Information pushing method, device and equipment, and storage medium

Abstract

The application discloses an information pushing method, device and equipment and a storage medium, and belongs to the technical field of vehicle communication. The application obtains owner information, vehicle information and interaction information between the owner and the vehicle, generates an owner tag and a vehicle tag according to the owner information, the vehicle information and the interaction information, obtains real-time driving data in a driving process of the vehicle, determines an owner tag weight corresponding to the owner tag and a vehicle tag weight corresponding to the vehicle tag according to the real-time driving data, and pushes information according to the owner tag weight and the vehicle tag weight. The application can make personalized tags closer to the real habits of users by combining the vehicle tag with the owner tag to push information to the users, realize personalized recommendation for thousands of people with thousands of faces, and improve the accuracy and authenticity of information pushing because the vehicle tag is combined to make the information pushing more in line with the actual driving environment of the owner.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle communication, in particular to an information pushing method and device, equipment and a storage medium. BACKGROUND

[0002] An artificial intelligence (AI) recommendation system is used to analyze user behavior and predict user needs by using user data, mainly including data collection, data processing, recommendation calculation, model training, etc.

[0003] At present, the AI recommendation system has been used in cars, and actively recommends scenarios and modes to users by collecting vehicle and user data, but there are currently three main problems: which data needs to be collected to more accurately analyze user behavior and make the predicted user behavior closer to the user's real habits; how to use the analyzed data in the recommendation calculation, so that the actively recommended scenarios can better meet the user's needs and be accepted by the user; and how to optimize according to the user's feedback if the recommended content is rejected by the user.

[0004] The current AI recommendation system cannot accurately analyze user behavior, and only refers to user behavior habits in the recommendation process without considering the actual driving environment of the user.

[0005] The above content is only used to assist in understanding the technical solutions of the present application and does not mean that the above content is prior art. SUMMARY

[0006] The main purpose of the present application is to provide an information pushing method, device, equipment and storage medium, which aims to solve the technical problems that the prior art cannot accurately analyze user behavior, and only refers to user behavior habits in the recommendation process without considering the actual driving environment of the user.

[0007] To achieve the above purpose, the present application provides an information pushing method, which comprises the following steps:

[0008] Obtain the owner information, vehicle information and interaction information between the owner and the vehicle;

[0009] Generate an owner tag and a vehicle tag according to the owner information, the vehicle information and the interaction information;

[0010] Obtain real-time driving data during vehicle driving;

[0011] Determine the owner tag weight corresponding to the owner tag and the vehicle tag weight corresponding to the vehicle tag according to the real-time driving data;

[0012] According to the owner tag weight and the vehicle tag weight, information pushing is performed.

[0013] Optionally, the determining of the owner tag weight corresponding to the owner tag and the vehicle tag weight corresponding to the vehicle tag according to the real-time driving data comprises:

[0014] According to the real-time driving data, a current vehicle state and an information pushing type are determined.

[0015] According to the current vehicle state and the information pushing type, the owner tag weight corresponding to the owner tag and the vehicle tag weight corresponding to the vehicle tag are determined.

[0016] Optionally, the information pushing according to the owner tag weight and the vehicle tag weight comprises:

[0017] According to the real-time driving data, an information pushing type is determined.

[0018] According to the information pushing type, the owner tag weight and the vehicle tag weight, information pushing is performed.

[0019] Optionally, the information pushing according to the information pushing type, the owner tag weight and the vehicle tag weight comprises:

[0020] When the information pushing type is a first type, a target tag referred to in information pushing is determined according to the owner tag weight and the vehicle tag weight.

[0021] When the target tag referred to in the information pushing is the owner tag and the vehicle tag, information pushing is performed according to a historical pushing frequency corresponding to a user habit.

[0022] When the target tag referred to in the information pushing is the vehicle tag, information pushing is performed according to a set pushing frequency.

