CN110702131A

CN110702131A - Data processing method and device

Info

Publication number: CN110702131A
Application number: CN201910842370.2A
Authority: CN
Inventors: 卢学远; 石宽
Original assignee: Hangzhou Feibao Technology Co Ltd
Current assignee: Hangzhou Feibao Technology Co Ltd; Hangzhou Fabu Technology Co Ltd
Priority date: 2019-09-06
Filing date: 2019-09-06
Publication date: 2020-01-17
Anticipated expiration: 2039-09-06
Also published as: CN110702131B

Abstract

The embodiment of the invention provides a data processing method and a device, wherein the method comprises the following steps: obtaining a first planned route according to the path information of a first passenger and obtaining a second planned route according to the path information of a second passenger, wherein the path information of the first passenger comprises a departure place and a destination of the first passenger, and the path information of the second passenger comprises a departure place and a destination of the second passenger; obtaining a matching matrix according to the first planned route and the second planned route, wherein the matching matrix is used for indicating roads through which the first planned route and the second planned route respectively pass; inputting the matching matrix into a car pooling matching degree model to obtain a matching degree; and comparing the matching degree with a preset threshold value, and judging whether the first passenger and the second passenger share the car according to the comparison result. The scheme provided by the embodiment of the invention can improve the car sharing efficiency.

Description

Data processing method and device

Technical Field

The embodiment of the invention relates to the technical field of internet, in particular to a data processing method and device.

Background

With the development of mobile internet and the popularization of taxi-taking software, the traveling mode of people is changed profoundly. When the passenger needs to go out, the passenger can call the car to the destination place by inputting the destination on the network car booking platform, and great convenience is brought to the passenger.

When passengers take a car, the passengers are often a person, which wastes vehicle resources and increases the cost of riding the car for the passengers. Therefore, the existing network car booking platform also provides car pooling service for pooling two or more passengers. The existing car-sharing route matching degree calculation method is that digital characteristics such as the distance and the time of a planned route before car sharing of passengers and digital characteristics such as the distance and the time of the planned route after car sharing are extracted, and then the characteristics are subjected to simple difference calculation to judge whether the current car sharing can be matched.

The existing method for calculating the matching degree of the car sharing route only uses abstract route characteristics such as distance, time and the like of a planned route to represent the route, and the obtained matching degree of the car sharing has larger difference with an actual route, so that the car sharing efficiency is lower.

Disclosure of Invention

The embodiment of the invention provides a data processing method and device, and aims to solve the problems that the matching degree of carpooling obtained by the existing carpooling scheme is large in difference with an actual route, and the carpooling efficiency is low.

In a first aspect, an embodiment of the present invention provides a data processing method, including:

obtaining a first planned route according to the path information of a first passenger and obtaining a second planned route according to the path information of a second passenger, wherein the path information of the first passenger comprises a departure place and a destination of the first passenger, and the path information of the second passenger comprises a departure place and a destination of the second passenger;

obtaining a matching matrix according to the first planned route and the second planned route, wherein the matching matrix is used for indicating roads through which the first planned route and the second planned route respectively pass;

inputting the matching matrix into a car pooling matching degree model to obtain a matching degree, wherein the car pooling matching degree model is obtained by training according to sample matching matrixes of a first sample passenger and a second sample passenger, and the sample matching matrixes are used for indicating roads through which a first sample planning route of the first sample passenger and a second sample planning route of the second sample passenger respectively pass;

and comparing the matching degree with a preset threshold value, and judging whether the first passenger and the second passenger share the car according to a comparison result.

In a possible implementation manner, the car pooling matching degree model is obtained through the following steps:

obtaining a first sample planned route according to the path information of a first sample passenger, and obtaining a second sample planned route according to the path information of a second sample passenger, wherein the path information of the first sample passenger comprises the departure place and the destination of the first sample passenger, and the path information of the second sample passenger comprises the departure place and the destination of the second sample passenger;

obtaining a sample matching matrix according to the first sample planning route and the second sample planning route;

obtaining the matching degree of the first sample passenger and the second sample passenger according to the sample matching matrix, and obtaining sample data according to the sample matching matrix and the matching degree of the first sample passenger and the second sample passenger;

and training the carpooling matching degree model according to the sample data.

