Human-computer interaction method and device, vehicle, terminal and medium

Abstract

The invention relates to a man-machine interaction method and device, a vehicle, a terminal and a medium. The method comprises the steps of obtaining question information input by a user; inputting the problem information into a preset big language model to enable the preset big language model to perform task planning on the problem information, determining a task type corresponding to the problem information, and generating task information corresponding to the task type; the task information comprises a task execution object and a task parameter; the task execution object has a corresponding task execution mode; in a preset large language model, executing the task information according to a task execution mode corresponding to the task execution object based on the task parameters, and obtaining a task execution result corresponding to the task information; the task execution mode comprises one or more of an interface calling mode, a task instruction generation mode and an answer generation mode; reasoning the task execution result based on a preset large language model, and outputting reply information of the question information.

Description

Technical Field

[0001] The present disclosure relates to the technical field of natural language processing, and in particular, to a human-computer interaction method, device, vehicle, terminal, and medium. Background Art

[0002] Currently, in-vehicle voice interaction systems include various interaction scenarios such as task-based conversations and knowledge Q&A. Among them, task-based conversations account for more than 70% of in-vehicle voice scenarios. Task-based conversations mean that users send control instructions to the in-vehicle system, such as "open the window", "play a song", etc. Knowledge Q&A (including casual conversations) is mainly based on retrieval. For example, "What is the capital of China?", "Who is the world's richest person?", etc.

[0003] In related technologies, for task-based conversations, the in-vehicle system receives the control instructions sent by the user and notifies the corresponding controller to execute the corresponding control commands; for knowledge Q&A, casual conversations, etc., answers are fed back to the user through retrieval. That is, when the in-vehicle system receives a user's question, it sends the question to the server, and the server retrieves the question and answer closest to the question in the database, so as to provide the answer to the user. However, the existing in-vehicle voice interaction system is limited by the capabilities of the model and cannot perform result reasoning in multiple interaction scenarios through a single model. Summary of the Invention

[0004] To solve the above technical problems, the present disclosure provides a human-computer interaction method, device, vehicle, terminal, and medium.

[0005] In a first aspect, the present disclosure provides a human-computer interaction method, including:

[0006] Obtaining question information input by a user;

[0007] Inputting the question information into a preset large language model so that the preset large language model performs task planning on the question information, determines the task type corresponding to the question information, and generates task information corresponding to the task type; the task information includes a task execution object and task parameters; the task execution object has a corresponding task execution method; the task types include: retrieval-based Q&A type, logical Q&A type, instruction control type, generation-based Q&A type, and function request type;

[0008] In the preset large language model, based on the task parameters, executing the task information according to the task execution method corresponding to the task execution object, and obtaining a task execution result corresponding to the task information; the task execution method includes one or more of an interface call method, a task instruction generation method, and an answer generation method;

[0009] Based on the preset large language model, reason about the task execution result and output a reply message to the question information.

[0010] As an optional implementation manner of the embodiment of the present disclosure, the inputting the question information into a preset large prediction model to enable the preset large language model to perform task planning on the question information, determine the task type corresponding to the question information, and generate task information corresponding to the task type includes:

[0011] Input the question information into a preset large prediction model to enable the preset large prediction model to identify the sentence type of the question information and determine the task type corresponding to the question information;

[0012] Based on a preset correspondence, determine the task execution object corresponding to the task type; the preset correspondence includes the correspondence between each task type and each task execution object;

[0013] Match corresponding task parameters for the task execution object, and use the task execution object and the task parameters as the task information corresponding to the task type.

[0014] As an optional implementation manner of the embodiment of the present disclosure, the correspondence between the task type and the task execution object includes: the task execution object corresponding to the retrieval-based question and answer type is an external application; the task execution object corresponding to the logical question and answer type is an internal application; the task execution object corresponding to the instruction control type is a vehicle-mounted controller; the task execution object corresponding to the generative question and answer type is a question and answer model; the task execution object corresponding to the function request type is a function model program.

[0015] As an optional implementation manner of the embodiment of the present disclosure, when the task type is one or more of the retrieval-based question and answer type, the logical question and answer type, and the function request type,

[0016] The determining the task execution object corresponding to the task type based on the preset correspondence includes:

[0017] Based on the preset correspondence, determine the target call program required by the task execution object; the target call program is one or more of an external application, an internal application, or a function model program;

[0018] The matching corresponding task parameters for the task execution object includes:

[0019] Based on a preset data management table, obtain the task parameters of the target call program required by the task execution object; the preset data management table includes a first data management table and a second data management table.

[0020] As an alternative implementation manner of an embodiment of the present disclosure, the types of the interface call manners include: an external program interface call manner, an internal program interface call manner, and a model program interface call manner.

[0021] Obtaining the task parameters of the target call program required by the task execution object based on a preset data management table includes:

[0022] Obtaining a first data management table; the first data management table is used to manage the relevant parameters of various external application programs included in the external program interface call manner and the relevant parameters of various internal application programs included in the internal program interface call manner, and the relevant parameters include: the names of various application programs, the interface parameters of various application programs, and the description information and status information of various application programs;

[0023] In the first data management table, matching whether the target call program required by the task execution object is an external application program or an internal application program, and obtaining the relevant parameters corresponding to the target call program.

[0024] As an alternative implementation manner of an embodiment of the present disclosure, obtaining the task parameters of the target call program required by the task execution object based on a preset data management table further includes:

[0025] Obtaining a second data management table; the second data management table is used to manage the relevant parameters of various function model programs included in the model program interface call manner, and the relevant parameters of the function model programs include: the names of various function model programs, the interface parameters of various function model programs, and the description information and status information of various function model programs;

[0026] In the second data management table, matching the target function model program required by the task execution object, and obtaining the relevant parameters corresponding to the target function model program.