[0023] Optionally, the information pushing according to the information pushing type, the owner tag weight and the vehicle tag weight comprises:

[0024] When the information pushing type is a second type, a target tag referred to in information pushing is determined according to the owner tag weight and the vehicle tag weight.

[0025] When the target tag referred to in the information pushing is the owner tag, information pushing is performed according to a historical vehicle parameter value corresponding to a user habit.

[0026] When the target tag referred to in the information pushing is the vehicle tag, information pushing is performed according to a set vehicle parameter value.

[0027] Optionally, the information pushing according to the information pushing type, the car owner tag weight and the vehicle tag weight comprises:

[0028] When the information pushing type is the third type, a plurality of recommended scenes are acquired;

[0029] A scene score corresponding to each recommended scene is determined according to the car owner tag weight and the vehicle tag weight;

[0030] A plurality of reference recommended scenes with a scene score greater than a preset score threshold are selected from the plurality of recommended scenes;

[0031] The plurality of reference recommended scenes are sorted according to the score, and a reference recommended scene with the highest score is taken as a target recommended scene;

[0032] Information is pushed according to the target recommended scene.

[0033] Optionally, after the information is pushed according to the target recommended scene, the method further comprises:

[0034] Feedback information input by a user based on the pushed information is received;

[0035] A scene score corresponding to each recommended scene is adjusted according to the feedback information.

[0036] In addition, to achieve the above-mentioned purpose, the application further provides an information pushing device, which comprises:

[0037] An acquisition module is configured to acquire car owner information, vehicle information and interaction information between the car owner and the vehicle;

[0038] A generation module is configured to generate a car owner tag and a vehicle tag according to the car owner information, the vehicle information and the interaction information;

[0039] The acquisition module is further configured to acquire real-time driving data in a vehicle driving process;

[0040] A calculation module is configured to determine a car owner tag weight corresponding to the car owner tag and a vehicle tag weight corresponding to the vehicle tag according to the real-time driving data;

[0041] A pushing module is configured to push information according to the car owner tag weight and the vehicle tag weight.

[0042] In addition, to achieve the above-mentioned purpose, the application further provides an information pushing device, which comprises a memory, a processor and an information pushing program stored in the memory and running on the processor, and the information pushing program is configured to implement the information pushing method as described above.

[0043] In addition, to achieve the above object, the application further provides a storage medium, wherein the storage medium stores an information pushing program, and the information pushing program is executed by a processor to realize the information pushing method.

[0044] The application obtains owner information, vehicle information and interaction information between the owner and the vehicle, generates an owner tag and a vehicle tag according to the owner information, the vehicle information and the interaction information, obtains real-time driving data in a driving process of the vehicle, determines an owner tag weight corresponding to the owner tag and a vehicle tag weight corresponding to the vehicle tag according to the real-time driving data, and pushes information according to the owner tag weight and the vehicle tag weight, so that the personalized tag is closer to the real habits of the user, the personalized recommendation for thousands of people is realized, and the accuracy and authenticity of the information pushing are improved due to the combination of the vehicle tag. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 is a structural schematic diagram of an information pushing device of a hardware running environment related to the embodiment scheme of the application.

[0046] Figure 2 is a flowchart of the first embodiment of the information pushing method of the application.

[0047] Figure 3 is a schematic diagram of a recommendation system architecture in the embodiment of the information pushing method of the application.

[0048] Figure 4 is a flowchart of the second embodiment of the information pushing method of the application.

[0049] Figure 5 is a structural block diagram of the first embodiment of the information pushing device of the application.

[0050] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0052] Reference Figure 1 , Figure 1 is a structural schematic diagram of an information pushing device of a hardware running environment related to the embodiment scheme of the application.

[0053] As Figure 1As shown in the figure, the information pushing device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between the components. The user interface 1003 can include a display, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM), such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0054] Those skilled in the art can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the information pushing device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0055] As Figure 1 As shown in the figure, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and an information pushing program.

