User request processing method and device, terminal equipment and vehicle

Abstract

The invention is suitable for the technical field of man-machine interaction, and provides a user request processing method and device, terminal equipment and a vehicle, and the method comprises the steps: obtaining a user request, processing the user request, obtaining a preliminary request processing result, if the processing of the user request is not completed, generating inquiry information according to a request failure reason, and sending the inquiry information to the terminal equipment; the user is inquired with more information; and finally, continuously processing the user request according to supplementary information input by the user based on the inquiry information to obtain a final processing result of the request in this round. In the prior art, when the user request is not completed, the information that the task is not completed is directly output, so that the user cannot obtain a satisfactory result. Under the condition that the user request cannot be completed, the inquiry is actively initiated to the user, so that the user can supplement more key information, an intelligent assistant in the electronic equipment can continue to complete the user request according to the information supplemented by the user, and convenience is brought to the user.

Description

Technical Field

[0001] The present application belongs to the field of human-computer interaction technology, and in particular, relates to a method, apparatus, terminal device and vehicle for processing user requests. Background Art

[0002] An intelligent assistant is a software program that uses artificial intelligence technology to provide users with a variety of assistance services. For example, it provides users with information query, device control, language translation and other functions through human-computer interaction.

[0003] At present, many electronic devices are equipped with intelligent assistants, for example, mobile phones and car computers are equipped with intelligent assistants, so that the devices can better serve humans. When electronic devices interact with users through intelligent assistants to complete user requests, they are often not intelligent enough. When executing user requests, if the task cannot be completed, it will directly output information that the task is not completed, and then end the current round of requests, which cannot meet the needs of users. Therefore, improving the intelligence of intelligent assistants and providing more convenience for users is a problem that needs to be solved at present. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, terminal device, and vehicle for processing user requests, which can improve the intelligence of the smart assistant and provide more convenience for users.

[0005] In a first aspect, an embodiment of the present application provides a method for processing a user request, including:

[0006] Get user request;

[0007] Processing the user request to obtain a preliminary request processing result;

[0008] If the request processing result includes an uncompleted request, generate inquiry information according to the request failure reason included in the request processing result, and display the inquiry information, wherein the inquiry information is used to instruct the user to input supplementary information according to the inquiry information, and the inquiry information is the information required to complete the user request;

[0009] Acquiring supplementary information input by the user;

[0010] The user request is continued to be processed according to the supplementary information to obtain the final processing result of this round of requests.

[0011] In a possible implementation manner of the first aspect, the method further includes:

[0012] Using the reflection model, the final processing result of the current round of requests is evaluated to obtain the evaluation result of the current round of requests, 1≤i≤n, n is the preset maximum number of execution rounds;

[0013] If the evaluation result of the current round of requests is passed, the final processing result of the current round of requests is output.

[0014] In a possible implementation manner of the first aspect, the method further includes:

[0015] If the evaluation result of the current round of requests is failure, determining a correction strategy for the next round of processing of the user requests based on the problems that occurred during the current round of request processing;

[0016] Processing the user request again based on the revised strategy to obtain a final processing result of the next round of processing of the user request;

[0017] If it is determined that the evaluation result of the next round of requests is passed, or the next round of requests has reached the preset maximum number of request execution rounds, the final processing result obtained by processing the user request in the next round is displayed to the user.

[0018] In a possible implementation manner of the first aspect, the processing the user request to obtain a preliminary request processing result includes:

[0019] Extracting keywords from the user request, and determining the part of speech of each keyword and the grammatical relationship between the keywords;

[0020] Based on the part of speech of each keyword and the grammatical relationship between the keywords, semantic analysis is performed on the user request to obtain the user's request intention;

[0021] Generate a processing task corresponding to the user request according to the request intention;

[0022] Execute the processing task and obtain a preliminary request processing result.

[0023] In a possible implementation manner of the first aspect, generating a processing task corresponding to the user request according to the request intent includes:

[0024] Determine, based on the request intent, the subtasks that need to be performed to complete the user request;

[0025] If there are multiple subtasks, the subtasks are sorted to obtain the execution order of the subtasks, and the sorted subtasks constitute the processing task corresponding to the user request.

[0026] In a possible implementation manner of the first aspect, sorting the subtasks to obtain the execution order of the subtasks includes:

[0027] Querying the subtasks with dependency relationships among the subtasks, and obtaining a first task group and a second task group among the subtasks, wherein the first task group is composed of the subtasks with dependency relationships, and the second task group is composed of the subtasks without dependency relationships;

[0028] Sorting the subtasks in the first task group according to the dependency relationship between the subtasks in the first task group to obtain an execution order of the subtasks in the first task group;

[0029] Determining the priority of each subtask in the second task group;

[0030] According to the priority of each subtask in the second task group, each subtask in the second task group is sorted to obtain the execution order of each subtask in the second task group.

[0031] In a possible implementation manner of the first aspect, the method further includes:

[0032] If the supplementary information input by the user is not received and the device operation information of the user is detected after closing the current round of requests, determining the target intention of the user according to the device operation information;

[0033] storing the user request and the target intention in association with each other;

[0034] After receiving the user request after the current moment, searching for the target intent corresponding to the stored user request;

[0035] The user request is processed according to the target intent.

