User travel habit-oriented message mining and pushing method and system

Abstract

The invention provides a user travel habit oriented message mining and pushing method and system, and belongs to the technical field of vehicle-mounted information services, and the method comprises the steps: obtaining a vehicle driving state, a vehicle driving track and the corresponding time of the vehicle driving track; obtaining a user travel habit according to the vehicle driving track and the corresponding time of the vehicle driving track, and generating a predicted travel route and travel time of the next travel based on the user travel habit; acquiring hotspot information and traffic information according to the predicted travel route and travel time, and generating a message queue; and determining a message queue pushing opportunity and mode according to the vehicle driving state. According to the method and the system, the travel route and time are predicted or planned in advance based on the travel habits of the user, so that the message mining and pushing can be accurately performed according to the predicted or planned route, the requirements of the user are well met, the relationship with the user is closer, and the product recognition sense of the user can be increased.

Description

Technical Field

[0001] This invention relates to the field of vehicle information service technology, and in particular to a method and system for message mining and push based on users' travel habits. Background Technology

[0002] With the development of smartphone applications for smart cars, driving and operating vehicles has become simpler for users, while making travel smarter and more convenient. Considering the characteristics of users' driving behavior, taking commuting to work as an example, with fixed times and routes, in order to solve problems that users may encounter before they set off and to provide users with different travel experiences, we can push the latest network hotspots or traffic control information related to the relevant routes to users, allowing them to plan their routes in advance.

[0003] However, existing technologies are all based on the internal and external environmental information of the vehicle to realize scenario-based message push, which focuses on reminders and does not provide more real-time messages and warnings based on the user's driving behavior habits, and cannot make predictions or plans in advance. Summary of the Invention

[0004] This invention aims to solve at least one of the aforementioned problems in the prior art by proposing a message mining and push method. Based on information such as users' historical route preferences and favorite routes, combined with real-time network information monitoring and driving behavior analysis, it provides intelligent information push, offering warnings or recommendations to users before they travel.

[0005] In a first aspect, embodiments of the present invention provide a method for message mining and push based on users' travel habits, including:

[0006] Obtain vehicle driving status, vehicle driving trajectory, and the corresponding time of the vehicle driving trajectory;

[0007] Based on the vehicle's driving trajectory and the corresponding time, the user's travel habits are obtained, and the expected travel route and travel time for the next trip are generated based on the user's travel habits.

[0008] Based on the expected travel route and travel time, obtain hotspot information and traffic information, and generate a message queue;

[0009] The timing and method of message queue push are determined based on the vehicle's driving status.

[0010] In a preferred embodiment, the step of obtaining user travel habits based on vehicle travel trajectories and their corresponding times, and generating the expected travel route and travel time for the next trip based on these user travel habits, includes:

[0011] The vehicle's trajectory within the first preset time period is determined based on the corresponding time of the vehicle's trajectory.

[0012] Based on the vehicle's driving trajectory within a first preset time period, highly repetitive travel patterns are identified as user travel habits. The travel patterns include travel routes, locations, and departure time periods.

[0013] Based on users' travel habits, the next travel destination is generated through natural language processing and word frequency statistics.

[0014] Based on the next travel destination and the map API, the expected travel route for the next trip is generated, and the set of locations to be passed through and the travel time are calculated based on the expected travel route.

[0015] In a preferred embodiment, the step of obtaining hotspot information and traffic information based on the expected travel route and travel time, and generating a message queue, includes:

[0016] Using the set of locations along the expected travel route as keywords, hotspot information and traffic information within a second preset time period before the travel time are obtained, forming a hotspot information set and a traffic information set;

[0017] Calculate and sort the importance of messages in the hotspot information set and traffic information set, and generate a message queue.

[0018] In a preferred embodiment, the step of calculating and ranking the importance of messages in the hotspot information set and traffic information set, and generating a message queue, includes:

[0019] Each message in the hot topic information set and traffic information set is segmented into words and divided into three levels through natural language processing: warning level, suggestion level, and ordinary message level, which are stored in the warning level message queue, suggestion level message queue, and ordinary message level message queue, respectively.

