Agent control method, electronic device, vehicle, storage medium and program product

Abstract

An agent control method, an electronic device, a vehicle, a storage medium and a program product. The agent control method comprises: determining environment information corresponding to a vehicle-mounted agent; and on the basis of the environment information, controlling the vehicle-mounted agent to output chat information.

Description

Intelligent agent control methods, electronic devices, vehicles, storage media and program products

[0001] Cross-references to related applications

[0002] This disclosure claims priority to Chinese Patent Application No. 202411003613.0, filed on July 25, 2024, entitled "Intelligent Agent Control Method, Electronic Device, Vehicle, Storage Medium and Program Product", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of vehicles, and more particularly to an intelligent agent control method, electronic device, vehicle, storage medium, and program product. Background Technology

[0004] Intelligent agents are widely used in daily life, such as smart speakers, smart home systems, intelligent agent chat groups, or smartphone assistants. However, intelligent agents in these technologies are generally activated by the user, which suffers from the problem of a single activation method. Summary of the Invention

[0005] The purpose of this disclosure is to provide an intelligent agent control method, electronic device, vehicle, storage medium, and program product to solve the aforementioned technical problems.

[0006] To achieve the above objectives, the first aspect of this disclosure provides an intelligent agent control method, the intelligent agent control method comprising:

[0007] Determine the environmental information corresponding to the in-vehicle intelligent agent;

[0008] Based on the environmental information, the vehicle-mounted intelligent agent is controlled to output chat information.

[0009] A second aspect of this disclosure provides an electronic device, the electronic device comprising:

[0010] processor;

[0011] Memory used to store processor-executable instructions;

[0012] The processor is configured to perform the steps of the method described in any one of the first aspects.

[0013] A third aspect of this disclosure provides a vehicle including a processor and a memory for storing processor-executable instructions, wherein the processor is configured to perform the steps of the method described in any of the first aspects.

[0014] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0015] The fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0016] The above technical solution can determine the environmental information corresponding to the in-vehicle intelligent agent and control the in-vehicle intelligent agent to output chat information based on the environmental information. Therefore, this disclosure can automatically control the in-vehicle intelligent agent to output chat information based on the environmental information; that is, this disclosure can automatically start the in-vehicle intelligent agent and output chat information based on the environmental information. Compared with related technologies where the user starts the intelligent agent and outputs chat information, this disclosure can automatically start the in-vehicle intelligent agent based on the environmental information, enriching the intelligent agent startup methods while improving the user experience.

[0017] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0019] Figure 1 is a flowchart illustrating an intelligent agent control method according to an exemplary embodiment of the present disclosure;

[0020] Figure 2 is a flowchart illustrating a target vehicle-mounted intelligent agent outputting chat information according to an exemplary embodiment of the present disclosure;

[0021] Figure 3 is a flowchart illustrating another intelligent agent control method according to an exemplary embodiment of the present disclosure;

[0022] Figure 4 is a structural block diagram of an intelligent agent control device according to an exemplary embodiment of the present disclosure;

[0023] Figure 5 is a functional block diagram of a vehicle according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0024] The specific embodiments of this disclosure will now be described in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0025] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0026] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0027] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0028] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0029] As mentioned in the background section, with the development of intelligent technology, intelligent agents are widely used in daily life, such as smart speakers, smart home systems, smartphone assistants, and intelligent agent chat groups. Among these, an intelligent agent chat group refers to a chat group composed of intelligent agents, each of which is an autonomous software program capable of simulating human dialogue and communication. In an intelligent agent chat group, each agent plays a virtual role and possesses independent identity, characteristics, and abilities. They interact in real time through text, voice, or images, simulating the form of real conversations.

[0030] However, intelligent agents in related technologies are generally activated by the user and cannot be activated automatically according to the needs of the scenario. For example, they cannot activate automatically according to changes in the environment, thus resulting in a lack of intelligence and a single activation method.

[0031] For example, invention patent CN109407925A discloses an interaction method, device, and related equipment based on a chatbot. In this patent, the chatbot cannot automatically activate based on changes in the environment.

[0032] In view of this, the present disclosure provides an intelligent agent control method, electronic device, vehicle, storage medium, and program product to solve the above-mentioned technical problems.

[0033] The embodiments of this disclosure will be further explained below with reference to the accompanying drawings.

[0034] Figure 1 is a flowchart illustrating an intelligent agent control method according to an exemplary embodiment of the present disclosure. Referring to Figure 1, the method may include the following steps:

[0035] S101: Determine the environmental information corresponding to the vehicle-mounted intelligent agent.

[0036] The vehicle-mounted intelligent agent may include one or more. When there is one vehicle-mounted intelligent agent, it may correspond to multiple control devices of the vehicle; when there are multiple vehicle-mounted intelligent agents, one vehicle-mounted intelligent agent may correspond to one or multiple control devices of the vehicle, and this disclosure does not impose any restrictions on this.

[0037] For example, when there are multiple in-vehicle intelligent agents, and each in-vehicle intelligent agent corresponds to a control device of the vehicle, the in-vehicle intelligent agents may include window in-vehicle intelligent agents, seat in-vehicle intelligent agents, and / or air conditioning in-vehicle intelligent agents. Accordingly, the window in-vehicle intelligent agent may correspond to the vehicle's window control device, the seat in-vehicle intelligent agent may correspond to the vehicle's seat control device, and the air conditioning in-vehicle intelligent agent may correspond to the vehicle's air conditioning control device. When there are multiple in-vehicle intelligent agents, and each in-vehicle intelligent agent may correspond to multiple control devices of the vehicle, the in-vehicle intelligent agents may include temperature regulation in-vehicle intelligent agents and ventilation regulation intelligent agents. Accordingly, the temperature regulation in-vehicle intelligent agent may correspond to the vehicle's air conditioning control device and window control device, and the ventilation regulation intelligent agent may correspond to the vehicle's air conditioning control device, window control device, and sunroof control device.

[0038] S102: Based on environmental information, control the onboard intelligent agent to output chat information.