[0027] As an alternative implementation manner of an embodiment of the present disclosure, after matching the corresponding task parameters for the task execution object, the method further includes:

[0028] Based on the status information in the preset data management table, determining whether the interface of the target call program is in a callable state; wherein, the preset data management table includes the first data management table and the second data management table;

[0029] If the interface of the target call program is in a callable state, outputting the interface parameters and the description information of the target call program;

[0030] If the interface of the target calling program is in an unavailable state, a prompt message is output, and the prompt message is used to prompt the user that the interface of the target calling program is unavailable.

[0031] As an optional implementation manner of the embodiments of the present disclosure, when the task type is an instruction control type, based on the task parameters, the task information is executed according to the task execution manner corresponding to the task execution object, and the task execution result corresponding to the task information is obtained, including:

[0032] Generate a task execution instruction based on the task parameters;

[0033] Send the task execution instruction to the corresponding target controller, so that the target controller executes the task execution instruction, and obtain the execution result corresponding to the task execution instruction; the execution result includes: execution success, execution failure.

[0034] In a second aspect, an embodiment of the present disclosure provides a human-computer interaction device, including:

[0035] An acquisition module, configured to acquire problem information input by a user;

[0036] A planning module, configured to input the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type; the task information includes a task execution object and task parameters; the task execution object has a corresponding task execution manner; the task types include: a retrieval-based question and answer type, a logical question and answer type, an instruction control type, a generation-based question and answer type, and a function request type;

[0037] A generation module, configured to execute the task information in the preset large language model based on the task parameters according to the task execution manner corresponding to the task execution object, and obtain the task execution result corresponding to the task information; the task execution manner includes one or more of an interface call manner, a task instruction generation manner, and an answer generation manner;

[0038] An inference module, configured to perform inference on the task execution result based on the preset large language model, and output a reply message to the problem information.

[0039] As an optional implementation manner of the embodiments of the present disclosure, the planning module includes:

[0040] An identification unit, configured to input the problem information into a preset large prediction model, so that the preset large prediction model performs statement type identification on the problem information, and determines the task type corresponding to the problem information;

[0041] A determination unit, configured to determine a task execution object corresponding to the task type based on a preset correspondence relationship; the preset correspondence relationship includes the correspondence relationship between each task type and each task execution object;

[0042] A matching unit, configured to match corresponding task parameters for the task execution object, and use the task execution object and the task parameters as task information corresponding to the task type.

[0043] As an optional implementation manner of an embodiment of the present disclosure, the correspondence relationship between the task type and the task execution object includes: the task execution object corresponding to the retrieval-based question answering type is an external application; the task execution object corresponding to the logical question answering type is an internal application; the task execution object corresponding to the instruction control type is a vehicle-mounted controller; the task execution object corresponding to the generative question answering type is a question answering model; the task execution object corresponding to the function request type is a function model program.

[0044] As an optional implementation manner of an embodiment of the present disclosure, when the task type is one or more of the retrieval-based question answering type, the logical question answering type, and the function request type,

[0045] The determination unit is specifically configured to:

[0046] Based on the preset correspondence relationship, determine a target call program required by the task execution object; the target call program is one or more of an external application, an internal application, or a function model program;

[0047] The matching unit is specifically configured to:

[0048] Based on a preset data management table, obtain task parameters of the target call program required by the task execution object; the preset data management table includes a first data management table and a second data management table.

[0049] As an optional implementation manner of an embodiment of the present disclosure, the types of the interface call methods include: an external program interface call method, an internal program interface call method, and a model program interface call method, and the matching unit is further specifically configured to:

[0050] Obtain a first data management table; the first data management table is used to manage relevant parameters of multiple external applications included in the external program interface call method and relevant parameters of multiple internal applications included in the internal program interface call method, and the relevant parameters include: names of various applications, interface parameters of various applications, and description information and status information of various applications;

[0051] In the first data management table, the target calling program required to match the task execution object is an external application or an internal application, and relevant parameters corresponding to the target calling program are obtained.

[0052] As an optional implementation manner of an embodiment of the present disclosure, the matching unit is further specifically configured to:

[0053] Obtain a second data management table; the second data management table is used to manage relevant parameters of multiple functional model programs included in the model program interface call method, and the relevant parameters of the functional model programs include: names of various functional model programs, interface parameters of various functional model programs, and description information and status information of various functional model programs;

[0054] In the second data management table, match the target functional model program required by the task execution object, and obtain relevant parameters corresponding to the target functional model program.

[0055] As an optional implementation manner of an embodiment of the present disclosure, when the task execution method is the task instruction generation method, the generation module is specifically configured to:

[0056] Generate a task execution instruction based on the task parameters;

[0057] Send the task execution instruction to a corresponding target controller, so that the target controller executes the task execution instruction, and obtain an execution result corresponding to the task execution instruction; the execution result includes: execution success, execution failure.

[0058] In a third aspect, an embodiment of the present disclosure provides a vehicle-mounted terminal, including: a memory and a processor; the memory stores a computer program, and when the processor executes the computer program, the human-computer interaction method described in the first aspect or any implementation manner of the first aspect is implemented.

[0059] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the human-computer interaction method described in any implementation manner in the first aspect is implemented.

[0060] In a fifth aspect, an embodiment of the disclosure provides a vehicle, including: the vehicle-mounted terminal described in the third aspect.