[0056] In Figure 1 In the information pushing device shown in the figure, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the information pushing device of the present application can be arranged in the information pushing device, and the information pushing device calls the information pushing program stored in the memory 1005 through the processor 1001, and executes the information pushing method provided by the embodiments of the present application.

[0057] The embodiment of the present application provides an information pushing method, which refers to Figure 2 , Figure 2 The flowchart of a first embodiment of the information pushing method of the present application.

[0058] In this embodiment, the information pushing method includes the following steps:

[0059] Step S10: acquiring owner information, vehicle information, and interaction information between the owner and the vehicle.

[0060] In the embodiment, the execution subject of the embodiment can be the information pushing device, which has functions of data processing, data communication, program running, etc. The information pushing device can be a terminal device such as a vehicle-mounted computer, and of course, can also be other devices with similar functions, which are not limited in the embodiment. For the convenience of description, the embodiment is described by taking the information pushing device as an example.

[0061] It should be noted that the current pushing mainly has the following two ways. One of the ways is to recommend content for the user according to the established rules. The input of the rules only has vehicle data, and does not have behavior data of the user. When the condition of entering the scene is met, the user is directly pushed. The frequency of pushing is updated according to the feedback of acceptance or rejection of the user. For example, a recommendation rule is formulated. When the vehicle is X km away from the gas station, the gear is X gear, and the remaining oil is less than XX%, the XX gas filling APP is pushed. All users are judged by the same rule, and personalized intelligent recommendation for thousands of people cannot be realized. Another way generally includes a scene recognition model and an action execution model. Whether the user vehicle currently meets the recommended scene judgment condition is recognized by a deep learning, neural network, etc. After the scene recommendation condition is met, the action is recommended in combination with the owner's preference, such as automatically opening the air conditioner according to the temperature, the window, and the air conditioner state, and setting the temperature to the user's habit. However, after the user refuses the recommended content, the reason for the user's refusal cannot be further analyzed, and the scene cannot be optimized.

[0062] The above-mentioned way cannot accurately obtain the real use habit of the user, and all the recommendations are based on the behavior habit of the user, without considering the vehicle-related information. The recommendation that only caters to the user's habit is one-sided. In order to solve the above technical problems, in the embodiment, when the information is pushed to the user, not only the user information is considered, but also the vehicle information is combined. The information is pushed to the user based on the user information and the vehicle information.

[0063] In the specific implementation, the recommendation system architecture of the embodiment is first described by taking Figure 3 as an example. Referring to Figure 3 , the recommendation system architecture in the embodiment is composed of four parts of data collection, user analysis, recommendation model, and pushing system. The role of data collection is to collect user data and vehicle data. The role of user analysis is to extract features from the collected data, generate personalized labels, set weights for the personalized labels, and determine the recommended scene. The role of the pushing system is to execute the recommended action in combination with the state of the vehicle, and record the interactive information of the user and feed back to the recommendation model.

[0064] In a specific implementation, before generating the owner label and the vehicle label, the owner information, the vehicle information, and the interaction information between the owner and the vehicle need to be acquired, wherein the owner information includes but is not limited to the owner age, the owner resident area, the owner contact information, and the device information used by the owner, the vehicle information includes but is not limited to the vehicle identification number (VIN), the delivery date, the maintenance date, and the repair parts, and the interaction information includes but is not limited to the APP use frequency, the navigation destination, the music type, and the air conditioner temperature.

[0065] Step S20: generating the owner label and the vehicle label according to the owner information, the vehicle information, and the interaction information.

[0066] In a specific implementation, the user personalized label matrix is generated through data acquisition and data fusion, the owner label can be obtained after the driving data is fused with the owner information and the interaction information, such as the air conditioner temperature preference, the window opening preference, the music type preference, and the driving behavior preference (intense or gentle), and the vehicle feature data can be obtained after the driving data is fused with the vehicle information, such as the fast / slow charging ratio, the cumulative driving time, the maintenance cycle, the daily driving frequency, and the alarm information.