[0039] The above technical solution can determine the environmental information corresponding to the in-vehicle intelligent agent and control the in-vehicle intelligent agent to output chat information based on the environmental information. Therefore, this disclosure can automatically control the in-vehicle intelligent agent to output chat information based on the environmental information; that is, this disclosure can automatically start the in-vehicle intelligent agent and output chat information based on the environmental information. Compared with related technologies where the user starts the intelligent agent and outputs chat information, this disclosure can automatically start the in-vehicle intelligent agent based on the environmental information, enriching the intelligent agent startup methods while improving the user experience.

[0040] Determining the environmental information corresponding to the in-vehicle intelligent agent, among possible methods, may include:

[0041] The environmental information corresponding to the vehicle-mounted intelligent agent is determined based on at least one of the vehicle's internal environmental information, vehicle's external environmental information, and network information.

[0042] The vehicle interior environment information may include in-vehicle temperature, in-vehicle humidity, and / or in-vehicle noise level, while the vehicle exterior environment may include outside temperature, outside humidity, and / or visibility. Network information may include network information of a preset category and / or network information with a network popularity value greater than a preset network popularity value. The preset category of network information may be entertainment-related, sports-related, or technology-related, and can be set according to actual circumstances; this embodiment does not impose any limitations on this. Accordingly, determining the environmental information corresponding to the in-vehicle intelligent agent may involve determining at least one of the following: in-vehicle temperature, in-vehicle humidity, in-vehicle noise level, outside temperature, outside humidity, visibility, network information of a preset category, and network information with a popularity value greater than a preset popularity value. For example, outside temperature may be determined as the environmental information corresponding to the in-vehicle intelligent agent, both outside and inside temperatures may be determined as the environmental information corresponding to the in-vehicle intelligent agent, or network information related to the vehicle may be determined as the environmental information corresponding to the in-vehicle intelligent agent.

[0043] In possible ways, determining the environmental information corresponding to the in-vehicle intelligent agent based on at least one of vehicle internal environment information, vehicle external environment information, and network information may include:

[0044] The vehicle interior environment is determined based on in-vehicle temperature and / or in-vehicle humidity information; the vehicle exterior environment is determined based on weather information; and the environmental information corresponding to the in-vehicle intelligent agent is determined based on at least one of the vehicle interior environment information, vehicle exterior environment information, and network information of a preset category.

[0045] For example, the vehicle interior temperature information can be obtained through an onboard temperature sensor, and the vehicle interior temperature information obtained by the onboard temperature sensor can be determined as the environmental information corresponding to the onboard intelligent agent.

[0046] For example, network information from a media platform can be obtained through the vehicle's in-vehicle infotainment system, and when a preset category of network information appears in the network information, the preset category of network information is identified as the environmental information corresponding to the in-vehicle intelligent agent.

[0047] For example, the pre-defined category of network information could be entertainment-related network information that users are interested in. Thus, when network information from a media platform is obtained through the in-vehicle infotainment system in a vehicle, keywords can be extracted from the obtained network information using keyword extraction technology. Based on these keywords, it can be determined whether the obtained network information is entertainment-related or contains entertainment-related network information. If the obtained network information is entertainment-related or contains entertainment-related network information, then the corresponding network information can be identified as the environmental information corresponding to the in-vehicle intelligent agent.

[0048] For example, weather information can be obtained through the vehicle's in-vehicle infotainment system and identified as the environmental information corresponding to the in-vehicle intelligent agent.

[0049] In possible ways, controlling the in-vehicle intelligent agent to output chat information based on environmental information may include:

[0050] Based on changes in environmental information, determine descriptive text to describe these changes; based on the descriptive text, control the in-vehicle intelligent agent to output chat information.

[0051] In this embodiment, the descriptive text used to describe changes in environmental information can be determined by detecting changes in environmental information in real time or periodically. Once a change in environmental information is detected, the descriptive text used to describe the change is determined. Alternatively, the changes in environmental information can be detected in real time or periodically, and when a change occurs and the change conforms to a preset change condition, the descriptive text used to describe the change is determined. This embodiment does not impose any limitations on this method.

[0052] For example, a temperature sensor collects the vehicle interior temperature in real time. When it detects that the interior temperature rises by 3°C within 30 minutes, a descriptive text can be determined based on this temperature change. For instance, the descriptive text could be: "The interior temperature rose by 3°C within 30 minutes."

[0053] For example, network information from a media platform can be acquired in real time. When network information of a preset category appears on a preset media platform, such as network information related to vehicles, the descriptive text can be determined based on the changes in the network information on the preset media platform. For example, the descriptive text can be determined as: "Network information appears on the media platform: XXXX". Here, "XXXX" can be the title of the network information of the preset category that appeared on the media platform, or it can be a summary obtained by extracting the content of the network information of the preset category that appeared on the media platform through keyword extraction technology, or it can be other than that. This embodiment of the disclosure does not impose any restrictions on this.

[0054] In possible ways, determining descriptive text to describe the changes in environmental information based on those changes may include:

[0055] Based on the changes in environmental information, an initial descriptive text is determined to describe these changes. The initial descriptive text is then optimized using a text optimization model to obtain a new descriptive text that describes the changes in environmental information. The text optimization model is used to output the optimized descriptive text based on the input initial descriptive text.

[0056] The text optimization model can be an existing model in related technologies, or an improved model of an existing model. This disclosure does not impose any limitations on this. For example, the text optimization model can be a large language model, a natural language understanding model, or a convolutional neural network.

[0057] For example, when the temperature sensor detects that the interior temperature rises by 3°C within 30 minutes, an initial descriptive text can be generated based on this temperature change: "The interior temperature rose by 3°C within 30 minutes." Then, the initial descriptive text "The interior temperature rose by 3°C within 30 minutes" can be input into a large language model, which will then output an optimized descriptive text, such as: "During the half-hour journey, the interior temperature rose gently by 3°C."

