CN111126949A - Intelligent transportation tool, and intelligent travel service matching planning device and method - Google Patents
Intelligent transportation tool, and intelligent travel service matching planning device and method Download PDFInfo
- Publication number
- CN111126949A CN111126949A CN201911255101.2A CN201911255101A CN111126949A CN 111126949 A CN111126949 A CN 111126949A CN 201911255101 A CN201911255101 A CN 201911255101A CN 111126949 A CN111126949 A CN 111126949A
- Authority
- CN
- China
- Prior art keywords
- service
- user
- neural network
- intelligent
- travel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000013439 planning Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000013528 artificial neural network Methods 0.000 claims description 64
- 238000012549 training Methods 0.000 claims description 60
- 230000000306 recurrent effect Effects 0.000 claims description 51
- 238000005516 engineering process Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 8
- 230000000295 complement effect Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 14
- 230000006855 networking Effects 0.000 description 11
- ADLSFYJDHWUKFP-UHFFFAOYSA-N 5-methoxy-11,12-dihydroindolo[2,3-a]carbazole-6-carbonitrile Chemical compound N1C2=C3NC4=CC=C[CH]C4=C3C(OC)=C(C#N)C2=C2[C]1C=CC=C2 ADLSFYJDHWUKFP-UHFFFAOYSA-N 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000005282 brightening Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000010705 motor oil Substances 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1093—Calendar-based scheduling for persons or groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
Abstract
The application relates to the technical field of service matching processing, and provides an intelligent vehicle, an intelligent travel service matching planning device and an intelligent travel service matching planning method. The method and the device can provide an intelligent and rapid service booking function for the user, facilitate the user to carry out convenient travel action, provide personalized close-fitting service according to the individual habit of the user, and improve user experience.
Description
Technical Field
The application relates to the technical field of business processing, in particular to an intelligent travel business matching planning method, an intelligent travel business matching planning device and an intelligent vehicle applying the intelligent travel business matching planning method.
Background
With the continuous improvement of living standard, automobiles are more and more common in the life of people, and gradually become one of indispensable vehicles in the life of people in cities and villages.
Meanwhile, people no longer simply define the automobile as a transportation tool and a travel tool, and the requirements on the aspects of safety, environmental protection, comfort, entertainment and the like of the automobile are increasing.
However, at present, more and more private cars are used, the work of a user is more and more busy, sometimes, the user suddenly receives a call to go out of business, sometimes, the user may need to stop to manually search for relevant information, a lot of time is wasted, and the departure time of some trains or planes is just missed, so that a longer time delay is caused.
On the other hand, existing smart devices such as mobile phones and vehicle-mounted devices can all realize a service processing function, but how to provide better service when travel planning is performed on the mobile phones or the vehicle-mounted devices is a great challenge in the technical field.
For example, the current method for booking airline tickets still needs to be manually selected, a method similar to manual reminding is not available, voice cannot interact for multiple times to complete booking of train tickets, and generally, the method does not have memory of context memory background, and closed loop booking of users cannot be continuously realized, so that how to quickly find and book a satisfactory ticket in the whole voice process without any characters, and how to realize quick booking according to historical travel time and habits is a great problem to be solved in the technical field.
In addition, the prior art has a plurality of technical difficulties and prejudices which are difficult to realize, such as:
1. the service providers are often independent and unrelated to each other, such as hotels, air tickets, special cars and restaurants;
2. users often need to switch different software service software to complete different service reservations;
3. the preset position information is not correlated, and the user often does not know the distance from an airport to a hotel, the distance from the hotel to a restaurant, the time and the position of receiving and delivering a special car;
4. the user needs to switch between different software in a troublesome way and input the position information to find more appropriate peripheral information, such as finding a restaurant near a travel hotel, finding a hotel near a meeting place, no map visualization, and the like.
Aiming at the defects in various aspects of the prior art, the inventor of the application provides an intelligent vehicle, an intelligent travel business matching planning device and an intelligent travel business matching planning method through deep research.
Disclosure of Invention
The purpose of the application is to provide an intelligent vehicle, and a device and a method for planning the intelligent travel business matching, which can provide an intelligent and rapid business booking function for a user, facilitate the user to carry out convenient travel actions, and can provide personalized close-fitting service according to the individual habits of the user, thereby improving the user experience.
In order to solve the above technical problem, the present application provides an intelligent travel service matching planning method, as one implementation manner, the intelligent travel service matching planning method includes:
acquiring a service booking instruction of a user;
obtaining the booking intention of the user according to the service booking instruction;
acquiring historical data information of a user, and intelligently processing the booking intention according to the historical data information to obtain a service booking scheme according with the expectation of the user;
at least two service booking schemes are provided which temporally and/or spatially link the associated services.
As an implementation manner, the step of providing at least two service subscription schemes that temporally and/or spatially link with a supporting service specifically includes: providing a first service and a second service which are realized to be connected with a matching service in time, or a first service and a second service which are realized to be connected with a matching service in space, or a first service and a second service which are realized to be connected with a matching service in time and space, wherein the first service and the second service comprise the same or different travel tools, the same or different living and eating services and the same or different third-party service application programs.
