Method for actively providing vehicle service

Abstract

Provided in the present application are a method for actively providing a vehicle service, a device, a medium and a program product. The method can comprise: acquiring driving data of a vehicle, and on the basis of the driving data, determining a target driving scenario where the vehicle is located; determining a target workflow corresponding to the target driving scenario, wherein the target workflow is generated on the basis of vehicle usage habits of a target user, the target workflow comprises at least one target vehicle service, and the target user is a user who currently drives the vehicle; and executing the target workflow, so as to provide the at least one target vehicle service to the target user.

Description

Method for actively providing vehicle service Cross-reference to related applications

[0001] This application claims priority to the Chinese patent application No. 202411272625.3, filed on September 11, 2024, to the Chinese Patent Office, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] Embodiments of the present application relate to, but are not limited to, the field of automobile technology, and in particular to a method for actively providing vehicle service. BACKGROUND

[0003] With the improvement of the intelligent level of automobiles, the types of services that vehicles can provide to users are also increasing. For example, vehicles can provide users with intelligent navigation, voice interaction, and other services. SUMMARY

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims. According to a first aspect of one or more embodiments of the present application, a method for actively providing vehicle service is provided, the method comprising: obtaining driving data of a vehicle, and determining a target driving scenario in which the vehicle is located according to the driving data; determining a target workflow corresponding to the target driving scenario, wherein the target workflow is generated based on a driving habit of a target user, the target workflow includes at least one target vehicle service, and the target user is a user currently driving the vehicle; and executing the target workflow to provide the at least one target vehicle service to the target user.

[0005] In some embodiments, the determining the target driving scenario in which the vehicle is located according to the driving data comprises: determining a preset condition of each candidate driving scenario in a plurality of candidate driving scenarios; for each candidate driving scenario, calculating a matching score of the driving data and the candidate driving scenario according to the preset condition of the candidate driving scenario; and determining a candidate driving scenario whose matching score exceeds a score threshold as the target driving scenario.

[0006] In some embodiments, the driving data comprises a current driving time, a current geographic position of the vehicle, and a current operation of the target user; the preset condition of any candidate driving scenario in the plurality of candidate driving scenarios comprises a preset condition in a time dimension, a preset condition in a position dimension, and a preset condition in a user operation dimension; and the matching score of the driving data and the candidate driving scenario is calculated according to the preset condition of the candidate driving scenario, including: calculating a time matching score corresponding to the current driving time according to the preset condition of the candidate driving scenario in the time dimension; calculating a position matching score corresponding to the current geographic position according to the preset condition of the candidate driving scenario in the position dimension; calculating an operation matching score corresponding to the current operation of the target user according to the preset condition of the candidate driving scenario in the user operation dimension; and calculating the matching score of the driving data and the candidate driving scenario based on the time matching score, the position matching score, and the operation matching score.

[0007] In some embodiments, the target workflow corresponding to the target driving scenario is determined by: obtaining target user portrait data of the target user in the target driving scenario, and generating the target workflow according to the target user portrait data; or querying a candidate driving scenario matching the target driving scenario from a workflow database, and determining a candidate workflow corresponding to the queried candidate driving scenario as the target workflow, wherein the workflow database stores a plurality of candidate driving scenarios and candidate workflows corresponding thereto, and the candidate workflows are generated in advance based on comprehensive user portrait data of the target user; and the target user portrait data or the comprehensive user portrait data is used to represent a driving habit of the target user.

[0008] In some embodiments, the target workflow is generated according to the target user portrait data by: inputting the target user portrait data and a prompt word into a workflow generation model, so as to generate the target workflow matching the target user portrait data under the indication of the prompt word and output the target workflow by the workflow generation model.

[0009] In some embodiments, the workflow generation model is trained by: obtaining sample user portrait data and a sample workflow corresponding to the sample user portrait data; inputting the sample user portrait data and a sample prompt word into a pre-trained workflow generation model, so as to generate a sample predicted workflow matching the sample user portrait data under the indication of the sample prompt word and output the sample predicted workflow by the pre-trained workflow generation model; and adjusting the sample prompt word and iteratively training the pre-trained workflow generation model according to the difference between the sample workflow and the sample predicted workflow.

[0010] In some embodiments, the executing the target workflow comprises: outputting the target workflow to the target user, and executing the target workflow upon receiving a confirmation instruction of the target user for the target workflow.

[0011] In some embodiments, the method further comprises: obtaining feedback information of the target user for the target workflow, and optimizing the target workflow based on the feedback information, the feedback information comprising evaluation information and / or improvement suggestions for the target workflow.

[0012] According to a second aspect of one or more embodiments of the present application, there is provided an apparatus for actively providing vehicle services, comprising: a driving scene determination unit configured to obtain driving data of a vehicle, and determine a target driving scene of the vehicle based on the driving data; a workflow determination unit configured to determine a target workflow corresponding to the target driving scene, wherein the target workflow is generated based on a driving habit of a target user, the target workflow comprises at least one target vehicle service, and the target user is a user currently driving the vehicle; and a workflow execution unit configured to execute the target workflow to provide the at least one target vehicle service to the target user.