In a possible implementation manner, the obtaining a matching matrix according to the first planned route and the second planned route includes:

acquiring road network data of a preset area, wherein the preset area comprises roads passed by the first planned route and roads passed by the second planned route;

obtaining a first matrix corresponding to the first planned route according to the road network data of the preset area and the first planned route, and obtaining a second matrix corresponding to the second planned route according to the road network data of the preset area and the second planned route, wherein the first matrix is used for indicating roads passed by the first planned route, and the second matrix is used for indicating roads passed by the second planned route;

and obtaining the matching matrix according to the first matrix and the second matrix.

In a possible implementation manner, the obtaining a first matrix corresponding to the first planned route according to the road network data of the preset area and the first planned route, and obtaining a second matrix corresponding to the second planned route according to the road network data of the preset area and the second planned route includes:

dividing the road in the preset area into a plurality of sub-roads which are arranged according to a preset sequence according to the road network data;

obtaining the first matrix according to sub-roads passed by the first planned route and sub-roads not passed by the first planned route, wherein the sub-roads are in one-to-one correspondence with elements in the first matrix, and element values in the first matrix are used for indicating whether the first planned route passes through the sub-roads corresponding to the elements;

and obtaining the second matrix according to the sub-roads passed by the second planned route and the sub-roads not passed by the second planned route, wherein the sub-roads are in one-to-one correspondence with elements in the second matrix, and element values in the second matrix are used for indicating whether the second planned route passes through the sub-roads corresponding to the elements.

In a possible implementation manner, the obtaining the matching matrix according to the first matrix and the second matrix includes:

adding the first matrix and the second matrix to obtain the matching matrix; alternatively, the first and second electrodes may be,

and subtracting the first matrix and the second matrix to obtain the matching matrix.

In a possible implementation manner, before obtaining the first planned route according to the path information of the first passenger and obtaining the second planned route according to the path information of the second passenger, the method further includes:

the method comprises the steps of obtaining a first car sharing request of a first passenger, and obtaining path information of the first passenger according to the first car sharing request, wherein the first car sharing request comprises a departure place and a destination of the first passenger;

and acquiring a second car sharing request of a second passenger, and acquiring path information of the second passenger according to the second car sharing request, wherein the second car sharing request comprises a departure place and a destination of the second passenger.

In a possible implementation manner, after the comparing the matching degree with a preset threshold and determining whether the first passenger and the second passenger share the car according to the comparison result, the method further includes:

if the first passenger and the second passenger are determined to share the car according to the comparison result, generating a car sharing order, wherein the car sharing order comprises the path information of the first passenger and the path information of the second passenger;

and generating a carpooling planning route according to the path information of the first passenger and the path information of the second passenger.

In a second aspect, an embodiment of the present invention provides a data processing apparatus, including:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for obtaining a first planned route according to the path information of a first passenger and obtaining a second planned route according to the path information of a second passenger, the path information of the first passenger comprises a departure place and a destination of the first passenger, and the path information of the second passenger comprises a departure place and a destination of the second passenger;

the first processing module is used for obtaining a matching matrix according to the first planned route and the second planned route, wherein the matching matrix is used for indicating roads through which the first planned route and the second planned route respectively pass;

the second processing module is used for inputting the matching matrix into a car pooling matching degree model to obtain a matching degree, wherein the car pooling matching degree model is obtained by training according to sample matching matrixes of a first sample passenger and a second sample passenger, and the sample matching matrixes are used for indicating roads through which a first sample planning route of the first sample passenger and a second sample planning route of the second sample passenger respectively pass;

and the car sharing module is used for comparing the matching degree with a preset threshold value and judging whether the first passenger and the second passenger share the car or not according to a comparison result.

In a possible implementation manner, the system further includes a model training module, and the model training module is configured to:

and training the carpooling matching degree model according to the sample data.

In a possible implementation manner, the first processing module is specifically configured to:

In a possible implementation manner, the obtaining module is further configured to, before obtaining the first planned route according to the path information of the first passenger and obtaining the second planned route according to the path information of the second passenger:

In a possible implementation manner, the car pooling module is further configured to, after the matching degree is compared with a preset threshold, determine whether the first passenger and the second passenger have car pooling according to a comparison result:

In a third aspect, an embodiment of the present invention provides a data processing apparatus, including: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the data processing method of any one of the first aspects.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the data processing method according to any one of the first aspect is implemented.

