinerary fusion to solve the above technical problems.

The embodiment of the present invention is realized by adopting the following technical solutions:

In a first aspect, some embodiments of the present invention provide a itinerary fusion method, which is applied to a vehicle. The method includes: acquiring a itinerary to be fused, and acquiring a time interval between a first time and a second time based on the to-be-fused itinerary, where The first time is the start time corresponding to the trip to be fused, and the second time is the stop time of the previous trip corresponding to the to-be-fused; determine whether the time interval is less than the first time threshold; if the time If the interval is smaller than the first time threshold, the itinerary to be fused is determined as a temporary itinerary; the itinerary to be fused and the previous itinerary are fused to obtain a target itinerary; and the target itinerary is stored.

In a second aspect, some embodiments of the present invention further provide an apparatus for itinerary fusion, including an acquisition module, a first determination module, a second determination module, a fusion module, and a storage module. an acquisition module, configured to acquire the itinerary to be merged, and obtain the time interval between a first time and a second time based on the itinerary to be merged, where the first time is the start time corresponding to the itinerary to be merged, and the second time is the stop time of the previous trip corresponding to the to-be-fused. A first determination module, configured to determine whether the time interval is less than a first time threshold. A second determining module, configured to determine that the to-be-fused itinerary is a temporary itinerary if the time interval is less than the first time threshold. The fusion module is configured to fuse the to-be-fused itinerary with the previous itinerary to obtain a target itinerary. The storage module is used for storing the target itinerary.

In a third aspect, some embodiments of the present invention further provide an electronic controller, including a processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are called by the processor, execute any of the above Itinerary fusion method

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where computer program instructions are stored in the computer-readable storage medium, and the computer program code can be invoked by a processor to execute any one of the above-mentioned stroke fusion methods.

In the itinerary fusion method, device, and vehicle provided by the embodiments of the present invention, by obtaining the time interval between the first time and the second time, the present invention can more quickly and effectively determine whether to combine the to-be-fused itinerary with the previous itinerary. Specifically, the present invention can first obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, wherein the first time is the start time corresponding to the itinerary to be merged, and the second time is the start time of the itinerary to be merged The stop time of the corresponding previous trip, and then the present invention can determine whether the time interval between the first time and the second time is less than the first time threshold, and if it is less than the first time threshold, it is determined that the trip to be merged is a temporary trip, and then A target itinerary is obtained by merging the itinerary to be fused with the previous itinerary, and finally the application can store the target itinerary. The present invention determines whether to fuse the to-be-fused itinerary with the previous itinerary by judging whether the time interval between the first time and the second time is less than the first time threshold, which can improve the accuracy of the itinerary acquisition to a certain extent, Thus, the user experience can be improved.

These and other aspects of the invention will be more clearly understood from the description of the following embodiments.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 shows a schematic diagram of an application environment provided according to an embodiment of the present invention.

FIG. 2 shows a schematic flowchart of a stroke fusion method provided by an embodiment of the present invention.

FIG. 3 shows a schematic flowchart of a stroke fusion method provided by another embodiment of the present invention.

FIG. 4 shows an example diagram of obtaining a time threshold in a stroke fusion method provided by another embodiment of the present invention.

FIG. 5 shows a schematic flowchart of step S250 in a stroke fusion method provided by another embodiment of the present invention.

FIG. 6 shows a schematic flowchart of a stroke fusion method provided by another embodiment of the present invention.

FIG. 7 shows a schematic flowchart of step S370 in a method for itinerary fusion provided by another embodiment of the present invention.

FIG. 8 shows a block diagram of a module of a stroke fusion apparatus provided by an embodiment of the present invention.

FIG. 9 shows a module block diagram of an electronic controller provided by an embodiment of the present invention.

FIG. 10 shows a module block diagram of a computer-readable storage medium provided by an embodiment of the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the present invention, and should not be construed as a limitation of the present invention.

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the present invention, and should not be construed as a limitation of the present invention.

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

The following is an introduction to the application environment of the itinerary fusion method provided by the implementation of the present invention:

Referring to FIG. 1 , a vehicle control method provided in an embodiment of the present invention can be applied to a control system 10 of a vehicle. The control system 10 of the vehicle may include a vehicle 11 and a server 12 , wherein the vehicle 11 may be connected to the server 12 for communication , that is, the vehicle 11 can send data to the server 12 , and can also receive data sent by the server 12 . In addition, the server 12 may be a background server, which may be a TSP (Telematics Service Provider, telematics service provider) background, and the server 12 is configured to be connected to the vehicle 11 for communication and to receive data uploaded by the vehicle 11 , and send the data analysis result to the vehicle 11 according to the data. Optionally, the number of vehicles 11 may be one or multiple.

At present, when displaying relevant vehicle data to users, the data with the dimension of travel as the dimension is usually one of the data with the highest frequency, and the number of daily trips is also one of the information that the user cares about. Due to the loss of signal and the possibility that the user may get off the bus for a short time in the middle, one trip of the user may be cut into multiple different trips, and the trip merging operation needs to be performed at this time. The existing itinerary merging algorithm instructs to merge different itineraries according to the interval of the itineraries. However, there is no way to merge some transit point itineraries that stay too long, which also makes the itinerary merging algorithm rough and not intelligent enough. , the user experience is not high.