[0013] According to a third aspect of one or more embodiments of the present application, there is provided an electronic device, comprising: a processor; a memory configured to store processor-executable instructions; wherein the processor implements the method of any of the above-mentioned first aspect by running the executable instructions.

[0014] According to a fourth aspect of one or more embodiments of the present application, there is provided a computer-readable storage medium having stored thereon computer instructions, which, when executed by a processor, implement the steps of the method of any of the above-mentioned first aspect.

[0015] According to a fifth aspect of one or more embodiments of the present application, there is provided a computer program product comprising computer programs and / or instructions, which, when executed by a processor, implement the steps of the method of any of the above-mentioned first aspect.

[0016] It can be seen from the above technical solutions that, in one or more embodiments of the present application, driving data of a vehicle is acquired, and a target driving scenario currently experienced by the vehicle is determined according to the driving data of the vehicle, and then a target workflow corresponding to the target driving scenario is determined for execution. The above-mentioned manner realizes that the target workflow is determined by the vehicle according to the target driving scenario for execution, and each target vehicle service included in the target workflow is automatically provided to the user without the user initiating an instruction, which significantly improves the convenience of user operation and the vehicle use experience. In addition, the vehicle use requirements of the user in different driving scenarios are usually inconsistent, and therefore, the current vehicle use requirements of the user can be accurately determined according to the target driving scenario. The target workflow corresponding to the target driving scenario is generated based on the vehicle use habits of the target user, that is, the target workflow fully considers the user habits / preferences of the target user in the target driving scenario, and therefore, the target workflow can flexibly meet the vehicle use requirements of the target user in the target driving scenario, and intelligent and personalized services are provided for the target user.

[0017] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present application. Other aspects can be apparent to those skilled in the art after reading and understanding the drawings and detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate an embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0019] FIG. 1 is a schematic diagram of an architecture of a vehicle service system according to an example embodiment.

[0020] FIG. 2 is a schematic diagram of a method of actively providing vehicle services according to an example embodiment.

[0021] FIG. 3 is a schematic diagram of generating and storing candidate workflows according to an example embodiment.

[0022] FIG. 4 is a schematic diagram of a method of training a workflow generation model according to an example embodiment.

[0023] FIG. 5 is a schematic diagram of outputting a target workflow to a user according to an example embodiment.

[0024] FIG. 6 is a block diagram of a vehicle service system according to an example embodiment.

[0025] FIG. 7 is a schematic diagram of the structure of an electronic device according to an example embodiment.

[0026] FIG. 8 is a block diagram of an apparatus for actively providing vehicle services according to an example embodiment. DETAILED DESCRIPTION

[0027] The user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal. In the related art, the services that the vehicle can provide to the user usually need to be triggered by the user to start, in other words, the vehicle can only passively respond to the user's instructions to provide services. This results in the user having to manually operate when using the vehicle service, reducing the convenience of user operation. Especially for frequently used services, the user needs to repeatedly input instructions, not only increasing the user's operation burden, but also reducing the overall driving experience. The present application provides a method, device, medium and program product for actively providing vehicle services to solve the deficiencies in the related art.

[0028] Next, one or more embodiments of the present application will be described in detail.

[0029] FIG. 1 is a schematic diagram of an architecture of a vehicle service system provided by an exemplary embodiment. As shown in FIG. 1, the vehicle service system can include a server 11, a network 12, and a plurality of vehicles, such as vehicles 13-14, etc. In the present application, the vehicle service system is responsible for providing vehicle services to users on vehicles.

[0030] The server 11 can be a physical server containing a standalone host, or the server 11 can be a virtual server carried by a host cluster. In the running process, the server 11 can run the server-side program of the vehicle service system to realize the service end of the vehicle service system.

[0031] The vehicles 13-14 can be any vehicle. The vehicles 13-14 and the server 11 can be directly or indirectly connected through wired communication or wireless communication, which is not specially limited by the present application.

[0032] Based on the vehicle service system shown in FIG. 1, any of the vehicles 13-14 can obtain the driving data of the vehicle and submit the obtained driving data to the server 11. The server 11 can determine the target driving scene in which the vehicle submitting the driving data is located according to the received driving data. Then, the server 11 determines the target workflow corresponding to the target driving scene and returns the target workflow to the vehicle submitting the driving data, so that the vehicle executes the target workflow.

[0033] In another embodiment, the vehicle service system can only include a vehicle. Taking the vehicle 13 in FIG. 1 as an example, the vehicle 13 can acquire driving data of the vehicle, and determine a target driving scenario in which the vehicle is located based on the acquired driving data. Then, a target workflow corresponding to the target driving scenario is determined, and the target workflow is executed to provide various vehicle services included in the target workflow to a user on the vehicle.

[0034] FIG. 2 is a flowchart of a method for actively providing vehicle services according to an example embodiment, which can be applied to the vehicle service system. As shown in FIG. 2, the method can include steps S201-S203.

[0035] S201, acquiring driving data of a vehicle, and determining a target driving scenario in which the vehicle is located based on the driving data.