[0061] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art: obtaining the problem information input by the user, inputting the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type, where the task information includes a task execution object and task parameters, and the task execution object has a corresponding task execution method; the task types include: retrieval-based question and answer type, logical question and answer type, instruction control type, generation-based question and answer type, and function request type; in the preset large language model, based on the task parameters, execute the task information according to the task execution method corresponding to the task execution object, and obtain the task execution result corresponding to the task information, and the execution method of the task information includes: one or more of an interface call method, a task instruction generation method, and an answer generation method, and perform reasoning on the task execution result based on the preset large language model, and output the reply information of the problem information. Through the preset large language model, task planning can be performed on the problem information, the task type corresponding to the problem information can be obtained, and the task execution object and task parameters corresponding to the task type can be generated. Since different interaction scenarios correspond to different task execution objects and task parameters, and different task objects have corresponding task execution methods, for different interaction scenarios, in the preset large language model, based on the task parameters, execute the corresponding task information according to the execution method corresponding to the task execution object, obtain the task execution result corresponding to the task information, and then perform reasoning on the task execution result based on the preset large language model to obtain the reply information of the problem information, so as to realize result reasoning in multiple interaction scenarios through one model, avoiding the defect that the in-vehicle voice interaction system in the prior art is limited by the capabilities of the model and cannot realize result reasoning in multiple interaction scenarios through one model. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0064] Figure 1 is a flowchart of a human-computer interaction method provided by an embodiment of the present disclosure;

[0065] Figure 2 is a structural diagram of a human-computer interaction device provided by an embodiment of the present disclosure;

[0066] Figure 3 This is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0067] In order to more clearly understand the above objects, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0068] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0069] The relational terms such as "first" and "second" in the specification and claims of the present disclosure are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0070] In the embodiments of the present disclosure, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present disclosure should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner. In addition, in the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality of" refers to two or more.

[0071] Glossary:

[0072] LLM: (Large Language Model), an artificial intelligence model designed to understand and generate human language. They are trained on a large amount of text data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, etc.

[0073] API: (Application Programming Interface), a computing interface that defines the interaction between multiple software intermediaries, as well as the types of calls or requests that can be made, how to make calls or requests, the data formats to be used, the conventions to be followed, etc.

[0074] NLG: (Natural Language Generation), a part of natural language processing that generates natural language from machine representation systems such as knowledge bases or logical forms.

[0075] In view of the above problems, an embodiment of the present disclosure provides a human-computer interaction method, which is applied to a preset large language model. Among them, the preset large language model includes various capabilities such as dialogue generation, language understanding, knowledge Q&A, and logical reasoning. The preset large language model can serve as a large model controller to call external tools, continuously expanding the ability coverage of the large model. At the same time, the preset large language model comes with a memory network, and users can choose to let the in-vehicle system remember personalized preferences and habits based on historical conversations, understand the user's recent status, and provide high-quality services for users. For example, in the embodiment of the present disclosure, the preset large language model acts as a controller. For different scenarios, the preset large language model can autonomously decide whether to directly generate answers, call external APIs (such as encyclopedias, news, and other dedicated model interfaces, etc.), generate end-side instructions, etc. According to the results of external APIs and the execution results of end-side instructions, the preset large language model completes the final result reasoning and outputs the reply information of the question information, so as to realize the unified scheduling of in-vehicle scenarios based on the large model.

[0076] In some embodiments, as Figure 1 shown, a human-computer interaction method is provided, including the following steps S11-S14:

[0077] S11. Obtain the question information input by the user.

[0078] Among them, the question information input by the user can be different types of conversations in different scenarios. In addition, the question information input by the user can include the input information of the user's current round of conversation and / or the input information of historical conversations.

[0079] Specifically, the question information input by the user can adopt various input methods such as voice and text. When the user uses voice input, the in-vehicle system recognizes the input voice information to obtain the voice recognition text as the question information input by the user. When the user uses text input, the question information input by the user can be directly input into the in-vehicle system.

[0080] Exemplarily, the question information input by the user can be chatting, asking questions, or issuing control instructions to the in-vehicle system, etc. For example, when the question information input by the user is chatting, it can be "Please help me draw a picture of a child running on the grass", "Please draw the child's clothes red", etc. When the question information input by the user is asking questions, it can be "Where is the capital of China?", "How many people are there?", "Is there a concert this month?", and "Where will the concert be held specifically?", etc. When the user's question information is to issue control instructions to the in-vehicle system, it can be "Please close the window", "Turn on the air conditioner", and "Start refrigerating", etc.

[0081] S12. Input the problem information into a preset large language model so that the preset large language model performs task planning on the problem information and generates task information corresponding to the problem information.

[0082] Among them, the task information includes a task execution object and task parameters; the task execution object has a corresponding task execution method.

[0083] In some embodiments, the above step S12 (inputting the problem information into a preset large language model so that the preset large language model performs task planning on the problem information and generates task information corresponding to the problem information) can be implemented in the following manner:

[0084] a. Input the problem information into a preset large prediction model so that the preset large prediction model performs sentence type recognition on the problem information and determines the task type corresponding to the problem information.

[0085] Among them, the task types include: retrieval-based question and answer type, logical question and answer type, instruction control type, generative question and answer type, and function request type.

[0086] Exemplarily, the retrieval-based question and answer type can be but is not limited to: "What are Li Bai's works?", "What are the masterpieces of Zhou xx?", etc. The retrieval-based question and answer type can be applied to question and answer scenarios such as encyclopedia questions, entertainment news questions, stock price trend questions, and mathematical calculation inquiries. The logical question and answer type can be but is not limited to: "What is 25 multiplied by 18?", "What is 100 to the 5th power?", etc. The instruction control type can be but is not limited to: "Please close the window", "Turn on the air conditioner", etc. The instruction control type can be for instruction control scenarios such as issuing vehicle control instructions and querying vehicle status instructions. The generative question and answer type can be but is not limited to: "Please help me write a letter", "How many glove boxes does the Ideal L9 have?", "Who is the founder of Ideal Automobile?", etc. The function request type can be but is not limited to: "Help me draw a picture of the Ideal L9 running on the highway", "Please help me draw a picture of a child running on the grass", etc.

