Interface skin generation method, device and equipment of vehicle-mounted system, medium and vehicle

Abstract

The invention relates to an interface skin generation method, device and equipment of a vehicle-mounted system, a medium and a vehicle, and the interface skin generation method of the vehicle-mounted system comprises the steps: obtaining image information and user voice information collected by the vehicle-mounted system, and obtaining the interface skin of the vehicle-mounted system based on the image information and the user voice information; performing intention analysis in combination with music playing information of the vehicle-mounted system to obtain skin changing intention information of the user, determining interface skin characteristic information based on the skin changing intention information, and then performing interface skin generation according to the interface characteristic skin characteristic information to obtain target interface skin corresponding to the vehicle system; therefore, the target interface skin can be adaptively generated according to different environments and scenes, the user experience can be effectively improved, and the problem that the user experience is poor due to the small skin selection range of a vehicle-mounted system in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method, device, equipment, medium and vehicle for generating an interface skin of an in-vehicle system. Background Art

[0002] With the development of smart cars, the in-vehicle system has become an indispensable part of modern cars. The in-vehicle system can provide multiple functions such as navigation, entertainment, and communication. The in-vehicle system displays specific interactive screens to users through layout and image rendering. In order to provide users with choices or freshness, multiple sets of skin interfaces are usually pre-configured for the in-vehicle system so that users can choose and switch according to their needs. However, although this update based on pre-configured skins can provide users with choices, the range of choices is small, and users will feel bored and lose freshness in a short time, that is, there is a problem of poor user experience. Summary of the invention

[0003] The present application provides a method, device, equipment, medium and vehicle for generating an interface skin of an in-vehicle system, so as to solve the problem of poor user experience caused by a small selection range of in-vehicle system skins in the existing related technologies.

[0004] In a first aspect, the present application provides a method for generating an interface skin of an in-vehicle system, comprising:

[0005] Obtain image information and user voice information collected by the vehicle system;

[0006] Based on the image information and the user voice information, the intention analysis is performed in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information;

[0007] Based on the skin-changing intention information, determining interface skin characteristic information;

[0008] An interface skin is generated according to the interface characteristic skin property information to obtain a target interface skin corresponding to the vehicle system.

[0009] Optionally, the performing intention analysis based on the image information and the user voice information in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information includes:

[0010] Performing intent analysis based on the image information to obtain interface layout intent information;

[0011] Perform intent analysis based on user voice information to obtain topic style intent information;

[0012] Performing feature analysis on the music playing information to obtain rhythm feature information;

[0013] The skin change intention information is determined based on the interface layout intention information, the theme style intention information and the rhythm feature information.

[0014] Optionally, performing intent analysis based on the image information to obtain interface layout intent information includes:

[0015] Performing image recognition on the image information to obtain emotional state information corresponding to the user;

[0016] Determining a target interface layout attribute corresponding to the emotional state information;

[0017] The interface layout intention information is generated based on the target interface layout attributes.

[0018] Optionally, performing intent analysis based on user voice information to obtain topic style intent information includes:

[0019] Performing voice recognition on the user voice information to obtain voice text information;

[0020] Extracting topic keywords from the voice text information;

[0021] Based on the topic keywords, the topic intention information is generated.

[0022] Optionally, the generating the topic style intention information based on the topic style keyword includes:

[0023] Determine whether the theme keyword is empty;

[0024] When the theme keyword is empty, obtaining the historical theme information corresponding to the user, and generating the theme intention information according to the historical theme information;

[0025] In the case that the theme keyword is not empty, the theme intention information is generated according to the target theme attribute corresponding to the theme keyword.

[0026] Optionally, performing feature analysis on the music playing information to obtain rhythm feature information includes:

[0027] Performing feature analysis on the music playing information to obtain rhythm features and emotional features;

[0028] Determining target rhythm attributes according to the rhythm features and the emotional features;

[0029] The rhythm feature information is generated based on the target rhythm attribute.

[0030] Optionally, determining the target rhythm attribute according to the rhythm feature and the emotion feature includes:

[0031] Determining a rhythm attribute corresponding to the rhythm feature;

[0032] The target rhythm attribute is determined according to the rhythm attribute and in combination with the preset tone attribute corresponding to the emotional feature.

[0033] Optionally, determining the interface skin characteristic information based on the skin changing intention information includes:

[0034] Extracting interface layout intention information, theme style intention information and rhythm feature intention information from the skin-changing intention information;

[0035] Determine a target interface layout attribute corresponding to the interface layout intention information;

[0036] Determine a target theme attribute corresponding to the theme intent information;

[0037] Determining a target rhythm attribute corresponding to the rhythm feature intention information;

[0038] Based on the target interface layout attributes, the target theme style attributes and the target rhythm attributes, skin characteristic fusion is performed to obtain the interface skin characteristic information.

[0039] In a second aspect, the present application provides an interface skin generating device for a vehicle-mounted system, characterized in that it includes:

[0040] The acquisition module is used to obtain the image information and user voice information collected by the vehicle system

[0041] An intention analysis module, used to perform intention analysis based on the image information and the user voice information in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information;

[0042] A determination module, used to determine interface skin characteristic information based on the skin change intention information;

[0043] The interface skin generation module is used to generate the interface skin according to the interface characteristic skin property information to obtain the target interface skin corresponding to the vehicle system.