In order to solve the above-mentioned technical problems, the inventor, after long-term research, proposes a method, device, and vehicle for travel fusion in the embodiments of the present invention. Effectively determine whether to combine the trip to be fused with the previous trip. Specifically, the present invention can first obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, wherein the first time is the start time corresponding to the itinerary to be merged, and the second time is the start time of the itinerary to be merged The stop time of the corresponding previous trip, and then the present invention can determine whether the time interval between the first time and the second time is less than the first time threshold, and if it is less than the first time threshold, it is determined that the trip to be merged is a temporary trip, and then A target itinerary is obtained by merging the itinerary to be fused with the previous itinerary, and finally the application can store the target itinerary. The present invention determines whether to fuse the to-be-fused itinerary with the previous itinerary by judging whether the time interval between the first time and the second time is less than the first time threshold, which can improve the accuracy of the itinerary acquisition to a certain extent, Thus, the user experience can be improved.

As shown in FIG. 2 , FIG. 2 schematically shows a schematic flowchart of a stroke fusion method provided by an embodiment of the present invention. The method may include the following steps S110 to S150.

Step S110: Obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged.

In some embodiments, the electronic controller of the vehicle may acquire multiple itineraries to be merged, and the itineraries to be merged may be stored in the memory of the vehicle, or may be stored in a server, which communicates with the vehicle through wired or wireless communication. way to connect with the vehicle. As an approach, the vehicle may acquire the newly acquired itinerary to be fused every preset time period, and the newly acquired itinerary to be fused may be based on the itinerary after the last acquired itinerary to be fused. For example, the itinerary to be merged acquired by the vehicle at 17:00 on November 23, 2020 may be all the itineraries generated between 00:00 on October 23, 2020 and 17:00 on November 23, 2020.

In other embodiments, the trip to be merged may include trip start time, trip end time, trip start location latitude, vehicle trip end location latitude, trip start location longitude, vehicle trip end location longitude, and trip duration (unit: seconds) ), travel distance, SOC (State Of Charge State, state of charge) at the beginning of the trip, SOC at the end of the trip, kilometers traveled at the beginning, kilometers traveled at the end of the trip, drivable kilometers at the beginning of the trip, and the end of the trip The number of kilometers that can be driven, etc. As a way, different itineraries to be merged can be distinguished by the time when the itinerary is generated. For example, the start time of the itinerary can be used as the unique identifier of the itinerary to be merged, and the end time of the itinerary can be used as the unique identifier of the itinerary to be merged. , or the start time and end time of the itinerary can also be used as the unique identifier of the itinerary to be merged. For example, the start time of itinerary A is 17:00 on November 23, 2020, and the end time is 18:00 on November 23, 2020. At this time, the logo of itinerary A can be set as: 2020/11/23/17: 00～2020/11/23/18:00. In addition, in order to make the acquisition of itinerary A more accurate, the identifier of the itinerary can also be accurate to minutes or seconds. Specifically, how to set the identifier of the itinerary through the start time or end time of the itinerary is not limited here and can be selected according to the actual situation.

As another way, in this embodiment of the present invention, different itineraries to be fused can also be distinguished by configuring different itinerary identifiers for each of the itineraries to be fused. The configuration can be determined in combination with the location of the trip, the time of the trip, and the number of kilometers traveled. In addition, the identifier corresponding to the fusion itinerary may also be an identifier manually given by the user according to its usage.

It can be known from the above description that each itinerary to be merged may include a start time and an end time of the itinerary. Therefore, after obtaining the itinerary to be merged, the vehicle can obtain the start time (start time) corresponding to the itinerary, which may be called the first time, and then the embodiment of the present invention may obtain the stop time of the migration itinerary corresponding to the itinerary to be merged (end time), the stop time is regarded as the second time. The stroke to be merged and the previous stroke may constitute a continuous stroke, that is, there is no other stroke between the stroke to be merged and the previous stroke. In other words, after the vehicle in the previous trip is stopped, the trip generated when the vehicle is started again is the trip to be merged.

Step S120: Determine whether the time interval is less than a first time threshold.

In some embodiments, after obtaining the time interval between the first time and the second time, the vehicle can determine whether the time interval is less than a first time threshold, where the first time is the start time corresponding to the itinerary to be merged, The second time is the stop time of the previous trip corresponding to the to-be-fused. In addition, the first time threshold can be set based on experience, or can be determined based on the usage habits of the user corresponding to the vehicle, or can also be determined based on the age of the user corresponding to the vehicle. The older the age, the more the first time threshold can be set. big. For example, if the user's age is about 20-30 years old, the first time threshold can be set to 5 minutes, and if the user's age is about 60-70 years old, the first time threshold can be set to 10 minutes Wait.

In other embodiments, the first time threshold may also be determined according to the gender of the user who uses the vehicle. When the gender of the user is female, the corresponding first time threshold may be 10 minutes, and when the gender of the user is male, the corresponding first time threshold may be 10 minutes. The first time threshold may be 5 minutes. In addition, the first time threshold may also be input by the user according to the actual situation. How to set the first time threshold is not specifically limited here, and can be set according to the usage.

In some embodiments, when the vehicle determines that the time interval between the first time and the second time is less than the first time threshold, it may determine that the trip to be merged is a temporary trip, that is, step S120 is entered. If the time interval between the first time and the second time is greater than the first time threshold, the embodiment of the present invention may re-acquire the itinerary to be merged, and may also determine whether the time interval is greater than the second time threshold, or the like.