As an embodiment, the step of acquiring historical data information of the user and intelligently processing the booking intention according to the historical data information specifically includes:
collecting historical data information of a user to generate a marking file;
generating a training sample according to the label file and the input and the output of the local recurrent neural network;
training the local recurrent neural network by adopting a differential evolution algorithm, and generating a weight and a threshold of the local recurrent neural network according to the training sample;
and acquiring the booking intention approximation degree of the user to each travel service type according to the weight value and the threshold value of the local regression neural network.
As an embodiment, the generating the training sample according to the label file and the input and the output of the local recurrent neural network specifically includes:
analyzing the marked file;
capturing training historical data information in the marked file;
and generating training samples from the training historical data information according to the input and output structures or parameters of the local recurrent neural network.
As an implementation manner, the training the local recurrent neural network by using the differential evolution algorithm, and generating a weight and a threshold of the local recurrent neural network according to the training sample specifically include:
judging whether the content distribution network server is available;
under the condition that the content distribution network server is available, the training sample is sent to the content distribution network server, wherein the content distribution network server trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network; and under the condition that the content distribution network server is unavailable, the equipment per se trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network.
As an implementation manner, the generating the weight and the threshold of the local recurrent neural network according to the training sample by using the differential evolution algorithm specifically includes:
the local regression neural network initializes population and algorithm parameters according to the training samples;
determining a fitness function, obtaining different network structures according to individuals and algorithm parameters of the population, and evaluating the network performance according to the fitness function value;
carrying out variation operation, cross operation and selection operation in sequence to generate a new population, decoding each individual in the new population to obtain a weight and a threshold value to form a neural network, and directly calculating an output error of the corresponding network as a fitness value of the individual in the new population;
and when the fitness value reaches the maximum evolution algebra, decoding the optimal individuals in the new population to be used as the weight and the threshold of the local regression neural network.
As an embodiment, the historical data information of the user includes at least one of the following: the travel times, travel tool selection, travel time period selection and total cost of the user; the training sample comprises at least one of the following: departure time, trip duration, trip tools, return time and various consumption expense combination modes.
As an implementation manner, the step of obtaining the service subscription instruction of the user specifically includes:
acquiring a service booking instruction input by a user voice;
identity recognition and authentication verification are carried out through a voiceprint recognition technology;
and after the voiceprint recognition technology carries out identity recognition and authentication verification, adopting a semantic recognition technology to recognize and obtain the service booking instruction.
In order to solve the above technical problem, the present application further provides an intelligent travel service complement planning device, as one implementation manner, the intelligent travel service complement planning device includes a memory and a processor, the memory stores an intelligent travel planning program, and the processor is configured to execute the intelligent travel planning program, so as to implement the steps of the intelligent travel service complement planning method.
In order to solve the technical problem, the present application further provides an intelligent vehicle, as one implementation manner, where the intelligent vehicle is configured with the intelligent travel service matching planning device.
According to the intelligent transportation tool, the intelligent travel service matching planning device and the intelligent travel service matching planning method, firstly, a service booking instruction of a user is obtained, booking intentions of the user are obtained according to the service booking instruction, historical data information of the user is obtained, the booking intentions are intelligently processed according to the historical data information, a service booking scheme which is in line with the expectation of the user is obtained, and at least two service booking schemes which are linked in time and/or space and are matched with services are provided. The method and the device can provide an intelligent and rapid service booking function for the user, facilitate the user to carry out convenient travel action, provide personalized close-fitting service according to the individual habit of the user, and improve user experience.
The foregoing description is only an overview of the technical solutions of the present application, and in order to make the technical means of the present application more clearly understood, the present application may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present application more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of the intelligent travel service matching planning method according to the present application.
Fig. 2 is a schematic block diagram of an embodiment of an intelligent travel service matching planning apparatus according to the present application.
Detailed Description
To further illustrate the technical means and effects of the present application for achieving the intended application purpose, the following detailed description is provided with reference to the accompanying drawings and preferred embodiments for specific implementation, method, steps, features and effects of the intelligent transportation, intelligent travel business matching planning device and method according to the present application.
The foregoing and other technical matters, features and effects of the present application will be apparent from the following detailed description of preferred embodiments, which is to be read in connection with the accompanying drawings. While the present application has been described in terms of specific embodiments and examples for achieving the desired objects and objectives, it is to be understood that the invention is not limited to the disclosed embodiments, but is to be accorded the widest scope consistent with the principles and novel features as defined by the appended claims.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of an intelligent travel business matching planning method according to the present application.
It should be noted that the method for planning a matching intelligent travel service according to the present embodiment may be applied to an intelligent terminal such as a mobile phone, a tablet computer, and a vehicle-mounted device, and may include, but is not limited to, the following steps.
Step S101, obtaining a service booking instruction of a user;
step S102, obtaining the booking intention of the user according to the service booking instruction;
step S103, acquiring historical data information of a user, and intelligently processing the booking intention according to the historical data information to obtain a service booking scheme according with the expectation of the user;
step S104, at least two service booking schemes which are connected with the matching service in time and/or space are provided.
It should be noted that, in the present embodiment, the step of acquiring the historical data information of the user and performing intelligent processing on the booking intention according to the historical data information specifically includes the following steps:
s31, collecting the historical data information of the user to generate a label file;
s32, generating a training sample according to the label file and the input and output of the local recurrent neural network;
s33, training the local recurrent neural network by adopting a differential evolution algorithm, and generating a weight and a threshold of the local recurrent neural network according to the training sample;
and S34, acquiring the booking intention approximation degree of the user to each travel service type according to the weight value and the threshold value of the local regression neural network.