[0044] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0045] Memory, used to store computer programs;

[0046] The processor is used to implement the interface skin generation method of the vehicle-mounted system described in any one of the first aspects when executing the program stored in the memory.

[0047] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for generating an interface skin of a vehicle-mounted system as described in any one of the first aspects is implemented.

[0048] In a fourth aspect, a vehicle is provided, wherein the vehicle comprises the interface skin generating device of the vehicle-mounted system as described in the second aspect.

[0049] The embodiment of the present application obtains image information and user voice information collected by the vehicle-mounted system, and performs intent analysis based on the image information and user voice information in combination with the music playback information of the vehicle-mounted system to obtain the user's skin change intention information, and then determines the interface skin characteristic information based on the skin change intention information, and then generates the interface skin according to the interface characteristic skin characteristic information to obtain the target interface skin corresponding to the vehicle system; thereby, the target interface skin can be adaptively generated according to different environments and scenarios, which can effectively improve the user experience, thereby solving the problem of poor user experience caused by the small range of skin selection for the vehicle-mounted system in the existing related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a flow chart of a method for generating an interface skin of a vehicle-mounted system provided in an embodiment of the present application;

[0051] Figure 2 Another schematic diagram of a flow chart of a method for generating an interface skin of a vehicle-mounted system provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the structure of an interface skin generating device for an in-vehicle system provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0055] Vehicles have become a means of transportation for most people, and users spend more and more time in vehicles. The vehicle's onboard system is the main way for users to control the vehicle. Users interact with the onboard system under different emotions or in different scenarios, and may use different interface skins of the onboard system. Usually the onboard system will be pre-configured with one or more sets of interface skins for users to choose to switch between, but users may not be satisfied with or have lost interest in the pre-configured interface skins, which will lead to poor user experience.

[0056] In order to provide users with more interface skin options in the existing related technologies, multiple interface skin components are usually pre-configured, and different interface skins are combined by selecting different interface skin components, so that users can customize the interface skins. Although this method can provide users with more interface skin options, the combined interface skins are still limited. In addition, users are required to perform multiple operations such as selection, configuration, and application to complete the switching of interface skins. That is, the existing vehicle system interface skin selection and switching process has great limitations, resulting in poor user experience.

[0057] In order to solve the problem that the vehicle-mounted system interface skin selection and switching process in the existing related technology is greatly limited, resulting in poor user experience, the present application provides a vehicle-mounted system interface skin generation method, device, equipment, medium and vehicle, by acquiring image information and user voice information collected by the vehicle-mounted system, and performing intent analysis based on the image information and user voice information in combination with the music playback information of the vehicle-mounted system to obtain the user's skin change intention information, and based on the skin change intention information, determine the interface skin characteristic information, and then generate the interface skin according to the interface characteristic skin characteristic information to obtain the target interface skin corresponding to the vehicle system; thereby, the target interface skin can be adaptively generated according to different environments and scenarios, which can effectively improve the user experience, thereby solving the problem that the vehicle-mounted system interface skin selection and switching process in the existing related technology is greatly limited, resulting in poor user experience.

[0058] Figure 1 A flow chart of a method for generating an interface skin for an in-vehicle system provided in an embodiment of the present application. The method can be applied to one or more electronic devices such as vehicles and in-vehicle systems. In addition, the execution subject of the method can be hardware or software. When the above-mentioned execution subject is hardware, the execution subject can be one or more of the above-mentioned electronic devices. For example, a single electronic device can execute the method, or multiple electronic devices can cooperate with each other to execute the method. When the above-mentioned execution subject is software, the method can be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0059] like Figure 1As shown, a method for generating an interface skin of a vehicle-mounted system provided in an embodiment of the present application may specifically include the following steps:

[0060] Step S110: Acquire image information and user voice information collected by the vehicle-mounted system.

[0061] Among them, the vehicle-mounted system may refer to a system pre-configured in the vehicle for vehicle control, and the vehicle-mounted system may include but is not limited to functions such as in-vehicle information collection, information provision, entertainment, navigation, communication and vehicle control; user voice information may refer to user voice collected by the vehicle-mounted system through an audio collection device pre-configured in the vehicle, and the preset audio collection device may be a microphone or other device; image information may refer to in-vehicle images collected by the vehicle-mounted system through an image collection device pre-configured in the vehicle, and the preset image collection device may be a camera or a scanning device or other device. It should be noted that in this embodiment, the image information may include one or more collected images, for example, it may be a video frame contained in the in-vehicle video collected by the vehicle-mounted system, and this embodiment does not specifically limit this.

[0062] Step S120: Based on the image information and the user's voice information, the intention analysis is performed in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information.

[0063] Specifically, after obtaining the voice information, the music playback information of the vehicle system can be obtained. The music playback information can indicate the music information currently played by the vehicle system through the vehicle media, which can specifically include music lyrics, music type, music emotion and other information. This embodiment does not make specific limitations on this. After obtaining the music playback information, the image information, the user voice information and the music playback information can be combined to perform intent analysis to obtain the user's skin-changing intent information. The skin-changing intent information indicates the user's corresponding skin-changing intent in the current environment, which can specifically include but is not limited to one or more intents such as interface layout intent, theme style intent and rhythm feature intent. This embodiment does not make specific limitations on this.