[0036] The driving data of the vehicle refers to various data during the driving of the vehicle, including but not limited to: driving environment data (such as weather, traffic conditions, etc.), user operation data (such as air conditioning settings, seat position adjustment, multimedia playback settings, etc.), vehicle driving state data (such as brake distance control, vehicle speed, tire pressure, etc.). The driving data can be acquired through various sensors installed on the vehicle or Internet of Vehicles technology. Generally, the driving data of the vehicle in different driving scenarios is different, therefore, by performing data statistics and mining on the acquired driving data, the target driving scenario represented by the driving data can be determined.

[0037] In an embodiment, candidate driving scenarios and preset conditions of each candidate driving scenario can be set, so as to determine the target driving scenario according to the preset conditions. Generally, the candidate driving scenarios and their preset conditions can be set by the user himself / herself, or set by the vehicle service system according to the user's daily driving data, and the application does not limit the specific setting method. Table 1 shows four candidate driving scenarios and their preset conditions according to an example embodiment, please refer to Table 1:

[0038] In the process of determining the target driving scenario of the vehicle according to the obtained driving data, the candidate driving scenarios and their preset conditions are determined first, and then the matching scores of the obtained driving data and each candidate driving scenario are calculated according to the preset conditions of each candidate driving scenario, and the candidate driving scenario whose matching score exceeds the score threshold is determined as the target driving scenario. The matching score is used to represent the similarity between the driving data and the preset conditions. The higher the matching score is, the more similar the driving data is to the preset conditions, that is, the driving data meets the preset conditions better. In combination with Table 1, it is assumed that the score threshold is 0.8, and the obtained driving data includes that the current time is 17:00 on Friday and the user's navigation destination is a school. The matching scores of the driving data and the preset conditions of the four candidate driving scenarios in Table 1 are calculated respectively, and the matching score of the working scenario is 0, the matching score of the long-distance travel scenario is 0, the matching score of the shopping scenario is 0.5, and the matching score of the child pickup scenario is 0.85. Obviously, only the matching score of the child pickup scenario exceeds the score threshold 0.8, so the candidate driving scenario of picking up children can be determined as the target driving scenario. In addition, the maximum value in the calculated matching scores can also be used to determine the target driving scenario without setting the score threshold.

[0039] It should be noted that the candidate driving scenarios and their preset conditions are not fixed and can be updated according to user needs or adjusted according to actual driving habits / preferences of the user.

[0040] In this embodiment, by setting clear candidate driving scenarios and their candidate conditions, the target driving scenario is screened from the clear candidate driving scenarios, which helps to improve the accuracy of the determined target driving scenario. Moreover, this way divides the determination of the target driving scenario into simple condition matching, which helps to reduce the difficulty and complexity of determining the target driving scenario and improve the determination efficiency of the target driving scenario.

[0041] In an embodiment, the driving data itself has many dimensions, so when setting the preset conditions of the candidate driving scenarios, multiple dimensional preset conditions can be set, and then the matching scores can be calculated by using the preset conditions and the driving data in the same dimension.

[0042] Exemplarily, the preset conditions of any candidate driving scene can include preset conditions in time dimension, preset conditions in location dimension, and preset conditions in user operation dimension. The acquired driving data can include current driving time, current geographical position of the vehicle, and current operation of the target user. The target user refers to the user who is currently driving the vehicle. Assuming that the candidate driving scene is the work scene, the preset condition in time dimension of the candidate driving scene is that the current time is between 7:00-9:00 in the morning, the preset condition in location dimension is that the vehicle is located on the driving route from home to the company, and the preset condition in user operation dimension is that the user has already gotten into the vehicle. Then, the time matching score can be calculated according to the current driving time of the vehicle and the preset condition in time dimension, the location matching score can be calculated according to the current geographical position of the vehicle and the preset condition in location dimension, and the operation matching score can be calculated according to the current operation of the target user and the preset condition in user operation dimension. The above-mentioned time matching score, location matching score, and operation matching score can be calculated by means such as semantic matching, keyword matching, etc., and the application does not limit the specific matching manner.

[0043] Further, the matching score of the acquired driving data and the candidate driving scene “work” is calculated according to the time matching score, the location matching score, and the operation matching score. In the calculation process, weighted average calculation, average calculation, standard deviation calculation, etc. can be adopted, and the application does not limit this. Assuming that the weighted average calculation is adopted to calculate the matching score of the driving data and the candidate driving scene, the calculation principle can be referred to the following formula (1): score = w1 x T score + w2 x L score + w3 x B score (1)

[0044] In formula (1), S score represents the matching score of the driving data and a candidate driving scene, T score represents the time matching score, L score represents the location matching score, B score represents the operation matching score, and w1, w2, w3 represent the weight, which can be set by oneself. For example, in the case that the time matching score is 0.9, the location matching score is 0.95, the operation matching score is 1.0, w1 is 0.4, and w2, w3 are both 0.3, according to formula (1), the matching score of the driving data and the candidate driving scene is 0.935.

[0045] It should be noted that the dimensions of the preset conditions described above are only examples, and in the actual implementation process of the scheme of the present application, the preset conditions of any candidate driving scene can also include preset conditions in other dimensions, and correspondingly, the obtained driving data can also include driving data in other dimensions.