It is easily understood that, in this embodiment, the training samples may also be updated at preset time intervals.
It should be noted that, in this embodiment, the step of providing at least two service subscription schemes that temporally and/or spatially link with a supporting service specifically includes: providing a first service and a second service which are realized to be connected with a matching service in time, or a first service and a second service which are realized to be connected with a matching service in space, or a first service and a second service which are realized to be connected with a matching service in time and space, wherein the first service and the second service comprise the same or different travel tools, the same or different living and eating services and the same or different third-party service application programs.
For example, the first service is a flight service, the second service is a connected vehicle service, or the first service is a vehicle service, the second service is a schedule alarm service, or the first service is a hotel service, the second service is a restaurant dining service, and so on.
For example, in one embodiment:
1. when a user meets at an office, a mobile phone software screen is lightened to display, a special car service is scheduled, and a car arrives in ten minutes;
2. meanwhile, the voice reminds the user that ' precious owners want to go to an airport, catch up with a seven-o ' clock airplane, and arrive ten minutes after a special car ';
3. after the user arrives at Beijing airport, the mobile phone is turned on, the screen is lighted up, and a prompt is given to 'special car arrives, p2 parking lot C11, you can just go in the past, white, Beijing, 122'.
In particular, it may adopt the following embodiments:
1. setting voice assistant software to read the short message information of the reserved flight of the user; or the calendar software knows the flight from which the user departed;
2. calculating the time of arrival of the user at the airport according to the current position and road conditions of the user;
3. reminding a user that the user should start and prompting whether to call a special car for delivery, and directly calling the car if the user determines;
4. the user can also be set to remind the user to start through the car, and if a long time is needed, the user needs to call the car in advance; after the car is delivered, reminding a user that the user has helped you call the car and needs to go out; ten minutes later, the finish will be downstairs and so on ";
5. when the user arrives at the destination airport, the assistant software also can remind the user that the user has called the vehicle automatically to realize the pick-up service.
Further, the generating of the training sample according to the input and the output of the labeled file and the local recurrent neural network in the embodiment specifically includes the following steps:
step S41, analyzing the markup file;
step S42, capturing training historical data information in the label file;
and step S43, generating training samples from the training historical data information according to the input and output structures or parameters of the local recurrent neural network.
It should be noted that, in this embodiment, training the local recurrent neural network by using a differential evolution algorithm, and generating a weight and a threshold of the local recurrent neural network according to the training sample specifically includes: judging whether the content distribution network server is available; under the condition that the content distribution network server is available, the training sample is sent to the content distribution network server, wherein the content distribution network server trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network; and under the condition that the content distribution network server is unavailable, the equipment per se trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network.
In a specific embodiment, the generating the weight and the threshold of the local recurrent neural network according to the training sample by using the differential evolution algorithm may specifically include the following implementation processes:
s51, initializing population and algorithm parameters by the local recurrent neural network according to the training sample;
s52, determining a fitness function, obtaining different network structures according to the individuals of the population and the algorithm parameters, and evaluating the network performance according to the fitness function value;
s53, performing variation operation, crossover operation and selection operation in sequence to generate a new population, decoding each individual in the new population to obtain a weight and a threshold value to form a neural network, and directly calculating the output error of the corresponding network as the fitness value of the individual in the new population;
and S54, when the fitness value reaches the maximum evolution algebra, decoding the optimal individuals in the new population to be used as the weight and the threshold of the local regression neural network.
It should be noted that, in the present embodiment, the historical data information of the user includes at least one of the following: the travel times, travel tool selection, travel time period selection and total cost of the user; the training sample comprises at least one of the following: departure time, trip duration, trip tools, return time and various consumption expense combination modes.
In addition, the step of acquiring the service subscription instruction of the user in this embodiment may specifically include:
s61, acquiring a service booking instruction input by the user voice;
s62, identity recognition and authentication verification are carried out through the voiceprint recognition technology;
and S63, after the voiceprint recognition technology carries out identity recognition and authentication verification, the service booking instruction is obtained by adopting semantic recognition technology for recognition.
The method and the device can provide an intelligent and rapid service booking function for the user, facilitate the user to carry out convenient travel action, provide personalized close-fitting service according to the individual habit of the user, and improve user experience.
Referring to fig. 2, as an implementation manner, the present application further provides an intelligent travel service complement planning apparatus, which includes a memory 20 and a processor 21, where the memory 20 stores an intelligent travel planning program, and the processor 21 is configured to execute the intelligent travel planning program to implement the steps of the intelligent travel service complement planning method as described above.
It should be noted that, the intelligent travel service matching planning apparatus according to this embodiment may be an intelligent user device such as a mobile phone, a car machine device, a tablet computer, and the like, which is not limited herein.
Specifically, the processor 21 is configured to obtain a service subscription instruction of a user;
the processor 21 is configured to obtain a subscription intention of the user according to the service subscription instruction;
the processor 21 is configured to obtain historical data information of a user, and perform intelligent processing on the booking intention according to the historical data information to obtain a service booking scheme meeting expectations of the user;
the processor 21 is configured to provide at least two service subscription schemes for temporally and/or spatially linking with the supporting service.