Step S130: Determine that the to-be-fused itinerary is a temporary itinerary.

In some implementation manners, when the determined time interval is less than the first time threshold, the embodiments of the present invention may determine that the to-be-fused trip is a temporary trip, where the temporary trip refers to a trip generated by the user temporarily stopping while driving. For example, a trip generated by a user temporarily stopping to answer a phone while driving is a temporary trip. Because the temporary itinerary is a temporary itinerary generated by the user while driving through the car, the itinerary is not very useful for analyzing the user's behavior and habits. Therefore, when it is determined that the itinerary to be merged is a temporary itinerary, the embodiment of the present invention may Integrate with the previous itinerary to obtain the target itinerary, that is, go to step S140.

In other embodiments, when it is determined that the time interval between the first time and the second time is less than the first time threshold, the embodiment of the present invention may also acquire the POI information (Point of Information) of the location of the vehicle at the first time , information point), and then determine whether the location of the vehicle is the first designated location according to the POI information, the scene corresponding to the first designated location is the user's interest scene, and the POI information may include the interest scene. Name, location coordinates, category and classification, etc. It can be a house, a shop, a mailbox or a bus stop, etc.

In other embodiments, when the vehicle determines that the time interval between the first time and the second time is less than the first threshold, the vehicle may determine whether to fuse the information to be fused with the previous itinerary according to scene information corresponding to the first time. The scene corresponding to the first time may be a scene where the user goes to and from get off work, a scene when he goes shopping in a supermarket, and the like.

In the embodiment of the present invention, when it is determined that the location of the vehicle is not the first designated location, the itinerary to be merged is determined to be a temporary itinerary, and the to-be-fused itinerary and the previous itinerary are fused to obtain the target itinerary, that is, the first time corresponding to When the scene that is not the user's interest scene, the to-be-fused itinerary and the previous itinerary are fused. In addition, when the location of the vehicle is the first designated location, it is determined that the itinerary to be merged is a non-temporary itinerary, and the itinerary to be merged is taken as the target itinerary, that is, when the scene corresponding to the first time is the user's interest scene, It is not necessary to fuse the to-be-fused stroke and the previous stroke, it is only necessary to regard the to-be-fused stroke and the previous stroke as two front and rear strokes.

Step S140: Integrate the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

As one way, the to-be-fused itinerary and the previous itinerary are fused, which may also be referred to as merging the to-be-fused itinerary and the previous itinerary. Specifically, the start time of the previous itinerary can be used as the start time of the target itinerary, and the end time corresponding to the itinerary to be merged can be used as the end time of the target itinerary; Take the longitude and latitude of the end position of the trip to be merged as the longitude and latitude of the end position of the target trip; take the sum of the previous trip duration and the duration of the trip to be integrated as the duration of the target trip; take the sum of the travel distance of the previous trip and the travel distance of the trip to be merged as Distance of the target trip; take the SOC at the beginning of the previous trip as the SOC at the beginning of the target trip, and the SOC at the end of the previous trip as the SOC at the end of the target trip; take the number of kilometers traveled at the beginning of the previous trip as the target The number of kilometers traveled at the beginning of the trip, and the number of kilometers traveled at the end of the to-be-fused trip as the number of kilometers traveled at the end of the target trip; the number of kilometers traveled at the beginning of the previous trip as the number of kilometers traveled at the beginning of the target trip, and Take the drivable kilometers at the end of the to-be-integrated trip as the drivable kilometers at the end of the target trip, etc.

In some other implementations, after the itinerary to be merged and the previous itinerary are fused to obtain the target itinerary, the itinerary identifier corresponding to the itinerary to be merged may be used as the itinerary identifier corresponding to the target itinerary, or the previous itinerary may correspond to The itinerary identifier corresponding to the target itinerary, or the sum of the itinerary identifier corresponding to the itinerary to be merged and the itinerary identifier corresponding to the previous itinerary can also be used as the itinerary identifier corresponding to the target itinerary. clearly restricted. It should be noted that, in the process of merging the itinerary to be merged with the previous itinerary to obtain the target itinerary, it is necessary to ensure that the merged itinerary information is compatible with the information of a single itinerary.

Step S150: Store the target itinerary.

In the embodiment of the present invention, after the to-be-fused itinerary and the previous itinerary are fused to obtain the target itinerary, the vehicle may store the target itinerary. Specifically, the vehicle may store the specific information corresponding to the target itinerary in In the memory of the vehicle, or the specific information corresponding to the target itinerary may also be sent to the server to instruct the server to store the specific information.

In other implementations, after acquiring multiple target itineraries, the vehicle or the server may also analyze the target itineraries, thereby realizing the mining of the user's travel habits. Specifically, in this embodiment of the present invention, a travel record of a user within a preset time period may be obtained, and the preset time period may be 30 days, and the travel record may include multiple target itineraries and information related thereto, and then the vehicle may The gps information in the travel record is processed by geohash, and the POI information association operation is performed at the same time, that is, the POI information is associated with the gps address of the user's travel. The purpose of the association is to mine the user's travel behavior, and the mining of this behavior can be more It is good to recommend routes to users, recommend products, and do something for users in advance. For example, inform the weather conditions of the destination, predict that the user is about to leave work, turn on the air conditioner in advance, and so on.