[0046] In this embodiment, the matching scores in each preset dimension are calculated by using the preset conditions in the preset dimension and the driving data in the corresponding dimension, and then the matching score of the driving data and the candidate driving scene is calculated by comprehensively considering the matching scores in each preset dimension, which helps to consider the matching degree of the driving data and the candidate driving scene from multiple dimensions, improves the accuracy of the final matching score, and further improves the accuracy of the determined target driving scene. Moreover, this method only needs to calculate based on the driving data in the preset dimension, without considering other invalid driving data, greatly reducing the data amount and effectively improving the calculation efficiency.

[0047] S202, determine the target working flow corresponding to the target driving scene, the target working flow is generated based on the driving habit of the target user, and the target working flow includes at least one target vehicle service, and the target user is the user currently driving the vehicle.

[0048] Since the driving habits of the target user are different in different driving scenes, the working flow corresponding to each driving scene can be generated according to the driving habit of the target user. The driving habit (or driving preference) of the target user can include driving habit, driving habit, etc., such as setting temperature of air conditioner, habit playing song, brake distance, etc. Any working flow includes at least one vehicle service, and the vehicle service refers to the service provided by the vehicle to the user, such as automatic adjustment of seat position, automatic adjustment of air conditioner temperature, etc. When a working flow contains two or more vehicle services, each vehicle service needs to be implemented in a specific order, which can include parallel order and / or serial order. Table 2 is five driving scenes and their corresponding working flows provided by an exemplary embodiment, please refer to Table 2:

[0049] Table 2 is only an example, and the implementation order of each vehicle service in the working flow can be determined according to the actual driving habit of the target user.

[0050] In an embodiment, daily vehicle use data of a target user can be collected through a vehicle-mounted system and an intelligent cockpit interface, and the disordered daily vehicle use data can be cleaned and normalized to obtain structured user portrait data, which is used to represent the user's vehicle use habits / preferences. The user portrait data includes but is not limited to: user personal data, safety domain data, entertainment domain data, and economic domain data. The user personal data can include user name, age, occupation, and other data related to user personal information. The safety domain data can be understood as data related to the user's driving safety habits, such as brake distance, seat position, vehicle speed, etc. The entertainment domain data can be understood as data related to entertainment habits, such as radio, playing songs, and other multimedia data settings, air conditioning temperature settings, etc. The economic domain data can be understood as data related to vehicle expenses, such as power saving / oil saving mode, power consumption / oil consumption mode, etc. The user portrait data can be stored in a portrait database, so that the user portrait data of the target user can be obtained from the portrait database during the implementation of the present application. The portrait database can be deployed locally on the vehicle or on a server, which is not limited in the present application. The user portrait data is not fixed and can be updated in time as the user's vehicle use habits change. In addition, during the collection of user vehicle use data and the generation and storage of user portrait data, the privacy protection of various data should be strengthened to avoid data leakage leading to misuse of user data.

[0051] In the present embodiment, the user portrait data of the target user in all driving scenarios is referred to as "comprehensive user portrait data", and the user portrait data of the target user in the target driving scenario is referred to as "target user portrait data".

[0052] A plurality of candidate driving scenarios respectively corresponding to candidate workflows can be generated in advance according to the comprehensive user portrait data stored in the portrait database, and the plurality of candidate driving scenarios and their corresponding candidate workflows can be stored in the workflow database. The comprehensive user portrait data is used to represent the target user's vehicle use habits in each candidate driving scenario. For example, during storage, a relational database or a NoSQL database can be used as the workflow database, and the candidate workflows can be stored in JSON format (JSON format facilitates subsequent parsing and management of candidate workflows). In addition, the candidate driving scenarios, candidate workflows, and vehicle use requirements corresponding to the candidate driving scenarios can also be stored in association. For example, the candidate driving scenario is the work scenario, the vehicle use requirement is to leave home to go to work from 7:00 to 9:00 in the morning, and the candidate workflow is

adjust the air conditioning temperature to 22℃, play the podcast program, navigate to the company, query the weather forecast

[0053] In the above example, scenario represents a candidate driving scenario, conditions represent the corresponding vehicle use demand of the candidate driving scenario, and actions represent the candidate workflow.

[0054] The workflow database stores a plurality of candidate driving scenarios and corresponding candidate workflows. In the implementation of the scheme of the present application, after the target driving scenario is determined, the candidate driving scenario matching the target driving scenario can be queried in the workflow database, and the candidate workflow corresponding to the queried candidate driving scenario is determined as the target workflow. This approach helps to improve the efficiency of determining the target workflow and reduce errors or delays that may occur during real-time generation.

[0055] In addition, the target workflow corresponding to the target driving scenario can also be temporarily generated according to the target user portrait data after the target driving scenario is determined. For example, the target user portrait data is obtained from the portrait database, which is used to represent the target user's driving habits / preferences in the target driving scenario. For example, the target user portrait data includes: the target user is used to set the air conditioner to 22℃ in the work scenario, and listens to podcasts during driving and listens to singer Xiaobai's songs when waiting for traffic lights. Therefore, based on the target user portrait data, the target workflow can be generated: air conditioner temperature is set to 22℃ → play podcasts during driving → play singer Xiaobai's songs when waiting for traffic lights. This temporary generation of the target workflow realizes real-time generation of the target workflow according to the latest collected target user portrait data, which can further improve the accuracy of the target workflow, so that the target workflow can flexibly meet the current vehicle use demand of the target user.