[0036] In a second aspect, an embodiment of the present application provides a device for processing a user request, including:

[0037] Request acquisition module, used to obtain user requests;

[0038] A request processing module, used to process the user request and obtain a preliminary request processing result;

[0039] an inquiry information generating module, configured to generate inquiry information according to the request failure reason included in the request processing result if the request processing result includes an uncompleted request, and display the inquiry information, wherein the inquiry information is used to instruct the user to input supplementary information according to the inquiry information, and the inquiry information is information required to complete the user request;

[0040] An information acquisition module, used to acquire the supplementary information input by the user;

[0041] The request processing module is further used to continue processing the user request according to the supplementary information to obtain the final processing result of this round of requests.

[0042] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for processing user requests described in any one of the first aspects above is implemented.

[0043] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for processing user requests described in any one of the first aspects above when executing the computer program.

[0044] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for processing user requests described in any one of the above-mentioned first aspects is implemented.

[0045] In a sixth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute the method for processing user requests described in any one of the above-mentioned first aspects.

[0046] Compared with the prior art, the first aspect of the present application has the following beneficial effects: the present application first obtains the user request, processes the user request, and obtains the request processing result. If the processing of the user request is not completed, an inquiry message can be generated according to the reason for the request failure to ask the user for more information that is convenient for completing the user request; finally, the user request is continued to be processed according to the supplementary information input by the user based on the inquiry information to obtain the final processing result of this round of requests. Compared with the prior art, when the user request is not completed, the task is directly outputted incompletely, resulting in the user being unable to obtain a satisfactory result; when the user request cannot be completed, the present application actively initiates an inquiry to the user, so that the user can supplement more key information, so that the intelligent assistant in the electronic device can continue to complete the user request according to the information supplemented by the user, thereby improving the intelligence of the intelligent assistant and bringing convenience to the user.

[0047] It can be understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0049] Figure 1 It is a flowchart of a method for processing a user request provided by an embodiment of the present application;

[0050] Figure 2 It is a flowchart of a method for reflecting on a processing process of a user request provided by an embodiment of the present application;

[0051] Figure 3 It is a flowchart of a method for obtaining a request processing result according to a user request provided by an embodiment of the present application;

[0052] Figure 4 It is a flowchart of a method for generating a processing task provided in an embodiment of the present application;

[0053] Figure 5 It is a flowchart of a method for sorting processing tasks provided in an embodiment of the present application;

[0054] Figure 6 is a flowchart of a method for determining user intention according to user operation provided by an embodiment of the present application;

[0055] Figure 7 It is a structural diagram of a device for processing user requests provided by an embodiment of the present application;

[0056] Figure 8 It is a structural diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0057] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0058] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0059] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0060] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0061] An intelligent assistant is a software program that uses artificial intelligence technology to provide users with various assistance services, such as information query, device control, language translation, etc.

[0062] At present, in order to provide users with more convenient services, smart assistants are installed in electronic devices. The electronic device can be a mobile phone or a car computer in a vehicle. When using it, people can talk to the smart assistant and send a request to the smart assistant. After receiving the user's request, the smart assistant can perform related tasks according to the user's request and finally feedback the result to the user.

[0063] However, due to the performance issues of current smart assistants, when the smart assistant executes a user request, if the task fails due to an error in the user request or missing information in the user request, the smart assistant will directly feedback to the user that the request could not be completed. At this time, the user will not be able to get a satisfactory result, resulting in a poor user experience.

[0064] For example, if the user's request is to "query the four treasures", since the information in the user's request is incomplete, it cannot be determined whether it is "the four treasures of the study", "the four treasures under the sea" or "the four treasures at home", etc. Therefore, the smart assistant cannot give an accurate response. The smart assistant feedbacks that the search failed and the request ends.

[0065] Alternatively, if the user's request is "Find the capital of the four treasures of the study in area A", since the capital of the four treasures of the study is not in area A but in area B, the smart assistant cannot find the capital of the four treasures of the study in area A. The result returned by the smart assistant is "The capital of the four treasures of the study was not found in area A", and the request ends.

[0066] When the smart assistant fails to complete the user's request, the user needs to determine the reason for the task failure and improve the request sent to the smart assistant, and then send the improved request to the smart assistant again so that the smart assistant can complete the request. If the user cannot determine the reason for the task failure by himself, the user cannot initiate the request again, which brings inconvenience to the user.

[0067] Based on the above problems, this application proposes a method for processing user requests. After obtaining the user request, if the user request cannot be completed, an inquiry message can be generated according to the reason for the incomplete user request, and the user can be asked for help through the inquiry message, so as to obtain the user's supplementary information that can further complete the user request; finally, the user request is continued to be processed according to the obtained user's supplementary information to obtain the final execution result of the user request. After the task fails, this application can obtain more information that is convenient for completing the user request by asking questions to the user, so as to further process the user request and output the result required by the user.

[0068] The following is a detailed description of the method for processing user requests in an embodiment of the present application. In addition, the present application can be executed in an electronic device, which may be a mobile phone or a vehicle computer, etc. For ease of description, the following description will take the application of the method of the present application in a vehicle computer as an example.

[0069] Figure 1 A schematic flow chart of a method for processing a user request provided by the present application is shown, referring to Figure 1 , the method is described in detail as follows:

[0070] S101, obtaining a user request.

[0071] In this embodiment, the user request may be a voice request of the user, or a text request input by the user.

[0072] As an example, the user request may be "turn on the air conditioner in the vehicle" or "query the weather in area A".