[0020] In a preferred embodiment, the step of calculating and ranking the importance of messages in the hotspot information set and traffic information set, and generating a message queue, further includes:

[0021] Using term frequency and inverse document frequency algorithms, ordinary message-level messages are divided into three dimensions to calculate scores:

[0022] Spatial dimension: Based on messages in the normal message level With messages The locations mentioned in the planned travel route Calculate the spatial dimension score: Where score1 is the spatial dimension score, This is the TF-IDF algorithm formula. It is a corpus of ordinary message-level messages;

[0023] Time dimension: Scenarios are divided based on the expected travel route and travel time, and based on the scenario... The pre-set word segmentation calculation time dimension score: In this context, score2 represents the score over time.

[0024] Behavioral dimension: A behavioral dimension score is calculated by combining historical feedback data on user clicks to view and skip push notifications. In this context, score3 represents the behavioral dimension score, where X represents the historical data that the user clicked to view, and Y represents the historical data that was pushed to the user but not viewed.

[0025] The correlation between each ordinary message and the expected travel route is calculated based on the scores of the ordinary message level across three dimensions: Where α is the correlation degree, and k1, k2, and k3 are preset weight values;

[0026] Messages at the ordinary message level are sorted by their relevance, and messages with a relevance greater than a preset threshold are stored in the ordinary message level message queue.

[0027] In a preferred embodiment, the step of determining the message queue push timing and method based on the vehicle's driving status includes:

[0028] If the traveler does not travel during the designated travel time and the warning-level message queue and suggestion-level message queue are not empty, push messages from the warning-level message queue and suggestion-level message queue.

[0029] If the traveler does not travel during the designated travel time and both the warning-level and suggestion-level message queues are empty, messages from the normal message-level message queue will be pushed.

[0030] In a preferred embodiment, the step of determining the message queue push timing and method based on the vehicle's driving status further includes:

[0031] When the trip has already started and the warning-level message queue is not empty, update the expected travel route to the actual route and execute the steps of obtaining hotspot information and traffic information based on the expected travel route L and travel time T to generate a message queue, and determine the timing and method of message queue push based on the vehicle's driving status.

[0032] In a second aspect, embodiments of the present invention provide a message mining and push system for user travel habits, configured to implement any of the methods described in the first aspect, the system comprising:

[0033] The data acquisition layer is used to obtain the vehicle's driving status, vehicle trajectory, and the corresponding time of the vehicle trajectory;

[0034] The trajectory analysis layer is used to obtain users' travel habits based on vehicle travel trajectories and the corresponding times of vehicle travel trajectories, and to generate the expected travel route and travel time for the next trip based on users' travel habits.

[0035] The message analysis layer is used to obtain hotspot information and traffic information based on the expected travel route and travel time, and generate message queues.

[0036] The push decision layer is used to determine the timing and method of message queue pushes based on the vehicle's driving status.

[0037] Thirdly, embodiments of the present invention provide an electronic device, including:

[0038] One or more processors;

[0039] Memory, used to store one or more programs;

[0040] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described in the first aspect.

[0041] Fourthly, embodiments of the present invention provide a computer-readable medium storing a computer program that, when executed by a processor, implements the steps of any of the methods described in the first aspect.

[0042] Beneficial effects of this invention:

[0043] This invention addresses user travel habits by predicting or planning travel routes and times in advance. As a result, it can accurately mine and push messages based on the predicted or planned routes, which effectively meets user needs, strengthens the relationship with users, and increases users' sense of product identification.

[0044] This invention can simulate the driver's next travel route and timing, providing the driver with information to know before the trip, and can provide risk warnings before the trip.

[0045] This invention can solve problems that users may encounter before they travel and provide them with a different travel experience. It can push the latest online hotspots or traffic control information related to the route to users, so that users can plan their routes in advance.