It should be noted that, in the embodiment, the acquiring historical data information of the user and intelligently processing the booking intention according to the historical data information specifically includes the following steps:
the processor 21 is configured to collect historical data information of a user to generate a markup file;
the processor 21 is configured to generate a training sample according to the markup file and the input and output of the local recurrent neural network;
the processor 21 is configured to train the local recurrent neural network by using a differential evolution algorithm, and generate a weight and a threshold of the local recurrent neural network according to the training sample;
the processor 21 is configured to obtain a booking intention approximation degree of each travel service type by the user according to the weight and the threshold of the local recurrent neural network.
It is easily understood that, in this embodiment, the training samples may also be updated at preset time intervals.
It should be noted that, in this embodiment, the step of providing at least two service subscription schemes that temporally and/or spatially link with a supporting service specifically includes: providing a first service and a second service which are realized to be connected with a matching service in time, or a first service and a second service which are realized to be connected with a matching service in space, or a first service and a second service which are realized to be connected with a matching service in time and space, wherein the first service and the second service comprise the same or different travel tools, the same or different living and eating services and the same or different third-party service application programs.
For example, the first service is a flight service, the second service is a connected vehicle service, or the first service is a vehicle service, the second service is a schedule alarm service, or the first service is a hotel service, the second service is a restaurant dining service, and so on.
For example, in one embodiment:
1. when a user meets at an office, a mobile phone software screen is lightened to display, a special car service is scheduled, and a car arrives in ten minutes;
2. meanwhile, the voice reminds the user that ' precious owners want to go to an airport, catch up with a seven-o ' clock airplane, and arrive ten minutes after a special car ';
3. after the user arrives at Beijing airport, the mobile phone is turned on, the screen is lighted up, and a prompt is given to 'special car arrives, p2 parking lot C11, you can just go in the past, white, Beijing, 122'.
In particular, it may adopt the following embodiments:
1. setting voice assistant software to read the short message information of the reserved flight of the user; or the calendar software knows the flight from which the user departed;
2. calculating the time of arrival of the user at the airport according to the current position and road conditions of the user;
3. reminding a user that the user should start and prompting whether to call a special car for delivery, and directly calling the car if the user determines;
4. the user can also be set to remind the user to start through the car, and if a long time is needed, the user needs to call the car in advance; after the car is delivered, reminding a user that the user has helped you call the car and needs to go out; ten minutes later, the finish will be downstairs and so on ";
5. when the user arrives at the destination airport, the assistant software also can remind the user that the user has called the vehicle automatically to realize the pick-up service.
Further, the generating of the training sample according to the input and the output of the labeled file and the local recurrent neural network in the embodiment specifically includes the following steps:
the processor 21 is configured to parse the markup file;
the processor 21 is configured to capture training history data information in the markup file;
the processor 21 is configured to generate training samples from the training history data information according to the input and output structures or parameters of the local recurrent neural network.
It should be noted that, in this embodiment, the processor 21 is configured to train the local recurrent neural network by using a differential evolution algorithm, and generate a weight and a threshold of the local recurrent neural network according to the training sample, specifically including: the processor 21 is configured to determine whether a content distribution network server is available; under the condition that the content distribution network server is available, the training sample is sent to the content distribution network server, wherein the content distribution network server trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network; and under the condition that the content distribution network server is unavailable, the equipment per se trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network.
In a specific embodiment, the processor 21 is configured to generate the weights and the threshold of the local recurrent neural network according to the training sample by using a differential evolution algorithm, and specifically may include the following implementation processes:
s51, initializing population and algorithm parameters by the local recurrent neural network according to the training sample;
s52, determining a fitness function, obtaining different network structures according to the individuals of the population and the algorithm parameters, and evaluating the network performance according to the fitness function value;
s53, performing variation operation, crossover operation and selection operation in sequence to generate a new population, decoding each individual in the new population to obtain a weight and a threshold value to form a neural network, and directly calculating the output error of the corresponding network as the fitness value of the individual in the new population;
and S54, when the fitness value reaches the maximum evolution algebra, decoding the optimal individuals in the new population to be used as the weight and the threshold of the local regression neural network.
It should be noted that, in the present embodiment, the historical data information of the user includes at least one of the following: the travel times, travel tool selection, travel time period selection and total cost of the user; the training sample comprises at least one of the following: departure time, trip duration, trip tools, return time and various consumption expense combination modes.
In addition, the processor 21 in this embodiment is configured to obtain a service subscription instruction of a user, and specifically may include:
the processor 21 is configured to obtain a service subscription instruction input by a user voice;
the processor 21 is used for identity recognition and authentication verification through a voiceprint recognition technology;
the processor 21 is configured to obtain the service subscription instruction by using a semantic recognition technology to recognize after the voiceprint recognition technology performs identity recognition and authentication verification.
The method and the device can provide an intelligent and rapid service booking function for the user, facilitate the user to carry out convenient travel action, provide personalized close-fitting service according to the individual habit of the user, and improve user experience.
Correspondingly, the application also provides an intelligent vehicle, and as one implementation mode, the intelligent vehicle is configured with the intelligent travel service matching planning device.
Specifically, the intelligent vehicle according to the present embodiment may be a vehicle, an aircraft, or other vehicle-mounted device, and is not limited herein.