[0067] In the embodiment, the generated owner label is shown in Table 1, and the generated vehicle label is shown in Table 2.

[0068] Table 1:

[0069]

[0070] Table 2:

[0071]

[0072] Step S30: acquiring real-time driving data in a driving process of the vehicle.

[0073] In the embodiment, the real-time driving data in the driving process of the vehicle also needs to be further acquired, wherein the real-time driving data in the driving process of the vehicle includes but is not limited to the vehicle speed, the gear, the air conditioner state, and the engine state.

[0074] Step S40: determining the owner label weight corresponding to the owner label and the vehicle label weight corresponding to the vehicle label according to the real-time driving data.

[0075] In a specific implementation, when the real-time driving data is acquired, the vehicle owner label weight corresponding to the vehicle owner label and the vehicle label weight corresponding to the vehicle label can be further determined according to the real-time driving data in this embodiment. Specifically, the current vehicle state and the information push type can be determined according to the real-time driving data in this embodiment. The current vehicle state includes a parking state, a driving state, and a parking state. The information push type includes a warning type, a reminder type, and a recommendation type. The label weights corresponding to different vehicle states and different information push types are different. The vehicle owner label weight corresponding to the vehicle owner label and the vehicle label weight corresponding to the vehicle label can be determined according to the current vehicle state and the information push type in this embodiment. The label weights generated in this embodiment can be seen from Table Three. The weight setting in this embodiment is for illustration. In actual situations, the weight values can be adjusted accordingly according to different setting requirements. This embodiment does not limit this.

[0076] Table Three:

[0077]

[0078] It should be noted that, for the information push of the warning type, in the parking state, the vehicle label weight B1 is much greater than the user label weight. In the parking state, the vehicle label weight B2 is also much greater than the user label weight A2. For the information push of the reminder type, in the driving state, the vehicle label weight B4 is greater than the user label weight A4. For the information push of the push type, in the parking state, the user label weight A6 is much greater than the vehicle label weight B6. In the driving state, the user label weight A7 is greater than the vehicle label weight B7. In the parking state, the user label weight A8 is much greater than the vehicle label weight B8. An implementation manner is proposed in this embodiment. Specifically, a weight difference threshold can be set in this embodiment. When the difference between the user label weight and the vehicle label weight is greater than the weight difference threshold, it indicates that the user label weight is much smaller or much greater than the vehicle label weight.

[0079] Step S50: performing information push according to the vehicle owner label weight and the vehicle label weight.

[0080] In a specific implementation, after obtaining the owner label weight and the vehicle label weight, the embodiment can select a corresponding push mode based on the different owner label weights and the vehicle label weights, and then perform information push. For example, the information push of the warning type, such as the safety belt unfastening warning. In the parking state, the user label weight is A1, the vehicle label weight is B1, and B1 >> A1. In the parking state, the vehicle label is given priority, and the user label is also considered. The driver / passenger does not fasten the safety belt, and the safety belt reminder is recommended. If the user refuses, the frequency of push is updated to reduce the push. However, in the driving state, the vehicle label weight is 1, and the user label weight is 0. Only the vehicle label is considered, and the safety belt reminder is performed. The user refusal is also pushed according to the set frequency.

[0081] The embodiment obtains owner information, vehicle information, and interaction information between the owner and the vehicle, generates an owner label and a vehicle label according to the owner information, the vehicle information, and the interaction information, obtains real-time driving data in a vehicle driving process, determines an owner label weight corresponding to the owner label and a vehicle label weight corresponding to the vehicle label according to the real-time driving data, and performs information push according to the owner label weight and the vehicle label weight. By combining the vehicle label and the owner label to push information to the user, the personalized label is closer to the real habits of the user, the personalized recommendation of thousands of people is realized, and the accuracy and authenticity of the information push are improved because the vehicle label is combined.