[0073] In one implementation, before obtaining the user request, the method further includes:

[0074] The vehicle computer receives the wake-up word of the smart assistant in the vehicle computer and controls the smart assistant to enter the wake-up state. The wake-up word of the smart assistant can be set as needed. After the smart assistant enters the wake-up state, the user request can be obtained.

[0075] S102: Process the user request to obtain a preliminary request processing result.

[0076] In one embodiment, after receiving a user request, keywords in the user request are extracted, and a processing task corresponding to the user request is generated according to the semantics of the keywords, and the processing task is executed to obtain a request processing result.

[0077] For example, if the user request is "turn on the air conditioner in the vehicle", the keywords are: turn on, air conditioner. The processing task determined according to the keywords in the user request is "turn on the air conditioner".

[0078] If the user request is "Please query the four treasures", the intention is clear, and the keywords are: query, four treasures. The processing task determined based on the keywords of the user request is "query the four treasures".

[0079] In another embodiment, a large number of rule templates are pre-set, and when a user request meets a certain rule, it is determined to be a corresponding intention. For example, a sentence containing keywords such as "query" and "weather" and a specific location and time related expression may be determined as an intention to query the weather. According to the determined user intention, a processing task corresponding to the user request is generated, the processing task is executed, and the request processing result is obtained.

[0080] In this embodiment, the request processing result includes an uncompleted request and a completed request. In the case of an uncompleted request, the request processing result may also include the reason for the request failure, such as lack of key information, incorrect request keywords, no relevant information found, etc. In the case of a completed request, the request processing result may also include information fed back to the user. For example, if the user needs to query weather information, the information fed back to the user is the queried weather information; if the user needs to turn on device A, the information fed back to the user is "device A is turned on", etc.

[0081] S103, if the request processing result includes an uncompleted request, generate an inquiry message according to the request failure reason included in the request processing result, and display the inquiry message, wherein the inquiry message is used to instruct the user to input supplementary information according to the inquiry message, and the inquiry information is the predicted information required to complete the user request.

[0082] In this embodiment, if the vehicle computer has not completed the request, the processing flow of the user request can be suspended first, and more key information can be obtained by interacting with the user. Specifically, the inquiry information is displayed to the user so that the user can supplement it according to the inquiry information, avoiding the situation where the request fails again because the information supplemented by the user is not the required information.

[0083] In this embodiment, the user does not need to input the wake-up word again before inputting the supplementary information, and can directly input the supplementary information. For example, after the vehicle computer displays the inquiry information, the user can directly input the supplementary information in the form of voice.

[0084] For example, if the user's request is "find the four treasures of the study", although the user's intention is very clear, the car computer has not completed the request, and the reason for the request failure is the lack of key information. The query information that can be generated is "Do you need to find the four treasures of the study?" The user can directly say "yes" based on the query information, and the supplementary information is "yes".

[0085] If the user's request is "Find the four treasures of the study in country A", although the user's intention is very clear, the car computer does not complete the request, and the task fails because the four treasures of the study do not exist in country A. The query information that can be generated is "Do you need to find the four treasures of the study in country B?" The user can directly say "yes" based on the query information, and the supplementary information is "yes".

[0086] It should be noted that the vehicle computer can send multiple inquiry messages to obtain sufficient and correct supplementary information.

[0087] In another embodiment, if the request processing result includes a completed request, information to provide feedback to the user is displayed.

[0088] S104: Acquire the supplementary information input by the user.

[0089] In this embodiment, the supplementary information may be voice information or text information.

[0090] S105: Continue to process the user request according to the supplementary information to obtain a final processing result of this round of requests.

[0091] In this embodiment, the supplementary information is a further supplement to the user request. According to the supplementary information, the user request is modified, and the modified user request is continued to be executed to complete the response to the user request in this round.

[0092] For example, if the user request is "find the four treasures of the study", the car computer has not completed the request, and the reason for the request failure is the lack of key information, the query information that can be generated is "Do you need to find the four treasures of the study?" The user can directly say "yes" based on the query information, and the supplementary information is "yes". Then the car computer determines that the user request is "find the four treasures of the study", and the car computer continues to execute the user request, that is, continues to search for the four treasures of the study, and obtains the final processing result of this round of requests.

[0093] In this embodiment, if the user request is to query certain information, the final processing result includes the information queried according to the user request. If the user request is to open a certain device, the final processing result includes that the device has been turned on. If the user request is to open a certain application software, the final processing result includes that the application software has been opened.

[0094] In one implementation, the above method can be implemented in the Agent of the car computer, and the Agent refers to an artificial intelligence program that performs user tasks. In the car computer, the Agent is responsible for processing tasks such as navigation and information query, and performs task processing according to user needs. Specifically, a prompt word project is set in the Agent, and the prompt words in the Agent are used to prompt the tasks that the car computer should perform. For example, a prompt word "what is your responsibility" is set in the Agent and the tasks that the car computer should perform are explained in "what is your responsibility". For example, when the user asks about vehicle-related information, please answer as A to ensure that the information is accurate and avoid misleading the user. This application relies on the ability of the Agent to perform tasks and provide intelligent services in specific scenarios. When the task execution fails, the task of asking the user to obtain richer query information is set in the Agent, which can cope with chat questions and answers in diversified scenarios and realize emotional interaction and task execution.