[0058] The above technical solution optimizes the initial description text, reducing grammatical, spelling, and logical errors. This allows the in-vehicle intelligent agent to more quickly and accurately understand the semantics of the description text when subsequently controlling it to output chat messages.

[0059] In possible ways, the in-vehicle intelligent agent may include multiple agents, and accordingly, controlling the in-vehicle intelligent agent to output chat information based on the description text may include:

[0060] The descriptive text is used as the initial target prompt text, and the following process is executed repeatedly: the target vehicle intelligent agent related to the target prompt text is determined from multiple vehicle intelligent agents; according to the target prompt text, the target vehicle intelligent agent is controlled to output chat information; at least the chat information output by the target vehicle intelligent agent is used as the new target prompt text, until the preset condition for stopping the output of chat information is met.

[0061] The conditions for stopping the output of chat messages can be set according to actual conditions, and this embodiment of the disclosure does not impose any restrictions on this. For example, the conditions for stopping the output of chat messages may be that the duration of a single chat reaches a preset chat duration, the user is identified as having no intention to continue chatting through semantic recognition or intent recognition, and / or the output chat messages have resolved the user's problem, etc.

[0062] It should be understood that a single chat message provides limited information. Therefore, using only a single output from the in-vehicle agent as the target prompt text and determining the target in-vehicle agent based on the target prompt text results in a lack of continuity between the chat messages output by the target in-vehicle agent and its previous outputs. Therefore, one possible approach is to record the chat messages output by the in-vehicle agent during its startup phase and use the recorded chat history as new target prompt text. This allows the target prompt text to provide richer contextual information, maintaining the coherence of the dialogue.

[0063] In possible ways, identifying the target in-vehicle agent related to the target prompt text from multiple in-vehicle agents may include:

[0064] The target prompt text is input into the control model to obtain the speaking order information of the vehicle intelligent agent in response to the target prompt text. The control model is used to output the speaking order information based on the input target prompt text. The vehicle intelligent agent that speaks first in the speaking order information is identified as the target vehicle intelligent agent related to the target prompt text.

[0065] The control model can be an existing model in related technologies, or an improved model of an existing model. This disclosure does not impose any limitations on this. For example, the control model can be a large language model.

[0066] In order to obtain the speaking order information of the vehicle intelligent agent in response to the target prompt text based on the target prompt text and the control model, training data can also be constructed to fine-tune or train the control model.

[0067] For example, for each in-vehicle intelligent agent, the user manual document can be split into multiple document blocks. Then, document blocks containing the core functions and name of the in-vehicle intelligent agent can be extracted from these blocks, resulting in a sample library containing multiple core functions and names of in-vehicle intelligent agents. Next, sample prompt texts are constructed, and the control model is trained based on these prompt texts, labels indicating the speaking order, and the sample library until a preset number of iterations is reached. Thus, when the target prompt text is input into the control model, the model can infer the speaking order information of the in-vehicle intelligent agent in response to the target prompt text based on the information in the sample library.

[0068] In possible ways, controlling the target in-vehicle intelligent agent to output chat information based on the target prompt text may include:

[0069] Based on the target prompt text, a target document block is determined from a preset knowledge base. The preset knowledge base is used to store at least the document blocks of the target vehicle-mounted intelligent agent. The document blocks are obtained by splitting the user manual document of the target vehicle-mounted intelligent agent. A new prompt text is determined based on the target document block and the target prompt text. The new prompt text is input into the target vehicle-mounted intelligent agent, and the target vehicle-mounted intelligent agent is controlled to output chat information.

[0070] The target document block can be a document block that is semantically similar to the target prompt text, or a document block in which the keywords in the target document block match the keywords in the target prompt text, or other types of documents. This disclosure does not impose any restrictions on these types of documents.

[0071] In this process, determining the new prompt text based on the target document block and the target prompt text can be achieved by pre-setting a prompt text template, and then filling the prompt text template with the target document block and the target prompt text after obtaining the target document block.

[0072] For example, the prompt text template could be set as: Please respond to the target prompt text "XXXX" based on the content in the target document block "XXX".

[0073] The method of splitting the user manual document can be set according to the actual situation, and this embodiment of the disclosure does not impose any restrictions on it. For example, the first-level headings in the user manual document can be used as split points to split the user manual document into multiple document blocks. Alternatively, each functional module in the user manual document can be used as a split point to split the user manual document into multiple document blocks.

[0074] In some possible approaches, the pre-defined knowledge base also stores document block vectors corresponding to document blocks. Accordingly, determining the target document block from the pre-defined knowledge base based on the target prompt text may include:

[0075] Determine the text vector of the target prompt text; based on the text vector, determine the target document block vector from the preset knowledge base whose similarity to the text vector is greater than a preset similarity threshold; determine the document block corresponding to the target document block vector as the target document block.

[0076] The text vector of the target prompt text and / or the target document block vector can be obtained by inputting the target prompt text and / or the target document block vector into a text embedding model, a bag of words (BoW) model, or a word embedding model (Word2Vec).

[0077] For example, as shown in Figure 2, the user manual document for each in-vehicle intelligent agent can be pre-segmented into multiple document blocks. Each document block is then input into a text embedding model to obtain a document block vector. Finally, all document block vectors and document blocks are stored in a database to obtain a preset knowledge base for each in-vehicle intelligent agent. When transmitting target prompt text to the target in-vehicle intelligent agent, the target prompt text is first input into the text embedding model to obtain its text vector. Then, vector retrieval is performed based on the text vector and the target in-vehicle intelligent agent's preset knowledge base to obtain target document block vectors from the target in-vehicle intelligent agent's preset knowledge base that have a similarity greater than a preset similarity threshold to the text vector. The target document block is then determined based on the target document block vector. Finally, a new prompt text is generated based on the target document block and the target prompt text, and this new prompt text is input into the target in-vehicle intelligent agent to generate chat information.

[0078] The similarity between text vectors and document block vectors can be calculated based on Euclidean distance, cosine similarity, or Manhattan distance, depending on the specific circumstances. This disclosure does not impose any restrictions on this.