[0046] This invention primarily targets commuters and other car owners with relatively fixed routes, and has a significant impact. On one hand, it can provide risk warnings before travel; on the other hand, the pushed messages can add a unique narrative to the commute route. Furthermore, users can make various plans along the way based on the pushed messages, such as information about new store events. This invention, through its message push method, fosters a closer relationship with car owners and increases their sense of product identification. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the overall process of a message mining and push method based on user travel habits provided in an embodiment of the present invention.

[0048] Figure 2 This is a schematic diagram of a message mining and push method based on user travel habits provided in an embodiment of the present invention.

[0049] Figure 3 This is a schematic flowchart of an optional implementation of step S3 provided in an embodiment of the present invention.

[0050] Figure 4 This is a schematic diagram of a message mining and push system based on user travel habits, provided as an embodiment of the present invention.

[0051] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0052] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0053] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0054] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0055] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0056] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0057] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0058] The related technologies propose a vehicle scene recommendation method and related equipment technical solution. The technical solution adopts a vehicle-end and cloud-end integrated architecture, which is divided into a vehicle-end engine and a cloud-end engine. The cloud-end engine adopts scene rule visualization configuration and real-time recommendation technology to realize dynamic real-time push scene recommendation content to the vehicle end. The vehicle-end engine is responsible for collecting the user's weather, environment, road conditions and other parameters in real time and reporting them to the cloud-end engine, and obtaining the scene recommendation content issued by the cloud-end engine to display to the user. The technical solution obtains real-time driving data through the vehicle end, configures rules through the cloud, and then pushes the message to the vehicle end through the cloud to achieve the real-time scene push effect. However, the technical solution has the following limitations: (1) The scene-based message push is based on the internal environment information and external environment information of the vehicle end, and cannot provide more real-time messages and warnings based on the user's driving behavior habits, and cannot make predictions or plans in advance; (2) If the vehicle end is frequently pushed while the user is driving, it is easy to cause the driver to be distracted and there is a driving risk.

[0059] In summary, the message mining and push technologies involved in the relevant technologies are only for reminders, and do not take into account users' travel habits, nor do they achieve advance prediction or planning.

[0060] In this embodiment, for ease of description, the cloud is used as the execution subject in the following description. The cloud can be a software module, or other electronic devices capable of performing the following functions.

[0061] like Figure 1 As shown in the figure, the overall process of a message mining and push method based on user travel habits provided by this embodiment of the invention is as follows: analyze vehicle travel habits; obtain relevant online hotspots and related traffic information for the day; calculate the importance of the information; obtain vehicle status; and push the information to the APP at regular intervals.

[0062] Figure 2 This is a flowchart illustrating a message mining and push method based on user travel habits provided in an embodiment of the present invention; as shown below. Figure 2 As shown, the method includes:

[0063] Step S1: Obtain the vehicle driving status, vehicle driving trajectory, and the corresponding time of the vehicle driving trajectory;

[0064] Step S2: Obtain user travel habits based on vehicle travel trajectory and corresponding time, and generate the expected travel route L and travel time T for the next trip based on user travel habits;

[0065] Step S3: Obtain hotspot information and traffic information based on the expected travel route L and travel time T, and generate a message queue;

[0066] Step S4: Determine the timing and method for pushing messages to the message queue based on the vehicle's driving status.

[0067] The above steps of the present invention can simulate the driver's next travel route and time based on the user's travel habits, and obtain a message queue to push to the driver based on the hot spot information and traffic information obtained from the next travel route and time, thereby providing the driver with information content that can be known before the trip.

[0068] This demonstrates that the present invention is geared towards users' travel habits, and predicts or plans travel routes and times in advance based on these habits. As a result, it can accurately mine and push messages based on the predicted or planned routes, which effectively meets users' needs, makes the relationship with users closer, and also increases users' sense of product recognition.