[0082] Reference Figure 4 , Figure 4 The figure is a flowchart of a second embodiment of the information push method.

[0083] Based on the first embodiment, in the information push method, the step S50 specifically includes the following steps.

[0084] Step S501: determining an information push type according to the real-time driving data.

[0085] In a specific implementation, after obtaining the real-time driving data, the embodiment can determine the information push type that needs to be pushed at this time according to the real-time driving data. For example, the safety belt is unfastened, the information push type at this time is the warning type, the oil / electricity is low, the corresponding information push type is the reminder type, the child is in the vehicle in the time period of 7:00-8:00, the outside temperature is higher than 30℃, the destination is the central kindergarten, and the information push type at this time is the recommendation type.

[0086] Step S502: performing information push according to the information push type, the owner label weight, and the vehicle label weight.

[0087] In a specific implementation, the information push can be performed based on the information push type, the owner tag weight, and the vehicle tag weight.

[0088] Further, in the embodiment, when the information push type is the first type, the target tag to which reference is made when the information is pushed is determined according to the owner tag weight and the vehicle tag weight. The target tag is a main tag to which reference is made when the information is pushed. The first type in the embodiment is warning type information. When the information is warning type information, the target tag to which reference is made when the information is pushed is the owner tag and the vehicle tag, that is, the owner tag and the owner tag are considered at the same time. In the embodiment, the information is pushed according to the historical push frequency corresponding to the user's behavior habit. When the target tag to which reference is made when the information is pushed is the vehicle tag, that is, only the vehicle tag is considered. In the embodiment, the user's habit is not referenced, that is, the information is pushed according to the set push frequency. For example, the information push of the warning type, taking the warning of the unbuckled safety belt as an example. In the parking / stop state, the vehicle tag is given priority, and the user tag is also considered, that is, the target tag at this time is the owner tag and the vehicle tag. The driver / assistant driver is not buckled, the safety belt reminder is recommended, if the user refuses, the push frequency will be updated to reduce the push, and the next time the information is pushed, the information is pushed based on the frequency corresponding to the user's behavior habit. However, in the driving state, only the vehicle tag is considered, that is, the target tag at this time is the vehicle tag. The safety belt reminder is given, even if the user refuses, the information is pushed according to the set frequency, and the user's behavior habit does not need to be considered. The set frequency can be set according to the actual situation, which is not limited in the embodiment.

[0089] Further, in the embodiment, when the information push type is the second type, the target tag to which reference is made when the information is pushed is also determined according to the owner tag weight and the vehicle tag weight in the embodiment. The target tag is a main tag to which reference is made when the information is pushed. The second type in the embodiment is reminder type information. When the information is reminder type information, the target tag to which reference is made when the information is pushed is the owner tag, that is, only the owner tag is considered. In the embodiment, the information is pushed according to the historical vehicle parameter value corresponding to the user's behavior habit. When the target tag to which reference is made when the information is pushed is the vehicle tag, that is, only the vehicle tag is considered. In the embodiment, the user's habit is not referenced, that is, the information is pushed according to the set vehicle parameter value. For example, the information push of the reminder type. In the parking / stop state, the user tag is given priority, that is, the target tag at this time is the owner tag. According to the user's refueling / charging habit, different users are recommended to refuel / charge when different oil / electricity thresholds are reached. However, in the driving state, the vehicle tag is given priority, that is, the target tag at this time is the vehicle tag. For example, the user is reminded to refuel or charge when the oil / electricity is low.

[0090] The embodiment also provides a mode, and specifically, the reminding can be performed according to the user's activity area label, if the user mainly has short-distance activities, the reminding can be performed according to the user's habit in a relatively low oil amount; if the user's activity area is relatively large, for example, the user often exceeds a certain mileage or has long and short mileage in the past month, the reminding is performed in a relatively high oil amount, which is contrary to the user's habit. Therefore, for example, the reminding is different for the same user in different vehicle use conditions.