[0079] In possible ways, controlling the in-vehicle intelligent agent to output chat information based on environmental information may include:

[0080] Based on environmental information, chat messages are generated; when the chat messages pass information verification, the in-vehicle intelligent agent is controlled to output chat messages.

[0081] Information verification can be used to check for the presence of preset sensitive words in chat messages, the logical coherence of chat messages, and the correctness of chat message syntax, etc., depending on the actual situation. This embodiment of the disclosure does not impose any limitations on this. For example, after generating chat messages, semantic verification can be performed on the chat messages. When the semantic verification result indicates that the chat messages do not contain hateful, biased, or excessive information, and the chat messages are determined to have passed the information verification, the in-vehicle intelligent agent is controlled to output the chat messages.

[0082] The above technical solution allows for the verification of chat messages, and when the chat messages pass verification, the in-vehicle intelligent agent can be controlled to output the chat messages externally. This reduces the spread of erroneous information and improves the user experience.

[0083] In possible ways, when the chat information passes information verification, controlling the in-vehicle intelligent agent to output the chat information may include:

[0084] When the chat message does not contain preset sensitive words and the chat message matches the user manual of the in-vehicle intelligent agent that outputs the chat message, control the in-vehicle intelligent agent to output the chat message.

[0085] The preset sensitive words can be set according to the actual situation, and this embodiment does not impose any restrictions on them.

[0086] Among them, matching the chat information with the user manual document of the vehicle-mounted intelligent agent that outputs the chat information means that the chat information output by the vehicle-mounted intelligent agent must correspond to the existing functions in the user manual document.

[0087] For example, the air conditioning vehicle intelligent agent has the function of controlling the air conditioning, but not the function of controlling devices such as windows or windshield wipers. Therefore, if the chat message output by the air conditioning vehicle intelligent agent is "Do you need me to adjust the air conditioning to 25℃?", it is considered that the chat message output by the air conditioning vehicle intelligent agent matches the user manual document. If the chat message output by the air conditioning vehicle intelligent agent is "Do you need me to open the window?", it is considered that the chat message output by the air conditioning vehicle intelligent agent does not match the user manual document.

[0088] In possible ways, when the chat information passes information verification, controlling the in-vehicle intelligent agent to output the chat information may include:

[0089] Based on chat information and information verification model, the system determines whether the chat information passes the information verification. The information verification model is used to output the verification result of the chat information based on the input chat information. After the verification result indicates that the chat information has passed the information verification, the system controls the in-vehicle intelligent agent to output the chat information.

[0090] The information verification model can be an existing model in related technologies, or it can be an improved model of an existing model. This disclosure does not impose any limitations on this. For example, the information verification model can be a syntax verification model, a semantic verification model, a logic verification model, or a large language model, etc.

[0091] Among the possible approaches are:

[0092] If the chat message fails the information verification, the vehicle-mounted intelligent agent that controls the output of the chat message will re-output the chat message.

[0093] For example, the air conditioning vehicle intelligent agent has the function of controlling the air conditioning, but not the function of controlling devices such as windows or windshield wipers. Therefore, if the chat message output by the air conditioning vehicle intelligent agent is "Do you need me to open the window for you?", it is determined that the chat message output by the air conditioning vehicle intelligent agent does not match the user manual document of the air conditioning vehicle intelligent agent. In this case, the target prompt text can be transmitted to the air conditioning vehicle intelligent agent again to control the air conditioning vehicle intelligent agent to re-output the chat message.

[0094] In possible ways, controlling the in-vehicle intelligent agent to output chat information based on environmental information may include:

[0095] Based on environmental information, generate chat messages; control the in-vehicle intelligent agent to output chat messages in the form of audio and / or text.

[0096] When the in-vehicle intelligent agent outputs chat messages in audio format, the generated chat messages can be sent to the vehicle's speakers for output. When the in-vehicle intelligent agent outputs chat messages in text format, the generated chat messages can be sent to the central control screen for display.

[0097] Among possible methods, controlling the in-vehicle intelligent agent to output chat information in the form of audio may include:

[0098] At least based on the chat information and tone determination model, the tone information of the chat information is determined, wherein the tone determination model is used at least to output the tone information of the chat information based on the input chat information; based on the tone information, the in-vehicle intelligent agent is controlled to output the chat information in the form of audio.

[0099] The tone determination model can be an existing model in related technologies, or an improved model of an existing model; this disclosure does not impose any limitations on this. For example, the tone determination model can be a sentiment analysis model or a large language model.

[0100] For example, after generating chat messages, the chat messages can be input into a sentiment analysis model to obtain sentiment tendencies, such as humorous, mature and stable, or shy and naive, and the sentiment tendencies can be determined as the tone information of the chat messages.

[0101] It should be understood that this is only an illustrative illustration and does not constitute a limitation on the solution. In possible ways, the tone information of chat messages can also be randomly assigned by the tone determination model.

[0102] The above technical solution allows for the determination of the tone of a chat message before its output. Based on this tone, the in-vehicle intelligent agent can be controlled to output the message in audio format. This enables different chat messages to have different tones, increasing the enjoyment of the conversation and further enhancing the user experience.

[0103] Among the possible approaches, agent control methods may also include:

[0104] During the process of controlling the vehicle-mounted intelligent agent to output chat information based on environmental information, if feedback information from the user is received, the vehicle-mounted intelligent agent is controlled to output chat information in response to the feedback information, or, based on the feedback information, the vehicle-mounted intelligent agent is controlled to perform a target action.

[0105] For example, upon receiving user feedback, intent recognition can be performed on the feedback. If the intent recognition result indicates that the user prefers to chat, the in-vehicle intelligent agent can be controlled to output chat information in response to the feedback. If the intent recognition result indicates that the user prefers the in-vehicle intelligent agent to perform a target action, the in-vehicle intelligent agent can be controlled to perform the target action. Alternatively, upon receiving user feedback, it can be determined whether there is a preset in-vehicle control command in the feedback. If a preset in-vehicle control command exists in the feedback, the in-vehicle intelligent agent can be controlled to perform the target action corresponding to the in-vehicle control command. If no preset in-vehicle control command exists in the feedback, the in-vehicle intelligent agent can be controlled to output chat information in response to the feedback.