According to the data processing method and device provided by the embodiment of the invention, the first planned route is obtained according to the path information of the first passenger, the second planned route is obtained according to the path information of the second passenger, and then the matching matrix is obtained according to the first planned route and the second planned route. And finally, inputting the matching matrix into a car-sharing matching degree model to obtain the matching degree, comparing the matching degree with a preset threshold value, and judging whether the first passenger and the second passenger share the car according to the comparison result. According to the scheme provided by the embodiment of the invention, the first planned route of the first passenger and the second planned route of the second passenger are respectively determined, then the obtained matching matrix comprises the roads respectively passed by the first planned route and the second planned route, the car pooling matching degree model is obtained according to the sample matching matrix, the sample matching matrix comprises the roads respectively passed by the first sample planned route and the second sample planned route, and the matching degree of the first planned route and the second planned route can be reflected according to the matching degree output by the car pooling matching degree model.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a schematic structural diagram of a data processing system for a carpool route according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a data processing method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a training process of a car pooling matching degree model according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating a data processing method according to another embodiment of the present invention;

fig. 5 is a schematic diagram of a client initiating a car pooling request according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a client display provided in an embodiment of the present invention;

FIG. 7 is a diagram illustrating a corresponding matrix generated according to a planned route according to an embodiment of the invention;

fig. 8 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;

fig. 9 is a schematic diagram of a hardware structure of a data processing apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 1 is a schematic structural diagram of a data processing system of a carpool route according to an embodiment of the present invention, and as shown in fig. 1, the data processing system includes a server 11, a client 12 and a vehicle 13, where the server 11 and the client 12 are connected through a wireless network, the number of the clients 12 is multiple, and the server 11 and the vehicle 13 are connected through a wireless network.

The description will be given by taking two clients 12 as an example, which are client a and client B. When two passengers have car sharing requirements, the passenger A can send a car sharing request to the server 11 through the client A, the passenger B can send a car sharing request to the server 11 through the client B, after receiving the car sharing requests of the client A and the client B, the server 11 obtains the path information of the passenger A and the path information of the passenger B, corresponding processing is carried out, the matching degree of the paths of the passenger A and the passenger B is obtained, and therefore whether the passenger A and the passenger B share cars or not is judged. If the carpooling is determined, a carpooling order is generated, carpooling operation is executed, otherwise, the carpooling operation is not executed.

In the concrete implementation, the passenger can send out the car sharing request through the APP, or send out the car sharing request through logging in corresponding website on the webpage and operating, APP or webpage provide for corresponding net car booking platform, after the APP or website that provides through net car booking platform send out the car sharing request, backend server 11 can obtain the car sharing request, and server 11 carries out wireless network connection with a plurality of vehicles 13 simultaneously, can distribute corresponding vehicle 13 for the passenger.

The technical solution of the present invention and how to solve the above technical problems will be described in detail with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Fig. 2 is a schematic flow chart of a data processing method according to an embodiment of the present invention, as shown in fig. 2, including:

and 21, obtaining a first planned route according to the path information of the first passenger and obtaining a second planned route according to the path information of the second passenger, wherein the path information of the first passenger comprises the departure place and the destination of the first passenger, and the path information of the second passenger comprises the departure place and the destination of the second passenger.

It is necessary to determine whether a first passenger and a second passenger perform car sharing, and route information of the first passenger can be obtained according to a car sharing request of the first passenger, where the route information of the first passenger includes a departure place and a destination of the first passenger, that is, a place where the first passenger is to depart and a place where the first passenger is to arrive. It is understood that the carpooling request of the first passenger may be initiated by the first passenger through the client, or may be initiated by other people for the first passenger through the client. Similarly, the route information of the second passenger can be obtained according to the car sharing request of the second passenger, and the route information of the second passenger comprises the departure place and the destination of the second passenger.

A first planned route is generated according to the departure place and the destination of the first passenger, and a second planned route is generated according to the departure place and the destination of the second passenger. The first planned route is a route generated only according to the departure place and the destination of the first passenger without considering the car pool, and the second planned route is a route generated only according to the departure place and the destination of the second passenger without considering the car pool.

In practice, from the departure place to the destination, there is often more than one route, taking the first planned route as an example, it can be understood that when there are multiple routes from the departure place to the destination of the first passenger, all the routes may be displayed to the passenger through the client for the passenger to select one of the routes, the multiple routes may also be ranked according to certain conditions, the route with the highest priority is preferentially displayed, for example, the "high speed priority", "minimum traffic jam risk", "shortest estimated time" and the like may be set for sequential display, and the like.

And step 22, obtaining a matching matrix according to the first planned route and the second planned route, wherein the matching matrix is used for indicating roads respectively passed by the first planned route and the second planned route.