[0095] In this embodiment, the user request is first obtained, the user request is processed, and the request processing result is obtained. If the processing of the user request is not completed, an inquiry message can be generated according to the reason for the request failure to ask the user for more information that is convenient for completing the user request; finally, the user request is continued to be processed according to the supplementary information input by the user based on the inquiry information to obtain the final processing result of this round of requests. Compared with the prior art that directly outputs information that the task is not completed when the user request is not completed, resulting in the user being unable to obtain a satisfactory result; the present application actively initiates inquiries to the user when the user request cannot be completed, and through multiple rounds of dialogue with the user, the user is allowed to supplement more key information, avoiding the phenomenon of user request failure due to insufficient or incorrect information, so that the intelligent assistant in the electronic device can continue to complete the user request according to the information supplemented by the user, reducing the task failure rate, improving the intelligence of the intelligent assistant, and bringing convenience to the user.

[0096] In one possible implementation, when the smart assistant in the car computer processes user requests, it often experiences hallucinations, resulting in inaccurate processing of user requests. Specifically, hallucinations in the smart assistant include errors in calling programs, fabricated information, and response information that does not match the request. The reason for the hallucinations in the smart assistant may be that the user request is complex, resulting in an incorrect processing result; on the other hand, it may be that the smart assistant is not capable enough to evaluate whether the request is completed correctly.

[0097] In order to make the final processing result displayed to the user more accurate, when displaying the processing result of the user request to the user, the processing process of the current round of requests can be verified to determine whether the final processing result obtained is accurate. Specifically, the present application introduces a reflection model, through which the processing process of the user request is evaluated, thereby ensuring the accuracy and completeness of the processing of the user request.

[0098] like Figure 2 Specifically, after obtaining the final processing result of this round, the application method may further include:

[0099] S201, evaluating the final processing result of the current round of requests to obtain the evaluation result of the current round of requests.

[0100] In this embodiment, the reflection model is an algorithm used to evaluate and verify the execution of artificial intelligence tasks. It reflects on or reviews the results of the executed tasks, that is, it performs a secondary evaluation of the generated results to determine whether they meet the expected requirements and decide whether the task needs to be retried or adjusted.

[0101] In this embodiment, one round of processing of the user request is from receiving the user request to obtaining the final processing result.

[0102] In this embodiment, the final processing results obtained from the current round of requests are evaluated to obtain the completion degree of the current round of requests, and the evaluation results of the current round of requests are determined according to the completion degree.

[0103] Specifically, the evaluation of the final processing results obtained in this round of requests may include: accuracy evaluation, completeness evaluation, relevance evaluation, etc., and the completion degree of this round of requests is determined based on the accuracy evaluation, completeness evaluation and relevance evaluation.

[0104] Among them, accuracy assessment can include factual accuracy and logical accuracy.

[0105] Factual accuracy is about checking whether the information provided by the smart assistant is consistent with known facts. For example, if a user asks for the date of a historical event, the smart assistant’s answer should be consistent with reliable historical records.

[0106] Logical accuracy is to check whether the answers of the smart assistant are logically coherent. For example, when answering causal questions, there should be a reasonable deduction between the cause and the effect. For example, if a user asks "Why do plants need sunlight for photosynthesis", the answer of the smart assistant should accurately explain the mechanism of sunlight in photosynthesis, such as the logical relationship that light energy is absorbed by chlorophyll and converted into chemical energy.

[0107] Completeness assessment can include content completeness and step completeness assessment.

[0108] Content completeness is to evaluate whether the information provided is sufficient to meet the user's request. If a user asks about the functions of a product, the smart assistant should not only list the main functions, but also mention some important auxiliary functions or special features. For example, if a user asks "What are the characteristics of the camera function of a smartphone", in addition to mentioning basic content such as pixels and number of lenses, the smart assistant should also include other related functions such as anti-shake and night scene mode to be considered complete.

[0109] Step completeness is to detect whether the given steps are complete. For tasks involving steps, such as cooking steps, software installation steps, etc., the smart assistant should list every necessary step in full.

[0110] Relevance assessment can include the relevance of the answer to the question and the relevance of the cited content, etc.

[0111] The relevance of the answer to the question is to detect whether the answer of the intelligent assistant is closely related to the question asked by the user.

[0112] Relevance of referenced content: If the smart assistant refers to other materials to answer questions, these references should be relevant to the question. For example, when answering the technical specifications of a technology product, the referenced technical standard documents or review articles should be specific to the product, rather than irrelevant content from other products.

[0113] Specifically, the first standard weight for accuracy assessment, the second standard weight for integrity assessment, and the third standard weight for relevance assessment are pre-set, and the standard weight is the weight when there is no problem or error. The first standard weight is adjusted according to the accuracy assessment result to obtain the accuracy, and the adjusted first standard weight is the accuracy. For example, if there is an inaccurate place, the first standard weight is correspondingly reduced by a preset value. The second standard weight is adjusted according to the integrity assessment result to obtain the completeness. The third standard weight is adjusted according to the relevance assessment result to obtain the relevance. The sum of the standard degree, completeness, and relevance is calculated to obtain the completion degree when processing the user request.

[0114] If the completion degree is greater than the preset threshold, the evaluation result is passed; if the completion degree is less than or equal to the preset threshold, the evaluation result is failed. The preset threshold can be set as needed.

[0115] S202: If the evaluation result of the current round of requests is passed, the final processing result of the current round of requests is output.