[0106] In possible ways, controlling the in-vehicle intelligent agent to output chat messages in response to feedback information may include:

[0107] If feedback information is received after the vehicle-mounted intelligent agent outputs chat information, and the chat information includes preset vehicle control commands, then when the feedback information indicates that the vehicle control commands will not be executed, the vehicle-mounted intelligent agent is controlled to output chat information in response to the feedback information; or, if feedback information is received after the vehicle-mounted intelligent agent outputs chat information, and the chat information does not include preset vehicle control commands, the vehicle-mounted intelligent agent is controlled to output chat information in response to the feedback information.

[0108] The vehicle control commands can be determined according to the actual situation, and this disclosure does not impose any restrictions on them. For example, vehicle control commands may include opening the windows, turning on the air conditioner, or adjusting the air conditioner temperature.

[0109] For example, after the air conditioning vehicle's intelligent agent outputs "Do you need me to adjust the air conditioning temperature to 25℃ for you?", and receives the user's feedback "No", the vehicle's intelligent agent can be controlled to output chat messages in response to the feedback. For example, the window intelligent agent can be controlled to output "Do you need me to open the window for you?".

[0110] For example, after the car window's in-vehicle AI agent outputs "The air quality has been really good this past week," and receives feedback from the user such as "Yes, it even makes me feel happier," the in-vehicle AI agent can be controlled to output chat messages in response to the feedback. For instance, the multimedia AI agent can be controlled to output "It would be even better to play a cheerful song at this time."

[0111] It is worth noting that if user feedback is received while the vehicle-mounted intelligent agent is outputting chat information, the vehicle-mounted intelligent agent can be controlled to output chat information in response to the feedback after the chat information has been output. Alternatively, the output of chat information can be interrupted and the vehicle-mounted intelligent agent can be controlled to output chat information in response to the feedback. This embodiment does not impose any restrictions on this.

[0112] In possible ways, controlling the onboard intelligent agent to perform the target action based on feedback information may include:

[0113] If feedback information is received after the vehicle-mounted intelligent agent outputs chat information, and the chat information includes preset vehicle control commands, then when the feedback information indicates that the vehicle control commands should be executed, the vehicle-mounted intelligent agent will be controlled to execute the actions corresponding to the vehicle control commands.

[0114] For example, after the air conditioning vehicle intelligent agent outputs "Do you need me to adjust the air conditioning temperature to 25℃?", and receives the user's feedback "Yes", it can control the air conditioning vehicle intelligent agent to adjust the air conditioning temperature to 25℃.

[0115] It should be understood that this is merely illustrative and does not constitute a limitation on the paired solutions. In some possible approaches, to more accurately execute the target action in response to feedback information, after receiving the feedback information, it can be determined whether the feedback information contains a preset vehicle control command. If the feedback information contains a vehicle control command, the target action corresponding to the vehicle control command in the feedback information is executed.

[0116] For example, after the air conditioning vehicle's intelligent agent outputs "The temperature has risen from 27°C to 30°C," and receives the user's feedback "Yes, it's so hot, please open the car window for me," the vehicle's intelligent agent can then control the window to open.

[0117] For example, after the in-vehicle air conditioning intelligent agent outputs "The temperature has risen to 32℃, do you need to turn on the air conditioning?", and receives the user's feedback message "Please open the car window for me", it can control the in-vehicle window intelligent agent to open the car window.

[0118] It is worth noting that if user feedback is received while the vehicle-mounted intelligent agent is outputting chat information, the vehicle-mounted intelligent agent can be controlled to perform a target action in response to the feedback after the chat information is output. Alternatively, the output of the chat information can be interrupted and the vehicle-mounted intelligent agent can be controlled to perform a target action in response to the feedback. This embodiment does not impose any restrictions on this.

[0119] The above technical solution can control the in-vehicle intelligent agent to perform target actions. Thus, during driving, users can control the in-vehicle intelligent agent to operate in-vehicle equipment via voice, which improves driving safety and further enhances the user experience.

[0120] To facilitate understanding of the agent control method provided in this disclosure, one implementation of the agent control method provided in this disclosure is described below.

[0121] For example, as shown in Figure 3, when the vehicle-mounted intelligent agent is not started, there are two ways to start the intelligent agent: Method 1: The vehicle-mounted intelligent agent starts automatically based on environmental information; Method 2: The user actively starts the vehicle-mounted intelligent agent.

[0122] Regarding Method 1, after sensing changes in environmental information, the in-vehicle intelligent agent generates initial descriptive text to describe these changes. This initial descriptive text is then transmitted to a text optimization model for optimization, resulting in an optimized descriptive text. Next, the descriptive text is transmitted to a control model, which determines the target in-vehicle intelligent agent that needs to output chat information based on this descriptive text and transmits the descriptive text to that target agent. Then, the target in-vehicle intelligent agent generates chat information based on the descriptive text and transmits it to an information verification model to verify compliance. If the chat information is non-compliant, the target agent regenerates the chat information based on the descriptive text. If the chat information is compliant, it is transmitted to a tone determination model to obtain tone information for the chat information, and then the chat information is output based on this tone information.

[0123] After outputting chat messages, in order to control the in-vehicle intelligent agent to execute accurate actions (outputting chat messages or controlling in-vehicle devices) based on user feedback, the system can also determine whether the chat messages contain preset in-vehicle control commands. If the chat messages contain in-vehicle control commands, the system can determine whether the user agrees to execute the in-vehicle control command within a preset time period. If the user agrees to execute the in-vehicle control command, the control command is converted into control command text and input into the target in-vehicle control command to control the target in-vehicle control agent to execute the action corresponding to the control command text. If the user does not agree to execute the in-vehicle control command, the control and management model redetermines the target in-vehicle intelligent agent to speak based on the user's feedback and / or historical chat message records (chat messages output during the current activation of the in-vehicle intelligent agent). If the chat messages do not contain in-vehicle control commands, the system can determine whether the preset conditions for stopping the output of chat messages are met. If the preset conditions for stopping the output of chat messages are not met, the control and management model redetermines the target in-vehicle intelligent agent to speak based on the output chat messages and / or historical chat message records (chat messages output during the current activation of the in-vehicle intelligent agent). If the preset conditions for stopping the output of chat information are met, the in-vehicle intelligent agent will be controlled to end the chat.