[0087] Optionally, the method of sentence type recognition can be but is not limited to performing keyword recognition on the problem information, obtaining multiple keywords corresponding to the problem information; and based on the multiple keywords, matching a corresponding task type for the problem information.

[0088] Specifically, the in-vehicle system receives the problem information input by the user and sends the problem information to the preset large language model in the server. In response to the user's request, the preset large language model extracts the keywords of the problem information and determines the corresponding task type according to the keywords of the problem information.

[0089] Exemplarily, when the question information input by the user is "What are the works of Li X?", "What are the representative works of Zhou XX?", etc., the extracted keywords are "Li X", "works"; "Zhou XX", "representative works". Since obtaining the answers to such questions depends on external applications (such as encyclopedia APIs, search APIs, news APIs, etc.), the task type matched for such question information is the retrieval-based Q&A type. When the question information input by the user is "What is 25 multiplied by 18?", "What is 100 to the 5th power?", etc., the extracted keywords are "25", "multiplied by", "18"; "100", "5th power". Since obtaining the answers to such questions depends on internal applications (such as calculators, etc.), the task type matched for such question information is the logical Q&A type. When the question information input by the user is "Please close the window", "Turn on the air conditioner", etc., the extracted keywords are "close", "window"; "turn on", "air conditioner". Since such questions involve sending control instructions to the in-vehicle system terminal, the task type matched for such question information is the instruction control type. When the question information input by the user is "How many glove boxes does the Li L9 have?", "Who is the founder of Li Auto?", etc., the extracted keywords are "Li L9", "glove box"; "Li Auto", "founder". Since the answers to such questions belong to the enterprise's internal information and the pre-set large language model can directly output the results, the task type matched for such question information is the generative Q&A type. When the question information input by the user is "Draw a picture of the Li L9 running on the highway for me", "Please draw a picture of a child running on the grass for me", etc., the extracted keywords are "draw", "Li L9", "highway", "run", "picture"; "draw", "child", "grass", "run", "picture". Since obtaining the answers to such questions depends on applications with professional functions, the task type matched for such question information is the function request type.

[0090] b. Based on the pre-set corresponding relationship, determine the task execution object corresponding to the task type.

[0091] Among them, the pre-set corresponding relationship includes the corresponding relationship between each task type and each task execution object.

[0092] In some embodiments, the corresponding relationship between each task type and each task execution object includes: the task execution object corresponding to the retrieval-based Q&A type is an external application; the task execution object corresponding to the logical Q&A type is an internal application; the task execution object corresponding to the instruction control type is an in-vehicle controller; the task execution object corresponding to the generative Q&A type is a Q&A model; the task execution object corresponding to the function request type is a function model program.

[0093] Among them, the external application can be, but is not limited to, applications related to encyclopedias, searches, information, stocks, etc. The internal application can be, but is not limited to, a calculator application, a local voice playback application, a local video playback application, etc. The vehicle-mounted controller can be, but is not limited to, a window controller, an air conditioner controller, a door controller, etc. The question-and-answer model can be a preset large language model, and the preset large language model includes various capabilities such as dialogue generation, language understanding, knowledge Q&A, and logical reasoning. The function model program can be a professional function model program such as a painting master application program.

[0094] Optionally, the above step b (determining the task execution object corresponding to the task type based on the preset correspondence) can be implemented in the following manner:

[0095] Based on the preset correspondence, determine the target call program required by the task execution object.

[0096] Among them, the target call program is one or more of an external application, an internal application, or a function model program.

[0097] c. Match corresponding task parameters for the task execution object, and use the task execution object and the task parameters as the task information corresponding to the question information.

[0098] Among them, the task execution parameters can include content information to be generated, API parameters, function model parameters, etc. For example, when the task execution object is an external application or an internal application, the task execution parameters can be: relevant parameters of the external API, relevant parameters of the internal API; when the task execution object is a function model program; the task execution parameters can be function model parameters; when the task execution object is a vehicle-mounted controller, the task execution parameters can include specific execution units and execution actions; when the task execution object is a question-and-answer model, the task execution parameters can include specific content information to be generated.

[0099] The above step c (matching corresponding task parameters for the task execution object) can be implemented in the following manner:

[0100] Based on the preset data management table, obtain the task parameters of the target call program required by the task execution object.

[0101] Among them, the preset data management table includes a first data management table and a second data management table.

[0102] In some embodiments, (based on the preset data management table, obtaining the task parameters of the target call program required by the task execution object) has the following implementation manner:

[0103] Obtain the first data management table.

[0104] Among them, the first data management table is used to manage the relevant parameters of various external application programs included in the external program interface call method and the relevant parameters of various internal application programs included in the internal program interface call method. The relevant parameters include: the names of various application programs, the interface parameters of various application programs, and the description information and status information of various application programs.

[0105] In the first data management table, the target call program required to match the task execution object is an external application program or an internal application program, and the relevant parameters corresponding to the target call program are obtained.

[0106] Specifically, obtain the first data management table. In the first data management table, match whether the target call program required by the task execution object is an external application program or an internal application program, and obtain the relevant parameters corresponding to the target call program. Further, match according to the name corresponding to the target call program, and judge whether the status information of the target call program is in a callable state and whether the target call program is sent to the in-vehicle system terminal for execution.