[0064] It should be noted that the intention analysis process in this embodiment can be to analyze the image information, user voice information and music playback information respectively, to obtain a first analysis result corresponding to the image information, a second analysis result corresponding to the user voice information and a third analysis result corresponding to the music playback information, and combine the first analysis result, the second analysis result and the third analysis result to obtain the skin change intention information; different analysis methods can be used for the analysis of different information, and this embodiment does not make any specific limitations on this.

[0065] Step S130: Determine the interface skin characteristic information based on the skin changing intention information.

[0066] Specifically, after obtaining the skin changing intention information, the interface skin characteristic information can be determined based on the skin changing intention information. The interface skin characteristic information can represent the features used to generate the vehicle system interface skin, such as including but not limited to interface layout attributes, theme style attributes, and rhythm attributes, etc.; among which, the interface layout attributes can represent the overall layout of the interface skin, the theme style attributes can represent the theme style of the interface skin map, the rhythm attributes can represent the attributes of the rhythm elements in the interface skin, etc. This embodiment does not make specific limitations on this.

[0067] Specifically, in the process of determining the interface skin characteristic information, a pre-configured preset skin feature can be obtained, and the preset skin feature can be matched with the skin changing intention information, and the target skin feature that matches the preset skin feature with the skin changing intention information can be determined, so that the interface skin characteristic information can be obtained from all the target skin features, wherein the skin feature can be the layout feature of the interface skin, the theme feature of the texture style, or the rhythm attribute feature, etc., and this embodiment does not make specific limitations on this. In addition, skin features can also be generated based on the skin changing intention information to obtain at least one target skin feature. At this time, the target skin feature can represent the real-time generation of skin features that match the skin changing intention information, so that the interface skin characteristic information can be obtained from all the target skin features; of course, the above is only an example for illustration, and other methods can be used to determine the interface skin characteristic information during specific implementation, and this embodiment does not make specific limitations on this.

[0068] Step S140: Generate an interface skin according to the interface characteristic skin property information to obtain a target interface skin corresponding to the vehicle system.

[0069] Specifically, after determining the interface skin characteristic information, the interface skin can be generated based on the interface characteristic skin characteristic information to obtain the target interface skin corresponding to the vehicle system. The target interface skin can represent the interface skin specifically applied to the vehicle system, and the specific interface skin generation can adopt preset neural networks, algorithm models, etc. This embodiment does not make specific limitations on this.

[0070] It can be seen that in this embodiment, the user's emotions and intentions are analyzed by collecting image information and user voice information in the vehicle, and then the environmental factors are analyzed in combination with the music playback information of the vehicle-mounted system, so as to perform a multi-faceted analysis of the user and the environment in the vehicle, and then determine the skin change intention information that matches the current user and environment, and determine the interface skin characteristic information based on the skin change intention information, and then generate the interface skin according to the interface characteristic skin characteristic information to obtain the target interface skin corresponding to the vehicle system; thereby, the target interface skin can be adaptively generated according to different environments and scenarios, which can effectively improve the user experience, and thus solve the problem of poor user experience caused by the small range of vehicle system skin selection in the existing related technologies.

[0071] like Figure 2 As shown, in an optional embodiment of the present application, step S120 performs intention analysis based on image information and user voice information in combination with the music playback information of the vehicle-mounted system to obtain the user's skin-changing intention information, including:

[0072] Step S121: performing intent analysis based on the image information to obtain interface layout intent information;

[0073] Step S122: performing intention analysis based on the user voice information to obtain topic style intention information;

[0074] Step S123: performing feature analysis on the music playing information to obtain rhythm feature information;

[0075] Step S124: Determine skin change intention information based on the interface layout intention information, theme style intention information and rhythm feature information.

[0076] After obtaining the image information and the user voice information, this embodiment can perform intent analysis based on the image information to obtain the interface layout intent information. The interface layout intent information can represent the intent information for indicating the page layout that meets the user's needs, and the specific intent analysis can include but is not limited to performing face recognition, face feature extraction, emotion analysis and other processing on the image information, which is not specifically limited in this embodiment.

[0077] Specifically, this embodiment can extract user emotions through images, perform intent analysis based on user emotions, and determine the page layout intent information that currently meets the user's emotional state; it can also perform intent analysis based on user voice information to obtain theme style intent information, wherein the theme style intent information can represent intent information for indicating a theme style that meets user needs, and the specific intent analysis can include but is not limited to performing voice-to-text recognition, keyword extraction, and intent analysis on the user voice information. This implementation does not make specific limitations on this, that is, this embodiment can perform intent analysis on the text corresponding to the user voice information to determine the page layout intent information that currently meets the semantic expression of the user through voice. Theme style intention information; feature analysis can also be performed on the music playback information to obtain rhythm feature information, wherein the rhythm feature information can be used to indicate a rhythm feature that matches the rhythm of the currently playing music, and the specific feature analysis can include but is not limited to rhythm feature extraction, emotion feature extraction, rhythm feature analysis, and emotion feature analysis on the music playback information. The present implementation does not make specific limitations on this, that is, the present embodiment can determine the rhythm feature information that matches the current music playing in the car through the emotion or rhythm corresponding to the music playback information; then, the interface layout intention information, theme style intention information, and rhythm feature information can be integrated to determine the skin change intention information.