[0069] In some embodiments, step S2, which involves obtaining user travel habits based on vehicle travel trajectories and their corresponding times, and generating the expected travel route L and travel time T for the next trip based on these user travel habits, includes:

[0070] The vehicle's trajectory within the first preset time period is determined based on the corresponding time of the vehicle's trajectory.

[0071] Based on the vehicle's driving trajectory within a first preset time period, highly repetitive travel patterns are identified as user travel habits. The travel patterns include travel routes, locations, and departure time periods.

[0072] The next travel destination is generated based on the user's travel habits through natural language processing (NLP) and word frequency statistics;

[0073] Based on the next travel destination and the map API, the expected travel route L for the next trip is generated. Based on the expected travel route L, the set of locations R to be passed through and the travel time T are calculated.

[0074] If the preset time is the past seven days, the system can identify frequently occurring travel patterns by analyzing the vehicle's driving trajectory (i.e., historical travel data, including routes, locations, and times) over the past seven days. These patterns include commuting routes to and from get off work, gym workouts, and supermarket shopping trips. These common travel patterns represent users' travel habits. The map API can utilize existing map software interface functions.

[0075] In some embodiments, such as Figure 3 As shown, step S3, which involves obtaining hotspot information and traffic information based on the expected travel route L and travel time T, and generating a message queue, includes:

[0076] Step S31: Using the set of locations R of the expected travel route L as keywords, obtain hotspot information and traffic information within a second preset time period before the travel time T to form a hotspot information set. and traffic information collection ;

[0077] Step S32, calculate the hotspot information set and traffic information collection Messages are ranked according to their importance, and a message queue is generated.

[0078] If the second preset time is 30 minutes, then based on the keyword set R, relevant hot topics are repeatedly crawled from the web 30 minutes before the travel time each day to form a set. Collect relevant traffic information to form a set .

[0079] In some embodiments, step S32 involves calculating a hotspot information set. and traffic information collection The steps for generating a message queue include prioritizing and ordering messages based on their importance, and then proceeding as follows:

[0080] Collection of hot information and traffic information collection Each message is segmented into words and divided into three levels through natural language processing: S0 warning level, S1 suggestion level, and S2 normal message level, which are stored in the S0 warning level message queue, S1 suggestion level message queue, and S2 normal message level message queue, respectively.

[0081] The natural language processing employs the open-source machine learning library sklearn. S0-level warnings, indicating route L interruptions, disaster alerts, etc., are stored in the S0 queue and prioritized for push notifications. S1-level suggestions indicate risks associated with route L, such as accidents, traffic jams, or traffic control measures, recommending alternative routes; these are stored in the S1 queue. S2-level general messages represent the latest news, anecdotes, etc., along the route L passes through; these are stored in the S2 queue and displayed to users before their trips, such as promotional activities or new store openings, allowing users to plan their routes accordingly.

[0082] In some embodiments, step S32 involves calculating a hotspot information set. and traffic information collection The steps for generating a message queue include prioritizing and sorting messages based on their importance, as well as:

[0083] The S2 ordinary message level messages are scored by dividing them into three dimensions using the term frequency and inverse document frequency (TF-IDF) algorithm:

[0084] Spatial dimension: Based on messages in the S2 normal message level With messages The locations in the expected travel route L mentioned above Calculate the spatial dimension score: Where score1 is the spatial dimension score, The formula for the TF-IDF algorithm is... It is an S2 ordinary message-level message corpus;

[0085] Time dimension: Scenarios are divided based on the expected travel route L and travel time T, and then further divided according to the scenario. The pre-set word segmentation calculation time dimension score: In this context, score2 represents the score over time.

[0086] Behavioral dimension: A behavioral dimension score is calculated by combining historical feedback data on user clicks to view and skip push notifications. In this context, score3 represents the behavioral dimension score, where X represents the historical data that the user clicked to view, and Y represents the historical data that was pushed to the user but not viewed.