In the intelligent transportation tool of the embodiment, the vehicle and the intelligent travel service matching planning device are combined by using the vehicle-mounted equipment, so that the embodiment of the intelligent travel service matching planning method is realized.
It is worth mentioning that the vehicle and the vehicle-mounted device in the embodiment may adopt a 5G communication network technology, and may be a technology oriented to a scene, and the application uses the 5G technology to play a key supporting role for the vehicle (especially an intelligent internet automobile), and simultaneously realizes connection of people, objects or vehicles, and may specifically adopt the following three typical application scenarios.
The first is eMBB (enhanced Mobile Broadband), which enables the user experience rate to be 0.1-1 gpbs, the peak rate to be 10 gpbs, and the traffic density to be 10Tbps/km2；
For the second ultra-reliable low-delay communication, the main index which can be realized by the method is that the end-to-end time delay is in the ms (millisecond) level; the reliability is close to 100%;
the third is mMTC (mass machine type communication), and the main indexes which can be realized by the method are the connection number density, 100 ten thousand other terminals are connected per square kilometer, and 106/km2。
Through the mode, the characteristics of the super-reliable of this application utilization 5G technique, low time delay combine for example radar and camera etc. just can provide the ability that shows for the vehicle, can realize interdynamic with the vehicle, utilize the interactive perception function of 5G technique simultaneously, and the user can do an output to external environment, and the unable light can detect the state, can also do some feedbacks etc.. Further, the method and the device can also be applied to cooperation of automatic driving, such as cooperation type collision avoidance and vehicle formation among vehicles, so that the vehicle speed is integrally formed and the passing efficiency is improved.
In addition, the communication enhancement automatic driving perception capability can be achieved by utilizing the 5G technology, and the requirements of passengers in the automobile on AR (augmented reality)/VR (virtual reality), games, movies, mobile office and other vehicle-mounted information entertainment and high precision can be met. According to the method and the device, the downloading amount of the 3D high-precision positioning map at the centimeter level can be 3-4 Gb/km, the data volume of the map per second under the condition that the speed of a normal vehicle is limited to 120km/h (kilometer per hour) is 90 Mbps-120 Mbps, and meanwhile, the real-time reconstruction of a local map fused with vehicle-mounted sensor information, modeling and analysis of dangerous situations and the like can be supported.
It should be noted that the method and the device can also be applied to an automatic driving layer, can assist in realizing partial intelligent cloud control on the urban fixed route vehicles by utilizing a 5G technology, and can realize cloud-based operation optimization and remote display and control under specific conditions on unmanned vehicles in parks and ports.
In the present application, the above-mentioned system and method CAN be used in a vehicle system having a vehicle TBOX, i.e. the vehicle is a vehicle system that CAN have a vehicle TBOX, and CAN be further connected to a CAN bus of the vehicle.
In this embodiment, the CAN may include three network channels CAN _1, CAN _2, and CAN _3, and the vehicle may further include one ethernet network channel, where the three CAN network channels may be connected to the ethernet network channel through two in-vehicle networking gateways, for example, where the CAN _1 network channel includes a hybrid power assembly system, where the CAN _2 network channel includes an operation support system, where the CAN _3 network channel includes an electric dynamometer system, and the ethernet network channel includes a high-level management system, the high-level management system includes a human-vehicle-road simulation system and a comprehensive information collection unit that are connected as nodes to the ethernet network channel, and the in-vehicle networking gateways of the CAN _1 network channel, the CAN _2 network channel, and the ethernet network channel may be integrated in the comprehensive information collection unit; the car networking gateway of the CAN _3 network channel and the Ethernet network channel CAN be integrated in a man-car-road simulation system.
Further, the nodes connected to the CAN _1 network channel include: the hybrid power system comprises an engine ECU, a motor MCU, a battery BMS, an automatic transmission TCU and a hybrid power controller HCU; the nodes connected with the CAN _2 network channel are as follows: the system comprises a rack measurement and control system, an accelerator sensor group, a power analyzer, an instantaneous oil consumption instrument, a direct-current power supply cabinet, an engine water temperature control system, an engine oil temperature control system, a motor water temperature control system and an engine intercooling temperature control system; the nodes connected with the CAN _3 network channel are as follows: electric dynamometer machine controller.
The preferable speed of the CAN _1 network channel is 250Kbps, and a J1939 protocol is adopted; the rate of the CAN _2 network channel is 500Kbps, and a CANopen protocol is adopted; the rate of the CAN _3 network channel is 1Mbps, and a CANopen protocol is adopted; the rate of the Ethernet network channel is 10/100Mbps, and a TCP/IP protocol is adopted.
In this embodiment, the car networking gateway supports a 5G technology V2X car networking network, which may also be equipped with an IEEE802.3 interface, a DSPI interface, an eSCI interface, a CAN interface, an MLB interface, a LIN interface, and/or an I2C interface.
In this embodiment, for example, the IEEE802.3 interface may be used to connect to a wireless router to provide a WIFI network for the entire vehicle; the DSPI (provider manager component) interface is used for connecting a Bluetooth adapter and an NFC (near field communication) adapter and can provide Bluetooth connection and NFC connection; the eSCI interface is used for connecting the 4G/5G module and communicating with the Internet; the CAN interface is used for connecting a vehicle CAN bus; the MLB interface is used for connecting an MOST (media oriented system transmission) bus in the vehicle, and the LIN interface is used for connecting a LIN (local interconnect network) bus in the vehicle; the IC interface is used for connecting a DSRC (dedicated short-range communication) module and a fingerprint identification module. In addition, the application can merge different networks by mutually converting different protocols by adopting the MPC5668G chip.