[0078] It can be seen that in this embodiment, the page layout intention information that indicates the page layout meets the user's needs is determined through image information, the theme style intention information that indicates the page layout meets the user's needs is determined through user voice information, and the rhythm characteristics that indicate the rhythm that meets the rhythm of the currently playing music are determined through music playback information. Then, the interface layout intention information, theme style intention information and rhythm characteristic information are integrated to obtain the skin change intention information. That is, this embodiment plays a role in determining the different characteristic attributes of the interface skin through different types of collected data, so that the target interface skin generated by the skin change intention information can be more in line with the user and the current vehicle music environment, and the flexibility of generating the target interface skin is improved, which greatly improves the user experience.

[0079] In an optional embodiment of the present application, intent analysis is performed based on image information to obtain interface layout intent information, including: performing image recognition on the image information to obtain emotional state information corresponding to the user; determining target interface layout attributes corresponding to the emotional state information; and generating interface layout intent information based on the target interface layout attributes.

[0080] In the process of performing intent analysis based on image information to obtain interface layout intention information, this embodiment can perform image recognition on the image information to obtain the user's corresponding emotional state information; the emotional state information represents the current user's emotional state, such as cold, hot, tired, happy, etc., and the specific image recognition process may include but is not limited to face extraction, body movement extraction, face emotion recognition, body movement emotion recognition, emotion fusion and other processing, and this embodiment does not make specific limitations on this.

[0081] After determining the emotional state information, the target interface layout attributes corresponding to the emotional state information can be determined, and the target interface layout attributes represent the interface layout attributes that match the emotional state information; thereby, based on the target interface layout attributes, interface layout intention information can be generated, so that the interface layout intention information can be used as intention information for indicating the target interface layout attributes that meet user needs.

[0082] It should be noted that, in the process of determining the target interface layout attributes corresponding to the emotional state information in the present embodiment, the specific determination method can be to obtain preset emotional matching relationship information, and match the emotional state information with each preset interface layout attribute based on the emotional matching relationship information; wherein, the preset interface layout attribute can represent a pre-configured page layout attribute, and the emotional matching relationship information can represent a pre-configured matching relationship between the emotional state information and the preset interface layout attribute, so that the preset interface layout attribute that matches the emotional state information can be determined as the target interface layout attribute.

[0083] In addition, the embodiment of the present application can also obtain a preset interface layout attribute generation strategy, so as to adopt the interface layout attribute generation strategy, generate interface layout attributes in combination with the emotional state information, and obtain target interface layout attributes; wherein, the interface layout attribute generation strategy can represent a pre-configured strategy for real-time generation of page layout attributes, and the specific interface layout attribute generation process can include but is not limited to emotional state classification, determining the degree of emotion, and generating interface layout attributes in combination with preset attribute materials, etc., which is not specifically limited in this embodiment. Of course, the embodiment of the present application can also use other methods to determine the target interface layout attributes corresponding to the emotional state information, which is not specifically limited in this implementation.

[0084] In one example, in this embodiment, the emotional state of the image information is identified and determined, and the corresponding target interface layout attributes are determined by the emotional state information, so that different target interface layout attributes can display different page layouts in the target interface skin generated subsequently. For example, when the emotional state information indicates that the user has a "cold" feeling, the target interface layout attribute can be an air-conditioning prominent interface layout attribute. At this time, in the target interface skin generated subsequently, the air-conditioning button interface layout range can be large, so that the user can intuitively and quickly view and operate the air-conditioning button through the target interface skin; or, when the emotional state information indicates that the user is in a sad emotion, the target interface layout attribute can be an entertainment area prominent interface layout attribute. At this time, in the target interface skin generated subsequently, the entertainment area interface layout range can be large, so that the user can intuitively and quickly view and operate the entertainment area through the target interface skin, thereby prompting the user to entertain and eliminate sad emotions. Of course, the above is only an example for illustration, and this embodiment does not make specific limitations on this.

[0085] It can be seen that in this embodiment, the target interface layout attributes of the skin interface are determined by corresponding the emotional state information of the user through the image information, which plays a role in determining the interface layout attributes suitable for the current user's emotions based on the processing and analysis of the image information. That is, the user does not need to actively configure or adjust the interface layout, but can adaptively determine the target interface layout attributes based on the collected image information, making the user less sensitive to the process of generating the target skin interface, and making the target skin interface fit the user's emotional state, thereby effectively improving the user experience.

[0086] In an optional embodiment of the present application, intent analysis is performed based on user voice information to obtain topic style intent information, including: performing voice recognition on the user voice information to obtain voice text information; extracting topic style keywords from the voice text information; and generating topic style intent information based on the topic style keywords.

[0087] In the process of performing intent analysis based on user voice information to obtain theme intent information, this embodiment can perform voice recognition on the user voice information to obtain voice text information, and the voice text information represents the text contained in the user voice information; theme keywords can be extracted from the voice text information, and the theme keywords can represent keywords used to indicate specific theme styles, such as cool colors, liveliness, passion, etc., which are not specifically limited in this embodiment; thus, theme intent information can be generated based on the theme keywords, so that the theme intent information can be used as intent information for indicating a target theme style that meets the corresponding requirements of the user voice information, that is, the theme intent information can be intent information indicating the target theme style.