To sum up, the present invention can obtain the information such as departure place and transit place used by the user by analyzing the itinerary within the preset time period after obtaining the target itinerary. Hash is performed, and then the information of these locations in a certain period is counted. At the same time, the embodiment of the present invention can also mine personalized information such as the travel distribution, time-consuming distribution, and frequently traveled routes of the user's travel, and these information will be updated on a daily basis to automatically adapt to Changes in user habits.

By acquiring the time interval between the first time and the second time in the itinerary fusion method provided by the embodiment of the present invention, it can more quickly and effectively determine whether to perform the to-be-fused itinerary with the previous itinerary. Specifically, the present invention can first obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, wherein the first time is the start time corresponding to the itinerary to be merged, and the second time is the start time of the itinerary to be merged The stop time of the corresponding previous trip, and then the present invention can determine whether the time interval between the first time and the second time is less than the first time threshold, and if it is less than the first time threshold, it is determined that the trip to be merged is a temporary trip, and then A target itinerary is obtained by merging the itinerary to be fused with the previous itinerary, and finally the application can store the target itinerary. The present invention determines whether to fuse the to-be-fused itinerary with the previous itinerary by judging whether the time interval between the first time and the second time is less than the first time threshold, which can improve the accuracy of the itinerary acquisition to a certain extent, Thus, the user experience can be improved.

As shown in FIG. 3 , another embodiment of the embodiment of the present invention provides a stroke fusion method, which can be applied to a vehicle, and includes the following steps S210 to S270 .

Step S210: Acquire the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged.

Step S220: Determine whether the time interval is less than a first time threshold.

In some embodiments, when it is determined that the time interval between the first time and the second time is less than the first time threshold, it may be determined that the to-be-fused trip is a temporary trip, that is, step S230 is entered. In addition, if the time interval between the first time and the second time is greater than or equal to the first time threshold, this embodiment of the present invention may determine whether the time interval is greater than the second time threshold. Wherein, the second time threshold is greater than the first time threshold, and the second time threshold may be set according to experience, or may be determined according to the usage habits of the user corresponding to the vehicle, or may also be determined according to the attributes of the user corresponding to the vehicle, such as the age of the user , gender, etc. to set the second time threshold. To sum up, in this embodiment of the present invention, the first time threshold and the second time threshold may be set in different ways.

In other implementations, the embodiment of the present invention can also determine the first time threshold and the second time threshold by analyzing the travel interval distribution. Please refer to FIG. 4 for details. It can be known from FIG. Select different threshold intervals for cutting, and then verify through the manually marked verification set, and after verification that there is no problem, the embodiment of the present invention can relax the threshold, perform verification again, and repeat this step until the accuracy rate drops to the set value. The interval stops. On this basis, the effect comparison of different threshold intervals can be realized, and finally the first time threshold and the second time threshold interval can be determined. The first time threshold in FIG. 4 may be 5 minutes, and the second time threshold may be 20 minutes.

Step S230: Determine that the to-be-fused itinerary is a temporary itinerary.

Step S240: Determine whether the time interval is greater than a second time threshold.

As one way, when it is determined that the time interval between the first time and the second time is less than the first time threshold, the embodiment of the present invention may determine whether the time interval between the first time and the second time is greater than the second time threshold, if If it is greater than the second time threshold, it is determined that the to-be-fused itinerary is a non-temporary itinerary, and the to-be-fused itinerary is taken as the target itinerary, that is, step S250 is entered. In addition, if the time interval between the first time and the second time is less than the second time threshold, the itinerary to be merged is acquired again, that is, step S210 is entered.

Step S250: Determine that the to-be-fused itinerary is a non-temporary itinerary, and use the to-be-fused itinerary as a target itinerary.

In other embodiments, when it is determined that the time interval between the first time and the second time is greater than the second time threshold, the embodiment of the present invention may also determine whether to Fusion of the to-be-fused itinerary and the previous itinerary is specifically shown in FIG. 5 . As can be seen from FIG. 5 , step S250 may include steps S251 to S254 .

Step S251 : if the time interval is greater than the second time threshold, acquire the information point of the location of the vehicle at the first time.

It can be known from the above introduction that the information point of the location of the vehicle at the first time may include the name, location coordinates, category and classification of the scene corresponding to the location, and the time point of the location of the vehicle at the first time is obtained. Afterwards, the embodiment of the present invention may determine whether the location of the vehicle is the second designated location according to the information point, that is, step S252 is entered.

Step S252: Determine whether the location of the vehicle is a second designated location according to the information point.

As a way, the embodiment of the present invention can determine whether the location of the vehicle is the second designated location according to the POI information of the location of the vehicle at the first time point, or determine whether the scene corresponding to the location of the vehicle is the designated scene, if it is the designated location In the scenario, the to-be-fused itinerary and the previous itinerary are fused to obtain the target itinerary, that is, step S253 is entered, wherein the specified scenario may be a highway service station, a gas station, or the like. If it is not the specified scene, it is determined that the to-be-fused itinerary is a non-temporary itinerary, and the to-be-fused itinerary is taken as the target itinerary, that is, step S254 is entered.

Step S253: Integrate the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

Step S254: Determine that the to-be-fused itinerary is a non-temporary itinerary, and use the to-be-fused itinerary as a target itinerary.

Step S260: Integrate the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

Step S270: Store the target itinerary.