First, road data of a predetermined area needs to be acquired, for example, road data of a city, including each road of the city and the position of each road, may be acquired. Each road of the city may then be divided into a segment of sub-roads, and each segment of sub-road is numbered and sorted. The number and the sequence of each segment of sub-road can be set arbitrarily, but after the setting, the sequence of the sub-roads cannot be modified when the first passenger and the second passenger are spliced, that is, the sequence of the sub-roads cannot be modified in the process of obtaining the matching matrix according to the first planned route and the second planned route.

And after the serial number and the sequence of each sub-road are obtained, obtaining a first matrix corresponding to the first planned route according to the road passed by the first planned route. Specifically, each sub-road corresponds to an element in the first matrix, if the first planned road passes through the sub-road, the value of the corresponding element may be m, and if the first planned road does not pass through the sub-road, the value of the corresponding element may be n, and the values of m and n are different. Therefore, according to the value of each element in the first matrix and the corresponding relationship between each element and the sub-road, which sub-roads the first planned route passes through can be obtained.

Similarly, a second matrix corresponding to the second planned route is obtained according to the roads passed by the second planned route. The specific obtaining manner is as described above, and is not described herein again. It should be noted that the specifications of the first matrix and the second matrix are the same, that is, the number of rows of the first matrix is equal to the number of rows of the second matrix, the number of columns of the first matrix is equal to the number of columns of the second matrix, and the sub-road corresponding to any element in the first matrix is the same sub-road as the sub-road corresponding to the element at the corresponding position in the second matrix.

After the first matrix and the second matrix are obtained, a matching matrix is obtained according to the first matrix and the second matrix, wherein the method for obtaining the matching matrix is various, for example, the first matrix and the second matrix may be added to obtain the matching matrix, or the first matrix and the second matrix may be subtracted to obtain the matching matrix, and for example, the first matrix and the second matrix may be directly juxtaposed to form a matching matrix with a row number twice as large as that of the first matrix, or a matching matrix with a column number twice as large as that of the first matrix, and so on. There are various methods for obtaining the matching matrix, and it should be understood that the above method is only one of the examples, and the specific manner is not particularly limited herein.

And step 23, inputting the matching matrix into a car pooling matching degree model to obtain a matching degree, wherein the car pooling matching degree model is obtained by training according to sample matching matrixes of a first sample passenger and a second sample passenger, and the sample matching matrixes are used for indicating roads through which a first sample planning route of the first sample passenger and a second sample planning route of the second sample passenger respectively pass.

The car pooling matching degree model is used for determining the matching degree of the car pooling of the first passenger and the second passenger, namely the matching degree of the first planned route and the second planned route, wherein each element in the matching matrix has corresponding weight information, and the car pooling matching degree model is used for processing the matching matrix according to the corresponding weight information to obtain the matching degree. The car pooling matching degree model is obtained by training according to sample matching matrixes of a first sample passenger and a second sample passenger, the sample matching matrixes comprise roads through which the first sample planning route and the second sample planning route respectively pass, and the obtaining mode of the sample matching matrixes is similar to the obtaining mode of the first planning route and the second planning route.

The car pooling matching degree model may be a convolutional neural network model, and the specific selection of the car pooling matching degree model may be set according to actual requirements, which is not limited herein, and the specific implementation manner of the car pooling matching degree model may refer to the related description in the prior art, which is not described herein in any greater detail.

And 24, comparing the matching degree with a preset threshold value, and judging whether the first passenger and the second passenger share the car according to the comparison result.

And after the matching degree of the first planned route and the second planned route is obtained, comparing the matching degree with a preset threshold value. If the matching degree exceeds the preset threshold value, the matching degree of the first planned route and the second planned route is high, and at the moment, it is confirmed that the first passenger and the second passenger can share the car. If the matching degree does not exceed the preset threshold value, the matching degree of the first planned route and the second planned route is low, and at the moment, it is determined that the first passenger and the second passenger do not share the car.

If the carpool is confirmed, a vehicle can be determined at a place which is not far away from the departure place of the first passenger and the second passenger to carry the first passenger and the second passenger, and the carpool and the destination of the first passenger and the second passenger are finished. If the taxi sharing is confirmed to be out of service, other passengers who send the taxi sharing requests can be selected, and the process is repeated until the passengers who can meet the taxi sharing requirements are found to share the taxi.