[0088] Specifically, after extracting topic style keywords from the voice text information, it can be determined whether at least two topic style keywords are extracted. When at least two topic style keywords are extracted, for each topic style keyword, the preset topic style corresponding to the topic style keyword can be determined, and style fusion is performed in combination with each preset topic style to generate target topic style attributes, and topic style intent information is generated based on the target topic style attributes, so that the topic style intent information can be used as intent information for indicating the target topic style attributes that meet the corresponding requirements of the user's voice information. For example, when two theme style keywords, a first theme style keyword and a second theme style keyword, are extracted, for the first theme style, a first preset theme style corresponding to the first theme style keyword is determined, and for the second theme style, a second preset theme style corresponding to the second theme style keyword is determined. At this time, the first preset theme style and the second preset theme style can be combined to perform style fusion to generate a target theme style attribute, so that theme style intention information can be generated based on the target theme style attribute; further, when the user voice information contains multiple theme style keywords, theme style fusion can be performed to generate and determine in real time the target theme style attribute that meets the current user needs. For example, if the user voice information is "I want a lively and green theme", the lively preset theme style corresponding to the lively theme style keyword can be determined, and the green preset theme style corresponding to the green theme style keyword can be determined, so that the lively preset theme style and the green preset theme style are merged to obtain the lively green target theme style attribute; this can meet the various needs of users and effectively improve the user experience.

[0089] In an optional embodiment of the present application, topic style intent information is generated based on topic style keywords, including: determining whether the topic style keyword is empty; if the topic style keyword is empty, obtaining historical topic style information corresponding to the user, and generating topic style intent information based on the historical topic style information; if the topic style keyword is not empty, generating topic style intent information based on the target topic style attribute corresponding to the topic style keyword.

[0090] In the process of generating theme style intention information based on theme style keywords, this embodiment can determine whether the theme style keyword is empty. If the theme style keyword is empty, it means that there is no text about the theme style in the current user voice, or the user has not made a user voice. At this time, the historical theme style information corresponding to the user can be obtained. The historical theme style information can represent the theme style that the current user has historically configured or used, so that theme style intention information can be generated based on the historical theme style information; and when the theme style keyword is not empty, it means that there is text about the theme style in the user voice. At this time, the theme style intention information can be generated based on the target theme style attribute corresponding to the theme style keyword, wherein the target theme style attribute can be used to represent the theme style attribute that conforms to the theme style keyword, wherein the correspondence between the target theme style attribute and the theme style keyword can be a one-to-one or one-to-many relationship, and this embodiment does not make specific limitations on this.

[0091] It should be noted that in the process of generating theme style intention information based on historical theme style information, specifically, user theme style preference analysis can be performed on the historical theme style information to obtain user theme style preference information. The user theme style preference information can indicate the user's preference for theme styles, such as preference for lively theme styles, preference for passionate theme styles, etc., and the specific user theme style preference analysis method can be based on the historical theme style information, determine the number of theme style usages, theme style interaction frequencies and other information corresponding to each theme style in the historical theme style information, wherein the number of theme style usages can indicate the number of usages corresponding to each theme style contained in the historical theme style information, and the theme style interaction frequency can indicate the number of interactions corresponding to each theme style contained in the historical theme style information; perform preference analysis in combination with the number of theme style usages and the theme style interaction frequency to determine the target theme style attributes that meet the user preferences, and the method for determining the target theme style attributes can be to determine the theme style with the largest cumulative number of theme style usages and theme style interaction frequencies as the target theme style attributes, of course, it can also be other methods for determining the target theme style attributes through the number of theme style usages and the theme style interaction frequencies, and this embodiment does not make specific limitations on this.

[0092] It can be seen that in the process of generating theme style intention information based on theme style keywords in this embodiment, when the theme style keyword is empty, the historical theme style information corresponding to the user can be used to generate theme style intention information, so that the theme style intention information can be used to indicate the theme style that conforms to the user's historical theme style preference habits; and when the theme style keyword is not empty, the target theme style attribute corresponding to the theme style keyword can be used to generate theme style intention information, so that the theme style intention information can be used to indicate the theme style that conforms to the user's current theme style intention needs; it can play a role in meeting the user's needs for different voice information correspondence, and achieve the effect of effectively improving the user experience.

[0093] In one example, different target theme style attributes in this embodiment can display different theme styles in the target interface skin generated subsequently. For example, when the target theme style attribute is a lively style, the overall picture of the target interface skin generated subsequently presents a lively style, which can be a lively theme sticker, a lively theme button shape, etc. At this time, the user can intuitively feel the lively atmosphere style through the target interface skin. Of course, the above is only an example for illustration, and this embodiment does not make specific limitations on this.

[0094] In this embodiment, the theme style intention information is determined by the theme style keywords contained in the user voice information or the historical theme style information corresponding to the user, which plays a role in determining the theme style attributes suitable for the current user needs based on the processing and analysis of the user voice information or the historical theme style information. In other words, there is no need for the user to actively configure or adjust the theme style, but the theme style intention information that meets the user needs can be adaptively determined based on the collected user voice information or historical theme style information, making the user more unaware of the process of determining the main style of the target skin interface, and making the main style of the target skin interface meet the user's needs, thereby effectively improving the user experience.

[0095] In an optional embodiment of the present application, feature analysis is performed on the music playback information to obtain rhythm feature information, including: performing feature analysis on the music playback information to obtain rhythm features and emotional features; determining target rhythm attributes based on the rhythm features and emotional features; and generating rhythm feature information based on the target rhythm attributes.