[0107] Exemplarily, as shown in Table 1, Table 1 is the first data management table. The first data management table is used to uniformly manage the external application program interface and the internal application program interface, mainly including the registration of various application program interface services, address management, names, input parameters, etc. For example, the API description information of "QASearch" is an encyclopedia knowledge engine, and this application program is not sent to the in-vehicle system terminal for execution, and this application program interface can be called.

[0108] Table 1

[0109]

[0110]

[0111] Exemplarily, when the question information input by the user is "What are the representative works of Zhou xx?", the task type is determined to be the retrieval-based question-and-answer type. Based on the preset corresponding relationship, the task execution object is determined to be an external application. The relevant parameters of the external application interface are obtained through the relevant parameters of multiple applications stored in the first data management table, such as the search API, and the API name, input parameters, type description information, etc. corresponding to the search API. Based on the API name, input parameters, type description information, etc. stored in the first data management table, the search API is called to obtain the interface call result of the search API, such as "Jasmine, Blue and White Porcelain, Nunchucks, Simple Love, Rice Fragrance, Dongfeng Po, Tornado, Going North All the Way, Sunny Day, Secret That Can't Be Told, etc.". When the text information input by the user is "What is 25 multiplied by 18?", the task type is determined to be the logical question-and-answer type. Based on the preset corresponding relationship, the task execution object is determined to be an internal application. The relevant parameters of the internal application interface are obtained through the relevant parameters of multiple applications stored in the first data management table, such as the calculation API, and the API name, input parameters, type description information, etc. corresponding to the calculation API. Based on the API name, input parameters, type description information, etc. stored in the first data management table, the calculation API is called to obtain the interface call result of the calculation API, such as "450".

[0112] In some embodiments, (obtaining the task parameters of the target calling program required by the task execution object based on a preset data management table) has the following implementation manners:

[0113] Obtain a second data management table.

[0114] Among them, the second data management table is used to manage the relevant parameters of multiple functional model programs included in the model program interface call method. The relevant parameters of the functional model program include: the names of various functional model programs, the interface parameters of various functional model programs, and the description information and status information of various functional model programs;

[0115] In the second data management table, match the target functional model program required by the task execution object, and obtain the relevant parameters corresponding to the target functional model program.

[0116] Specifically, obtain the second data management table. In the second data management table, match the target functional model program required by the task execution object, and obtain the relevant parameters corresponding to the target functional model program.

[0117] Exemplarily, as shown in Table 2, Table 2 is the second data management table. The second data management table is used to uniformly manage the interfaces of external professional artificial intelligence models, mainly including the description information, status information, application program interface call information, etc. of available artificial intelligence models.

[0118] Table 2

[0119] model id model name metadata model description Whether to start 00001 text-to-image meta-info Generate an image according to the text Yes

[0120] Exemplarily, when the problem information input by the user is "Please help me draw a picture of a child running on the grass", the task execution method generated by the preset large language model is the model interface call method at this time. Since the preset large language model itself does not have a painting function, an external model interface needs to be called to complete the painting. The extracted keywords are "draw", "child", "grassland", "running", "picture". Further determine the target function model interface corresponding to this execution method, such as an image generation AI model interface. The function of this AI model is to generate images according to text, as well as the interface parameters corresponding to this AI model interface; based on the interface parameters stored in the second data management table, call this AI model interface to obtain the corresponding target call result, that is, a drawn picture of a child running on the grass.

[0121] In addition, it should be noted that the first data management table and the second data management table need to be synchronized to the preset large language model in real time.

[0122] In some embodiments, when the first data management table and / or the second data management table is updated, the relevant parameters in the first data management table and / or the second data management table are updated.

[0123] Further, after updating the relevant parameters in the first data management table and / or the second data management table, the above step S13 (matching corresponding task parameters for the task execution object) can be implemented in the following manner:

[0124] Based on the updated first data management table and / or second data management table, obtain the task parameters of the target call program required by the task execution object.

[0125] Specifically, when certain information in the external application program, internal application program, and function model program is newly added, deleted, or modified in the first data management table and / or the second data management table, the relevant parameters in the first data management table and / or the second data management table are correspondingly newly added, deleted, or modified. Based on the updated first data management table and / or second data management table, obtain the task parameters of the target call program required by the task execution object.

[0126] In some embodiments, after matching corresponding task parameters for the task execution object, the following steps can also be executed:

[0127] Based on the status information in the preset data management table, determine whether the interface of the target call program is in a callable state.

[0128] Among them, the preset data management table includes a first data management table and a second data management table.

[0129] If the interface of the target calling program is in a callable state, output the interface parameters of the target calling program and the description information.

[0130] If the interface of the target calling program is in a non-callable state, output a prompt message.

[0131] Among them, the prompt message is used to prompt the user that the interface of the target calling program is unavailable.

[0132] Specifically, after matching the corresponding task parameters for the task execution object, based on the status information in the preset data management table, determine whether the interface of the target calling program is in a callable state. If the interface of the target calling program is in a callable state, output the interface parameters of the target calling program and the description information, so that the next preset large model can perform an API call according to the interface parameters of the target calling program and the description information in accordance with the task execution method corresponding to the task execution object, thereby obtaining the task execution result corresponding to the task information. If the interface of the target calling program is in a non-callable state, output a prompt message to prompt the user that the interface of the target calling program is unavailable, so that the user can know that the corresponding answer cannot be obtained for the currently input problem information.

[0133] S13. Execute the task information according to the task execution method corresponding to the task execution object based on the task parameters, and obtain the task execution result corresponding to the task information.