According to the data processing method provided by the embodiment of the invention, a first planned route is obtained according to the path information of a first passenger, a second planned route is obtained according to the path information of a second passenger, and then a matching matrix is obtained according to the first planned route and the second planned route. And finally, inputting the matching matrix into a car-sharing matching degree model to obtain the matching degree, comparing the matching degree with a preset threshold value, and judging whether the first passenger and the second passenger share the car according to the comparison result. According to the scheme provided by the embodiment of the invention, the first planned route of the first passenger and the second planned route of the second passenger are respectively determined, then the obtained matching matrix comprises the roads respectively passed by the first planned route and the second planned route, the car pooling matching degree model is obtained according to the sample matching matrix, the sample matching matrix comprises the roads respectively passed by the first sample planned route and the second sample planned route, and the matching degree of the first planned route and the second planned route can be reflected according to the matching degree output by the car pooling matching degree model.

On the basis of the foregoing embodiment, the data processing method provided in the embodiment of the present invention needs to train the car-pooling matching degree model in advance before processing according to the car-pooling matching degree model, which is described below with reference to fig. 3.

Fig. 3 is a schematic diagram of a training process of the car pooling matching degree model provided in the embodiment of the present invention, as shown in fig. 3, including:

step 31, obtaining a first sample planned route according to the path information of a first sample passenger, and obtaining a second sample planned route according to the path information of a second sample passenger, wherein the path information of the first sample passenger comprises the departure place and the destination of the first sample passenger, and the path information of the second sample passenger comprises the departure place and the destination of the second sample passenger;

step 32, obtaining a sample matching matrix according to the first sample planning route and the second sample planning route;

step 33, obtaining the matching degree of the first sample passenger and the second sample passenger according to the sample matching matrix, and obtaining sample data according to the matching degree of the sample matching matrix, the first sample passenger and the second sample passenger;

and step 34, training the carpooling matching degree model according to the sample data.

Specifically, steps 31 and 32 are implemented similarly to

steps

21 and 22. The difference is that the data adopted in the embodiment includes a first sample planned route and a second sample planned route, and the matching degree of the first sample passenger and the second sample passenger, that is, the matching degree of the first sample planned route and the second sample planned route and whether car sharing is performed are determined in advance, and the matching degree of the first sample passenger and the second sample passenger is adopted to train the car sharing matching model.

And when the matching result is incorrect, learning is carried out according to the matching degree of the first sample passenger and the second sample passenger and the sample matching matrix, so that the matching result is processed according to the learned related data during next training to obtain a trained car sharing matching model, and then the matching result is output according to whether the first passenger and the second passenger share cars.

The method for obtaining the first sample planned route according to the path information of the first sample passenger and the method for obtaining the second sample planned route according to the path information of the second sample passenger are similar to the method for obtaining the first planned route according to the path information of the first passenger and the method for obtaining the second planned route according to the path information of the second passenger. The method for obtaining the sample matching matrix according to the first sample planned route and the second sample planned route is similar to the method for obtaining the matching matrix according to the first planned route and the second planned route, and the process of inputting the matching matrix and the sample matching matrix into the car pooling matching degree model for processing is also similar, and the following description will be given by taking the relevant information of the first passenger and the second passenger as an example.

Fig. 4 is a schematic flow chart of a data processing method according to another embodiment of the present invention, as shown in fig. 4, including:

step 401, obtaining a first car sharing request of a first passenger, and obtaining path information of the first passenger according to the first car sharing request.

The first car sharing request comprises a departure place and a destination of the first passenger.

And 402, acquiring a second car sharing request of the second passenger, and acquiring the path information of the second passenger according to the second car sharing request.

The second carpool request comprises the departure place and the destination of the second passenger.

Specifically, the first passenger and the second passenger can log in the online car booking platform through the mobile phone and other clients and send car pooling requests. This is explained below with reference to fig. 5.

Fig. 5 is a schematic diagram of a client initiating a car sharing request according to an embodiment of the present invention, as shown in fig. 5, including a first passenger 51 and a first client 52, where the first passenger is at a location a, and if the first passenger 51 wants to share a car with another person and go from the location a to a location B, the car sharing request can be initiated through the first client 52. Fig. 6 is a schematic diagram of a client display provided by an embodiment of the present invention, as shown in fig. 6, a first passenger 51 logs in a taxi appointment platform through a first client 52, and can input a departure place and a destination on the platform. If the departure point of the first passenger 51 is the place where the first passenger 51 is located, the position of the first client 52 may be directly used as the departure point. If the first passenger 51 calls another passenger 53 and another passenger 53 shares a car with another passenger 53 to go to the location B from the location C, the location C needs to be manually input.