[0124] The difference between Method 2 and Method 1 is that the initial description text is not obtained based on changes in environmental information, but rather by converting the user's audio signal into a text signal. Therefore, the control process for Method 2 can be referenced from that for Method 1, and will not be elaborated here.

[0125] Based on the same concept, this disclosure also provides an intelligent agent control device, as shown in FIG4. The intelligent agent control device 400 may include:

[0126] The determination module 401 is used to determine the environmental information corresponding to the vehicle-mounted intelligent agent;

[0127] The first control module 402 is used to control the on-board intelligent agent to output chat information based on environmental information.

[0128] The aforementioned intelligent agent control device 400 can determine the environmental information corresponding to the in-vehicle intelligent agent and control the in-vehicle intelligent agent to output chat information based on the environmental information. Therefore, the in-vehicle intelligent agent can be automatically controlled to output chat information based on environmental information; that is, this disclosure can automatically start the in-vehicle intelligent agent and output chat information based on environmental information. Compared to related technologies where the user starts the intelligent agent and outputs chat information, this disclosure can automatically start the in-vehicle intelligent agent based on environmental information, enriching the intelligent agent startup methods while improving the user experience.

[0129] In some possible ways, the determining module 401 may include:

[0130] The first determining submodule is used to determine the environmental information corresponding to the vehicle-mounted intelligent agent based on at least one of the vehicle internal environment information, vehicle external environment information, and network information.

[0131] In some possible ways, the first determining submodule may include:

[0132] The first determining unit is used to determine the vehicle interior environment based on the vehicle interior temperature information and / or vehicle interior humidity information;

[0133] The second determining unit is used to determine the vehicle's external environment based on weather information;

[0134] The third determining unit is used to determine the environmental information corresponding to the vehicle-mounted intelligent agent based on at least one of the vehicle internal environment information, vehicle external environment information, and network information of a preset category.

[0135] In one possible manner, the first control module 402 may include:

[0136] The second determination submodule is used to determine the descriptive text used to describe the changes in environmental information based on the changes in environmental information.

[0137] The first control submodule is used to control the in-vehicle intelligent agent to output chat information based on the description text.

[0138] In some possible ways, the second determining submodule may include:

[0139] The fourth determining unit is used to determine the initial descriptive text used to describe the changes in environmental information based on the changes in environmental information.

[0140] The optimization unit is used to optimize the initial description text based on the text optimization model to obtain a description text that describes the changes in environmental information. The text optimization model is used to output the optimized description text based on the input initial description text.

[0141] In one possible manner, the vehicle-mounted intelligent agent includes multiple agents. The first control submodule can be used to take the descriptive text as the initial target prompt text and repeatedly execute the following process: determine the target vehicle-mounted intelligent agent related to the target prompt text from the multiple vehicle-mounted intelligent agents, control the target vehicle-mounted intelligent agent to output chat information according to the target prompt text, and at least use the chat information output by the target vehicle-mounted intelligent agent as the new target prompt text, until the preset condition for stopping the output of chat information is met.

[0142] In some possible ways, the first control submodule may include:

[0143] The input unit is used to input the target prompt text into the control model to obtain the speaking order information of the vehicle intelligent agent in response to the target prompt text. The control model is used to output the speaking order information based on the input target prompt text.

[0144] The fifth determining unit is used to determine the first vehicle-mounted intelligent agent to speak in the speaking order information as the target vehicle-mounted intelligent agent related to the target prompt text.

[0145] In some possible ways, the first control submodule may include:

[0146] The sixth determining unit is used to determine the target document block from the preset knowledge base based on the target prompt text. The preset knowledge base is used to store at least the document block of the target vehicle intelligent agent. The document block is obtained by splitting the user manual document of the target vehicle intelligent agent.

[0147] The seventh determining unit is used to determine new prompt text based on the target document block and the target prompt text;

[0148] The first control unit is used to input new prompt text into the target vehicle-mounted intelligent agent and control the target vehicle-mounted intelligent agent to output chat information.

[0149] In some possible ways, the pre-defined knowledge base also stores document block vectors corresponding to document blocks, and accordingly, the sixth determining unit may include:

[0150] The first determining subunit is used to determine the text vector of the target prompt text;

[0151] The second determining subunit is used to determine the target document block vector with a similarity greater than a preset similarity threshold from the preset knowledge base based on the text vector;

[0152] The third determining subunit is used to determine the document block corresponding to the target document block vector as the target document block.

[0153] In one possible manner, the first control module 402 may include:

[0154] The first generation submodule is used to generate chat information based on environmental information;

[0155] The second control submodule is used to control the in-vehicle intelligent agent to output chat information when the chat information passes the information verification.

[0156] In some possible ways, the second control submodule may include:

[0157] The second control unit is used to control the vehicle-mounted intelligent agent to output chat information when the chat information does not contain preset sensitive words and the chat information matches the user manual document of the vehicle-mounted intelligent agent that outputs the chat information.

[0158] In some possible ways, the second control submodule may include:

[0159] The eighth determining unit is used to determine whether the chat information passes the information verification based on the chat information and the information verification model. The information verification model is used to output the verification result of the chat information based on the input chat information.

[0160] The third control unit is used to control the in-vehicle intelligent agent to output chat information after the verification result indicates that the chat information has passed the information verification.

[0161] In some possible configurations, the second control submodule may also include:

[0162] The fourth control unit is used to control the onboard intelligent agent that outputs the chat information to re-output the chat information when the chat information fails the information verification.