In addition, the vehicle TBOX system, Telematics-BOX, of the present embodiment is simply referred to as a vehicle TBOX or a Telematics.
Telematics is a synthesis of Telecommunications and information science (information) and is defined as a service system that provides information through a computer system, a wireless communication technology, a satellite navigation device, and an internet technology that exchanges information such as text and voice, which are built in a vehicle. In short, the vehicle is connected to the internet (vehicle networking system) through a wireless network, and various information necessary for driving and life is provided for the vehicle owner.
In addition, Telematics is a combination of wireless communication technology, satellite navigation system, network communication technology and vehicle-mounted computer, when a fault occurs during vehicle running, the vehicle is remotely diagnosed by connecting a service center through wireless communication, and the computer built in the engine can record the state of main parts of the vehicle and provide accurate fault position and reason for maintenance personnel at any time. The vehicle can receive information and check traffic maps, road condition introduction, traffic information, safety and public security services, entertainment information services and the like through the user communication terminal, and in addition, the vehicle of the embodiment can be provided with electronic games and network application in a rear seat. It is easy to understand that, this embodiment provides service through Telematics, can make things convenient for the user to know traffic information, the parking stall situation that closes on the parking area, confirms current position, can also be connected with the network server at home, in time knows electrical apparatus running condition, the safety condition and guest's condition of visiting etc. at home.
The vehicle according to this embodiment may further include an Advanced Driver Assistance System (ADAS) that collects environmental data inside and outside the vehicle at the first time using the various sensors mounted on the vehicle, and performs technical processing such as identification, detection, and tracking of static and dynamic objects, so that a Driver can recognize a risk that may occur at the fastest time, thereby attracting attention and improving safety. Correspondingly, the ADAS of the present application may also employ sensors such as radar, laser, and ultrasonic sensors, which can detect light, heat, pressure, or other variables for monitoring the state of the vehicle, and are usually located on the front and rear bumpers, side view mirrors, the inside of the steering column, or on the windshield of the vehicle. It is obvious that various intelligent hardware used by the ADAS function can access the V2X car networking network by means of an ethernet link to implement communication connection and interaction.
The host computer of the present embodiment vehicle may comprise suitable logic, circuitry, and/or code that may enable operation and/or functional operation of the five layers above the OSI model (Open System Interconnection, Open communication systems Interconnection reference model). Thus, the host may generate and/or process packets for transmission over the network, and may also process packets received from the network. At the same time, the host may provide services to a local user and/or one or more remote users or network nodes by executing corresponding instructions and/or running one or more applications. In various embodiments of the present application, the host may employ one or more security protocols.
In the present application, the network connection used to implement the V2X car networking network may be a switch, which may have AVB functionality (Audio Video brightening, meeting the IEEE802.1 set of standards), and/or include one or more unshielded twisted pair wires, each of which may have an 8P8C module connector.
In a preferred embodiment, the V2X vehicle networking network specifically comprises a vehicle body control module BCM, a power bus P-CAN, a vehicle body bus I-CAN, a combination instrument CMIC, a chassis control device and a vehicle body control device.
In this embodiment, the body control module BCM may integrate the functions of the car networking gateway to perform signal conversion, message forwarding, and the like between different network segments, i.e., between the power bus P-CAN and the body bus I-CAN, for example, if a controller connected to the power bus needs to communicate with a controller connected to the body bus I-CAN, the body control module BCM may perform signal conversion, message forwarding, and the like between the two controllers.
The power bus P-CAN and the vehicle body bus I-CAN are respectively connected with a vehicle body control module BCM.
The combination instrument CMIC is connected with a power bus P-CAN, and the combination instrument CMIC is connected with a vehicle body bus I-CAN. Preferably, the combination meter CMIC of the present embodiment is connected to different buses, such as a power bus P-CAN and a vehicle body bus I-CAN, and when the combination meter CMIC needs to acquire controller information that is hung on any bus, it is not necessary to perform signal conversion and message forwarding through a vehicle body control module BCM, so that gateway pressure CAN be reduced, network load CAN be reduced, and the speed of acquiring information by the combination meter CMIC CAN be increased.
The chassis control device is connected with the power bus P-CAN. The vehicle body control device is connected with a vehicle body bus I-CAN. In some examples, the chassis control device and the body control device CAN respectively broadcast data such as information to the power bus P-CAN and the body bus I-CAN, so that other vehicle-mounted controllers and other devices hung on the power bus P-CAN or the body bus I-CAN CAN acquire the broadcast information, and communication between the vehicle-mounted devices such as different controllers is realized.
In addition, the V2X car networking network of the vehicle of the embodiment may use two CAN buses, i.e., a power bus P-CAN and a car body bus I-CAN, and use the car body control module BCM as a gateway, and a structure that the combination meter CMIC is connected to both the power bus P-CAN and the car body bus I-CAN, so that an operation that information of the chassis control device or the car body control device is forwarded to the combination meter CMIC through the gateway when the combination meter CMIC is hung on one of the two buses in the conventional manner CAN be omitted, thereby reducing the pressure of the car body control module BCM as a gateway, reducing network load, and more conveniently sending information of vehicle-mounted devices hung on the plurality of buses, e.g., the power bus P-CAN and the car body bus I-CAN, to the combination meter CMIC for display and with strong information transmission real-time.