By acquiring the time interval between the first time and the second time in the itinerary fusion method provided by the embodiment of the present invention, it can more quickly and effectively determine whether to perform the to-be-fused itinerary with the previous itinerary. Specifically, the present invention can first obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, wherein the first time is the start time corresponding to the itinerary to be merged, and the second time is the start time of the itinerary to be merged The stop time of the corresponding previous trip, and then the present invention can determine whether the time interval between the first time and the second time is less than the first time threshold, and if it is less than the first time threshold, it is determined that the trip to be merged is a temporary trip, and then A target itinerary is obtained by merging the itinerary to be fused with the previous itinerary, and finally the application can store the target itinerary. The present invention determines whether to fuse the to-be-fused itinerary with the previous itinerary by judging whether the time interval between the first time and the second time is less than the first time threshold, which can improve the accuracy of the itinerary acquisition to a certain extent, Thus, the user experience can be improved. In addition, in the embodiment of the present invention, by combining the first time threshold and the second time threshold, the final acquired target itinerary can be more accurate, and can better meet the actual needs of the user.

As shown in FIG. 6 , another embodiment of the present invention provides a stroke fusion method, which can be applied to a vehicle, and includes the following steps S310 to S390 .

Step S310: Acquire the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged.

Step S320: Determine whether the time interval is less than a first time threshold.

As one way, when the determined time interval is smaller than the first time threshold, the embodiment of the present invention may determine that the trip to be merged is a temporary trip, that is, enter step S330, and when the time interval between the first time and the second time is greater than the first time When the threshold value is greater than the second time threshold value, it is determined that the to-be-fused itinerary is a non-temporary itinerary, and the to-be-fused itinerary is taken as the target itinerary, that is, step S350 is entered.

Step S330: Determine that the to-be-fused itinerary is a temporary itinerary.

Step S340: Determine whether the time interval is greater than a second time threshold.

Step S350: Determine that the to-be-fused itinerary is a non-temporary itinerary, and use the to-be-fused itinerary as a target itinerary.

Step S360: Determine whether the information point of the location of the vehicle at the first time is obtained.

Step S370: Find the number of times that the vehicle appears at the position corresponding to the first time, and when the number of times is greater than a preset number of times, fuse the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

As one way, when it is determined that the time interval between the first time and the second time is greater than the first time threshold and less than the second time threshold, the embodiment of the present invention may search for the number of times the vehicle appears at the position corresponding to the first time, and determine Whether the number of times is greater than the preset number of times, if it is greater than the preset number of times, the to-be-fused stroke and the previous stroke are fused to obtain the target stroke. In addition, when the number of times the vehicle appears at the corresponding location at the first time is less than or equal to the preset number of times, the present invention can obtain the information point that is the location of the vehicle at the first time, as shown in FIG. 7 , and it can be seen from FIG. 7 , step S370 may include steps S371 to S374.

Step S371: If the number of times is less than or equal to a preset number of times, acquire the information point of the location of the vehicle at the first time.

In the embodiment of the present invention, when the number of times is less than or equal to the preset number of times, the vehicle can obtain the information point of the location of the vehicle at the first time, and input the information point into the machine learning model, through the machine learning model It is determined whether the to-be-fused itinerary is a temporary itinerary, that is, step S372 is entered.

Step S372: Use a machine learning model to determine whether the information point is a fused information point.

As a method, before using a machine learning model to determine whether the information point is a fused information point, the embodiment of the present invention may first obtain the machine learning model, specifically, first obtain a model training data set, and the model training The data set can be a common data set, or it can be data obtained by the user through manual labeling. First, the itinerary information can be sampled to obtain a preset number of sampling points, the preset number can be 15, and then on the map. Display the itinerary above, and then combine the POI information to realize the data collection. In addition, the trip data may also be acquired by means such as an internal vehicle survey.

In a specific embodiment, each itinerary can be divided into equal distances, for example, divided into 20 segments, then 2 segments from the beginning to the end, and the first GPS point of each segment in the remaining 16 segments is taken as a representative Via points, the route of the itinerary can be drawn on the map by using the information of these waypoints, and the route information and POI information displayed on the map are used to label these itineraries whether they need to be merged. Sampling over the phone ensures the accuracy of the labelling.

As another method, after the training data set is obtained, the embodiment of the present invention may input the training data set into the primary network, and use the training data set to train the primary network to obtain a machine learning model. The features used can be processed first, specifically including hashing the GPS geographic location information, normalizing the number of occurrences of transit points and initial points in the historical itinerary to between 0 and 1, and comparing the GPS information with POI information to associate and other operations.

As an example, in this embodiment of the present invention, characteristic data may be acquired by using the user's itinerary data and the information filled in by the user. For example, extract the gps information of different users' homes and companies, the hash value of 16 gps points for each trip, the POI information of the trip start point and end point, the normalized characteristics of the trip start time and end time, and the trip interval, etc. According to these data, the embodiment of the present invention can also extract the interval time of each trip of the user in the past 90 days, 30 days, and 7 days, the stay time at the POI point, and the hash value of the gps point of the user's frequent route. After acquiring these characteristic data, the embodiment of the present invention can implement the training of the machine learning model.