[0116] For example, if the current round of requests is the first round of requests, and the evaluation result of the first round of processing of the user request is passed, then the final processing result obtained by processing the user request in the first round is output.

[0117] S203: If the evaluation result of the current round of requests is failure, a correction strategy for processing the user requests in the next round is determined according to the problems that occurred during the processing of the current round of requests.

[0118] In this embodiment, if the evaluation result is failure, it means that there are many problems when processing the user request, resulting in inaccurate final processing results of this round, so the user request needs to be reprocessed.

[0119] Specifically, if the evaluation result is failure, the problems encountered in this round of processing the user request are extracted, such as program call errors, reference errors, step errors, etc., and corresponding correction strategies are generated according to the problems encountered in this round of processing the user request, so as to correct the problems existing in this processing when the user request is processed again.

[0120] For example, if the evaluation result of the first round of processing of the user request is failure, a correction strategy for the second round of processing of the user request is generated based on the problems that occurred in the first round of processing of the user request.

[0121] S204: Process the user request again based on the revised strategy to obtain a final processing result of the next round of processing of the user request.

[0122] In this embodiment, the process of processing user requests is corrected based on the correction strategy to obtain the process of the next round of processing user requests, and the user requests are processed using the obtained process of the next round of processing user requests to obtain the final processing result of the next round of processing user requests.

[0123] As an example, according to the obtained correction strategy for the second round of processing of user requests, the second round of processing of user requests is performed to obtain the final processing result of the second round of processing of user requests.

[0124] S205: If it is determined that the evaluation result of the next round of requests is passed, or the next round of requests has reached the preset maximum number of request execution rounds, the final processing result obtained by processing the user request in the next round is displayed to the user.

[0125] In this embodiment, the maximum number of request execution rounds for processing user requests is preset. For example, the maximum number of request execution rounds may be 5 or 4. If the same user request reaches the maximum number of request execution rounds, the processing of the user request is stopped and the final result is output to the user.

[0126] In another embodiment, if it is determined that the evaluation result of the next round of requests is not passed, or the next round of requests has reached a preset maximum number of request execution rounds, the final processing result obtained by processing the user request in the next round is displayed to the user.

[0127] In another embodiment, if it is determined that the evaluation result of the next round of requests is not passed and the next round of requests does not reach the preset maximum number of request execution rounds, the user request is processed again.

[0128] In this embodiment, the reflection model is used to reflect on the processing process of the user request, and the processing result is output after it is determined that the processing process of the user request is passed; when it is determined that the processing process of the user request is not passed, the problems that occurred in the processing process of the user request can be determined, and then the processing process of the user request can be improved according to the problems existing in the processing process, and the user request is processed again using the improved processing method, so as to obtain a more accurate processing result; the inspection of the processing process of the user request is completed through the reflection model, so that the final processing result is more accurate.

[0129] In one possible implementation, when completing a user request, in order to complete the user request more accurately and quickly, after obtaining the user request, the vehicle computer can determine the task to be performed based on the user request. The vehicle computer can quickly complete the user request by executing the determined task and obtain the request processing result of the user request.

[0130] like Figure 3 As shown, specifically, the implementation process of step S102 may include:

[0131] S1021, extracting keywords from the user request, and determining the part of speech of each keyword and determining the grammatical relationship between the keywords.

[0132] In this embodiment, the parts of speech include nouns, verbs, adjectives, adverbs, etc. For example, if the user request is "query book A", and the keywords of the user request are query and book A, then the keyword "query" is a verb and "book A" is a noun.

[0133] In this embodiment, the grammatical relationship includes subject-predicate relationship, verb-object relationship, parallel relationship, supplementary relationship, etc. The grammatical relationship between keywords can be determined by using a grammatical analyzer.

[0134] S1022: Based on the part of speech of each keyword and the grammatical relationship between the keywords, semantic analysis is performed on the user request to obtain the user's request intention.

[0135] In this embodiment, the keywords are combined based on the grammatical relationship between the keywords and the word parts of the keywords to obtain the key information in the user request, and the key information is semantically analyzed to determine the user's request intention. For example, if the key information is "open the skylight", then "open" is a verb and "skylight" is a noun, it can be determined that the action of opening needs to be performed, and the object of the action of "opening" is "skylight", and it can be determined that the user's request intention is: open the skylight.

[0136] S1023: Generate a processing task corresponding to the user request according to the request intent.

[0137] In this embodiment, the user's request Figure 1 It is generally a processing task that the vehicle computer needs to perform. For example, if the user's request intention is "open the sunroof", the corresponding processing task is "open the sunroof".

[0138] S1024, execute the processing task to obtain a preliminary request processing result.

[0139] In this embodiment, the part of speech of the keyword provides a basic characterization of the function of the keyword in the sentence, and the grammatical relationship between the keywords further defines the mutual connection between the words. Through the part of speech and grammatical relationship of the keywords in the user request, the role of the word can be clarified, semantic ambiguity can be eliminated, and implicit information can be completed, so as to achieve the effect of more accurately understanding the semantics of the user request, and then accurately determine the user's intention, ensure the accuracy of the user request processing, and make the request processing result more accurate.

[0140] The above is a process of determining the task to be performed through the part of speech and grammatical relationship of the keywords in the user request. In addition to the above method, specific tools can also be used to identify the intent of the user request, and determine the task to be performed based on the identified intent, so as to achieve the purpose of processing the user request.