[0134] Among them, the task execution method includes one or more of: an interface call method, a task instruction generation method, and an answer generation method. The types of the interface call method include: an external program interface call method, an internal program interface call method, and a model program interface call method.

[0135] Exemplarily, the external application program interface can be an encyclopedia API, a search API, a news API, a stock API, etc. The internal application program interface can be a calculator application program interface, a local voice playback application program interface, a local video playback application interface, etc. The model interface can be, for example, a painting master application program interface. For example, calling the painting master application program interface can generate an image according to the text.

[0136] S14. Reason about the task execution result and output the reply information of the problem information.

[0137] Among them, the task execution result includes: the target answer corresponding to the interface call method, the target instruction execution result corresponding to the task instruction generation method, and the target answer corresponding to the answer generation method.

[0138] Specifically, after obtaining the task execution result corresponding to the task execution method, reason about the task execution result and output the reply information of the question information.

[0139] Exemplarily, when the question information input by the user is "What are the representative works of Zhou xx?", the obtained task result is "Jasmine Flower, Blue and White Porcelain, Nunchucks, Simple Love, Rice Fragrance, Dongfeng Po, Tornado, Going North All the Way, Sunny Day, Secret That Can't Be Told, etc.", and the reply information output after the preset large language model reasons about the task result is: "The representative works of Zhou xx are Jasmine Flower, Blue and White Porcelain, Nunchucks, Simple Love, Rice Fragrance, Dongfeng Po, Tornado, Going North All the Way, Sunny Day, Secret That Can't Be Told, etc.".

[0140] Exemplarily, when the question information input by the user is "Please close the window", the obtained task result is "Execution successful", and the reply information output after the preset large language model reasons about the task result is: "The window has been opened for you.".

[0141] Exemplarily, when the question information input by the user is "Please help me draw a picture of a child running on the grass", the obtained task result is "Drawing completed, please refer", and the generated reply information is: "The picture of a child running on the grass has been drawn for you. Please refer to the display interface.".

[0142] The human-computer interaction method provided by the present disclosure obtains the problem information input by the user, inputs the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type, where the task information includes a task execution object and task parameters, and the task execution object has a corresponding task execution method; the task types include: retrieval-based question and answer type, logical question and answer type, instruction control type, generative question and answer type, and function request type; in the preset large language model, based on the task parameters, the task information is executed according to the task execution method corresponding to the task execution object, and the task execution result corresponding to the task information is obtained. The execution methods of the task information include one or more of: interface call method, task instruction generation method, and answer generation method. Based on the preset large language model, the task execution result is inferred, and the reply information of the problem information is output. Through the preset large language model, task planning can be performed on the problem information, the task type corresponding to the problem information can be obtained, and the task execution object and task parameters corresponding to the task type can be generated. Since different interaction scenarios correspond to different task execution objects and task parameters, and different task objects have corresponding task execution methods, for different interaction scenarios, in the preset large language model, based on the task parameters, the corresponding task information is executed according to the execution method corresponding to the task execution object, the task execution result corresponding to the task information is obtained, and then the preset large language model infers the task execution result to obtain the reply information of the problem information, so as to realize result inference in multiple interaction scenarios through one model, avoiding the defect that the in-vehicle voice interaction system in the prior art is limited by the capabilities of the model and cannot realize result inference in multiple interaction scenarios through one model.

[0143] In some embodiments, when the task execution method is the task instruction generation method, the above step S12 (based on the task parameters, executing the task information according to the task execution method corresponding to the task execution object, and obtaining the task execution result corresponding to the task information) can be implemented in the following manner:

[0144] Generate a task execution instruction based on the task parameters;

[0145] Send the task execution instruction to the corresponding target controller, so that the target controller executes the task execution instruction and obtains the execution result corresponding to the task execution instruction.

[0146] Wherein, the execution result includes: execution success, execution failure.

[0147] Specifically, when the task execution mode is the task instruction generation mode, a task execution instruction is generated according to the task parameters; the task execution instruction is sent to the target controller corresponding to the vehicle-mounted system. After the target controller executes the target instruction, the corresponding target instruction execution result is returned. The execution result may be successful execution or failed execution.

[0148] Exemplarily, when the problem information input by the user is "Please close the window", the corresponding task parameters are "close" and "window". Then, a task execution instruction, that is, the "close the window" instruction, is generated by combining the task parameters and the long short-term memory network. This "close the window" instruction is sent to the vehicle-mounted system, and the control unit of the vehicle-mounted system executes this "close the window" instruction and returns the execution result to the preset large language model. When the control unit of the vehicle-mounted system successfully executes this "close the window" instruction, a successful execution result is returned; when the control unit of the vehicle-mounted system fails to execute this "close the window" instruction, a failed execution result is returned.

[0149] Through the way of feedback of the execution result, the user can clearly know whether the instruction issued by himself / herself is successfully executed, improving the user's human-computer interaction experience in the vehicle.

[0150] In some embodiments, as shown in Figure 2 a human-computer interaction device 200 is provided, including:

[0151] an acquisition module 210, configured to acquire the problem information input by the user;

[0152] a planning module 220, configured to input the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type; the task information includes a task execution object and task parameters; the task execution object has a corresponding task execution mode; the task types include: retrieval-based question and answer type, logical question and answer type, instruction control type, generation-based question and answer type, and function request type;

[0153] a generation module 230, configured to, in the preset large language model, execute the task information based on the task parameters according to the task execution mode corresponding to the task execution object, and obtain the task execution result corresponding to the task information; the task execution mode includes one or more of an interface call mode, a task instruction generation mode, and an answer generation mode;

[0154] a reasoning module 240, configured to perform reasoning on the task execution result based on the preset large language model and output a reply message to the problem information.