In addition, before training the primary network, the embodiment of the present invention may select different network algorithms for joint training, and then select an algorithm with better effect from among them as the algorithm for training the machine learning model. Wherein, the algorithm may include LR, GBDT, XGboost and so on. Among them, GBDT is a model integrated by multiple base classifiers. The base classifiers mostly use the CART binary tree classifier, and Gradient Boosting is a progressive combination method. Each new classifier is in the previous classifier. LR is logistic regression analysis, which is a generalized linear regression analysis model, which is often used in data mining, economic forecasting and other fields. Logistic regression is essentially a binary classification problem and is based on the Sigmoid function (also known as "Sigmoid function") supervised two-class classification model; Adaboost is an iterative algorithm, its core idea is to train different classifiers (weak classifiers) for the same training set, and then aggregate these weak classifiers, A stronger final classifier (strong classifier) is formed, and the new data set with modified weights is sent to the lower classifier for training, and finally the classifiers obtained each time are finally fused as the final decision classifier.

As a method, in the embodiment of the present invention, the training data set can be fitted by the method of LR+GBDT, that is, the GBDT is used to fit the samples, and then the combined features with strong analysis are extracted from the generated trees. Then fuse these features with the original features, and finally use LR to fit these data sets and features. During this process, the embodiment of the present invention can also calculate a result value through the Adaboost model, in the case where the confidence level of LR is at the fuzzy boundary You can refer to the value of the Adaboost model below, so that the final obtained machine learning model can more accurately judge the fusion itinerary.

It should be noted that, after the machine learning model is obtained and goes online, the embodiment of the present invention can also continuously optimize the machine learning model according to user feedback and manual spot checks, so as to ensure the continuous effectiveness and stability of the model. For example, data adoption, cleaning, feature extraction and other tasks are automatically completed every 3 days, and then the machine learning model will be automatically trained. After the machine learning model is trained, the data in the training data set will be randomly selected for testing, as long as the accuracy rate is high. If the preset threshold interval of the previous model is exceeded, the embodiment of the present invention will replace the original model. If the preset threshold is not exceeded, the original machine learning model will remain unchanged. If the effect of the machine learning model does not improve for one month in a row , there will be manual intervention to check the relevant data and adjust the relevant model parameters, so as to achieve the accurate acquisition of the target itinerary.

Step S373: Integrate the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

Step S374: Use the to-be-fused itinerary as a target itinerary.

Step S380: Integrate the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

Step S390: Store the target itinerary.

It can be known from the above introduction that two kinds of rules are adopted in the embodiment of the present invention when judging whether to fuse the itinerary to be fused with the previous itinerary, the first rule can be called expert rule, and the second rule can be called machine learning When the relevant information corresponding to the itinerary to be merged is obtained, the embodiment of the present invention can first judge by expert rules. When the expert rules cannot determine whether the itinerary to be merged can be merged with the previous itinerary, machine learning can be used rule to judge. The expert rule can determine whether the time interval between the first time and the second time is less than the first time threshold, or whether it is greater than the second time threshold.

To sum up, when the itinerary to be merged is to be acquired, the embodiment of the present invention can first extract a preset number of gps sampling points corresponding to the itinerary, calculate the POI information of the starting point and the ending point, and the interval from the end of the previous itinerary. duration, where the preset number can be 16. Then use the expert rule to judge, if the expert gives a conclusion of merger or non-merge, the conclusion of the expert rule is adopted; if the expert rule gives an uncertain conclusion, the calculated itinerary characteristics and user id are passed to the machine learning model. Finally, the results of the machine learning model are used to determine whether to perform the trip fusion operation.

As a specific example, if the time interval between the first time and the second time is less than 2 minutes, they will be merged directly. For example, if the car owner suddenly stops to answer the phone and drives immediately, then this trip and the previous trip will be regarded as the same trip. , the time interval of 2 minutes is very short, and it can be considered that the two trips before and after can be combined from the perception. If it is greater than 20 minutes, it will not be merged, because of how long the interval between the front and rear trips is, it can be considered that the front and rear trips are separated from the perception. If it is between 2 and 20 minutes, obtain the POI information of the starting point of the itinerary, and determine whether the POI information is empty. If the POI information is empty, it is not a residential, commercial, station, etc., merge the itinerary, that is, determine whether the POI can be obtained. For example, if the vehicle stayed on the side of the road for ten minutes, and there is no information that can be mined at this starting point, it can be considered that the front and rear are the same trip. If the POI information is not empty, according to the owner's historical behavior, for example, the owner will send the child to the kindergarten on the way to work every day, and will stay in the kindergarten for a short time. journey. If the POI information is not empty, the owner's historical travel habits are obtained. If the owner's history has more than 5 short stops at the POI location, the itinerary will be merged, otherwise the machine learning model will be called for judgment.

By acquiring the time interval between the first time and the second time in the itinerary fusion method provided by the embodiment of the present invention, it can more quickly and effectively determine whether to perform the to-be-fused itinerary with the previous itinerary. Specifically, the present invention can first obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, wherein the first time is the start time corresponding to the itinerary to be merged, and the second time is the start time of the itinerary to be merged The stop time of the corresponding previous trip, and then the present invention can determine whether the time interval between the first time and the second time is less than the first time threshold, and if it is less than the first time threshold, it is determined that the trip to be merged is a temporary trip, and then A target itinerary is obtained by merging the itinerary to be fused with the previous itinerary, and finally the application can store the target itinerary. The present invention determines whether to fuse the to-be-fused itinerary with the previous itinerary by judging whether the time interval between the first time and the second time is less than the first time threshold, which can improve the accuracy of the itinerary acquisition to a certain extent, Thus, the user experience can be improved. In addition, in the embodiment of the present invention, by combining the first time threshold and the second time threshold, the final acquired target itinerary can be more accurate, and can better meet the actual needs of the user. In addition, the embodiments of the present invention can combine the itineraries more intelligently by combining expert rules and machine learning rules.