[0141] Specifically, the implementation process of step S102 may further include:

[0142] Use the function calling tool to call the trained intent recognition module, input the user request into the intent recognition module, and determine the user intent in the user request through the intent recognition module; generate the corresponding task planning list according to the user intent. Traverse each task in the task planning list and execute the corresponding task to obtain the request processing result.

[0143] In this embodiment, the intent recognition module is a trained module used to recognize user intent. The intent recognition module can more accurately mine the explicit and implicit intents in user requests to ensure that user intent is not missed.

[0144] In one possible implementation, when processing user requests, there are often multiple intentions in the user request, or one user intention needs to complete different tasks to be processed. Therefore, when there are multiple tasks, it is necessary to sort the multiple tasks so that the car computer can complete the tasks in an orderly manner to prevent the problem of car computer jamming due to too many tasks.

[0145] like Figure 4 Specifically, the implementation process of step S1024 may include:

[0146] S301, determining, according to the request intention, the subtasks that need to be performed to complete the user request.

[0147] In this embodiment, the request intention is analyzed to determine how many tasks need to be performed to complete the request intention, and each task that needs to be performed is a subtask.

[0148] For example, if the request intent is "turn on the air conditioner and adjust it to 22 degrees", then there are two subtasks, namely "turn on the air conditioner" and "adjust it to 22 degrees".

[0149] If the request intent is "navigate to City B", then you first need to find the location of City B on the map, and then plan a route to City B. Therefore, there are two subtasks, namely "find the location of City B" and "plan a route to City B".

[0150] S302: If there are multiple subtasks, sort the subtasks to obtain the execution order of the subtasks. The sorted subtasks constitute the processing task corresponding to the user request.

[0151] In one embodiment, the execution order of the subtasks is determined, and the subtasks are sorted according to the execution order of the subtasks.

[0152] like Figure 5 As shown, specifically, the method of sorting the subtasks to obtain the execution order of each subtask includes:

[0153] S3021, querying the subtasks with dependency relationships among the subtasks, and obtaining a first task group and a second task group among the subtasks, wherein the first task group is composed of subtasks with dependency relationships, and the second task group is composed of subtasks without dependency relationships.

[0154] In this embodiment, tasks with dependency relationships refer to tasks in a series of tasks where the execution of certain tasks must be based on the completion of other tasks. In other words, the start, progress or completion of a task depends on the specific state of another (or more) tasks. This relationship is like a chain, with one link after another, and the previous link provides the necessary basis for the subsequent link. Dependency relationships include sequential dependency and conditional dependency. Among them, sequential dependency means that tasks must be executed in a specific order; conditional dependency means that whether a task can be executed depends on whether the conditions generated by another task are met.

[0155] For example, if planning a route to City B depends on finding the location of City B, there is a dependency relationship between the two subtasks of "finding the location of City B" and "planning a route to City B".

[0156] S3022: Sort the subtasks in the first task group according to the dependency relationship between the subtasks in the first task group to obtain an execution order of the subtasks in the first task group.

[0157] In this embodiment, the starting task of each subtask with dependencies is determined, and other tasks are arranged step by step from the starting task. Each time the position of a task is determined, it is necessary to check whether the task it depends on has been arranged in the front position. After completing the preliminary sorting, the entire task sequence is checked again to ensure that all dependencies are correctly reflected and there is no situation where the task order violates the dependency. If a problem is found, such as a task's predecessor dependent task is not arranged before it, or a resource dependent task does not have a corresponding resource provision task first, it is necessary to adjust the task order in time.

[0158] S3023: Determine the priority of each subtask in the second task group.

[0159] In one embodiment of the present invention, a priority task table is preset, and the priority of different subtasks is stored in the priority task table. The priority of each subtask in the second task group is searched from the preset priority task table.

[0160] In another embodiment, the importance of each subtask in the second task group is compared, and the priority of the subtask is determined according to the importance of the subtask, and the higher the importance, the higher the priority. For example, the urgency of the task is determined by analyzing the keywords and tone in the user request, such as "immediately", "as soon as possible", "before..." and other words indicate that the urgency of the task is high; for example, "help me check the stock price immediately" is more urgent than "help me organize the investment portfolio report when you have time", and urgent tasks are usually more important. Alternatively, the importance of each subtask is determined according to the order of tasks described in the user request, and the subtasks that are ranked earlier in the user request have a higher priority than the subtasks that are ranked later in the user request.

[0161] S3024: Sort the subtasks in the second task group according to the priority of each subtask in the second task group to obtain an execution order of the subtasks in the second task group.

[0162] In this embodiment, by sorting the subtasks according to the dependency relationship between the subtasks, the order of the subtasks can be made more accurate, the risk of incorrect task execution order can be reduced, and the smoothness of subtask processing can be ensured. For subtasks that do not have a dependency relationship, the subtasks are sorted according to their priority, so that important or urgent subtasks are processed first, making the task processing more in line with the user's wishes. In addition, the present application sorts all subtasks so that the subtasks can be processed in order, avoiding the omission of subtasks, and making the final processing of user requests more accurate.

[0163] In one possible implementation, when processing a user request, it is possible that after the inquiry information is displayed, the user does not answer, or the inquiry information is not what the user wants to query, and the user will close this round of requests. The user may directly perform manual operations. At this time, the user intent can be extracted according to the order of the user's manual operations, and then the user request can be associated with the user intent and stored, so that after the same user request is received later, the user request can be processed according to the user intent stored in association with the user request, ensuring that the same user request can be processed smoothly when it is received later.