[0091] Further, in the embodiment, when the information push type is the third type, the third type is a recommendation type, and for this type, the embodiment sets multiple recommendation scenarios, each of which has a different scene score, and the embodiment can determine the scene score corresponding to each recommendation scenario according to the vehicle owner label weight and the vehicle label weight. It should be noted that the recommendation scenario in the embodiment contains the user's personalized data, that is, based on different personalized data of the user, the recommendation scenario preset for different users in the embodiment is different, and personalized recommendation for thousands of people can be achieved. In the embodiment, a scene score threshold is also set for the recommendation scenario, and before generating the information pushed according to the recommendation scenario, the embodiment first screens multiple reference recommendation scenarios with a scene score greater than a preset score threshold according to the scene score threshold, then sorts the multiple reference recommendation scenarios according to the score size, and finally takes the reference recommendation scenario with the highest score as the target recommendation scenario. For example, after collecting the data such as the vehicle owner information, the gear, the vehicle speed, the air conditioner temperature, the vehicle temperature, the outdoor temperature, the fragrance, the air purifier, the child seat, the window, the multimedia music type, the navigation destination, etc., it is obtained that when a child rides the vehicle in the time period of 7:00-8:00, the outdoor temperature is higher than 30℃, the window is closed, the air conditioner (temperature preference is 26℃) is turned on, the fragrance system is turned off, the children's songs are played, and the destination is the Central Kindergarten. At this time, three recommendation scenarios are generated, for example, scenario 1: close the window, turn on the air conditioner, turn on the air purifier, set the temperature to 26 degrees Celsius, play children's songs and ask whether to navigate to the Central Kindergarten, scenario 2: close the window, turn on the air conditioner, turn on the air purifier, turn on the fragrance, turn on the seat massage, and scenario 3: turn on the atmosphere lamp. Assuming that the preset score of scenario 1 is 0.8, the preset score of scenario 2 is 0.7, and the preset score of scenario 3 is 0.5, and the preset score threshold is 0.6, the embodiment performs information push on the user according to scenario 1, and the pushed information includes reminding the user to close the window, turn on the air conditioner, turn on the air purifier, set the temperature to 26 degrees Celsius, and ask the user whether to navigate to the Central Kindergarten.

[0092] Further, after the user is pushed with the above information, the embodiment receives feedback information of the user based on the push information, for example, the user can select to accept or reject the recommendation through the central control screen or other devices, if the user accepts, the preset score of the scene can be increased, otherwise, if the user rejects, the preset score of the scene can be reduced, the scene preset score and the preset score threshold can be set according to the actual needs of the user, and the embodiment does not limit this.

[0093] The embodiment further provides an implementation manner for the third type of information push, specifically, after the user selects to accept the recommendation, if the user accepts part of the suggestions in the recommendation, for example, the recommendation closes the window, opens the air conditioner and the air purifier, but only opens the air conditioner and the air purifier, but opens the window, for this case, the embodiment corrects the scene based on the operation of the user this time, and the next time the scene recommendation becomes to open the window, the air conditioner and the air purifier.

[0094] The embodiment adopts different manners to push new information to the user according to different types of information push, and obtains feedback of the user on the push information after pushing the information to the user, and optimizes each time of information push based on the feedback of the user, so that the real behavior habits of the user can be more in line with the real behavior habits of the user, and the user experience is improved.

[0095] In addition, the embodiment of the present application further provides a storage medium, and the storage medium stores an information push program, and the information push program is executed by a processor to realize the steps of the information push method as described above.

[0096] Since the storage medium adopts all the technical solutions of the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here.

[0097] Reference Figure 5 , Figure 5 FIG. 1 is a structural block diagram of an information push device according to a first embodiment of the present application.