As shown in FIG. 8 , an embodiment of the present invention further provides a journey fusion apparatus 400 , the journey fusion apparatus 400 includes an acquisition module 410 , a first determination module 420 , a second determination module 430 , a fusion module 440 and a storage module 450 .

The obtaining module 410 is configured to obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, the first time is the start time corresponding to the itinerary to be merged, the second time Time is the stop time of the previous trip corresponding to the to-be-fused.

The first determination module 420 is configured to determine whether the time interval is less than a first time threshold.

The second determination module 430 is configured to determine that the to-be-fused itinerary is a temporary itinerary if the time interval is less than the first time threshold.

The fusion module 440 is configured to fuse the to-be-fused itinerary with the previous itinerary to obtain a target itinerary.

Optionally, the fusion module 440 may be further configured to acquire the information point of the location of the vehicle at the first time if the time interval is less than the first time threshold, and determine the information point according to the information point. whether the location of the vehicle is the first designated location, the scene corresponding to the first designated location is the user's interest scene, and if the location of the vehicle is the first designated location, it is determined that the itinerary to be merged is a non-temporary itinerary, Taking the to-be-fused itinerary as the target itinerary, if the location of the vehicle is not the first designated location, then determine the to-be-fused itinerary as a temporary itinerary, and fuse the to-be-fused itinerary with the previous itinerary to obtain the target journey.

The storage module 450 is configured to store the target itinerary.

Optionally, the apparatus 400 is further configured to determine whether the time interval is greater than the second time threshold if the time interval is greater than the first time threshold, and determine whether the time interval is greater than the second time threshold if the time interval is greater than the second time threshold. The to-be-fused itinerary is a non-temporary itinerary, and the to-be-fused itinerary is used as a target itinerary.

Optionally, the apparatus 400 is further configured to acquire an information point of the location of the vehicle at the first time if the time interval is greater than the second time threshold; and determine the location of the vehicle according to the information point. Whether the location is the second designated location, the scene corresponding to the second designated location is a temporary parking scene; if the location of the vehicle is the second designated location, the to-be-fused itinerary and the previous itinerary are fused, A target itinerary is obtained; if the location of the vehicle is not the second designated location, it is determined that the itinerary to be merged is a non-temporary itinerary, and the itinerary to be merged is used as a target itinerary.

Optionally, the device 400 is further configured to, if the time interval is less than or equal to the second time threshold, determine whether to obtain the information point of the location of the vehicle at the first time; if not, Then, the to-be-fused itinerary and the previous itinerary are fused to obtain a target itinerary.

Optionally, the device 400 is further configured to find the number of times that the vehicle appears at the position corresponding to the first time if obtained, and determine whether the number of times is greater than a preset number of times; The described itinerary to be fused and the previous itinerary are fused to obtain the target itinerary.

Optionally, the device 400 is further configured to obtain the information point of the location of the vehicle at the first time if the number of times is less than or equal to a preset number of times; and use a machine learning model to determine whether the information point can be fused. information point; if it is an information point that can be fused, the itinerary to be fused and the previous itinerary are fused to obtain the target itinerary.

Optionally, the apparatus 400 is further configured to use the itinerary to be fused as a target itinerary if the information point is not a fused information point.

By acquiring the time interval between the first time and the second time, the stroke fusion device provided in the embodiment of the present invention can more quickly and effectively determine whether to perform the fusion stroke with the previous stroke. Specifically, the present invention can first obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, wherein the first time is the start time corresponding to the itinerary to be merged, and the second time is the start time of the itinerary to be merged The stop time of the corresponding previous trip, and then the present invention can determine whether the time interval between the first time and the second time is less than the first time threshold, and if it is less than the first time threshold, it is determined that the trip to be merged is a temporary trip, and then A target itinerary is obtained by merging the itinerary to be fused with the previous itinerary, and finally the application can store the target itinerary. The present invention determines whether to fuse the to-be-fused itinerary with the previous itinerary by judging whether the time interval between the first time and the second time is less than the first time threshold, which can improve the accuracy of the itinerary acquisition to a certain extent, Thus, the user experience can be improved.

As shown in FIG. 9 , an embodiment of the present invention further provides an electronic controller 500 . The electronic controller 500 includes a processor 510 and a memory 520 . The memory 520 stores computer program instructions, and the computer program instructions are called by the processor 510 in real time. Execute the itinerary fusion method described above

Processor 510 may include one or more processing cores. The processor 510 uses various interfaces and lines to connect various parts in the entire electronic controller, and executes by running or executing the instructions, programs, code sets or instruction sets stored in the memory 520, and calling the data stored in the memory 520. Various functions of the electronic controller and processing data. Optionally, the processor 510 may adopt at least one of a digital signal processing (Digital Signal Processing, DSP), a Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and a Programmable Logic Array (Programmable Logic Array, PLA). A hardware form is implemented. The processor 510 may integrate one or a combination of a central processing unit 510 (Central Processing Unit, CPU), a graphics processor 510 (Graphics Processing Unit, GPU), a modem, and the like. Among them, the CPU mainly handles the operating system, user interface and application programs, etc.; the GPU is used for rendering and drawing of the display content; the modem is used to handle wireless communication. It can be understood that, the above-mentioned modem may not be integrated into the processor 510, and is implemented by a communication chip alone.