[0164] like Figure 6 Specifically, after step S103, the method of the present application may further include:

[0165] S401: If the supplementary information input by the user is not received and the device operation information of the user is detected after closing the current round of requests, the target intention of the user is determined according to the device operation information.

[0166] In this embodiment, the user's device operation information may include the user opening an application software, the user searching for information in an information search software, the user opening the sunroof of the vehicle, or the user turning on the air conditioner of the vehicle.

[0167] In this embodiment, each step of the user operating the vehicle is recorded, and then the user's target intention is extracted through each step. For example, after the user clicks the sunroof opening button, it is determined that the user's target intention is to open the sunroof.

[0168] S402: Store the user request and the target intent in association with each other.

[0169] Specifically, the user request and the target intent may be stored in a preset intent query table, in which the intent corresponding to the user request is a determined target intent.

[0170] S403: After receiving the user request after the current moment, determine the user's intention as the target intention according to the user request.

[0171] In this embodiment, when the vehicle computer receives the same user request again, it can automatically query the target intention corresponding to the user request.

[0172] S404: Process the user request according to the target intent.

[0173] In this embodiment, the task to be performed is determined according to the target intent, thereby achieving the purpose of processing the user request.

[0174] In the present application, when the vehicle computer cannot process the user request, after the user closes this round of requests, the user's target intention can be automatically detected based on the user's operation on the device, and the user's target intention can be associated with the unfinished user request and stored, which is conducive to processing the user request after receiving the same user request again in the future.

[0175] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0176] Corresponding to the method for processing user requests described in the above embodiment, Figure 7 A structural block diagram of a user request processing device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0177] Reference Figure 7 The device 500 may include: a request acquisition module 510, a request processing module 520, a query information generation module 530 and an information acquisition module 540.

[0178] The request acquisition module 510 is used to acquire a user request;

[0179] The request processing module 520 is used to process the user request and obtain a preliminary request processing result;

[0180] The inquiry information generating module 530 is used to generate inquiry information according to the request failure reason included in the request processing result if the request processing result includes an uncompleted request, and display the inquiry information, wherein the inquiry information is used to instruct the user to input supplementary information according to the inquiry information, and the inquiry information is the information required to complete the user request;

[0181] The information acquisition module 540 is used to acquire the supplementary information input by the user;

[0182] The request processing module 520 is further used to continue processing the user request according to the supplementary information to obtain the final processing result of this round of requests.

[0183] In a possible implementation, the request processing module 520 is also connected to:

[0184] An evaluation module is used to evaluate the final processing result of the current round of requests by using a reflection model to obtain the evaluation result of the current round of requests;

[0185] The first result output module is used to output the final processing result of the current round of requests if the evaluation result of the current round of requests is passed.

[0186] In a possible implementation, the evaluation module is also connected to:

[0187] A strategy determination module is used to determine a correction strategy for processing the user request in the next round according to the problems that occurred during the processing of the request in the current round if the evaluation result of the request in the current round is not passed;

[0188] A second result output module, used to process the user request again based on the correction strategy to obtain a final processing result of the next round of processing of the user request;

[0189] The third result output module is used to display the final processing result obtained by processing the user request in the next round to the user if it is determined that the evaluation result of the next round of requests is passed or the next round of requests has reached a preset maximum number of request execution rounds.

[0190] In a possible implementation, the request processing module 520 may be specifically used to:

[0191] Extracting keywords from the user request, and determining the part of speech of each keyword and the grammatical relationship between the keywords;

[0192] Based on the part of speech of each keyword and the grammatical relationship between the keywords, semantic analysis is performed on the user request to obtain the user's request intention;

[0193] Generate a processing task corresponding to the user request according to the request intention;

[0194] Execute the processing task and obtain a preliminary request processing result.

[0195] In a possible implementation, the request processing module 520 may be specifically used to:

[0196] Determine, based on the request intent, the subtasks that need to be performed to complete the user request;

[0197] If there are multiple subtasks, the subtasks are sorted to obtain the execution order of the subtasks, and the sorted subtasks constitute the processing task corresponding to the user request.

[0198] In a possible implementation, the request processing module 520 may be specifically used to:

[0199] Querying the subtasks with dependency relationships among the subtasks, and obtaining a first task group and a second task group among the subtasks, wherein the first task group is composed of the subtasks with dependency relationships, and the second task group is composed of the subtasks without dependency relationships;

[0200] Sorting the subtasks in the first task group according to the dependency relationship between the subtasks in the first task group to obtain an execution order of the subtasks in the first task group;

[0201] Determining the priority of each subtask in the second task group;

[0202] According to the priority of each subtask in the second task group, each subtask in the second task group is sorted to obtain the execution order of each subtask in the second task group.

[0203] In a possible implementation, the query information generating module 530 is also connected to:

[0204] an intention determination module, configured to determine the target intention of the user according to the device operation information if the supplementary information input by the user is not received and the device operation information of the user is detected after closing the current round of requests;

[0205] A binding module, used for associating and storing the user request and the target intent;

[0206] A query module, configured to search for the target intent corresponding to the stored user request after receiving the user request after the current moment;

[0207] An execution module is used to process the user request according to the target intent.

[0208] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0209] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0210] An embodiment of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for processing user requests when executing the computer program.