[0098] As Figure 5 shown, the information push device provided by the embodiment of the present application comprises:

[0099] The acquisition module 10 is configured to acquire the owner information, the vehicle information and the interaction information between the owner and the vehicle.

[0100] The generation module 20 is configured to generate the owner label and the vehicle label according to the owner information, the vehicle information and the interaction information.

[0101] The acquisition module 10 is further configured to acquire real-time driving data in the driving process of the vehicle.

[0102] The computing module 30 is configured to determine a vehicle owner label weight corresponding to the vehicle owner label and a vehicle label weight corresponding to the vehicle label according to the real-time driving data.

[0103] The pushing module 40 is configured to push information according to the vehicle owner label weight and the vehicle label weight.

[0104] The embodiment can obtain vehicle owner information, vehicle information and interaction information between the vehicle owner and the vehicle, generate a vehicle owner label and a vehicle label according to the vehicle owner information, the vehicle information and the interaction information, obtain real-time driving data in a driving process of the vehicle, determine a vehicle owner label weight corresponding to the vehicle owner label and a vehicle label weight corresponding to the vehicle label according to the real-time driving data, and push information according to the vehicle owner label weight and the vehicle label weight. The information is pushed to the user by combining the vehicle label and the vehicle owner label, which can make the personalized label closer to the real habits of the user, realize personalized recommendation for thousands of people with different faces, and improve the accuracy and authenticity of information pushing because the vehicle label is combined to make the information pushing more consistent with the actual driving environment of the vehicle owner.

[0105] In an embodiment, the computing module 30 is further configured to determine a current vehicle state and an information pushing type according to the real-time driving data, and determine the vehicle owner label weight corresponding to the vehicle owner label and the vehicle label weight corresponding to the vehicle label according to the current vehicle state and the information pushing type.

[0106] In an embodiment, the pushing module 40 is further configured to determine an information pushing type according to the real-time driving data, and push information according to the information pushing type, the vehicle owner label weight and the vehicle label weight.

[0107] In an embodiment, the pushing module 40 is further configured to determine a target label referred to when information is pushed according to the vehicle owner label weight and the vehicle label weight when the information pushing type is a first type, push information according to a historical pushing frequency corresponding to a user habit when the target label referred to when the information is pushed is the vehicle owner label and the vehicle label, and push information according to a set pushing frequency when the target label referred to when the information is pushed is the vehicle label.

[0108] In an embodiment, the push module 40 is further configured to, when the information push type is a second type, determine a label to be referred to when pushing information according to the car owner label weight and the car label weight; when the target label to be referred to when pushing information is the car owner label, push information according to a historical car parameter value corresponding to a user habit; and when the target label to be referred to when pushing information is the car label, push information according to a set car parameter value.

[0109] In an embodiment, the push module 40 is further configured to, when the information push type is a third type, acquire a plurality of recommended scenarios; determine a scenario score corresponding to each recommended scenario according to the car owner label weight and the car label weight; select a plurality of reference recommended scenarios with a scenario score greater than a preset score threshold from the plurality of recommended scenarios; sort the plurality of reference recommended scenarios according to the size of the score, and take a reference recommended scenario with the highest score as a target recommended scenario; and push information according to the target recommended scenario.

[0110] In an embodiment, the push module 40 is further configured to receive feedback information input by a user based on pushed information; and adjust the scenario score corresponding to each recommended scenario according to the feedback information.

[0111] It should be understood that the above is only illustrative, and does not constitute any limitation on the technical solutions of the present application. In specific applications, those skilled in the art can set up according to the needs, and the present application does not limit this.

[0112] It should be noted that the above-described workflow is only illustrative and does not limit the scope of protection of the present application. In actual applications, those skilled in the art can select part or all of them to achieve the purpose of the embodiment according to actual needs, which is not limited here.

[0113] In addition, technical details not described in detail in the present embodiment can be referred to the information push method provided by any embodiment of the present application, which will not be described here.

[0114] In addition, it should be noted that in this document, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or system. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or system including the element.