The memory 520 may include a random access memory 520 (Random Access Memory, RAM), or may include a read-only memory 520 (Read-Only Memory). The memory 520 map may be used to store instructions, programs, codes, sets of codes, or sets of instructions. The memory 520 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the above method embodiments, and the like. The storage data area can also store data etc. created by the electronic controller in use.

As shown in FIG. 10, an embodiment of the present invention further provides a computer-readable storage medium 600, where computer program instructions 610 are stored in the computer-readable storage medium 600, and the computer program instructions 610 can be invoked by a processor to execute the above implementation method described in the example.

The computer-readable storage medium may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-volatile computer-readable storage medium (non-transitory computer-readable storage medium). Computer readable storage medium 600 has storage space for program code to perform any of the method steps in the above-described methods. These program codes can be read from or written to one or more computer program products. The program code may, for example, be compressed in a suitable form.

The above are only preferred embodiments of the present invention, and are not intended to limit the present invention in any form. Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Without departing from the scope of the technical solution of the present invention, when the technical content disclosed above can be used to make some changes or modifications to equivalent embodiments with equivalent changes, provided that the content of the technical solution of the present invention is not deviated from, the technical essence of the present invention is correct. Any brief modifications, equivalent changes and modifications made in the above embodiments still fall within the scope of the technical solutions of the present invention.

Claims (10)

A trip fusion method, characterized in that, applied to a vehicle, the method comprising: Obtain the itinerary to be merged, and obtain the time interval between the first time and the second time based on the itinerary to be merged, the first time is the start time corresponding to the itinerary to be merged, and the second time is the time to be merged The stop time of the corresponding previous trip; determining whether the time interval is less than a first time threshold; If the time interval is less than the first time threshold, determining that the to-be-fused itinerary is a temporary itinerary; Integrating the to-be-fused itinerary and the previous itinerary to obtain a target itinerary; The target itinerary is stored. The method according to claim 1, wherein, if the time interval is less than the first time threshold, determining the to-be-fused itinerary is a temporary itinerary, and combining the to-be-fused itinerary with the previous The itinerary is fused to get the target itinerary, including: If the time interval is less than the first time threshold, acquiring the information point of the location of the vehicle at the first time; According to the information point, determine whether the location of the vehicle is a first designated location, and the scene corresponding to the first designated location is the user's interest scene; If the location of the vehicle is the first designated location, determining that the itinerary to be merged is a non-temporary itinerary, and taking the itinerary to be merged as a target itinerary; If the location of the vehicle is not the first designated location, it is determined that the itinerary to be merged is a temporary itinerary, and the itinerary to be merged and the previous itinerary are merged to obtain a target itinerary. The method according to claim 1, wherein the method further comprises: If the time interval is greater than the first time threshold, determining whether the time interval is greater than a second time threshold; If the time interval is greater than the second time threshold, it is determined that the itinerary to be fused is a non-temporary itinerary, and the itinerary to be fused is used as a target itinerary. The method according to claim 3, wherein if the time interval is greater than the second time threshold, determining the to-be-fused itinerary is a non-temporary itinerary, and using the to-be-fused itinerary as a target itinerary, include: If the time interval is greater than the second time threshold, acquiring the information point of the location of the vehicle at the first time; Determine whether the location of the vehicle is a second designated location according to the information point, and the scene corresponding to the second designated location is a temporary parking scene; If the location of the vehicle is the second designated location, the to-be-fused itinerary and the previous itinerary are fused to obtain a target itinerary; If the location of the vehicle is not the second designated location, it is determined that the itinerary to be fused is a non-temporary itinerary, and the itinerary to be fused is used as a target itinerary. The method according to claim 3, wherein the method further comprises: If the time interval is less than or equal to the second time threshold, determining whether to obtain the information point of the location of the vehicle at the first time; If not obtained, the to-be-fused itinerary and the previous itinerary are fused to obtain the target itinerary. The method according to claim 5, wherein the method further comprises: If obtained, search for the number of times the vehicle appears at the position corresponding to the first time, and determine whether the number of times is greater than a preset number of times; If it is greater than the preset number of times, the to-be-fused stroke and the previous stroke are merged to obtain a target stroke. The method according to claim 6, wherein the method further comprises: If the number of times is less than or equal to the preset number of times, acquiring the information point of the location of the vehicle at the first time; Use a machine learning model to determine whether the information point is a fusible information point; If it is an information point that can be fused, the to-be-fused itinerary and the previous itinerary are fused to obtain a target itinerary. The method according to claim 7, wherein the method further comprises: If the information point is not a fused information point, the to-be-fused itinerary is used as a target itinerary. A trip fusion device, characterized in that, applied to a vehicle, the device comprising: an acquisition module, configured to acquire the itinerary to be fused, and obtain the time interval between a first time and a second time based on the itinerary to be fused, where the first time is the start time corresponding to the itinerary to be fused, and the second time is the stop time of the previous trip corresponding to the to-be-fused; a first determination module, configured to determine whether the time interval is less than a first time threshold; a second determining module, configured to determine that the to-be-fused itinerary is a temporary itinerary if the time interval is less than the first time threshold; a fusion module, configured to fuse the to-be-fused itinerary and the previous itinerary to obtain a target itinerary; The storage module is used for storing the target itinerary. An electronic controller, characterized in that it includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are invoked by the processor, the process described in any one of claims 1 to 8 is executed fusion method.

Images