[0163] In one possible manner, the first control module 402 may include:

[0164] The first generation submodule is used to generate chat information based on environmental information;

[0165] The third control submodule is used to control the in-vehicle intelligent agent to output chat information in the form of audio and / or text.

[0166] In some possible ways, the third control submodule may include:

[0167] The ninth determining unit is used to determine the tone information of the chat information based at least on the chat information and the tone determining model, wherein the tone determining model is used at least to output the tone information of the chat information based on the input chat information.

[0168] The fifth control unit is used to control the in-vehicle intelligent agent to output chat information in the form of audio based on tone information.

[0169] In some possible embodiments, the agent control device 400 may also include:

[0170] The second control module is used to control the vehicle-mounted intelligent agent to output chat information in the process of controlling the output of chat information based on environmental information. If user feedback information is received, the module controls the vehicle-mounted intelligent agent to output chat information in response to the feedback information, or controls the vehicle-mounted intelligent agent to perform a target action based on the feedback information.

[0171] In some possible configurations, the second control module may include:

[0172] The fourth control submodule is used to control the vehicle intelligent agent to output chat information in response to the feedback information if it receives feedback information after the vehicle intelligent agent outputs chat information, and the chat information includes preset vehicle control commands; or, if the feedback information indicates that the vehicle control commands should not be executed, the module is configured to do so.

[0173] The fifth control submodule is used to control the vehicle intelligent agent to output chat information in response to the feedback information if feedback information is received after the vehicle intelligent agent outputs chat information and the chat information does not include preset vehicle control commands.

[0174] In some possible configurations, the second control module may also include:

[0175] The sixth control submodule is used to control the vehicle intelligent agent to execute the action corresponding to the vehicle control command if feedback information is received after the vehicle intelligent agent outputs chat information and the chat information includes preset vehicle control commands, when the feedback information indicates that the vehicle control command should be executed.

[0176] In possible configurations, the in-vehicle intelligent agent corresponds to the vehicle's control equipment. The in-vehicle intelligent agent includes a window in-vehicle intelligent agent, a seat in-vehicle intelligent agent, and / or an air conditioning in-vehicle intelligent agent. The window in-vehicle intelligent agent corresponds to the vehicle's window control equipment, the seat in-vehicle intelligent agent corresponds to the vehicle's seat control equipment, and the air conditioning in-vehicle intelligent agent corresponds to the vehicle's air conditioning control equipment.

[0177] Regarding the intelligent agent control device 400 in the above embodiments, the specific methods by which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0178] Based on the same concept, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0179] processor;

[0180] Memory used to store processor-executable instructions;

[0181] The processor is configured to execute the steps of any of the above-mentioned intelligent agent control methods.

[0182] Based on the same concept, embodiments of this disclosure also provide a vehicle, the vehicle including a processor and a memory for storing processor-executable instructions, wherein the processor is configured to perform the steps of any of the above-described intelligent agent control methods.

[0183] Based on the same concept, embodiments of this disclosure also provide a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described intelligent agent control methods.

[0184] Based on the same concept, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described intelligent agent control methods.

[0185] Please refer to Figure 5, which is a functional block diagram of a vehicle according to an exemplary embodiment. The vehicle 500 may include various subsystems, such as an infotainment system 510, a perception system 520, a decision control system 530, a drive system 540, and a computing platform 550. The vehicle 500 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 500 can be interconnected via wired or wireless means.

[0186] In some embodiments, the infotainment system 510 may include a communication system, an entertainment system, and a navigation system, etc.

[0187] The perception system 520 may include several sensors for sensing information about the environment surrounding the vehicle 500. For example, the perception system 520 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0188] The decision control system 530 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0189] The drive system 540 may include components that provide powered motion to the vehicle 500. In one embodiment, the drive system 540 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0190] Some or all of the functions of vehicle 500 are controlled by computing platform 550. Computing platform 550 may include at least one processor 551 and memory 552, and processor 551 may execute instructions 553 stored in memory 552.

[0191] Processor 551 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.

[0192] The memory 552 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0193] In addition to instruction 553, memory 552 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 552 can be used by computing platform 550.

[0194] In this embodiment of the disclosure, processor 551 may execute instruction 553 to complete all or part of the steps of the above-described intelligent agent control method.

[0195] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0196] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

Claims

1. An agent control method, characterized by, The intelligent agent control method comprises: determining environment information corresponding to the vehicle-mounted intelligent agent; controlling the vehicle-mounted intelligent agent to output chat information according to the environment information.

2. The agent control method of claim 1, wherein, The determination of the environment information corresponding to the vehicle-mounted intelligent agent comprises: determining the environment information corresponding to the vehicle-mounted intelligent agent according to at least one of vehicle internal environment information, vehicle external environment information and network information.

3. The agent control method of claim 2, wherein, The determination of the environment information corresponding to the vehicle-mounted intelligent agent according to at least one of the vehicle internal environment information, the vehicle external environment information and the network information comprises: determining a vehicle internal environment according to vehicle internal temperature information and / or vehicle internal humidity information; determining a vehicle external environment according to weather information; determining the environment information corresponding to the vehicle-mounted intelligent agent according to at least one of the vehicle internal environment information, the vehicle external environment information and network information of a preset category.

4. The agent control method according to any one of claims 1-3, wherein, The control of the vehicle-mounted intelligent agent to output chat information according to the environment information comprises: determining a description text for describing a change in the environment information according to the change in the environment information; controlling the vehicle-mounted intelligent agent to output chat information according to the description text.

5. The agent control method of claim 4, wherein, The determination of the description text for describing the change in the environment information according to the change in the environment information comprises: determining an initial description text for describing the change in the environment information according to the change in the environment information; optimizing the initial description text based on a text optimization model to obtain the description text for describing the change in the environment information, wherein the text optimization model is configured to output an optimized description text according to an input initial description text.