[0115] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0116] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk), and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0117] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An information push method characterized by comprising: The information pushing method comprises: obtaining owner information, vehicle information and interaction information between the owner and the vehicle; generating an owner tag and a vehicle tag according to the owner information, the vehicle information and the interaction information; obtaining real-time driving data in a vehicle driving process; determining a current vehicle state and an information pushing type according to the real-time driving data, wherein the current vehicle state comprises a parking state, a driving state and a stopping state, and the information pushing type comprises a warning type, a reminding type and a recommendation type; determining an owner tag weight corresponding to the owner tag and a vehicle tag weight corresponding to the vehicle tag according to the current vehicle state and the information pushing type; pushing information according to the owner tag weight and the vehicle tag weight.

2. The information push method of claim 1, wherein, The information pushing according to the owner tag weight and the vehicle tag weight comprises: determining an information pushing type according to the real-time driving data; pushing information according to the information pushing type, the owner tag weight and the vehicle tag weight.

3. The information push method of claim 2, wherein, The information pushing according to the information pushing type, the owner tag weight and the vehicle tag weight comprises: when the information pushing type is a first type, determining a target tag referred to when pushing information according to the owner tag weight and the vehicle tag weight; when the target tag referred to when pushing information is the owner tag and the vehicle tag, pushing information according to a historical pushing frequency corresponding to a user habit; when the target tag referred to when pushing information is the vehicle tag, pushing information according to a set pushing frequency.

4. The information push method of claim 2, wherein, The information pushing according to the information pushing type, the owner tag weight and the vehicle tag weight comprises: when the information pushing type is a second type, determining a target tag referred to when pushing information according to the owner tag weight and the vehicle tag weight; when the target tag referred to when pushing information is the owner tag, pushing information according to a historical vehicle parameter value corresponding to a user habit; when the target tag referred to when pushing information is the vehicle tag, pushing information according to a set vehicle parameter value.

5. The information push method of claim 2, wherein, The information pushing according to the information pushing type, the owner tag weight and the vehicle tag weight comprises: when the information pushing type is a third type, obtaining a plurality of recommendation scenarios; determining a scenario score corresponding to each recommendation scenario according to the owner tag weight and the vehicle tag weight; selecting a plurality of reference recommendation scenarios with a scenario score greater than a preset score threshold from the plurality of recommendation scenarios; ranking the plurality of reference recommendation scenarios according to the scenario score, and taking a reference recommendation scenario with the highest score as a target recommendation scenario; pushing information according to the target recommendation scenario.

6. The information push method of claim 5, wherein, After the information is pushed according to the target recommendation scenario, the method further comprises: receiving feedback information input by a user based on the pushed information; adjusting the scenario score corresponding to each recommendation scenario according to the feedback information.

7. An information push apparatus characterized by comprising: The information pushing device comprises: An acquisition module is configured to acquire owner information, vehicle information, and interaction information between the owner and the vehicle; A generation module is configured to generate an owner tag and a vehicle tag according to the owner information, the vehicle information, and the interaction information; The acquisition module is further configured to acquire real-time driving data in a driving process of the vehicle; A calculation module is configured to determine a current vehicle state and an information push type according to the real-time driving data, the current vehicle state including a parking state, a driving state, and a stopping state, the information push type including a warning type, a reminding type, and a recommendation type, and determine an owner tag weight corresponding to the owner tag and a vehicle tag weight corresponding to the vehicle tag according to the current vehicle state and the information push type; A push module is configured to perform information push according to the owner tag weight and the vehicle tag weight.

8. An information push device characterized by comprising: The information push device includes a memory, a processor, and an information push program stored on the memory and running on the processor, the information push program being configured to implement the information push method in any one of claims 1 to 6.

9. A storage medium, characterized by The storage medium stores an information push program, and the information push program is executed by the processor to implement the information push method in any one of claims 1 to 6.

Images