[0087] The correlation α between each S2 ordinary message and the expected travel route L is calculated based on the scores of the three dimensions of the S2 ordinary message level messages: Where α is the correlation degree, and k1, k2, and k3 are preset weight values, such as k1=0.6, k2=0.1, and k3=0.3;

[0088] Based on the correlation of each message in the S2 ordinary message level, messages with a correlation greater than a preset threshold are stored in the S2 ordinary message level message queue. If the preset threshold is 0.3, messages with α>0.3 are stored in queue S2.

[0089] The calculation formula for the TF-DF algorithm is as follows: ;

[0090] in, The calculation is based on term frequency (TF), where TF represents the keyword. In the text Frequency of occurrence in , Keyword In the text The number of times it appears in Representing text Total number of all terms in the dictionary;

[0091] The calculation is based on the Inverse Document Frequency (IDF), which measures the frequency of keywords. The entire corpus The rarity of it, Indicates the total number of documents. Representation corpus Contains keywords The total number of documents, .

[0092] In some embodiments, step S4, determining the message queue push timing and method based on the vehicle's driving status, includes:

[0093] If the traveler has not traveled at travel time T and the S0 warning-level message queue and the S1 suggestion-level message queue are not empty, push messages in the S0 warning-level message queue and the S1 suggestion-level message queue.

[0094] If the traveler has not traveled at travel time T and the S0 warning-level message queue and the S1 suggestion-level message queue are empty, push messages from the S2 normal message-level message queue.

[0095] In some embodiments, step S4, which involves determining the timing and method of message queue push based on the vehicle's driving status, further includes:

[0096] If the journey has already begun at travel time T and the S0 warning-level message queue is not empty, then update the expected travel route L to the actual route and execute step S3 to obtain hotspot information and traffic information based on the expected travel route L and travel time T to generate a message queue, and step S4 to determine the timing and method of message queue push based on the vehicle's driving status.

[0097] The steps described above in this invention ensure that users receive all levels of messages, including S0 warning level, S1 suggestion level, and S2 normal message level, even when they are not driving. If S1 suggestion level and S2 normal message level messages are no longer pushed to users while they are driving, it can prevent the problem of frequent pushes to the vehicle terminal from easily distracting the driver and posing a driving risk.

[0098] Based on the same inventive concept, such as Figure 4 As shown, this embodiment of the invention also provides a message mining and push system based on user travel habits, configured to implement any of the methods described in the above embodiments. The system includes:

[0099] The data acquisition layer is used to obtain the vehicle's driving status, vehicle trajectory, and the corresponding time of the vehicle trajectory;

[0100] The trajectory analysis layer is used to obtain user travel habits based on vehicle travel trajectories and their corresponding times, and to generate the expected travel route L and travel time T for the next trip based on the user's travel habits.

[0101] The message analysis layer is used to obtain hotspot information and traffic information based on the expected travel route L and travel time T, and generate message queues.

[0102] The push decision layer is used to determine the timing and method of message queue pushes based on the vehicle's driving status.

[0103] The message analysis layer includes: a traffic analysis module, which generates queues S0 and S1; and a hotspot analysis module, which generates queue S2.

[0104] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0105] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0106] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0107] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0108] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable medium. This computer-readable medium stores a computer program, wherein, when executed by a processor, the program implements the steps of any of the methods described in the above embodiments. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium.

[0109] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0110] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0111] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0112] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0113] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0114] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0115] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0116] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0118] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for message mining and push based on user travel habits, characterized in that, include: Obtain vehicle driving status, vehicle driving trajectory, and the corresponding time of the vehicle driving trajectory; Based on the vehicle's driving trajectory and the corresponding time, the user's travel habits are obtained, and the expected travel route and travel time for the next trip are generated based on the user's travel habits. Based on the expected travel route and travel time, obtain hotspot information and traffic information, and generate a message queue; The timing and method of message queue push are determined based on the vehicle's driving status.