Therefore, after entering the car booking platform, the server back end of the car booking platform may directly display a message to display the location information of the first client 52, for example, display "the platform wants to obtain your current location", and click "yes" or "no" below. When "yes" is clicked, the server indicating the platform acquires the location of the first client 52, and fills the location of the first client 52 into the input box of the origin. The first passenger 51 can check whether the input of the departure place is correct, and if it is correct, only the destination needs to be input, and if it is incorrect, the departure place needs to be input again. When clicking "no", the server of the platform does not get the location of the first client 52, which requires manual input of the origin and destination by itself.

It is understood that whether the first passenger 51 calls the car for himself or herself, the background server may be allowed to obtain the location of the first client 52, or may be denied the location of the first client 52. If the departure place determined by the background server is correct, the first passenger 51 may not be required to re-input the departure place, and if the departure place determined by the background server is correct, the first passenger 51 may re-input the departure place in the departure place input box. If the user is not permitted, the first passenger 51 inputs the departure point in the departure point input box and the destination in the destination input box. After the departure place and the destination are determined, the lower 'confirmation car sharing button' can be clicked, and then a car sharing request is determined to be sent to the background server.

The process of the second passenger initiating the car sharing request is similar to the process of the first passenger initiating the car sharing request, and the detailed description is omitted here.

And 403, obtaining a first planned route according to the path information of the first passenger, and obtaining a second planned route according to the path information of the second passenger.

Wherein the path information of the first passenger includes a departure place and a destination of the first passenger, and the path information of the second passenger includes a departure place and a destination of the second passenger.

The route information of the first passenger comprises a departure place and a destination of the first passenger, and the server generates a first planned route according to the departure place and the destination of the first passenger after receiving a car sharing request of the first passenger, wherein the first planned route does not consider a route shared with other people and is determined by the departure place and the destination of the first passenger. Similarly, after receiving the car sharing request of the second passenger, the server generates a second planned route according to the departure place and the destination of the second passenger, and the second planned route is determined by the departure place and the destination of the second passenger.

It is understood that, during a period of time, the server may receive a plurality of client-initiated car sharing requests, and the car sharing requests of the first passenger and the second passenger are only two of the plurality of car sharing requests, where it is determined whether the first passenger and the second passenger are suitable for car sharing only for two of the plurality of car sharing requests, if so, car sharing is performed, if not, it may be determined whether the first passenger and other passengers are suitable for car sharing, and it is determined whether the second passenger and other passengers are suitable for car sharing until a passenger suitable for car sharing is found.

Step 404, road network data of a preset area is obtained, wherein the preset area comprises roads passed by the first planned route and roads passed by the second planned route.

In order to combine the spatial feature information of the roads, the embodiment of the present invention first obtains the road network data of a preset area, where the preset area includes the road passed by the first planned route and the road passed by the second planned route, and also includes many other roads.

For example, a car pool is generally in a city, and at this time, the preset area may be a corresponding city, obtain road network data of the city, and know each road in the city, a position of each road, a relationship between roads, and the like. If the ride share occurs between different cities, the predetermined area may be a larger area including the first planned route and the second planned route. The selection of the preset area is related to the passing positions of the first planned route and the second planned route, and the actual selection can be as required, and is not particularly limited herein.

Step 405, obtaining a first matrix corresponding to the first planned route according to the road network data of the preset area and the first planned route, and obtaining a second matrix corresponding to the second planned route according to the road network data of the preset area and the second planned route.

The first matrix is used for indicating roads passed by the first planned route, and the second matrix is used for indicating roads passed by the second planned route.

Specifically, firstly, dividing roads in a preset area into a plurality of sub-roads which are arranged according to a preset sequence according to road network data;

obtaining a first matrix according to sub-roads passed by the first planned route and sub-roads not passed by the first planned route, wherein the sub-roads are in one-to-one correspondence with elements in the first matrix, and element values in the first matrix are used for indicating whether the first planned route passes through the sub-roads corresponding to the elements;

and obtaining a second matrix according to the sub-roads passed by the second planned route and the sub-roads not passed by the second planned route, wherein the sub-roads are in one-to-one correspondence with elements in the second matrix, and element values in the second matrix are used for indicating whether the second planned route passes through the sub-roads corresponding to the elements.

This process will be described in detail below with reference to fig. 7.

Fig. 7 is a schematic diagram of generating a corresponding matrix according to a planned route according to an embodiment of the present invention, as shown in fig. 7, a preset area 70, a first planned route 71, and a second planned route 72 are first determined, where the preset area 70 includes a plurality of roads. The multiple roads are divided into different sub-roads, and the numbers are numbered for the sub-roads. As shown in fig. 7, includes sub-link 701, sub-link 702, sub-link 703.