[0096] In the process of performing feature analysis on music playback information to obtain rhythm feature information, this embodiment can perform feature analysis on the music playback information to obtain rhythm features and emotional features, wherein the rhythm features can indicate the rhythm of the music played corresponding to the music playback information, such as fast rhythm, slow rhythm, swing rhythm, etc., and the emotional features can indicate the emotions of the music played corresponding to the music playback information, such as cheerful emotions, sad emotions, etc.; thereby, the target rhythm attributes can be determined based on the rhythm features and emotional features, and the target rhythm attributes can indicate attributes that match the rhythm of the music played corresponding to the music playback information, such as dynamic warm color attributes, static cool color attributes, or soft mid-tone attributes, etc.; and then the rhythm feature information can be generated based on the target rhythm attributes, so that the rhythm feature information can be used to indicate the target rhythm attributes.

[0097] In an optional embodiment of the present application, the target rhythm attribute is determined based on the rhythm feature and the emotional feature, including: determining the rhythm attribute corresponding to the rhythm feature; determining the target rhythm attribute based on the rhythm attribute in combination with the preset tone attribute corresponding to the emotional feature.

[0098] In the process of determining the target rhythm attribute based on the rhythm feature and the emotional feature, the present embodiment can determine the rhythm attribute corresponding to the rhythm feature. The rhythm attribute can represent the rhythm related to the interface skin, such as dynamic rhythm, static rhythm, etc., and the specific method of determining the rhythm attribute can be determined based on pre-configured rhythm attribute feature relationship information. The rhythm attribute feature relationship information can include the corresponding relationship between the rhythm feature and the rhythm attribute, such as the rhythm attribute corresponding to the rhythm feature of the fast rhythm is the dynamic rhythm, and the rhythm attribute corresponding to the rhythm feature of the slow rhythm is the static rhythm. Of course, other methods of determining the rhythm attribute can also be used, and this embodiment does not make specific restrictions on this; it can also be determined that the emotional feature corresponds to the preset color tone attribute, and the color tone attribute can represent the color tone related to the interface skin, such as warm color, cold color Etc., and the specific way to determine the hue attribute can be determined based on pre-configured emotional attribute feature relationship information, which can include the correspondence between emotional features and hue attributes, such as the hue attribute corresponding to the emotional feature of cheerful emotion is warm hue, and the hue attribute corresponding to the emotional feature of sad emotion is cool hue. Of course, other ways to determine the rhythm attribute can also be used, and this embodiment does not make specific restrictions on this; then the rhythm attribute and the hue attribute can be combined to determine the target rhythm attribute, and the specific way to determine it can be to merge the rhythm attribute and the hue attribute, for example, if the rhythm attribute is a dynamic rhythm and the hue attribute is a warm hue, it can be merged into a target rhythm attribute of a dynamic warm color rhythm attribute. Of course, the above is only an example, and this embodiment does not make specific restrictions on this.

[0099] Specifically, different target rhythm attributes can display different effects in the target interface skin generated subsequently. For example, when the target rhythm attribute is a dynamic warm color rhythm attribute, the display effect in the target interface skin generated subsequently can be that the interface color is warm, and part of the interface will follow the rhythm of the music to perform synchronous rhythm dynamic shaking; when the target rhythm attribute is a static warm color rhythm attribute, the display effect in the target interface skin generated subsequently can be that the interface color is warm, and the interface will not follow the rhythm of the music to perform synchronous rhythm shaking but remain static. Of course, the above is only an example for illustration, and this embodiment does not make specific limitations on this.

[0100] In an optional embodiment of the present application, interface skin characteristic information is determined based on skin changing intention information, including: extracting interface layout intention information, theme style intention information and rhythm feature intention information from the skin changing intention information; determining target interface layout attributes corresponding to the interface layout intention information; determining target theme style attributes corresponding to the theme style intention information; determining target rhythm attributes corresponding to the rhythm feature intention information; and performing skin characteristic fusion based on the target interface layout attributes, target theme style attributes and target rhythm attributes to obtain interface skin characteristic information.

[0101] In the process of determining the interface skin characteristic information based on the skin changing intention information, this embodiment can extract the interface layout intention information, the theme style intention information and the rhythm characteristic intention information from the skin changing intention information, and respectively determine the target interface layout attributes corresponding to the interface layout intention information, determine the target theme style attributes corresponding to the theme style intention information, and determine the target rhythm attributes corresponding to the rhythm characteristic intention information; thereby, the target interface layout attributes, the target theme style attributes and the target rhythm attributes can be fused with skin characteristics, wherein the skin characteristic fusion can represent the fusion of different interface skin attributes, thereby obtaining the interface skin characteristic information for generating the vehicle system interface skin, so as to facilitate the subsequent generation of the skin interface based on the interface skin characteristic information to obtain the target skin interface.