[0056] In an embodiment, a workflow generation model can be used to generate a workflow. There are many workflow generation models, such as BERT (Bidirectional Encoder Representations from Transformers), Large Language Model (LLM), etc., and the present application does not limit the specific workflow generation model.

[0057] The user portrait data and the prompt word are input into the workflow generation model. The prompt word can help the model better understand the user's demand and guide the model to generate a result matching the input. In this embodiment, the workflow generation model can generate a workflow matching the input user portrait data under the guidance of the prompt word and output it.

[0058] Since the workflow generation model has strong language understanding and data analysis capabilities, a reasonable and accurate workflow can be generated by using the workflow generation model, so that the generated workflow can well adapt to the user's vehicle demand in various driving scenarios, thereby providing accurate and high-quality services / functions for users by executing accurate workflows, which helps to improve user satisfaction.

[0059] FIG. 3 is a schematic diagram of generating and storing candidate workflows according to an example embodiment. As shown in FIG. 3, the user portrait data and the prompt word are input into the workflow generation model, so that the workflow generation model summarizes a plurality of candidate driving scenarios according to the input user portrait data under the indication of the prompt word, and generates a candidate workflow corresponding to each candidate driving scenario to output. In FIG. 3, the workflow generation model outputs candidate driving scenario 1 to candidate driving scenario n, and candidate workflow 1 to candidate workflow n. The candidate workflows correspond one-to-one to the candidate driving scenarios. The generated candidate driving scenarios and the corresponding candidate workflows can be stored in the workflow database. It should be noted that the user portrait data can be updated regularly, so that new candidate scenarios and their corresponding new candidate workflows are generated based on the updated user portrait data, or the candidate workflows corresponding to the original candidate scenarios are updated.

[0060] In an embodiment, FIG. 4 is a flowchart of a training method of a workflow generation model according to an example embodiment. As shown in FIG. 4, the method can include steps S401-S403.

[0061] S401, obtaining sample user portrait data and sample workflows corresponding to the sample user portrait data.

[0062] The sample user portrait data and the sample workflows are known and determined. In order to improve the prediction accuracy of the workflow generation model, a plurality of sample user portrait data and their corresponding sample workflows can be obtained, and each sample workflow includes a preset number of sample vehicle services and each sample vehicle service is executed in a preset order.

[0063] For example, the sample user portrait data can refer to Table 3:

[0064] The sample workflows matched with the above sample user portrait data include a sample workflow corresponding to a work scene and a sample workflow corresponding to a work-off scene. The sample workflow corresponding to the work scene is: setting the air conditioner temperature to 22°C → navigating to the company → playing a podcast. The sample workflow corresponding to the work-off scene is: setting the air conditioner temperature to 24°C → navigating to home → playing soothing music.

[0065] S402, input the sample user portrait data and a sample prompt word into the pre-trained workflow generation model to generate a sample predicted workflow matching the sample user portrait data under the indication of the sample prompt word by the pre-trained workflow generation model and output.

[0066] In this embodiment, the pre-trained workflow generation model refers to a model that has completed preliminary training based on a large amount of unlabeled general data. In order to improve the performance of the pre-trained workflow generation model in the vertical task of generating a workflow, the pre-trained workflow generation model can be fine-tuned using workflow-related data to obtain a model suitable for the workflow generation task. For example, the pre-trained workflow generation model is fine-tuned using sample user portrait data and sample workflows corresponding to the sample user portrait data. During the fine-tuning process, the pre-trained workflow generation model generates a sample predicted workflow.

[0067] The sample predicted workflow includes at least one sample predicted vehicle service. When the sample predicted workflow includes two or more sample predicted vehicle services, each sample predicted vehicle service is executed in a sample predicted order. The sample prompt word can be obtained by initialization, and then the sample prompt word is adjusted during the training process to enable the adjusted sample prompt word to provide clear and accurate indications for the workflow generation model. The specific process of generating the sample predicted workflow can refer to the embodiment shown in S202, which will not be described here.

[0068] S403, according to the difference between the sample workflow and the sample predicted workflow, adjust the sample prompt word and iteratively train the pre-trained workflow generation model.

[0069] The difference between the sample workflow and the sample predicted workflow includes the difference between the sample vehicle service and the sample predicted vehicle service, and the difference between the preset order of each sample vehicle service and the sample predicted order of each sample predicted vehicle service.

[0070] After multiple iterations of training, the obtained workflow generation model meets the predefined training target or reaches the predefined number of iterations, and the training of the workflow generation model is completed. And through multiple adjustments, the prompt word for the workflow generation model is determined. The trained workflow generation model can be used to generate a corresponding workflow according to user portrait data.

[0071] Through the above training method, not only accurate and reasonable prompt words can be obtained, but also the performance of the workflow generation model in the vertical task of generating a workflow is very good, so that an accurate workflow with high accuracy can be obtained by using the workflow generation model.

[0072] S203, execute the target workflow to provide the target user with the at least one target vehicle service.

[0073] After the target workflow is determined, the corresponding functional component can be invoked to execute the target workflow to provide the target user with each target vehicle service included in the target workflow.

[0074] In the above embodiment, the vehicle actively determines the target workflow according to the target driving scenario to execute, without the need for the user to initiate an instruction, which realizes automatic provision of each target vehicle service included in the target workflow to the user at an appropriate time (i.e., in the target driving scenario), and significantly improves the convenience of user operation and the vehicle experience. In addition, the vehicle demands of the user in different driving scenarios are usually inconsistent, and therefore, the current vehicle demand of the user can be more accurately determined according to the target driving scenario. The target workflow corresponding to the target driving scenario is generated based on the vehicle habits of the target user, that is, the target workflow fully considers the user habits / preferences of the target user in the target driving scenario, and therefore, the target workflow can flexibly meet the vehicle demand of the target user in the target driving scenario, and realizes intelligent and personalized services for the target user.

[0075] In an embodiment, after the target workflow is determined, the target workflow can be output to the target user to determine whether to execute the target workflow according to an instruction of the target user. There are many output methods, for example, the target workflow and prompt information of whether to execute the target workflow can be displayed on a human-computer interaction interface, or whether to execute the target workflow can be voice broadcasted to the target user, and the present application does not limit the specific output method. In combination with the foregoing embodiment, the target user can be prompted on the human-computer interaction interface to execute the target workflow of setting the air conditioner temperature to 24°C→planning a home path→playing soothing music (see FIG. 5), or the target user can be voice broadcasted to execute the target workflow of setting the air conditioner temperature to 24°C, planning a home path, and playing soothing music.

[0076] If the target user confirms that each target vehicle service included in the target workflow is correct, and the execution order between each target vehicle service is also correct, the target user will issue a confirmation instruction (such as voice confirmation or trigger the consent control in the human-computer interaction interface). After the vehicle service system receives the confirmation instruction of the target user for the target workflow, the vehicle service system can control each target function component corresponding to each target vehicle service to execute the corresponding target vehicle service. For example, for the target workflow "set the air conditioner temperature to 24°C → plan the path home → play soothing music", if the target user confirms to execute the target workflow, the vehicle service system will send a control instruction to set the temperature to 24°C to the air conditioner controller function component, so that the air conditioner controller sets the air conditioner temperature in the vehicle to 24°C in response to the control instruction. And send a control instruction to the navigation system control unit function component to plan the optimal path from the company to home, so that the navigation system control unit plans the optimal driving path from the company to home in response to the control instruction. And send a control instruction to the multimedia control unit function component to play soothing music, so that the multimedia control unit plays soothing music through the speaker in response to the control instruction.

[0077] If the target user thinks that the target workflow is wrong, the target user can manually adjust the target vehicle service or the execution order between the target vehicle services included in the target workflow, so that the vehicle service system executes the adjusted target workflow.

[0078] In this embodiment, the generated target workflow is checked and confirmed by the target user, which ensures that the vehicle service system can execute the correct target workflow, thereby providing the target user with correct vehicle services. Moreover, for the correct target workflow, the target user only needs to perform a confirmation operation, and all vehicle services included in the target workflow can be automatically executed by the vehicle, effectively improving the convenience of the user driving.

[0079] In an embodiment, feedback information of the target user for the target workflow can be obtained, which can include evaluation information and / or improvement suggestions for the target workflow, so that the target workflow is improved according to the feedback information. The feedback information of the target user for the target workflow can be collected in real time during the execution of the target workflow, or can be collected after the execution of the target workflow is completed. There are many collection methods, such as displaying prompt information for collecting feedback information on the human-computer interaction interface of the vehicle, or sending prompt information for collecting feedback information to the client bound to the target user, which is not limited in the present application.

[0080] FIG. 6 is a block diagram of a vehicle service system according to an example embodiment. As shown in FIG. 6, the vehicle service system includes a data collection module 601, a data processing module 602, a workflow generation module 603, a workflow storage module 604, a scenario recognition module 605, a target workflow determination module 606, and a workflow execution module 607.

[0081] The data collection module 601 is configured to collect daily vehicle data of a user in each driving scenario and send the collected daily vehicle data to the data processing module 602. The data processing module 602 is configured to clean and normalize the daily vehicle data to remove noise and redundant information in the daily vehicle data, and obtain structured user portrait data. The data processing module 602 sends the user portrait data to the workflow generation module 603. The workflow generation module 603 is configured to generate a workflow corresponding to each driving scenario according to the user portrait data, and send the workflow and the corresponding driving scenario to the workflow storage module 604. The workflow storage module 604 is configured to store, update, and manage each driving scenario and the corresponding workflow.

[0082] The scenario recognition module 605 is configured to obtain driving data of a vehicle and determine a target driving scenario of the vehicle according to the driving data. The scenario recognition module 605 sends the determined target driving scenario to the target workflow determination module 606. The target workflow determination module 606 can obtain a target workflow corresponding to the target driving scenario from the workflow storage module 604 or obtain a temporarily generated target workflow from the workflow generation module 603, and send the obtained target workflow to the workflow execution module 607. The workflow execution module 607 is configured to call a vehicle machine / vehicle control interface to control a corresponding functional component to execute the target workflow.

[0083] FIG. 7 is a structural schematic diagram of an electronic device according to an example embodiment of the present application. Referring to FIG. 7, at the hardware level, the electronic device includes a processor 702, an internal bus 704, a network interface 706, a memory 708, and a non-volatile memory 710, and can also include other hardware required by a business. The processor 702 reads the corresponding computer program from the non-volatile memory 710 into the memory 708 and then runs. Of course, in addition to the software implementation, the present application does not exclude other implementation manners, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or a logic device.

[0084] Corresponding to the above method embodiment, the present application also provides an embodiment of an apparatus for actively providing vehicle services.

[0085] FIG. 8 is a block diagram of an apparatus for actively providing vehicle services according to an example embodiment of the present application. The apparatus can be applied to a vehicle service system. Referring to FIG. 8, the apparatus includes a driving scene determining unit 801, a workflow determining unit 802, and a workflow executing unit 803, wherein: the driving scene determining unit 801 is configured to acquire driving data of a vehicle, and determine a target driving scene in which the vehicle is located according to the driving data; the workflow determining unit 802 is configured to determine a target workflow corresponding to the target driving scene, the target workflow being generated based on a driving habit of a target user, the target workflow including at least one target vehicle service, the target user being a user currently driving the vehicle; and the workflow executing unit 803 is configured to execute the target workflow to provide the target user with the at least one target vehicle service.

[0086] In some embodiments, the driving scene determining unit 801 is configured to: determine a preset condition of each candidate driving scene in a plurality of candidate driving scenes; for each candidate driving scene, calculate a matching score of the driving data and the candidate driving scene according to the preset condition of the candidate driving scene; and determine a candidate driving scene whose matching score exceeds a score threshold as the target driving scene.

[0087] In some embodiments, the driving data includes a current driving time, a current geographic location of the vehicle, and a current operation of the target user; the preset condition of any candidate driving scene in the plurality of candidate driving scenes includes a preset condition in a time dimension, a preset condition in a location dimension, and a preset condition in an operation dimension of a user; and calculating a matching score of the driving data and the any candidate driving scene according to the preset condition of the candidate driving scene includes: calculating a time matching score corresponding to the current driving time according to the preset condition of the candidate driving scene in the time dimension; calculating a location matching score corresponding to the current geographic location according to the preset condition of the candidate driving scene in the location dimension; calculating an operation matching score corresponding to the current operation of the target user according to the preset condition of the candidate driving scene in the operation dimension of the user; and calculating the matching score of the driving data and the candidate driving scene based on the time matching score, the location matching score, and the operation matching score.

[0088] In some embodiments, the workflow determination unit 802 is configured to: obtain target user portrait data of the target user in the target driving scene, and generate the target workflow according to the target user portrait data; or query a candidate driving scene matching the target driving scene from a workflow database, and determine a candidate workflow corresponding to the queried candidate driving scene as the target workflow, the workflow database storing a plurality of candidate driving scenes and corresponding candidate workflows, the candidate workflows being generated in advance based on comprehensive user portrait data of the target user; and the target user portrait data or the comprehensive user portrait data is used to represent a driving habit of the target user.

[0089] In some embodiments, the target workflow is generated according to the target user portrait data, including: inputting the target user portrait data and a prompt word into a workflow generation model, so as to generate the target workflow matching the target user portrait data under the indication of the prompt word and output by the workflow generation model.

[0090] In some embodiments, the workflow generation model is trained in the following manner: obtaining sample user portrait data and a sample workflow corresponding to the sample user portrait data; inputting the sample user portrait data and a sample prompt word into a pre-trained workflow generation model, so as to generate a sample predicted workflow matching the sample user portrait data under the indication of the sample prompt word and output by the pre-trained workflow generation model; and adjusting the sample prompt word and iteratively training the pre-trained workflow generation model according to the difference between the sample workflow and the sample predicted workflow.

[0091] In some embodiments, the workflow execution unit 803 is configured to: output the target workflow to the target user, and execute the target workflow if a confirmation instruction of the target user for the target workflow is received.

[0092] In some embodiments, the apparatus further includes a feedback unit 804 configured to obtain feedback information of the target user for the target workflow, so as to optimize the target workflow based on the feedback information, the feedback information including evaluation information and / or improvement suggestions for the target workflow.

[0093] The implementation process of the functions and roles of each module in the above apparatus is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.

[0094] The apparatuses or modules illustrated in the foregoing embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, and the computer can be specifically a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an e-mail device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0095] In a typical configuration, the computer includes one or more processors, including a central processing unit (CPU) and a graphics processing unit (GPU), an input / output interface, a network interface, and a memory. Among them, the central processing unit is used for computing simulation, and the graphics processing unit is used for outputting high-quality three-dimensional images.

[0096] The memory can include non-permanent memory in the computer readable medium, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of the computer readable medium.

[0097] The computer readable medium includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, disk storage, quantum memory, graphene-based storage medium, or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition in this paper, the computer readable medium does not include transitory computer readable media, such as modulated data signals and carriers.

[0098] Corresponding to the embodiments of the foregoing method, the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of any one of the embodiments of the foregoing method.

[0099] Corresponding to the embodiments of the foregoing method, the present application also provides a computer program product, which includes a computer program and / or instructions, and the computer program and / or instructions are executed by a processor to realize the steps of any one of the embodiments of the foregoing method.

[0100] The above description is the some embodiments of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for actively providing vehicle services, comprising: obtaining driving data of a vehicle, and determining a target driving scenario in which the vehicle is located according to the driving data; determining a target workflow corresponding to the target driving scenario, wherein the target workflow is generated based on a driving habit of a target user, the target workflow comprises at least one target vehicle service, and the target user is a user currently driving the vehicle; executing the target workflow to provide the at least one target vehicle service to the target user.

2. The method of claim 1, wherein, The determining of the target driving scenario according to the driving data comprises: determining preset conditions of each candidate driving scenario in a plurality of candidate driving scenarios; for each candidate driving scenario, calculating a matching score of the driving data and the candidate driving scenario according to the preset conditions of the candidate driving scenario; determining a candidate driving scenario whose matching score exceeds a score threshold as the target driving scenario.

3. The method of claim 2, wherein, The driving data comprises a current driving time, a current geographic position of the vehicle, and a current operation of the target user; the preset conditions of any candidate driving scenario in the plurality of candidate driving scenarios comprise preset conditions in a time dimension, preset conditions in a position dimension, and preset conditions in a user operation dimension; The calculating of the matching score of the driving data and the candidate driving scenario according to the preset conditions of the candidate driving scenario comprises: calculating a time matching score corresponding to the current driving time according to the preset conditions of the candidate driving scenario in the time dimension; calculating a position matching score corresponding to the current geographic position according to the preset conditions of the candidate driving scenario in the position dimension; calculating an operation matching score corresponding to the current operation of the target user according to the preset conditions of the candidate driving scenario in the user operation dimension; calculating the matching score of the driving data and the candidate driving scenario based on the time matching score, the position matching score, and the operation matching score.

4. The method of any one of claims 1 to 3, wherein, The determining of the target workflow corresponding to the target driving scenario comprises: obtaining target user portrait data of the target user in the target driving scenario, and generating the target workflow according to the target user portrait data, wherein the target user portrait data is used to represent the driving habit of the target user.

5. The method of claim 4, wherein, The generating of the target workflow according to the target user portrait data comprises: inputting the target user portrait data and a prompt word into a workflow generation model, so as to generate the target workflow matched with the target user portrait data under the indication of the prompt word and output the target workflow by the workflow generation model.

6. The method of claim 5, wherein, The workflow generation model is trained in the following manner: obtaining sample user portrait data and a sample workflow corresponding to the sample user portrait data; inputting the sample user portrait data and a sample prompt word into a pre-trained workflow generation model, so as to generate a sample predicted workflow matched with the sample user portrait data under the indication of the sample prompt word and output the sample predicted workflow by the pre-trained workflow generation model; According to a difference between the sample workflow and the sample predicted workflow, the sample prompt word is adjusted and the pre-trained workflow generation model is iteratively trained.

7. The method of any one of claims 1 to 6, wherein, The determining of the target workflow corresponding to the target driving scene comprises: querying a candidate driving scene matching the target driving scene from a workflow database, and determining a candidate workflow corresponding to the queried candidate driving scene as the target workflow, wherein the workflow database stores a plurality of candidate driving scenes and candidate workflows corresponding thereto, and the candidate workflows are pre-generated based on comprehensive user portrait data of the target user; and the comprehensive user portrait data is used to represent driving habits of the target user.

8. The method of any one of claims 1 to 7, wherein, The executing of the target workflow comprises: outputting the target workflow to the target user, and executing the target workflow upon receiving a confirmation instruction of the target user for the target workflow.

9. The method of any one of claims 1-8, further comprising: obtaining feedback information of the target user for the target workflow, and optimizing the target workflow based on the feedback information, wherein the feedback information comprises evaluation information and / or improvement suggestions for the target workflow.

10. An apparatus for actively providing vehicle services, comprising: a driving scene determination unit configured to obtain driving data of a vehicle, and determine a target driving scene of the vehicle according to the driving data; a workflow determination unit configured to determine a target workflow corresponding to the target driving scene, wherein the target workflow is generated based on driving habits of a target user, the target workflow comprises at least one target vehicle service, and the target user is a user currently driving the vehicle; a workflow execution unit configured to execute the target workflow to provide the at least one target vehicle service to the target user.

11. An electronic device, comprising: one or more processors; a memory for storing executable instructions of the one or more processors; wherein the one or more processors implement the method of any one of claims 1-9 by running the executable instructions.

12. A computer readable storage medium having stored thereon computer instructions, wherein, The instructions, when executed by one or more processors, implement the steps of the method of any one of claims 1-9.

13. A computer program product, wherein, The instructions, when executed by one or more processors, implement the steps of the method of any one of claims 1-9. The instructions, when executed by one or more processors, implement the steps of the method of any one of claims 1-9.

Images