6. The agent control method according to claim 4 or 5, characterized by, The vehicle-mounted intelligent agent comprises a plurality of agents, and the control of the vehicle-mounted intelligent agent to output chat information according to the description text comprises: taking the description text as an initial target prompt text and cyclically executing the following process: determining a target vehicle-mounted intelligent agent related to the target prompt text from the plurality of vehicle-mounted intelligent agents, controlling the target vehicle-mounted intelligent agent to output chat information according to the target prompt text, and taking at least the chat information output by the target vehicle-mounted intelligent agent as a new target prompt text until a preset condition for stopping the output of chat information is met.

7. The agent control method of claim 6, wherein, The determination of the target vehicle-mounted intelligent agent related to the target prompt text from the plurality of vehicle-mounted intelligent agents comprises: inputting the target prompt text into a management and control model to obtain speaking order information of the vehicle-mounted intelligent agents for the target prompt text, wherein the management and control model is configured to output the speaking order information according to the input target prompt text; determining a vehicle-mounted intelligent agent speaking first in the speaking order information as the target vehicle-mounted intelligent agent related to the target prompt text.

8. The agent control method according to claim 6 or 7, characterized by, The control of the target vehicle-mounted intelligent agent to output chat information according to the target prompt text comprises: determining a target document block from a preset knowledge base according to the target prompt text, wherein the preset knowledge base is configured to at least store document blocks of the target vehicle-mounted intelligent agent, and the document blocks are obtained by splitting a user manual document of the target vehicle-mounted intelligent agent; determine a new prompt text based on the target document block and the target prompt text; input the new prompt text into the target in-vehicle intelligent agent, and control the target in-vehicle intelligent agent to output chat information.

9. The agent control method according to claim 8, wherein, The preset knowledge base also stores a document block vector corresponding to the document block. The determining the target document block from the preset knowledge base according to the target prompt text comprises: determining a text vector of the target prompt text; determining a target document block vector from the preset knowledge base based on the text vector, wherein the target document block vector has a similarity greater than a preset similarity threshold with the text vector; determining a document block corresponding to the target document block vector as the target document block.

10. The agent control method according to any one of claims 1-9, wherein, The controlling the in-vehicle intelligent agent to output chat information according to the environmental information comprises: generating chat information according to the environmental information; controlling the in-vehicle intelligent agent to output the chat information when the chat information passes information verification.

11. The agent control method of claim 10, wherein, The controlling the in-vehicle intelligent agent to output chat information when the chat information passes information verification comprises: controlling the in-vehicle intelligent agent to output the chat information when the chat information does not include a preset sensitive word and the chat information matches a user manual document of the in-vehicle intelligent agent outputting the chat information.

12. The agent control method according to claim 10 or 11, characterized by, The controlling the in-vehicle intelligent agent to output chat information when the chat information passes information verification comprises: determining, based on the chat information and an information verification model, a verification result of whether the chat information passes information verification, wherein the information verification model is configured to output the verification result of the chat information according to input of the chat information; controlling the in-vehicle intelligent agent to output the chat information when the verification result indicates that the chat information passes information verification.

13. The agent control method according to any one of claims 10-12, wherein, The method further comprises: controlling the in-vehicle intelligent agent outputting chat information again when the chat information does not pass information verification.

14. The agent control method according to any one of claims 1-13, wherein, The controlling the in-vehicle intelligent agent to output chat information according to the environmental information comprises: generating chat information according to the environmental information; controlling the in-vehicle intelligent agent to output the chat information in the form of audio and / or text.

15. The agent control method of claim 14, wherein, The controlling the in-vehicle intelligent agent to output the chat information in the form of audio comprises: determining, based on at least the chat information and a tone determination model, tone information of the chat information, wherein the tone determination model is configured to output the tone information of the chat information according to input of the chat information; controlling the in-vehicle intelligent agent to output the chat information in the form of audio based on the tone information.

16. The agent control method according to any one of claims 1-15, wherein, The method further comprises: controlling the in-vehicle intelligent agent to output chat information in response to feedback information of a user, or controlling the in-vehicle intelligent agent to perform a target action according to the feedback information, during the process of controlling the in-vehicle intelligent agent to output chat information according to the environmental information.

17. The agent control method of claim 16, wherein, The controlling the in-vehicle intelligent agent to output chat information in response to the feedback information comprises: If the feedback information is received after the vehicle-mounted intelligent agent outputs the chat information, and the chat information comprises a preset vehicle-mounted control instruction, when the feedback information indicates that the vehicle-mounted control instruction is not executed, the vehicle-mounted intelligent agent is controlled to output chat information for the feedback information; or, If the feedback information is received after the vehicle-mounted intelligent agent outputs the chat information, and the chat information does not comprise a preset vehicle-mounted control instruction, the vehicle-mounted intelligent agent is controlled to output chat information for the feedback information.

18. The agent control method according to claim 16 or 17, characterized by, The controlling the vehicle-mounted intelligent agent to perform a target action according to the feedback information comprises: If the feedback information is received after the vehicle-mounted intelligent agent outputs the chat information, and the chat information comprises a preset vehicle-mounted control instruction, when the feedback information indicates that the vehicle-mounted control instruction is executed, the vehicle-mounted intelligent agent is controlled to perform an action corresponding to the vehicle-mounted control instruction.

19. The agent control method according to any one of claims 1-18, wherein, The vehicle-mounted intelligent agent corresponds to a control device of a vehicle, and the vehicle-mounted intelligent agent comprises a vehicle window-mounted intelligent agent, a seat-mounted intelligent agent, and / or an air conditioner-mounted intelligent agent, the vehicle window-mounted intelligent agent corresponds to a control device of a window of the vehicle, the seat-mounted intelligent agent corresponds to a control device of a seat of the vehicle, and the air conditioner-mounted intelligent agent corresponds to a control device of an air conditioner of the vehicle.

20. An electronic device, comprising: The electronic device comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the steps of the method of any one of claims 1-19.

21. A vehicle characterized by The vehicle comprises a processor and a memory for storing processor-executable instructions, wherein the processor is configured to perform the steps of the method of any one of claims 1-19.

22. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein, The program is executed by the processor to implement the steps of the method of any one of claims 1-19.

23. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1-19.

Images