The sub-links are arranged in a predetermined order, for example, from sub-link 701 through sub-link 708. The preset sequence may be arbitrarily specified, but needs to be determined in advance, and cannot be modified after the determination is made, and the preset sequence is the same when the first matrix of the first planned route 71 is acquired and the second matrix of the second planned route 72 is acquired.

It is then necessary to look at the sub-roads passed by and the sub-roads not passed by the first planned route 71, respectively, to derive and assign a first vector. Where each sub-road corresponds to an element in the first vector, the values of the sub-roads passed by and not passed by the first planned route 71 are different, e.g., the value of the corresponding element may be assigned to 1 for the passed sub-road, the value of the corresponding element may be assigned to 0 for the not passed sub-road, and so on. The specific value of the element can be according to actual needs, but the values of the elements of the sub-road that generally passes through and the sub-road that does not pass through should be different.

As shown in fig. 7, the sub-roads passed by the first planned route 71 are the sub-roads 701, 703, 704, 705 and 707, and the first vector is [1,0,1,1,1,0,1,0 ]. Similarly, the sub-links traversed by the second planned route 72 are sub-link 702, sub-link 703, sub-link 704, sub-link 705, and sub-link 708, and the corresponding second vector is [0,1,1,1,1,0,0,1 ].

After the first vector and the second vector are obtained, the first vector may be converted into a first matrix, and the second vector may be converted into a second matrix, where the number of rows and columns of the first matrix may be arbitrarily specified, and elements in the first matrix are equal to elements in the first vector. The row number of the second matrix is equal to the row number of the first matrix, the column number of the second matrix is equal to the column number of the first matrix, and the sub-road corresponding to any element in the first matrix and the sub-road corresponding to the element at the corresponding position in the second matrix are the same sub-road. For example, when the element in the first row and the first column of the first matrix corresponds to sub-link a, the sub-link corresponding to the element in the first row and the first column of the second matrix should also be sub-link a. When the value of the element in the first row and the first column in the first matrix is 1, it indicates that the first planned route passes through the sub-road a, and when the value of the element in the first row and the first column in the second matrix is 0, it indicates that the second planned route does not pass through the sub-road a, and so on.

For example, when the first vector is [1,0,1,1,1,0]The second vector is [0,1,1,1,1,0,0,1]The first vector has 8 elements, and can be converted into a first matrix with two rows and four columns

Or into a first matrix of four rows and two columns

When the first matrix is

When the corresponding second matrix is

When the first matrix is

When the corresponding second matrix is

And so on.

And 406, obtaining a matching matrix according to the first matrix and the second matrix.

There are various ways to obtain the matching matrix, for example, at least two ways may be included. One is that the first matrix and the second matrix are added to obtain a matching matrix; and the other is to perform subtraction processing on the first matrix and the second matrix to obtain a matching matrix.

For example, let the first matrix be

The second matrix is

If the first matrix and the second matrix are added, a matching matrix is obtained

When the corresponding elements of the first matrix and the second matrix are both 1, it indicates that the first planned route and the second planned route both pass through the corresponding sub-roads. At this time, the first matrix and the second matrix are added, and the more elements with element values of 2 in the obtained matching matrix, the more the same sub-roads passed by the first planned route and the second planned route are, the higher the matching degree is.

If the first matrix and the second matrix are subtracted, a matching matrix is obtained

When the corresponding elements of the first matrix and the second matrix are both 1, it indicates that the first planned route and the second planned route both pass through the corresponding sub-roads. At this time, the first matrix and the second matrix are subtracted, and the more elements with element values of 1 in the obtained matching matrix, the more different sub-roads passed by the first planned route and the second planned route are indicated, the lower the matching degree correspondingly becomes, and the like.

And 407, inputting the matching matrix into the car pooling matching degree model to obtain the matching degree.

The car pooling matching degree model is obtained by training according to sample matching matrixes of a first sample passenger and a second sample passenger, and the sample matching matrixes are used for indicating roads through which a first sample planned route of the first sample passenger and a second sample planned route of the second sample passenger respectively pass.

And after obtaining the matching matrix, inputting the matching matrix into a car sharing matching degree model, wherein the car sharing matching degree model is obtained by training according to the sample matching matrix, and the obtaining method of the sample matching matrix is similar to that of the matching matrix. And obtaining a plurality of groups of sample matching matrixes for training a car-sharing matching degree model according to the first sample planning routes of a plurality of groups of first sample passengers and the second sample planning routes of second sample passengers.