[0155] As an optional implementation manner of an embodiment of the present disclosure, the planning module includes:

[0156] An identification unit, configured to input the problem information into a preset large prediction model, so that the preset large prediction model performs sentence type identification on the problem information and determines the task type corresponding to the problem information;

[0157] A determination unit, configured to determine a task execution object corresponding to the task type based on a preset correspondence; the preset correspondence includes the correspondence between each task type and each task execution object;

[0158] A matching unit, configured to match corresponding task parameters for the task execution object, and use the task execution object and the task parameters as the task information corresponding to the task type.

[0159] As an optional implementation manner of an embodiment of the present disclosure, the correspondence between the task type and the task execution object includes: the task execution object corresponding to the retrieval-based question and answer type is an external application; the task execution object corresponding to the logical question and answer type is an internal application; the task execution object corresponding to the instruction control type is a vehicle machine controller; the task execution object corresponding to the generative question and answer type is a question and answer model; the task execution object corresponding to the function request type is a function model program.

[0160] As an optional implementation manner of an embodiment of the present disclosure, when the task type is one or more of the retrieval-based question and answer type, the logical question and answer type, and the function request type,

[0161] The determination unit is specifically configured to:

[0162] Based on the preset correspondence, determine the target call program required by the task execution object; the target call program is one or more of an external application, an internal application, or a function model program;

[0163] The matching unit is specifically configured to:

[0164] Based on a preset data management table, obtain the task parameters of the target call program required by the task execution object; the preset data management table includes a first data management table and a second data management table.

[0165] As an optional implementation manner of an embodiment of the present disclosure, the types of the interface call manner include: an external program interface call manner, an internal program interface call manner, and a model program interface call manner. The matching unit is further specifically configured to:

[0166] Obtain a first data management table; the first data management table is used to manage the relevant parameters of various external application programs included in the external program interface call method and the relevant parameters of various internal application programs included in the internal program interface call method, and the relevant parameters include: the names of various application programs, the interface parameters of various application programs, as well as the description information and status information of various application programs;

[0167] In the first data management table, match the target call program required by the task execution object as an external application program or an internal application program, and obtain the relevant parameters corresponding to the target call program.

[0168] As an optional implementation manner of the embodiment of the present disclosure, the matching unit is further specifically configured to:

[0169] Obtain a second data management table; the second data management table is used to manage the relevant parameters of various function model programs included in the model program interface call method, and the relevant parameters of the function model programs include: the names of various function model programs, the interface parameters of various function model programs, as well as the description information and status information of various function model programs;

[0170] In the second data management table, match the target function model program required by the task execution object, and obtain the relevant parameters corresponding to the target function model program.

[0171] As an optional implementation manner of the embodiment of the present disclosure, when the task execution method is the task instruction generation method, the generation module is specifically configured to:

[0172] Generate a task execution instruction based on the task parameters;

[0173] Send the task execution instruction to the corresponding target controller, so that the target controller executes the task execution instruction, and obtain the execution result corresponding to the task execution instruction; the execution result includes: execution success, execution failure.

[0174] The human-computer interaction device provided by the present disclosure obtains the problem information input by the user, inputs the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type. Among them, the task information includes a task execution object and task parameters, and the task execution object has a corresponding task execution method; the task types include: retrieval-based question-and-answer type, logical question-and-answer type, instruction control type, generative question-and-answer type, and function request type; in the preset large language model, based on the task parameters, the task information is executed according to the task execution method corresponding to the task execution object, and the task execution result corresponding to the task information is obtained. The execution method of the task information includes one or more of an interface call method, a task instruction generation method, and an answer generation method. Based on the preset large language model, the task execution result is inferred, and the reply information of the problem information is output. Through the preset large language model, task planning can be performed on the problem information, the task type corresponding to the problem information can be obtained, and the task execution object and task parameters corresponding to the task type can be generated. Since different interaction scenarios correspond to different task execution objects and task parameters, and different task objects have corresponding task execution methods, for different interaction scenarios, in the preset large language model, based on the task parameters, the corresponding task information is executed according to the execution method corresponding to the task execution object, the task execution result corresponding to the task information is obtained, and then the task execution result is inferred by the preset large language model to obtain the reply information of the problem information, so as to realize the result inference in multiple interaction scenarios through one model, avoiding the defect that the in-vehicle voice interaction system in the prior art is limited by the capabilities of the model and cannot realize the result inference in multiple interaction scenarios through one model.

[0175] For the specific limitations of the human-computer interaction device, reference can be made to the limitations on the human-computer interaction method in the above text, which will not be elaborated here. Each module in the above human-computer interaction device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of the processor of the electronic device in the form of hardware, or stored in the processor of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0176] The embodiment of the present disclosure also provides an electronic device, Figure 3 which is a schematic structural diagram of the electronic device provided by the embodiment of the present disclosure. As Figure 3As shown in the figure, the electronic device provided in this embodiment includes: a memory 31 and a processor 32. The memory 31 is used to store computer programs. The processor 32 is used to execute the steps performed in any of the embodiments of the fault identification method of the image acquisition device provided in the above method embodiment when calling the computer program. The electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. When the computer program is executed by the processor, it realizes a fault identification method of an image acquisition device. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0177] Those skilled in the art can understand that Figure 3 the structure shown in the figure is only a block diagram of some structures related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0178] In some embodiments, the human-computer interaction device provided by the present disclosure can be implemented in the form of a computer, and the computer program can run on an electronic device as shown in Figure 3 the figure. Each program module constituting the human-computer interaction device of the electronic device can be stored in the memory of the electronic device. The computer program constituted by each program module enables the processor to execute the steps in the fault identification method of the image acquisition device of the electronic device in each embodiment of the present disclosure described in this specification.