[0102] It can be seen that in this embodiment, the interface skin is generated by integrating the interface skin characteristic information of the target interface layout attribute, the target theme style attribute and the target rhythm attribute, wherein the target interface layout attribute is the interface layout indicated by the interface layout intention information in the skin-changing intention information, the target theme style attribute is the theme style indicated by the theme style intention information in the skin-changing intention information, and the target rhythm attribute is the rhythm attribute indicated by the rhythm feature intention information in the skin-changing intention information; and the interface layout intention information is the intention determined by performing user emotional state recognition analysis on the image information, the theme style intention information is the intention determined by performing keyword recognition analysis on the user voice information, and the rhythm feature intention information is the intention determined by performing keyword recognition analysis on the current vehicle playback. The intention is determined by performing feature analysis on the music; thus, it can be seen that in the process of generating the target interface skin, the layout of the interface is determined by the user's emotional state, the theme style of the interface is determined by the user's voice keywords, and the rhythm attributes of the interface are determined by the characteristics of the played music. That is, different types of data are used for analysis to determine the different attributes of the target interface skin, which plays a role in combining multivariate data to generate the target interface skin, so that the target interface skin can be adaptively generated according to different environments and scenarios in the process, and the user does not need to configure or select in the process, which can effectively improve the user experience, thereby solving the problem of poor user experience caused by the small selection range of vehicle-mounted system skins in the existing related technologies.

[0103] like Figure 3 As shown, the present application also discloses an embodiment, which provides an interface skin generating device for a vehicle-mounted system, including:

[0104] The acquisition module 310 is used to acquire the image information and user voice information collected by the vehicle system.

[0105] The intention analysis module 320 is used to perform intention analysis based on the image information and the user voice information in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information;

[0106] A determination module 330, configured to determine interface skin characteristic information based on the skin changing intention information;

[0107] The interface skin generation module 340 is used to generate an interface skin according to the interface characteristic skin property information to obtain a target interface skin corresponding to the vehicle system.

[0108] In an optional embodiment of the present application, the intention analysis module 320 may include:

[0109] A first intention analysis unit, configured to perform intention analysis based on the image information to obtain interface layout intention information;

[0110] A second intention analysis unit is used to perform intention analysis based on user voice information to obtain topic style intention information;

[0111] A feature analysis unit, used for performing feature analysis on the music playing information to obtain rhythm feature information;

[0112] The first determining unit is used to determine the skin changing intention information based on the interface layout intention information, the theme style intention information and the rhythm feature information.

[0113] In an optional embodiment of the present application, the first intention analysis unit may include:

[0114] An image recognition subunit, used to perform image recognition on the image information to obtain the emotional state information corresponding to the user;

[0115] A first determining subunit, used to determine a target interface layout attribute corresponding to the emotional state information;

[0116] The first generating subunit is used to generate the interface layout intention information based on the target interface layout attributes.

[0117] In an optional embodiment of the present application, the second intention analysis unit may include:

[0118] A speech recognition subunit, used for performing speech recognition on the user's speech information to obtain speech text information;

[0119] A first extraction subunit, used to extract topic style keywords from the voice text information;

[0120] The second generating subunit is used to generate the topic style intention information based on the topic style keywords.

[0121] In an optional embodiment of the present application, the second generating subunit may include:

[0122] A second determining subunit is used to determine whether the theme style keyword is empty;

[0123] A third generating subunit is used to obtain the historical theme style information corresponding to the user when the theme style keyword is empty, and generate the theme style intention information according to the historical theme style information;

[0124] The fourth generating subunit is used to generate the topic style intention information according to the target topic style attribute corresponding to the topic style keyword when the topic style keyword is not empty.

[0125] In an optional embodiment of the present application, the feature analysis unit may include:

[0126] A feature analysis subunit, used for performing feature analysis on the music playing information to obtain rhythm features and emotional features;

[0127] A third determination subunit is used to determine a target rhythm attribute according to the rhythm feature and the emotional feature;

[0128] The fifth generating subunit is used to generate the rhythm feature information based on the target rhythm attribute.

[0129] In an optional embodiment of the present application, the third determining subunit may include:

[0130] a fourth determining subunit, configured to determine a rhythm attribute corresponding to the rhythm feature;

[0131] The fifth determining subunit is used to determine the target rhythm attribute according to the rhythm attribute and the preset tone attribute corresponding to the emotional feature.

[0132] In an optional embodiment of the present application, the determination module 330 may include:

[0133] An extraction unit, used to extract interface layout intention information, theme style intention information and rhythm feature intention information from the skin change intention information;

[0134] A second determining unit, used to determine a target interface layout attribute corresponding to the interface layout intention information;

[0135] A third determining unit, configured to determine a target theme attribute corresponding to the theme intention information;

[0136] A fourth determining unit, configured to determine a target rhythm attribute corresponding to the rhythm feature intention information;

[0137] The skin characteristic fusion unit is used to perform skin characteristic fusion based on the target interface layout attribute, the target theme style attribute and the target rhythm attribute to obtain the interface skin characteristic information.

[0138] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0139] like Figure 4 As shown, an embodiment of the present application provides an electronic device, including a processor 410, a communication interface 420, a memory 430 and a communication bus 430, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 430;

[0140] Memory 430, for storing computer programs;

[0141] In one embodiment of the present application, the processor 410, when executing the program stored in the memory 430, implements the interface skin generation method for the vehicle-mounted system provided by any of the aforementioned method embodiments, by acquiring image information and user voice information collected by the vehicle-mounted system, and performing intent analysis based on the image information and user voice information in combination with the music playback information of the vehicle-mounted system to obtain the user's skin change intention information, and based on the skin change intention information, determine the interface skin characteristic information, and then generate the interface skin according to the interface characteristic skin characteristic information to obtain the target interface skin corresponding to the vehicle system; thereby, the target interface skin can be adaptively generated according to different environments and scenarios, which can effectively improve the user experience, thereby solving the problem of poor user experience caused by the small range of vehicle-mounted system skin selection in the existing related technology.