And inputting the matching matrix into the carpool matching degree model to obtain the matching degree, wherein the matching degree indicates the matching degree of the first planned route and the second planned route.

And step 408, comparing the matching degree with a preset threshold value, and judging whether the first passenger and the second passenger share the car according to the comparison result.

The value of the preset threshold can be set to 70% according to actual needs, for example, when the matching degree exceeds 70%, it is determined that the first passenger and the second passenger share the car, and if the matching degree is lower than 70%, it is determined that the first passenger and the second passenger do not share the car.

And if the first passenger and the second passenger are determined to share the car according to the comparison result, generating a car sharing order, wherein the car sharing order comprises the path information of the first passenger and the path information of the second passenger.

After the car pooling planning route is obtained, the background server can select nearby vehicles according to the departure place of the first passenger and the departure place of the second passenger, and send the car pooling planning route to the client corresponding to the vehicles, and drivers of the vehicles can go to the departure place of the first passenger and the departure place of the second passenger according to the car pooling planning route to receive the first passenger and the second passenger, finish car pooling, and load the first passenger and the second passenger to respective destinations.

Fig. 8 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention, as shown in fig. 8, including:

the obtaining module 81 is configured to obtain a first planned route according to the path information of the first passenger and obtain a second planned route according to the path information of the second passenger, where the path information of the first passenger includes a departure place and a destination of the first passenger, and the path information of the second passenger includes a departure place and a destination of the second passenger;

the first processing module 82 is configured to obtain a matching matrix according to the first planned route and the second planned route, where the matching matrix is used to indicate roads through which the first planned route and the second planned route respectively pass;

the second processing module 83 is configured to input the matching matrix into a car pooling matching degree model to obtain a matching degree, where the car pooling matching degree model is obtained by training according to sample matching matrices of a first sample passenger and a second sample passenger, and the sample matching matrices are used to indicate roads through which a first sample planned route of the first sample passenger and a second sample planned route of the second sample passenger respectively pass;

the car pooling module 84 is configured to compare the matching degree with a preset threshold, and determine whether the first passenger and the second passenger have car pooling according to a comparison result.

and training the carpooling matching degree model according to the sample data.

In a possible implementation manner, the first processing module 82 is specifically configured to:

In a possible implementation manner, the obtaining module 81 is further configured to, before obtaining the first planned route according to the path information of the first passenger and obtaining the second planned route according to the path information of the second passenger:

In a possible implementation manner, the car pooling module 84 is further configured to, after the comparing the matching degree with a preset threshold and determining whether the first passenger and the second passenger have car pooling according to the comparison result:

The apparatus provided in the embodiment of the present invention may be used to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.

Fig. 9 is a schematic diagram of a hardware structure of a data processing apparatus according to an embodiment of the present invention, and as shown in fig. 9, the data processing apparatus includes: at least one processor 91 and a memory 92. The processor 91 and the memory 92 are connected by a bus 93.

Optionally, the model determination further comprises a communication component. For example, the communication component may include a receiver and/or a transmitter.

In a specific implementation, the at least one processor 91 executes computer-executable instructions stored by the memory 92, so that the at least one processor 91 performs the data processing method as described above.

For a specific implementation process of the processor 91, reference may be made to the above method embodiments, which implement similar principles and technical effects, and this embodiment is not described herein again.

In the embodiment shown in fig. 9, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the data processing method as described above is implemented.

The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.

The division of the units is only a logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method, comprising:

2. The method according to claim 1, wherein the car-pooling matching degree model is obtained by the following steps:

and training the carpooling matching degree model according to the sample data.

3. The method of claim 1, wherein said deriving a matching matrix from said first planned route and said second planned route comprises:

4. The method according to claim 3, wherein the obtaining a first matrix corresponding to the first planned route according to the road network data of the preset area and the first planned route, and obtaining a second matrix corresponding to the second planned route according to the road network data of the preset area and the second planned route comprises:

5. The method of claim 3, wherein the deriving the matching matrix from the first matrix and the second matrix comprises:

6. The method of claim 1, wherein prior to obtaining the first planned route based on the path information of the first passenger and the second planned route based on the path information of the second passenger, the method further comprises:

7. The method of claim 1, wherein after comparing the matching degree with a preset threshold and determining whether the first passenger and the second passenger share the car according to the comparison result, the method further comprises:

8. A data processing apparatus, comprising:

9. A data processing apparatus, characterized by comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the data processing method of any of claims 1 to 7.

10. A computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement a data processing method according to any one of claims 1 to 7.