[0179] The embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, it realizes the fault identification method of the image acquisition device provided in the above method embodiment.

[0180] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can adopt the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0181] The processor can be a Central Processing Unit (CPU), or can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0182] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0183] Computer-readable media includes permanent and non-permanent, removable and non-removable storage media. The storage media can implement information storage by any method or technology, and the information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, Phase Change Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other memory technologies, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0184] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0185] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A human-computer interaction method, characterized in that, The method includes: Obtaining the problem information input by the user; Inputting the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type; the task information includes a task execution object and task parameters; the task execution object has a corresponding task execution method; the task types include: retrieval-based question and answer type, logical question and answer type, instruction control type, generative question and answer type, and function request type; In the preset large language model, based on the task parameters, execute the task information according to the task execution method corresponding to the task execution object, and obtain the task execution result corresponding to the task information; the task execution method includes one or more of: interface call method, task instruction generation method, and answer generation method; Based on the preset large language model, reason about the task execution result and output the reply information of the problem information.

2. The method according to claim 1, characterized in that The inputting the problem information into a preset large prediction model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type includes: Inputting the problem information into a preset large prediction model, so that the preset large language model performs sentence type recognition on the problem information and determines the task type corresponding to the problem information; Based on a preset correspondence relationship, determine the task execution object corresponding to the task type; the preset correspondence relationship includes the correspondence relationship between each task type and each task execution object; Match corresponding task parameters for the task execution object, and use the task execution object and the task parameters as the task information corresponding to the task type.

3. The method according to claim 2, wherein The correspondence relationship between the task type and the task execution object includes: the task execution object corresponding to the retrieval-based question and answer type is an external application; the task execution object corresponding to the logical question and answer type is an internal application; the task execution object corresponding to the instruction control type is a vehicle machine controller; the task execution object corresponding to the generative question and answer type is a question and answer model; the task execution object corresponding to the function request type is a function model program.

4. The method according to claim 3, wherein When the task type is one or more of the retrieval-based question and answer type, logical question and answer type, and function request type, The determining the task execution object corresponding to the task type based on the preset correspondence relationship includes: Based on the preset correspondence relationship, determine the target call program required by the task execution object; the target call program is one or more of an external application, an internal application, or a function model program; The matching corresponding task parameters for the task execution object includes: Based on a preset data management table, obtain the task parameters of the target call program required by the task execution object; the preset data management table includes a first data management table and a second data management table.

5. The method according to claim 4, wherein The types of the interface call methods include: external program interface call method, internal program interface call method, and model program interface call method. Based on the preset data management table, obtaining the task parameters of the target call program required by the task execution object includes: Obtaining a first data management table; the first data management table is used to manage the relevant parameters of various external application programs included in the external program interface call method and the relevant parameters of various internal application programs included in the internal program interface call method, and the relevant parameters include: the names of various application programs, the interface parameters of various application programs, and the description information and status information of various application programs; In the first data management table, matching whether the target call program required by the task execution object is an external application program or an internal application program, and obtaining the relevant parameters corresponding to the target call program.

6. The method according to claim 5, characterized in that, Based on the preset data management table, obtaining the task parameters of the target call program required by the task execution object further includes: Obtaining a second data management table; the second data management table is used to manage the relevant parameters of various functional model programs included in the model program interface call method, and the relevant parameters of the functional model programs include: the names of various functional model programs, the interface parameters of various functional model programs, and the description information and status information of various functional model programs; In the second data management table, matching the target functional model program required by the task execution object, and obtaining the relevant parameters corresponding to the target functional model program.

7. The method according to claim 4, characterized in that After matching the corresponding task parameters for the task execution object, the method further includes: Based on the status information in the preset data management table, determining whether the interface of the target call program is in a callable state; wherein, the preset data management table includes the first data management table and the second data management table; If the interface of the target call program is in a callable state, outputting the interface parameters and description information of the target call program; If the interface of the target call program is in a non-callable state, outputting a prompt message, where the prompt message is used to prompt the user that the interface of the target call program is unavailable.

8. The method according to claim 3, characterized in that When the task type is an instruction control type, based on the task parameters, executing the task information according to the task execution method corresponding to the task execution object, and obtaining the task execution result corresponding to the task information includes: Generating a task execution instruction based on the task parameters; Sending the task execution instruction to the corresponding target controller, so that the target controller executes the task execution instruction, and obtaining the execution result corresponding to the task execution instruction; the execution result includes: execution success, execution failure.

9. A human-computer interaction device, characterized in that, The human-computer interaction device includes: An acquisition module, configured to acquire problem information input by a user; A planning module, configured to input the problem information into a preset large language model, so that the preset large language model performs task planning on the problem information, determines the task type corresponding to the problem information, and generates task information corresponding to the task type; the task information includes a task execution object and task parameters; the task execution object has a corresponding task execution method; the task types include: retrieval-based question-and-answer type, logical question-and-answer type, instruction control type, generation-based question-and-answer type, and function request type; A generation module, configured to execute the task information in the preset large language model based on the task parameters according to the task execution method corresponding to the task execution object, and obtain a task execution result corresponding to the task information; the task execution method includes one or more of: interface call method, task instruction generation method, and answer generation method; An inference module, configured to perform inference on the task execution result based on the preset large language model and output a reply message for the problem information.

10. A vehicle, characterized in that, It includes the human-computer interaction device according to claim 9.

11. An in-vehicle terminal, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the human-computer interaction method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and when the computer program is executed by a processor, it implements the human-computer interaction method according to any one of claims 1 to 8.

Images