According to the embodiment, the identity recognition and identification of the user can be realized by voice awakening keywords and using a voiceprint recognition technology and the like, the time period can be considered preferentially by mining the historical travel time preference of the user for traveling the destination, and the user does not need to input time again; the travel tool time of the historical travel time end can be prompted preferentially; in addition, the method and the device can reduce the input times of the user by mining the preference of the user for travel, such as the type of a high-speed railway ticket and a flight company.
Although the present application has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the application, and all changes, substitutions and alterations that fall within the spirit and scope of the application are to be understood as being included within the following description of the preferred embodiment.
Claims (10)
1. An intelligent travel service matching planning method is characterized by comprising the following steps:
acquiring a service booking instruction of a user;
obtaining the booking intention of the user according to the service booking instruction;
acquiring historical data information of a user, and intelligently processing the booking intention according to the historical data information to obtain a service booking scheme according with the expectation of the user;
at least two service booking schemes are provided which temporally and/or spatially link the associated services.
2. The intelligent travel business coordination planning method according to claim 1, wherein the step of providing at least two business booking schemes matching the coordination service in time and/or space specifically comprises:
providing a first service and a second service which are realized to be connected with a matching service in time, or a first service and a second service which are realized to be connected with a matching service in space, or a first service and a second service which are realized to be connected with a matching service in time and space, wherein the first service and the second service comprise the same or different travel tools, the same or different living and eating services and the same or different third-party service application programs.
3. The intelligent travel service matching planning method according to claim 2, wherein the step of obtaining historical data information of the user and intelligently processing the booking intention according to the historical data information specifically comprises:
collecting historical data information of a user to generate a marking file;
generating a training sample according to the label file and the input and the output of the local recurrent neural network;
training the local recurrent neural network by adopting a differential evolution algorithm, and generating a weight and a threshold of the local recurrent neural network according to the training sample;
and acquiring the booking intention approximation degree of the user to each travel service type according to the weight value and the threshold value of the local regression neural network.
4. The intelligent travel service matching planning method according to claim 3, wherein the generating of the training sample according to the markup file and the input and output of the local recurrent neural network specifically comprises:
analyzing the marked file;
capturing training historical data information in the marked file;
and generating training samples from the training historical data information according to the input and output structures or parameters of the local recurrent neural network.
5. The intelligent travel service matching planning method according to claim 3, wherein the training of the local recurrent neural network by using a differential evolution algorithm and the generation of the weight and the threshold of the local recurrent neural network according to the training samples specifically include:
judging whether the content distribution network server is available;
under the condition that the content distribution network server is available, the training sample is sent to the content distribution network server, wherein the content distribution network server trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network; and under the condition that the content distribution network server is unavailable, the equipment per se trains a local recurrent neural network by adopting a differential evolution algorithm according to the training sample so as to generate a weight value and a threshold value of the local recurrent neural network.
6. The intelligent travel service matching planning method according to claim 5, wherein the generating of the weights and the threshold values of the local recurrent neural network according to the training samples by using a differential evolution algorithm specifically comprises:
the local regression neural network initializes population and algorithm parameters according to the training samples;
determining a fitness function, obtaining different network structures according to individuals and algorithm parameters of the population, and evaluating the network performance according to the fitness function value;
carrying out variation operation, cross operation and selection operation in sequence to generate a new population, decoding each individual in the new population to obtain a weight and a threshold value to form a neural network, and directly calculating an output error of the corresponding network as a fitness value of the individual in the new population;
and when the fitness value reaches the maximum evolution algebra, decoding the optimal individuals in the new population to be used as the weight and the threshold of the local regression neural network.
7. The intelligent travel service complement planning method according to any one of claims 1-6, wherein the historical data information of the user includes at least one of: the travel times, travel tool selection, travel time period selection and total cost of the user; the training sample comprises at least one of the following: departure time, trip duration, trip tools, return time and various consumption expense combination modes.
8. The intelligent travel service coordination planning method according to any one of claims 1 to 6, wherein the step of obtaining a service booking instruction of a user specifically comprises:
acquiring a service booking instruction input by a user voice;
identity recognition and authentication verification are carried out through a voiceprint recognition technology;
and after the voiceprint recognition technology carries out identity recognition and authentication verification, adopting a semantic recognition technology to recognize and obtain the service booking instruction.
9. An intelligent travel business coordination planning device, comprising a memory and a processor, wherein the memory stores an intelligent travel planning program, and the processor is used for executing the intelligent travel planning program to realize the steps of the intelligent travel business coordination planning method according to any one of claims 1-8.