[0142] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for generating an interface skin for a vehicle-mounted system provided in any of the aforementioned method embodiments are implemented, by acquiring image information and user voice information collected by the vehicle-mounted system, and performing intent analysis based on the image information and user voice information in combination with the music playback information of the vehicle-mounted system to obtain the user's skin-changing intention information, and determining interface skin characteristic information based on the skin-changing intention information, and then generating the interface skin according to the interface characteristic skin characteristic information to obtain a target interface skin corresponding to the vehicle system; thereby, the target interface skin can be adaptively generated according to different environments and scenarios, which can effectively improve the user experience, thereby solving the problem of poor user experience due to the small range of skin selection for the vehicle-mounted system in the existing related technologies.

[0143] An embodiment of the present application also provides a vehicle, which includes the interface skin generating device of the vehicle-mounted system described in any of the aforementioned embodiments.

[0144] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0146] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0147] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for generating an interface skin of a vehicle-mounted system, characterized in that: include: Obtain image information and user voice information collected by the vehicle system; Based on the image information and the user voice information, the intention analysis is performed in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information; Based on the skin-changing intention information, determining interface skin characteristic information; An interface skin is generated according to the interface characteristic skin property information to obtain a target interface skin corresponding to the vehicle system.

2. The method for generating an interface skin of an in-vehicle system according to claim 1, characterized in that: The performing intention analysis based on the image information and the user voice information in combination with the music playing information of the vehicle-mounted system to obtain the user's skin changing intention information includes: Performing intent analysis based on the image information to obtain interface layout intent information; Perform intent analysis based on user voice information to obtain topic style intent information; Performing feature analysis on the music playing information to obtain rhythm feature information; The skin change intention information is determined based on the interface layout intention information, the theme style intention information and the rhythm feature information.

3. The method for generating an interface skin of an in-vehicle system according to claim 2, characterized in that: The performing intent analysis based on the image information to obtain interface layout intent information includes: Performing image recognition on the image information to obtain emotional state information corresponding to the user; Determining a target interface layout attribute corresponding to the emotional state information; The interface layout intention information is generated based on the target interface layout attributes.

4. The method for generating an interface skin of an in-vehicle system according to claim 2, characterized in that: The performing of intention analysis based on the user voice information to obtain the theme style intention information includes: Performing voice recognition on the user voice information to obtain voice text information; Extracting topic keywords from the voice text information; Based on the topic keywords, the topic intention information is generated.

5. The method for generating an interface skin of an in-vehicle system according to claim 4, characterized in that: The generating the topic style intention information based on the topic style keyword includes: Determine whether the theme keyword is empty; When the theme keyword is empty, obtaining the historical theme information corresponding to the user, and generating the theme intention information according to the historical theme information; In the case that the theme keyword is not empty, the theme intention information is generated according to the target theme attribute corresponding to the theme keyword.

6. The method for generating an interface skin of an in-vehicle system according to claim 2, characterized in that: The performing feature analysis on the music playing information to obtain rhythm feature information includes: Performing feature analysis on the music playing information to obtain rhythm features and emotional features; Determining target rhythm attributes according to the rhythm features and the emotional features; The rhythm feature information is generated based on the target rhythm attribute.

7. The method for generating an interface skin of a vehicle-mounted system according to claim 6, characterized in that: Determining the target rhythm attribute according to the rhythm feature and the emotional feature includes: Determining a rhythm attribute corresponding to the rhythm feature; The target rhythm attribute is determined according to the rhythm attribute and in combination with the preset tone attribute corresponding to the emotional feature.

8. The method for generating an interface skin of a vehicle-mounted system according to any one of claims 1 to 7, characterized in that: The determining of the interface skin characteristic information based on the skin changing intention information includes: Extracting interface layout intention information, theme style intention information and rhythm feature intention information from the skin-changing intention information; Determine a target interface layout attribute corresponding to the interface layout intention information; Determine a target theme attribute corresponding to the theme intent information; Determining a target rhythm attribute corresponding to the rhythm feature intention information; Based on the target interface layout attributes, the target theme style attributes and the target rhythm attributes, skin characteristic fusion is performed to obtain the interface skin characteristic information.

9. An interface skin generating device for a vehicle-mounted system, characterized in that: include: The acquisition module is used to obtain the image information and user voice information collected by the vehicle system An intention analysis module, used to perform intention analysis based on the image information and the user voice information in combination with the music playing information of the vehicle-mounted system to obtain the user's skin-changing intention information; A determination module, used to determine interface skin characteristic information based on the skin change intention information; The interface skin generation module is used to generate the interface skin according to the interface characteristic skin property information to obtain the target interface skin corresponding to the vehicle system.

10. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the interface skin generation method of the vehicle-mounted system described in any one of claims 1-8 when executing the program stored in the memory.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating an interface skin of an in-vehicle system according to any one of claims 1 to 8 is implemented.

12. A vehicle, characterized in that: The vehicle comprises the interface skin generating device of the vehicle-mounted system according to claim 9.

Images