[0211] The present application also provides a terminal device, see Figure 8 The terminal device 600 may include: at least one processor 610, a memory 620, and a computer program stored in the memory 620 and executable on the at least one processor 610. When the processor 610 executes the computer program, the steps in any of the above-mentioned method embodiments are implemented, for example Figure 1 Steps S101 to S105 in the illustrated embodiment. Alternatively, when the processor 610 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 7 The functions of the user request module 510 to the information acquisition module 540 are shown.

[0212] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 620, and executed by the processor 610 to complete the present application. The one or more modules / units may be a series of computer program segments capable of completing specific functions, and the program segments are used to describe the execution process of the computer program in the terminal device 600.

[0213] Those skilled in the art will understand that Figure 8 It is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0214] The processor 610 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0215] The memory 620 may be an internal storage unit of the terminal device, or an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. The memory 620 is used to store the computer program and other programs and data required by the terminal device. The memory 620 may also be used to temporarily store data that has been output or is to be output.

[0216] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0217] The method for processing user requests provided in the embodiment of the present application can be applied to terminal devices such as computers, tablet computers, laptop computers, netbooks, personal digital assistants (PDAs), etc. The embodiment of the present application does not impose any restrictions on the specific type of terminal devices.

[0218] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0219] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0220] In the embodiments provided in the present application, it should be understood that the disclosed terminal equipment, devices and methods can be implemented in other ways. For example, the terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0221] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0222] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0223] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by one or more processors, the steps of each of the above-mentioned method embodiments can be implemented.

[0224] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by one or more processors, the steps of each of the above-mentioned method embodiments can be implemented.

[0225] Similarly, as a computer program product, when the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0226] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0227] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for processing a user request, characterized in that: include: Get user request; Processing the user request to obtain a preliminary request processing result; If the request processing result includes an uncompleted request, generate inquiry information according to the request failure reason included in the request processing result, and display the inquiry information, wherein the inquiry information is used to instruct the user to input supplementary information according to the inquiry information, and the inquiry information is the information required to complete the user request; Acquiring supplementary information input by the user; The user request is continued to be processed according to the supplementary information to obtain the final processing result of this round of requests.

2. The method for processing user requests according to claim 1, characterized in that: The method further comprises: Using the reflection model, the final processing result of this round of requests is evaluated to obtain the evaluation result of this round of requests; If the evaluation result of the current round of requests is passed, the final processing result of the current round of requests is output.

3. The method for processing user requests according to claim 2, characterized in that: The method further comprises: If the evaluation result of the current round of requests is failure, determine the correction strategy for the next round of processing of the user requests based on the problems that occurred during the current round of request processing; Processing the user request again based on the revised strategy to obtain a final processing result of the next round of processing of the user request; If it is determined that the evaluation result of the next round of requests is passed, or the next round of requests has reached the preset maximum number of request execution rounds, the final processing result obtained by processing the user request in the next round is displayed to the user.

4. The method for processing user requests according to claim 1, characterized in that: The processing of the user request to obtain a preliminary request processing result includes: Extracting keywords from the user request, and determining the part of speech of each keyword and the grammatical relationship between the keywords; Based on the part of speech of each keyword and the grammatical relationship between the keywords, semantic analysis is performed on the user request to obtain the user's request intention; Generate a processing task corresponding to the user request according to the request intention; Execute the processing task and obtain a preliminary request processing result.

5. The method for processing user requests according to claim 4, characterized in that: Generating a processing task corresponding to the user request according to the request intent includes: Determine, based on the request intent, the subtasks that need to be performed to complete the user request; If there are multiple subtasks, the subtasks are sorted to obtain the execution order of the subtasks, and the sorted subtasks constitute the processing task corresponding to the user request.

6. The method for processing user requests according to claim 5, characterized in that: The step of sorting the subtasks to obtain the execution order of the subtasks includes: Querying the subtasks with dependency relationships among the subtasks, and obtaining a first task group and a second task group among the subtasks, wherein the first task group is composed of the subtasks with dependency relationships, and the second task group is composed of the subtasks without dependency relationships; Sorting the subtasks in the first task group according to the dependency relationship between the subtasks in the first task group to obtain an execution order of the subtasks in the first task group; Determining the priority of each subtask in the second task group; According to the priority of each subtask in the second task group, each subtask in the second task group is sorted to obtain the execution order of each subtask in the second task group.

7. The method for processing user requests according to claim 1, characterized in that: The method further comprises: If the supplementary information input by the user is not received and the device operation information of the user is detected after closing the current round of requests, determining the target intention of the user according to the device operation information; storing the user request and the target intention in association with each other; After receiving the user request after the current moment, searching for the target intent corresponding to the stored user request; The user request is processed according to the target intent.

8. A user request processing device, characterized in that: include: Request acquisition module, used to obtain user requests; A request processing module, used to process the user request and obtain a preliminary request processing result; an inquiry information generating module, configured to generate inquiry information according to the request failure reason included in the request processing result if the request processing result includes an uncompleted request, and display the inquiry information, wherein the inquiry information is used to instruct the user to input supplementary information according to the inquiry information, and the inquiry information is information required to complete the user request; An information acquisition module, used to acquire the supplementary information input by the user; The request processing module is further used to continue processing the user request according to the supplementary information to obtain the final processing result of this round of requests.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for processing user requests according to any one of claims 1 to 7 is implemented.

10. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for processing user requests according to any one of claims 1 to 7 is implemented.

Images