2. The method according to claim 1, characterized in that, The steps of obtaining user travel habits based on vehicle travel trajectories and their corresponding times, and generating the expected travel route and travel time for the next trip based on these travel habits, include: The vehicle's trajectory within the first preset time period is determined based on the corresponding time of the vehicle's trajectory. Based on the vehicle's driving trajectory within a first preset time period, highly repetitive travel patterns are identified as user travel habits. The travel patterns include travel routes, locations, and departure time periods. Based on users' travel habits, the next travel destination is generated through natural language processing and word frequency statistics. Based on the next travel destination and the map API, the expected travel route for the next trip is generated, and the set of locations to be passed through and the travel time are calculated based on the expected travel route.

3. The method according to claim 2, characterized in that, The step of obtaining hotspot information and traffic information based on the expected travel route and travel time, and generating a message queue includes: Using the set of locations along the expected travel route as keywords, hotspot information and traffic information within a second preset time period before the travel time are obtained, forming a hotspot information set and a traffic information set; Calculate and sort the importance of messages in the hotspot information set and traffic information set, and generate a message queue.

4. The method according to claim 3, characterized in that, The step of calculating and sorting the importance of messages in the hotspot information set and traffic information set, and generating a message queue, includes: Each message in the hot topic information set and traffic information set is segmented into words and divided into three levels through natural language processing: warning level, suggestion level, and ordinary message level, which are stored in the warning level message queue, suggestion level message queue, and ordinary message level message queue, respectively.

5. The method according to claim 4, characterized in that, The step of calculating and sorting the importance of messages in the hotspot information set and traffic information set, and generating a message queue, further includes: The algorithm uses term frequency and inverse document frequency to divide ordinary message-level messages into three dimensions and calculates their scores: Spatial dimension: Based on messages in the normal message level With message The locations mentioned in the planned travel route Calculate the spatial dimension score: Where score1 is the spatial dimension score. This is the TF-IDF algorithm formula. It is a corpus of ordinary message-level messages; Time dimension: Scenarios are divided based on the expected travel route and travel time, and based on the scenario... The pre-set word segmentation calculation time dimension score: In this context, score2 represents the score over time. Behavioral dimension: A behavioral dimension score is calculated by combining historical feedback data on user clicks to view and skip push notifications. In this context, score3 represents the behavioral dimension score, where X represents the historical data that the user clicked to view, and Y represents the historical data that was pushed to the user but not viewed. The correlation between each ordinary message and the expected travel route is calculated based on the scores of the ordinary message level across three dimensions: Where α is the correlation degree, and k1, k2, and k3 are preset weight values; Messages at the ordinary message level are sorted by their relevance, and messages with a relevance greater than a preset threshold are stored in the ordinary message level message queue.

6. The method according to claim 4, characterized in that, The steps for determining the timing and method of message queue push based on vehicle driving status include: If the traveler does not travel during the designated travel time and the warning-level message queue and suggestion-level message queue are not empty, push messages from the warning-level message queue and suggestion-level message queue. If the traveler does not travel during the designated travel time and both the warning-level and suggestion-level message queues are empty, messages from the normal message-level message queue will be pushed.

7. The method according to claim 6, characterized in that, The step of determining the timing and method of message queue push based on vehicle driving status also includes: When the trip has already started and the warning-level message queue is not empty, update the expected travel route to the actual route and execute the steps of obtaining hotspot information and traffic information based on the expected travel route L and travel time T to generate a message queue, and determine the timing and method of message queue push based on the vehicle's driving status.

8. A message mining and push system based on user travel habits, characterized in that, The system, configured to implement the method as described in any one of claims 1 to 7, comprises: The data acquisition layer is used to obtain the vehicle's driving status, vehicle trajectory, and the corresponding time of the vehicle trajectory; The trajectory analysis layer is used to obtain users' travel habits based on vehicle travel trajectories and the corresponding times of vehicle travel trajectories, and to generate the expected travel route and travel time for the next trip based on users' travel habits. The message analysis layer is used to obtain hotspot information and traffic information based on the expected travel route and travel time, and generate message queues. The push decision layer is used to determine the timing and method of message queue pushes based on the vehicle's driving status.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images