10. An intelligent vehicle, characterized in that the intelligent vehicle is equipped with the intelligent travel service complement planning device according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911255101.2A CN111126949A (en) | 2019-12-10 | 2019-12-10 | Intelligent transportation tool, and intelligent travel service matching planning device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911255101.2A CN111126949A (en) | 2019-12-10 | 2019-12-10 | Intelligent transportation tool, and intelligent travel service matching planning device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126949A true CN111126949A (en) | 2020-05-08 |
Family
ID=70497870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911255101.2A Pending CN111126949A (en) | 2019-12-10 | 2019-12-10 | Intelligent transportation tool, and intelligent travel service matching planning device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126949A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303487A (en) * | 2015-10-27 | 2016-02-03 | 北京妙计科技有限公司 | Method and device of travel service |
| CN106326984A (en) * | 2016-08-09 | 2017-01-11 | 北京京东尚科信息技术有限公司 | User intention identification method and device and automatic answering system |
| CN108399526A (en) * | 2018-01-31 | 2018-08-14 | 上海思愚智能科技有限公司 | Schedule based reminding method and device |
| CN109916423A (en) * | 2017-12-12 | 2019-06-21 | 上海博泰悦臻网络技术服务有限公司 | Intelligent navigation equipment and its route planning method and automatic driving vehicle |
-
2019
- 2019-12-10 CN CN201911255101.2A patent/CN111126949A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303487A (en) * | 2015-10-27 | 2016-02-03 | 北京妙计科技有限公司 | Method and device of travel service |
| CN106326984A (en) * | 2016-08-09 | 2017-01-11 | 北京京东尚科信息技术有限公司 | User intention identification method and device and automatic answering system |
| CN109916423A (en) * | 2017-12-12 | 2019-06-21 | 上海博泰悦臻网络技术服务有限公司 | Intelligent navigation equipment and its route planning method and automatic driving vehicle |
| CN108399526A (en) * | 2018-01-31 | 2018-08-14 | 上海思愚智能科技有限公司 | Schedule based reminding method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110798658A (en) | Remote vehicle moving control method, mobile terminal and vehicle | |
| CN108923808A (en) | Vehicle and its car-mounted terminal and speech interaction mode active triggering method | |
| CN108833589B (en) | Vehicle, vehicle equipment and vehicle equipment navigation data synchronization method thereof | |
| CN110920540B (en) | Vehicle, vehicle equipment and vehicle equipment theme automatic adjusting method thereof | |
| CN111311939A (en) | Vehicle, vehicle equipment and traffic light information map display method thereof | |
| CN110954117B (en) | Vehicle and navigation journey service pushing method thereof and cloud server | |
| CN109115235A (en) | Vehicle, vehicle device equipment, user communication terminal and its more equipment switch air navigation aid | |
| CN110576808B (en) | Vehicle, vehicle machine equipment and scene information pushing method based on artificial intelligence | |
| CN110958559A (en) | Vehicle, vehicle equipment and instant interaction method based on map display | |
| CN110654331A (en) | Vehicle, vehicle equipment and vehicle-mounted assistant interaction method thereof | |
| CN110920388B (en) | Vehicle, vehicle equipment and vehicle equipment style adjusting method based on environmental factors | |
| CN111291275A (en) | Vehicle, vehicle equipment and live-based tour scheme recommendation method thereof | |
| CN112017459A (en) | Vehicle, vehicle equipment and driving assistance method for signal lamp recognition thereof | |
| CN110954127A (en) | Vehicle, user terminal and navigation map theme automatic adjusting method thereof | |
| CN111047292A (en) | Intelligent transportation tool, intelligent equipment and intelligent travel reminding method | |
| CN111311943A (en) | Vehicle, vehicle equipment and signal lamp vehicle speed optimization method thereof | |
| CN110871810A (en) | Vehicle, vehicle equipment and driving information prompting method based on driving mode | |
| CN110853384A (en) | Vehicle and traffic light vehicle speed matching optimization system and method based on 5G technology | |
| CN111284325B (en) | Vehicle, vehicle equipment and vehicle along-the-road object detailed information display method thereof | |
| CN111291142A (en) | Vehicle, vehicle equipment and personalized vehicle equipment interest point searching and displaying method thereof | |
| CN111289009A (en) | Vehicle, vehicle equipment and vehicle equipment interest point input searching method thereof | |
| CN110689713A (en) | Vehicle, vehicle equipment and vehicle association control method thereof | |
| CN111024106A (en) | Vehicle, navigation device and integrated navigation planning method thereof | |
| CN111328042A (en) | Vehicle and equipment operation information display method and system thereof | |
| CN108983773A (en) | Vehicle, vehicle device equipment, user communication terminal and its stroke automatic planning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ying Zhenkai Inventor before: Ying Yilun |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210702 Address after: Room 208, building 4, 1411 Yecheng Road, Jiading District, Shanghai, 201821 Applicant after: SHANGHAI PATEO ELECTRONIC EQUIPMENT MANUFACTURING Co.,Ltd. Applicant after: SAIC GM WULING AUTOMOBILE Co.,Ltd. Address before: Room 208, building 4, 1411 Yecheng Road, Jiading District, Shanghai, 201821 Applicant before: SHANGHAI PATEO ELECTRONIC EQUIPMENT MANUFACTURING Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 208, building 4, 1411 Yecheng Road, Jiading District, Shanghai, 201821 Applicant after: Botai vehicle networking technology (Shanghai) Co.,Ltd. Applicant after: SAIC GM WULING AUTOMOBILE Co.,Ltd. Address before: Room 208, building 4, 1411 Yecheng Road, Jiading District, Shanghai, 201821 Applicant before: SHANGHAI PATEO ELECTRONIC EQUIPMENT MANUFACTURING Co.,Ltd. Applicant before: SAIC GM WULING AUTOMOBILE Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |