Data processing method and device

Abstract

The invention relates to the technical field of vehicle control, and discloses a data processing method and device, and the method comprises the steps: receiving an input content sent by a user side through a set calling interface; performing intention recognition on the input content to obtain a user intention of the input content; and based on the user intention, responding to the input content, and sending an execution result responding to the input content. Therefore, multi-contact interaction between the user side and the vehicle control and interaction application is fundamentally avoided, user side memory and flow waste caused by multiple applications is avoided, the complexity of interaction operation is remarkably reduced, and the user experience is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a data processing method and device. Background Art

[0002] With the rise of the big model industry, major car companies have applied big models to fields such as intelligent driving, providing users with more intelligent and convenient car services such as remote vehicle control services. Major automobile manufacturers mainly use APP (Application, mobile application) to provide users with vehicle control and interaction-related services. However, with the increasing popularity of APP applications, many users need to download and install multiple APPs to handle multiple intelligent services. It not only takes up a large amount of memory but also consumes a lot of traffic, and during use, it is necessary to switch between multiple APPs multiple times. In addition, during use, for multiple functions, users need to gradually use and understand them, and the time cost of user use and learning is high. In addition, users need to select the input port of the APP or application according to their purpose or needs, which is complicated and error-prone. Summary of the invention

[0003] In view of this, the present invention provides a data processing method and device to solve the problems of waste of application memory and traffic and complex operation related to vehicle control and interaction in the related art.

[0004] In a first aspect, the present invention provides a data processing method, the method comprising:

[0005] Receive input content sent by the user through the setting call interface;

[0006] Perform intent recognition on the input content to obtain the user's intent for the input content;

[0007] Based on the user's intention, respond to the input content and send an execution result responsive to the input content.

[0008] The data processing method of the present invention receives input content by setting a call interface, automatically identifies the user's intention of the input content, and then responds to the input content based on the user's intention, and sends an execution result in response to the input content. In this way, multi-touch interaction between the user end and vehicle control and interactive applications is fundamentally avoided, the waste of user end memory and traffic caused by multiple applications is avoided, and the complexity of interactive operations is significantly reduced, thereby effectively improving the user experience.

[0009] In an optional embodiment of the present invention, before receiving the input content sent by the user terminal through the setting calling interface, the method further includes:

[0010] Receiving registration information of the setting calling interface sent by the user end through the setting calling interface;

[0011] Bind the user end according to the registration information.

[0012] The data processing method of the present invention performs user terminal binding in advance by setting a calling interface, and realizes fast and effective interactive operation based on the user terminal input content.

[0013] In an optional embodiment of the present invention, performing intent recognition on the input content to obtain the user intent of the input content includes:

[0014] The user intention of the input content is determined according to a pre-configured text set, the text set is used to characterize the mapping relationship between multiple keywords and corresponding user intentions, and the input content includes at least one keyword.

[0015] The data processing method of the present invention automatically determines the user intention of the input content according to a pre-configured text set, effectively avoiding the user from selecting the input port of the APP or application according to the purpose or need, thereby fundamentally avoiding the error-prone problems caused by complex operations.

[0016] In an optional embodiment of the present invention, responding to input content based on user intent includes:

[0017] Call the input response component corresponding to the user's intention;

[0018] Get the parsed result of the input content obtained through the input response component;

[0019] Based on the parsing results, respond to the input content.

[0020] In an optional embodiment of the present invention, the user intends to belong to a chat category used to characterize a chat;

[0021] Get the parsed results of the input content obtained through the input response component, including:

[0022] Sending input content and / or user intent to an artificial intelligence laboratory configured at the back end of the automobile enterprise, where the artificial intelligence laboratory is configured with a first model for responding to the input content;

[0023] Receive feedback on input generated by the AI ​​Lab.

[0024] In an optional embodiment of the present invention, the user's intention belongs to a query category for characterizing a query vehicle condition;

[0025] Get the parsed results of the input content obtained through the input response component, including:

[0026] Send input content and / or user intent to a virtual call center platform configured at the back end of the car company;

[0027] Receive vehicle condition data corresponding to the input content obtained through query by the virtual call center platform.

[0028] In an optional embodiment of the present invention, the user intention belongs to a vehicle control category for characterizing control of a vehicle;

[0029] Get the parsed results of the input content obtained through the input response component, including:

[0030] Parsing the input content and / or the user intention to obtain a vehicle control instruction;

[0031] Sending the vehicle control command to a telematics processor configured at the back end of the vehicle manufacturer;

[0032] The control result of the vehicle control by the telematics processor based on the vehicle control command is received.

[0033] The data processing method of the present invention automatically calls the input response component corresponding to the user intention based on the identified user intention of the input content, effectively avoiding the user from selecting the input port of the APP or application according to the purpose or demand, thereby fundamentally avoiding the error-prone problems caused by complex operations.

[0034] In an optional embodiment of the present invention, the input content also includes a user identification of the user terminal;

[0035] Before sending the input content and / or user intention to the virtual call center platform configured at the back end of the automobile enterprise or sending the vehicle control command to the telematics processor configured at the back end of the automobile enterprise, obtaining the parsing result of the input content obtained by the input response component also includes:

[0036] Verify the user end according to the user ID.

[0037] In the data processing method of the present invention, the input content also includes the user identification of the user terminal. Before sending the input content and / or the user intention to the virtual call center platform or the vehicle-side remote control module configured at the back end of the automobile enterprise, the user terminal is also verified according to the user identification. The legitimacy of the user terminal is effectively guaranteed, thereby effectively ensuring the effectiveness of interaction with the vehicle and the legitimacy of controlling the vehicle.

[0038] In an optional embodiment of the present invention, the method further includes:

[0039] Determine customized vehicle control instructions based on the input contents and corresponding execution results obtained multiple times;

[0040] Send customized vehicle control commands to the user end;

[0041] Based on the confirmation result of the customized vehicle control command by the user end, the customized vehicle control command is executed.

[0042] The data processing method and device of the present invention analyze the behavioral habits of the user terminal by acquiring input content and corresponding execution results multiple times, thereby determining customized vehicle control instructions that are compatible with the historical data of the user terminal, realizing customized active interaction with the user terminal based on the user terminal behavior, and effectively improving the user experience.

[0043] In a second aspect, the present invention provides a data processing device, the device comprising:

[0044] The content receiving module is used to receive the input content sent by the user terminal through the setting calling interface;

[0045] An intention recognition module is used to recognize the intention of the input content and obtain the user's intention of the input content;

[0046] The response feedback module is used to respond to the input content based on the user's intention and send an execution result in response to the input content.

[0047] The data processing method and device of the present invention receives input content by setting a call interface, automatically identifies the user's intention of the input content, and then responds to the input content based on the user's intention, and sends an execution result in response to the input content. In this way, multi-touch interaction between the user end and vehicle control and interactive applications is fundamentally avoided, the waste of user end memory and traffic caused by multiple applications is avoided, and the complexity of interactive operations is significantly reduced, thereby effectively improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 is a flow chart of a data processing method according to an embodiment of the present invention;

[0050] Figure 2 is a flow chart of another data processing method according to an embodiment of the present invention;

[0051] Figure 3 is a flowchart of a specific application example of a data processing method according to an embodiment of the present invention;

[0052] Figure 4 is a structural block diagram of a data processing device according to an embodiment of the present invention;

[0053] Figure 5It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] In the related art, the remote control services provided by major car companies focus on the control connection between mobile terminals such as mobile phones and vehicles, but do not pay attention to the contact point between the mobile terminal itself as the user end and the user. For example: for vehicle startup, navigation and other operations, an APP specifically used for vehicle control is configured, for vehicle anti-theft and other operations, an APP specifically used for vehicle monitoring is configured, and for interactive operations such as audio and video playback and chat, a special entertainment control APP is configured. In addition, even if the functions of the above APPs are integrated into the same application, it is necessary to select the type of interaction or operation, and further input the specific content of the interaction or operation. Furthermore, the applications designed and configured by multiple vehicle suppliers are different. If a user owns multiple vehicles, he needs to download and select multiple applications according to his needs, and first select the correct application during use. As a result, in the process of the user end interacting with the vehicle or controlling the vehicle, the memory occupied and the energy consumed are relatively large, and the operation is complicated. Based on this, an embodiment of the present invention provides a data processing method to solve the above technical problems.

[0056] The embodiment of the present invention can be applied to the back end of a car enterprise, and interact with the user end by setting a calling interface. The setting calling interface can be an instant messaging application configured by most user ends, such as WeChat, Alipay, QQ, etc.

[0057] According to an embodiment of the present invention, a data processing method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] In this embodiment, a data processing method is provided, which can be used in the above-mentioned car enterprise backend. Figure 1 is a flow chart of a data processing method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0059] Step S101, receiving input content sent by the user terminal through the setting calling interface.

[0060] In an optional embodiment of the present invention, a user's mobile terminal or computer device can be configured with an instant messaging application, and the instant messaging application can establish a communication connection with the back end of the automobile enterprise through a server provided by a supplier. The instant messaging application can be WeChat, QQ (an instant messaging application) or Alipay, etc.

[0061] For example, a user follows the WeChat official account designated by the car manufacturer of the car used by the user through WeChat. The user can input text or audio through the WeChat official account, and can also choose to set the input content from the official account. The received text or audio can be recognized through WeChat and other applications to obtain the input content. If the user input is text content, it can be directly sent to the server as input content. If the user input is other forms of content such as voice and audio, the user's input voice, audio, etc. can be recognized and the recognition result sent to the server.

[0062] When the server receives the corresponding input content, it can send the input content to the application pre-configured by the car company's backend. Specifically, the user can bind a URL (Uniform Resource Locator) through the official account, and the server sends the input content to the data processing system pre-configured by the car company's backend through the URL bound by the user. Here, the input content can also carry information such as the user's terminal identification or the user's terminal APP identification.

[0063] Here, the user's vehicle control voice commands, vehicle data query voice or chat voice, etc. can all be used as input content. With WeChat and other instant messaging applications as touchpoints, the input content is sent to the car company's back end through the URL bound to the WeChat service account and other set calling interfaces. After receiving the input content, the car company's back end uses a large model to identify the input content's intent and respond.

[0064] It should be noted that the communication interface between the car company backend and the user end can be used as the setting call interface. In this way, the interaction between the car company backend and the user end can be realized through the existing instant messaging application on the user end, by following the corresponding public account, etc., effectively avoiding the user end from downloading and installing different applications for different car companies or different vehicles, which is convenient and fast to use and not prone to errors.

[0065] Step S102: perform intent recognition on the input content to obtain the user's intent of the input content.

[0066] In an optional embodiment of the present invention, the car company backend can be configured with a data processing system capable of receiving user input content, which can be configured in the form of an application. The data processing system can also include a dialogue management module configured with an NLU (Nature Language Understand) model.

[0067] The dialogue management module configured by the automobile enterprise's back-end data processing system can perform intent recognition on the input content. The result of intent recognition can be the user intention used to characterize the intent category. For example, user intent can include: a chat category used to characterize chatting, a query category used to characterize inquiries about vehicle conditions, and a vehicle control category used to characterize control of the vehicle, etc.

[0068] The user intent obtained by intent recognition can also represent the user's specific intent. For example, the user intent of the input content "Please increase the temperature by 3 degrees" is recognized as "Car control: increase the air conditioning temperature by 3 degrees".

[0069] Step S103: respond to the input content based on the user's intention, and send an execution result in response to the input content.

[0070] In an optional implementation of the present invention, multiple input response components configured by the car company's backend can be called based on user intent, such as: AILAB (Artificial Intelligence Laboratory), vehicle-mounted T-BOX (an intelligent terminal device of the Internet of Vehicles system) and VCCP (Virtual Call Center Platform), etc.

[0071] In an optional embodiment of the present invention, at least one of the user intention and the input content can be sent to the input response component, the input response component responds to the input content based on the user intention, and feeds back the execution result in response to the input content to the dialog management system. The user end can implement callback through the setting call interface in step S101, and obtain the execution result feedback in response to the input content from the dialog management system.

[0072] The data processing method of the present invention receives input content by setting a call interface, automatically identifies the user's intention of the input content, and then responds to the input content based on the user's intention, and sends an execution result in response to the input content. In this way, multi-touch interaction between the user end and vehicle control and interactive applications is fundamentally avoided, the waste of user end memory and traffic caused by multiple applications is avoided, and the complexity of interactive operations is significantly reduced, thereby effectively improving the user experience.

[0073] According to an embodiment of the present invention, a data processing method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0074] In this embodiment, a data processing method is provided, which can be used in the above-mentioned car enterprise backend. Figure 2 is a flow chart of a data processing method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0075] Step S201, receiving registration information of a setting calling interface sent by a user terminal through the setting calling interface.

[0076] In an optional embodiment of the present invention, a registration mechanism is used to ensure the security of communication between the user end and the back-end of the automobile enterprise. Specifically, the data processing system of the back-end of the automobile enterprise can receive the registration information of the setting call interface sent by the user end through the setting call interface. For example: the APPID (application identifier) ​​of the instant messaging application of the user end.

[0077] Step S202: Bind the user terminal according to the registration information.

[0078] The car company's back-end data processing system can bind the user end based on the registration information.

[0079] In a specific application example of the present invention, the process of user terminal registration may include:

[0080] Step S2021, the user terminal sends a binding instruction to the car manufacturer's back end.

[0081] In one embodiment of the present invention, the user searches for the WeChat service account "WeChat Elf" of the car company's backend in WeChat and follows the service account. The car company's backend automatically generates a user ID (Identity) after the user follows the service account. The user clicks the "Vehicle Binding" button in the Dark column (a user interface mode) configured by the WeChat service account "WeChat Elf" to enter the vehicle binding process. The user enters the mobile phone number and other information of the bound vehicle to perform operations such as verification code binding.

[0082] In step S2022, the car manufacturer's backend obtains the registration information of the user terminal based on the binding instruction received from the user terminal, and feeds back the registration information to the user terminal.

[0083] Specifically, the binding instruction may carry a user ID. Based on the user ID, the car company backend may obtain at least one of the registration information such as the WeChat ID that the user ID has been bound to, the frame number of the vehicle bound to the user end, and the vehicle picture, and feed back the obtained registration information to the user end.

[0084] Step S2023: The user terminal receives the registration information and if the user terminal has a bound vehicle, step S2024 is executed.

[0085] Step S2024, determine whether the vehicle to be bound is in the list of bound vehicles. If so, execute step S2025. If not, the vehicle to be bound is not in the list of bound vehicles, execute step S2026.

[0086] Step S2025: The user terminal displays registration information. For example, for multiple vehicles that have been bound, the information of multiple bound vehicles is displayed in sequence, and the default vehicle option is switched. The vehicle binding interface is displayed.

[0087] Step S2026: The user terminal displays a binding interface, and the user terminal performs operations based on the binding interface to implement binding of the vehicle to be bound.

[0088] For the vehicle to be bound, the user ID and the vehicle ID can be bound, and the WeChat Elf can obtain the vehicle owner's account control authority. Specifically, the following specific process can be included:

[0089] Step a1: obtaining the user account of the user terminal.

[0090] On the user side, users can enter user accounts such as mobile phone numbers and user names through the input box of the "WeChat Elf" service account, and click the button used to represent "get verification code". Here, the mobile phone number is used as an example. In actual applications, user names can also be used as user account information. The user side enters the mobile phone number bound to the vehicle, and obtains the verification code through the mobile phone number for verification.

[0091] When the car company's backend receives the mobile phone number entered by the user, it sends a verification code to the user's mobile phone or other devices. The verification code needs to be set with a valid time to ensure its validity. If the time for the user to enter the verification code exceeds the valid time, the verification code will be invalid and the user needs to obtain the verification code again.

[0092] Step a2: User account verification.

[0093] For example, if the verification code entered by the user is received by the car company backend and confirmed to be the verification code sent by the car company backend to the corresponding mobile phone number, the user is determined to be a legitimate user. Furthermore, if the verification code is correct, the car company backend can determine whether the user account has a vehicle that has been bound or authorized. Among them, the authorized vehicle means that during the process of user binding the vehicle, the control or interaction rights of the same vehicle can be bound to multiple user accounts.

[0094] If the verification code is wrong, the car company's backend determines that there is an error in the mobile phone number, then it sends a message indicating that the verification failed, and sends information indicating that the verification code is incorrect or that the user account is not the car owner's account, prompting the user to enter the correct mobile phone number.

[0095] If the query result based on the user's account by the car company's backend shows that the user account is not bound to a vehicle and does not have an authorized vehicle, it can be determined that the mobile phone number entered by the user is an invalid number, and a message can be sent to prompt the user to enter the mobile phone number bound to the corresponding vehicle.

[0096] Thus, a binding relationship between the user ID and the vehicle ID is established. When the verification is successful, a message indicating the successful verification is sent, and information such as the WeChat ID, vehicle frame number, and vehicle picture are sent to the user. The WeChat Elf service account can also obtain the control authority of the vehicle owner account corresponding to the vehicle ID.

[0097] Step a3, displaying the relevant information of the binding between the user terminal and the vehicle.

[0098] For example: After completing the binding between the vehicle and the user end, the car company's backend can obtain the user account, nickname, avatar, etc. from the account information provided by the setting call interface according to the user ID, and display the user's binding information on the user end display interface.

[0099] Step a4: Display a verification failure reminder.

[0100] In an optional implementation manner of the present invention, after step a4 or a6, after the binding of the to-be-bound vehicle is completed, the following may also be included:

[0101] Step S2027, unbinding operation.

[0102] Specifically, if the user end is bound to multiple vehicles, the user can operate on the user end interface to switch and unbind the controlled vehicles. This is to avoid the situation where the vehicle owner changes but the original owner's user end does not unbind the bound vehicle through WeChat Genie, resulting in the new owner being unable to use WeChat Genie on the user end to control the vehicle. The background default unbinding rules are also set here. For example, if the user cancels the service account on the user end, the vehicle bound to the user end will be automatically unbound. Changes in the vehicle owner account can also automatically unbind WeChat Genie and other WeChat service accounts of the car company's backend.

[0103] It should be noted that a specific user-side application is used as a carrier to illustrate the solution here. In actual applications, the setting call interface can be configured according to actual needs.

[0104] In an optional embodiment of the present invention, it may also include:

[0105] Step S2028, the user end authorizes the operation.

[0106] For example, by clicking the elf authorization function button of the user-side service account WeChat elf, you can enter the user-side authorization operation process.

[0107] Specifically, the vehicle that the current user has bound and the relevant information attached to the vehicle, such as the frame number, vehicle schematic diagram, authorized members, authorized WeChat avatar, etc., are displayed in the interface of the user's WeChat service account. Click Add Authorization to enter the new authorization process, enter the authorized mobile phone number on the authorization page, and perform a correctness check on the number of digits in the entered mobile phone number. If the check fails, a corresponding reminder is sent to the user. If the check passes, the authorization scope can be selected based on the specific vehicle, and the authorized account can obtain the control authority corresponding to the authorization scope determined by the operation. After completing the corresponding authorization operation, the final authorization confirmation process can be set. Therefore, the authorization operation can be completed by clicking Confirm Authorization on the user side, and the authorization result will be fed back to the corresponding authorized account. If the authorization is successful, it will prompt that the authorization is successful, and if it fails, it will prompt that the authorization failed.

[0108] Furthermore, in order to avoid the same vehicle being bound to multiple user accounts and thus bring security and control risks, the number of accounts bound to the vehicle can be limited. For example: a vehicle can be authorized to bind up to 5 user accounts. For authorized user accounts, the user end can modify and adjust the authorized account. For example: click the edit button of the authorization information to enter the authorization details interface, which displays the chassis number, vehicle schematic diagram, authorized account and other information of the authorized vehicle. The authorized user account information can include the authorized mobile phone number, authorization scope, etc. The authorization scope of the authorized user account can be adjusted or the authorization can be deleted on the user end.

[0109] The data processing method of the present invention performs user terminal binding in advance by setting a calling interface, and realizes fast and effective interactive operation based on the user terminal input content.

[0110] Step S203, receiving input content sent by the user terminal through the setting calling interface.

[0111] For details, please see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0112] Step S204: perform intent recognition on the input content to obtain the user's intent of the input content.

[0113] In an optional embodiment of the present invention, the above step S204 can be implemented by the following operations: determining the user intention of the input content based on a pre-configured text set, the text set is used to characterize the mapping relationship between multiple keywords and corresponding user intentions, and the input content includes at least one keyword.

[0114] The data processing method of the present invention automatically determines the user intention of the input content according to a pre-configured text set, effectively avoiding the user from selecting the input port of the APP or application according to the purpose or need, thereby fundamentally avoiding the error-prone problems caused by complex operations.

[0115] The intention recognition of the input content is to recognize the command of the user's input content. A large model can be used for recognition, and the large model can include modules such as text type determination module, call module and parsing module.

[0116] The text type determination module is used to determine the text type in the vehicle text set corresponding to the user's input content, and determine the user's intention based on the text type. Here, the text type can also be directly used as the user's intention. For example: the chat category used to represent chatting, the query category used to represent the query of vehicle conditions, and the vehicle control category used to represent the control of the vehicle.

[0117] For example, a keyword comparison is performed based on the user input content and the vehicle control corpus database composed of the vehicle text collection. If the vehicle control corpus keywords such as car locks, windows, and sunroof are not hit, it is identified as a chat category. If the keywords related to vehicle control are hit, it is identified as a vehicle control category. If it is a chat category, the big model also responds and gives feedback based on its own algorithms and knowledge base. If it is a vehicle control category, the big model can perform natural language recognition based on the user input content to obtain a more specific intent, search for vehicle control and intent keywords in the text of the user input content, match it with the vehicle control corpus database, and determine the specific category and specific intent of the vehicle control instruction based on the hit keywords. For example, the input content is "Help me open the window", the intent keyword "open" is hit, the vehicle control object keyword "window" is hit, and the inquiry keyword "may" is not hit, so the input content is a non-inquiry intent, and the user intent of the input content is identified as a vehicle control category used to characterize the need to open the window.

[0118] If the text input by the user is relatively complex and contains multiple user intentions, multi-dimensional user intention analysis and recognition can be performed, and the specific recognition dimensions include but are not limited to "time, type, location, control object, execution action", etc. For example, the user input content is "I want to celebrate Xiao A's birthday at 9 o'clock in the evening. At that time, please help me turn on the ambient light, open the trunk, turn on the fragrance, adjust the temperature to a more comfortable level, and play some beautiful music." The text recognition time is 21:00, the control objects are the ambient light, trunk, fragrance, music and air conditioner, the execution action is to turn on the ambient light, trunk, fragrance, music and air conditioner, and the music playback type is beautiful. Furthermore, the big model also calls user behavior data to analyze user behavior habits, and generates air conditioning fine control tasks based on the analysis of user preferences such as temperature, air volume, and air outlet mode when turning on the air conditioner within the set time period. The big model can create agent tasks in the cloud, and based on the trigger time and other trigger conditions obtained from the user behavior data, issue multi-dimensional control instructions when the set trigger conditions are met.

[0119] The calling module of the large model calls the input response component corresponding to each user intention according to the user intention of the input content. For detailed implementation details, please refer to step S205, which will not be repeated here.

[0120] For input content that the user intends to belong to the vehicle control category used to characterize the control of the vehicle, the parsing module can further parse the input content. The target text of the vehicle control signal is obtained to achieve vehicle control. During the semantic parsing process, common vehicle operation texts can be set. For example, common vehicle operation texts can be "turn on the air conditioner", "open the window", "turn on the seat heating", "set the air conditioner temperature to 24 degrees", etc.

[0121] The recognition accuracy of vehicle control commands obtained by recognizing the input content of the vehicle control category depends on the recognition training of the vehicle control commands provided by the large model. The training of vehicle control command text recognition is based on the vehicle control command corpus. The large model can be trained by providing a large amount of vehicle control-related corpus to the large model in the background, thereby improving the recognition performance and accuracy of the large model for vehicle control commands. You can refer to the rule that "the control text sentence pattern of vehicle control commands mainly includes verb-object and noun-verb-object structures", combine this sentence pattern with actual application scenarios, write or collect a large amount of training corpus, and import it into the large model training background. Verb-object structure distance: <open>Air conditioning, the generalized requirements based on this can be written as follows: <iwant> ] <open>[<yixia≥]Air conditioner[<Is that okay≥]; <Okay>[<Help me>] <open> [ <yixia>]Air conditioning<?>;<Can you>[<help me>] <open> [ <yixia>Air conditioner [<呢>]; <iwant> ][ <put>]air conditioner <open> [ <yixia>[<Is that okay?>]; <Can / Could it be done>[<Help me>] <put>air conditioner <open>[<yixia≥][<呢>]. The parsing module only needs to parse the verb and the object in the object, and then it can identify the vehicle control instruction.

[0122] For other detailed implementation details, please refer to Figure 1 Step S102 of the illustrated embodiment, which will not be elaborated here.

[0123] Step S205, based on the user intention, respond to the input content and send the execution result in response to the input content.

[0124] In an optional embodiment of the present invention, the above step S205 may include:

[0125] Step S2051, call the input response component corresponding to the user intention.

[0126] The input response component may include AILAB (Artificial Intelligence Laboratory), VCCP (Virtual Call Center Platform), and in-vehicle T-BOX (Telematics Box), etc.

[0127] Step S2052, obtain the parsing result of the input content obtained through the input response component.

[0128] In an optional embodiment of the present invention, the user intention belongs to the chat category for characterizing chatting. The above step S2053 may include:

[0129] Step b1, send the input content and / or the user intention to the Artificial Intelligence Laboratory configured at the back end of the vehicle enterprise. The Artificial Intelligence Laboratory is configured with a first model for answering the input content.

[0130] If the user intention belongs to the chat category for characterizing chatting, after processing the input content, the user intention can be sent to the Artificial Intelligence Laboratory, or the user content can be directly sent to the Artificial Intelligence Laboratory.

[0131] The Artificial Intelligence Laboratory is pre-configured with a natural language model for chatting with users.

[0132] It should be noted that in the present invention, the Artificial Intelligence Laboratory, the Virtual Call Center Platform, etc. can all be configured as part of the large model.

[0133] Step b2, receive the feedback information of the input content generated by the Artificial Intelligence Laboratory.

[0134] In another optional embodiment of the present invention, the user intention belongs to the query category for characterizing querying vehicle conditions. The above step S2053 may include:

[0135] Get the parsed results of the input content obtained through the input response component, including:

[0136] Step c1, sending input content and / or user intention to a virtual call center platform configured at the back end of the automobile enterprise.

[0137] Step c2, receiving the vehicle condition data corresponding to the input content obtained by querying the virtual call center platform.

[0138] In another optional embodiment of the present invention, the user's intention belongs to a vehicle control category used to characterize the control of the vehicle. The above step S2053 may include:

[0139] Get the parsed results of the input content obtained through the input response component, including:

[0140] Step d1, parsing the input content and / or the user intention to obtain a vehicle control instruction.

[0141] Step d2, sending the vehicle control command to a telematics processor configured at the back end of the vehicle manufacturer.

[0142] Step d3, receiving the control result of the vehicle control by the telematics processor based on the input content.

[0143] Step S2053: respond to the input content based on the analysis result.

[0144] The data processing method of the present invention automatically calls the input response component corresponding to the user intention based on the identified user intention of the input content, effectively avoiding the user from selecting the input port of the APP or application according to the purpose or demand, thereby fundamentally avoiding the error-prone problems caused by complex operations.

[0145] In an optional embodiment of the present invention, the input content also includes a user identification of the user terminal. Before the above step b1 or c1, the user terminal is also verified according to the user identification.

[0146] It should be noted that the various implementation methods of the above step S2053 can be freely combined and used, and the back-end of the automobile enterprise can be configured with at least one of an artificial intelligence laboratory, a virtual call center platform and a telematics processor.

[0147] In the data processing method of the present invention, the input content also includes the user identification of the user terminal. Before sending the input content and / or the user intention to the virtual call center platform or the vehicle-side remote control module configured at the back end of the automobile enterprise, the user terminal is also verified according to the user identification. The legitimacy of the user terminal is effectively guaranteed, thereby effectively ensuring the effectiveness of interaction with the vehicle and the legitimacy of controlling the vehicle.

[0148] In addition, the large models in related technologies are only used for functions such as smart driving car-side voice assistants. The industry does not yet have the ability to combine natural language with large models to achieve remote vehicle control and predict user behavior and provide users with smarter car and life services.

[0149] In this regard, in an optional embodiment of the present invention, it also includes: determining a customized vehicle control instruction based on the input content and corresponding execution results obtained multiple times, and sending the customized vehicle control instruction to the user end, and executing the customized vehicle control instruction based on the user end's confirmation result of the customized vehicle control instruction.

[0150] For example, we can analyze the user's driving behavior in winter, such as the time they use the car to go to work, the routes they often take, and the actions they take when they get in the car, and get customized car control instructions for specific users, such as preheating the battery, turning on the air conditioner, adjusting the temperature in the car, turning on the steering wheel heating, and letting the wizard push the road conditions and recommended routes to work. This eliminates the need for users to turn on and adjust the instructions one by one after getting in the car.

[0151] In order to ensure the safety of the vehicle and the timeliness and accuracy of the vehicle control instructions. The customized vehicle control instructions obtained by analyzing the user's behavior data can be sent to the user end, and after receiving the confirmation result of the customized vehicle control instructions from the user end, the customized vehicle control instructions can be executed. Further, the customized vehicle control instructions can be sent to the vehicle end T-BOX, and the vehicle end T-BOX executes the customized vehicle control instructions and feedbacks the execution results. The WeChat Elf feedbacks the execution results to the user end based on the execution results fed back by the vehicle end T-BOX. The WeChat Elf is not limited to the use of car owners. Car owners can share the WeChat Elf's car control permissions with family or friends. During the sharing process, the car owner can allocate permissions. The shared user can enjoy limited Elf services after following the service account and responding to the permission sharing. In addition to the user's active control, the WeChat Elf can also actively push reminders to users. When an abnormal situation occurs on the vehicle end or a sentinel is triggered, the WeChat Elf can remind the user of the abnormality and sentinel triggering.

[0152] The data processing method and device of the present invention analyze the behavioral habits of the user terminal by acquiring input content and corresponding execution results multiple times, thereby determining customized vehicle control instructions that are compatible with the historical data of the user terminal, realizing customized active interaction with the user terminal based on the user terminal behavior, and effectively improving the user experience.

[0153] According to an embodiment of the present invention, a specific application example of an embodiment of a data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0154] In this embodiment, a specific application example of a data processing method is provided, which can be used for the above-mentioned car enterprise backend. The car enterprise backend may include AILAB, etc. A large model can be uniformly configured at the car enterprise backend to identify and analyze the input content sent by the user through WeChat. Figure 3 is a flowchart of a specific application example of the data processing method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0155] Step S301, the user terminal sends input content to the car manufacturer's backend through a setting call interface.

[0156] The user end communicates with the car company's back-end through instant messaging applications such as WeChat. Specifically, the user end follows the official account corresponding to the car company's back-end and enters text or voice information. If the user enters voice, the received voice is first recognized to obtain the voice recognition result in text form, and the voice recognition result is sent as input content to the server configured with the instant messaging application. If the user enters text, the text can be directly sent as input content to the server configured with the instant messaging application. The server configured with the instant messaging application forwards the input content to the URL (Uniform Resource Locator) bound to the service number.

[0157] Step S302: the car manufacturer's backend performs intent recognition on the input content sent by the user.

[0158] Specifically, the car company's backend receives the user-side application identifier (APPID) and text through the URL bound to the instant messaging application, and performs semantic understanding based on the NLU model (Nature Language Understand) to obtain user intentions such as the chat category used to characterize chat, the query category used to characterize the query of vehicle conditions, and the vehicle control category used to characterize the control of the vehicle.

[0159] Step S3031, if the user's intention is to select the chat category that represents chatting, AILAB can be called as a question-and-answer interface to obtain the answer to the question input by the user.

[0160] Step S3032, if the user intends to use a query category for characterizing the query of vehicle conditions and a vehicle control category for characterizing the control of the vehicle, binding relationship acquisition can be performed, and binding relationship verification can be performed based on the user ID and vehicle ID.

[0161] Step S3033: If the verification is passed and the user intends to use the query category to characterize the query of vehicle condition, VCCP can be called to query the vehicle condition data to obtain the vehicle condition data.

[0162] Step S3034: If the verification is passed and the user intends to use the vehicle control category to characterize the control of the vehicle, the vehicle-side T-BOX can be called to execute the remote control process to obtain the control result.

[0163] Step S304: Feedback the answer to the question, vehicle condition data or control result to the user end as a response result to the input content.

[0164] Specifically, the answer to the question, the vehicle condition data and the control result can be fed back to the service number of the instant messaging application on the user side through the instant messaging application message callback interface for display. The message callback of the calling interface can set the callback time, for example: 5 seconds. Step S305, real-time push of the execution result of the input content.

[0165] Specifically, the backend of the car company can be configured in the cloud, and the VCCP can also obtain the remote actual execution results of the vehicle for the answers to the questions, the output of the vehicle condition data and the control results, and send the remote actual execution results to the cloud. In this way, the remote actual execution situation is monitored, and a push text is generated, and the generated push text is pushed to the user's instant messaging application public account in the form of a fixed message, so that the user can receive and view the actual execution results. It should be noted that in this embodiment of the present invention, the user ID is the user account described above, and the vehicle ID can be the vehicle information such as the frame number described above.

[0166] In this embodiment, a data processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0167] This embodiment provides a data processing device, such as Figure 4 As shown, including:

[0168] The content receiving module 401 is used to receive the input content sent by the user terminal through the setting calling interface;

[0169] Intention recognition module 402, used to perform intention recognition on the input content to obtain the user intention of the input content;

[0170] The response feedback module 403 is used to respond to the input content based on the user's intention and send an execution result in response to the input content.

[0171] In an optional embodiment of the present invention, the device further comprises:

[0172] A registration information receiving module, used for receiving registration information of the setting calling interface sent by the user terminal through the setting calling interface before receiving input content sent by the user terminal through the setting calling interface;

[0173] The binding module is used to bind the user terminal according to the registration information.

[0174] In an optional embodiment of the present invention, the intention recognition module 402 includes:

[0175] The first recognition unit is used to determine the user intention of the input content according to a pre-configured text set, the text set is used to represent the mapping relationship between multiple keywords and corresponding user intentions, and the input content includes at least one keyword.

[0176] In an optional embodiment of the present invention, the response feedback module 403 includes:

[0177] A calling unit, used to call an input response component corresponding to a user's intention;

[0178] The response acquisition unit is used to obtain the parsed response result of the input content obtained through the input response component.

[0179] In an optional embodiment of the present invention, the user intention belongs to the category of small talk used to characterize chat; the response acquisition unit includes:

[0180] A first sending subunit, used to send input content and / or user intention to an artificial intelligence laboratory configured at the back end of the automobile enterprise, where the artificial intelligence laboratory is configured with a first model for responding to the input content;

[0181] The first receiving subunit is used to receive feedback information of input content generated by the artificial intelligence laboratory.

[0182] In an optional embodiment of the present invention, the user intention belongs to a query category for characterizing a query vehicle condition; the response acquisition unit includes:

[0183] A second sending subunit is used to send input content and / or user intention to a virtual call center platform configured at the back end of the automobile enterprise;

[0184] The second receiving subunit is used to receive the vehicle condition data corresponding to the input content obtained by querying the virtual call center platform.

[0185] In an optional embodiment of the present invention, the user intention belongs to a vehicle control category used to characterize control of a vehicle; and the response acquisition unit includes:

[0186] A parsing subunit, used for parsing the input content and / or the user intention to obtain a vehicle control instruction;

[0187] A third sending subunit is used to send the vehicle control command to a telematics processor configured at the back end of the vehicle enterprise;

[0188] The third receiving subunit is used to receive the control result of the remote information processor on the vehicle control based on the vehicle control instruction.

[0189] In an optional embodiment of the present invention, the input content also includes a user identification of the user terminal;

[0190] The response acquisition unit also includes:

[0191] The verification subunit is used to verify the user terminal according to the user identification before sending the input content and / or user intention to the virtual call center platform, and before sending the vehicle control command to the remote information processor configured at the back end of the vehicle enterprise.

[0192] In an optional embodiment of the present invention, the device further comprises:

[0193] An active command module is used to determine customized vehicle control commands based on the input contents and corresponding execution results obtained multiple times;

[0194] A command sending module is used to send customized vehicle control commands to the user end;

[0195] The instruction execution module is used to execute the customized vehicle control instruction based on the confirmation result of the customized vehicle control instruction by the user end.

[0196] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0197] The data processing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0198] The embodiment of the present invention also provides a computer device, such as a server at the back end of a car company, having the above Figure 5 The data processing device shown.

[0199] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0200] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0201] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0202] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0203] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0204] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0205] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0206] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0207] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.< / open> < / put> < / yixia> < / open> < / put> < / iwant> < / yixia> < / open> < / yixia> < / open> < / open> < / iwant> < / open>

Claims

1. A data processing method, It is characterized in that The method comprises: Receive input content sent by the user through the setting call interface; Performing intent recognition on the input content to obtain the user intent of the input content; Based on the user intention, respond to the input content, and send an execution result responsive to the input content.

2. The method according to claim 1, It is characterized in that Before receiving the input content sent by the user terminal through the setting calling interface, the method further includes: Receiving registration information of the setting calling interface sent by the user end through the setting calling interface; The user terminal is bound according to the registration information.

3. The method according to claim 1, It is characterized in that The performing intention recognition on the input content to obtain the user intention of the input content includes: The user intention of the input content is determined according to a pre-configured text set, the text set is used to characterize a mapping relationship between keywords and user intentions, and the input content includes at least one of the keywords.

4. The method according to claim 1, It is characterized in that The responding to the input content based on the user intention includes: Invoke an input response component corresponding to the user intention; Obtaining a parsing result of the input content obtained by the input response component; Based on the parsing result, respond to the input content.

5. The method according to claim 4, It is characterized in that The user intention belongs to the chat class used to characterize chat; The obtaining of the parsing result of the input content obtained by the input response component includes: Sending the input content and / or the user intention to an artificial intelligence laboratory configured at the back end of the automobile enterprise, wherein the artificial intelligence laboratory is configured with a first model for responding to the input content; Receive feedback information of the input content generated by the artificial intelligence laboratory.

6. The method according to claim 4, It is characterized in that The user intention belongs to a query category used to characterize the query vehicle condition; The obtaining of the parsing result of the input content obtained by the input response component includes: Sending the input content and / or the user intention to a virtual call center platform configured at the back end of the automobile enterprise; The vehicle condition data corresponding to the input content obtained by querying the virtual call center platform is received.

7. The method according to claim 4, It is characterized in that The user intention belongs to a vehicle control category used to characterize control of a vehicle; The obtaining of the parsing result of the input content obtained by the input response component includes: Parsing the input content and / or the user intention to obtain a vehicle control instruction; Sending the vehicle control command to a telematics processor configured at the back end of the vehicle manufacturer; A control result of the vehicle control by the telematics processor based on the vehicle control command is received.

8. The method according to claim 6 or 7, It is characterized in that The input content also includes the user identification of the user terminal; Before sending the input content and / or the user intention to the virtual call center platform, and before sending the vehicle control command to the telematics processor configured at the back end of the vehicle manufacturer, the obtaining of the parsing result of the input content obtained by the input response component further includes: The user terminal is verified according to the user identifier.

9. The method according to claim 1, It is characterized in that The method further comprises: Determining customized vehicle control instructions according to the input contents and corresponding execution results obtained multiple times; Sending the customized vehicle control command to the user terminal; Based on the confirmation result of the user terminal on the customized vehicle control instruction, the customized vehicle control instruction is executed.

10. A data processing device, It is characterized in that The device comprises: The content receiving module is used to receive the input content sent by the user terminal through the setting calling interface; An intention recognition module, used to perform intention recognition on the input content to obtain the user intention of the input content; The response feedback module is used to respond to the input content based on the user intention and send an execution result in response to the input content.

Images