Method and system for progressive artificial intelligence assistant avatar appearance generation

Abstract

A method and system for progressive artificial intelligence assistant avatar appearance generation is provided. The method includes: initially collecting user prompts and user facial information; initially generating the avatar appearance based on both initially collected user cues and user facial information, the user facial information occupying an initial proportion in the initial generation compared to the user facial information and the user cues; and according to a predetermined rule, recollecting the user face information to update the avatar appearance. With each update, the proportion of the recollected user face information in the update is gradually increased compared with the recollected user face information and the user prompt, and does not exceed a predetermined target proportion.

Description

Technical Field

[0001] The present invention relates to artificial intelligence assistants, and more particularly, to methods and systems for progressive artificial intelligence assistant avatar appearance generation. Background Art

[0002] With the development of AIGC (artificial intelligence generated content), the application of artificial intelligence is becoming increasingly widespread. In the automotive industry, intelligent personal assistants (IPAs) have been developed for in-vehicle systems, capable of interacting with users in real time to provide various services. In some in-vehicle applications, IPAs avatars (e.g., instantiated animated characters displayed on the vehicle's display) can provide users with a humanized experience.

[0003] However, currently, IPA avatars can only provide a limited amount of expressive feedback to users in vehicles. This is because the avatar's expressions are predefined and its appearance lacks the expressiveness of a real human. Furthermore, the avatar's appearance cannot be customized and can sometimes appear stiff and unpleasant, impacting the user experience. Summary of the Invention

[0004] This Summary is provided to introduce some concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0005] According to one embodiment of the present invention, a method and system for progressively generating an avatar appearance for an artificial intelligence assistant is provided. The method includes: initially collecting user prompts and user facial information; initially generating the avatar appearance based on both the initially collected user prompts and user facial information, wherein the user facial information accounts for an initial proportion of the user facial information and the user prompts in the initial generation; and re-collecting user facial information according to predetermined rules to update the avatar appearance. With each update, the proportion of the re-collected user facial information in the update relative to the re-collected user facial information and the user prompts gradually increases, without exceeding a predetermined target proportion.

[0006] According to another embodiment of the present invention, a system for progressively generating an avatar appearance for an artificial intelligence assistant is provided, comprising: an information collection module and an avatar appearance generation module. The information collection module is configured to: initially collect user prompts and user facial information; and recollect the user facial information according to predetermined rules. The avatar appearance generation module is configured to initially generate an avatar appearance based on both the initially collected user prompts and user facial information, wherein the user facial information occupies an initial proportion in the initial generation compared to the user facial information and the user prompts; and update the avatar appearance based on the recollected user facial information and the user prompts. With each update, the proportion of the recollected user facial information in the update compared to the recollected user facial information and the user prompts gradually increases without exceeding a predetermined target proportion.

[0007] These and other features and advantages will become apparent from reading the following detailed description and referring to the associated drawings.It is to be understood that both the foregoing general description and the following detailed description are illustrative only and are not restrictive of the aspects claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order that the manner in which the above-mentioned features of the present invention are understood in detail, a more particular description of the contents briefly summarized above may be given with reference to various embodiments, some aspects of which are illustrated in the accompanying drawings. It should be noted, however, that the accompanying drawings illustrate only certain typical aspects of the invention and are not to be considered limiting of its scope, as the description may admit to other equally effective aspects.

[0009] Figure 1 An architectural diagram of an environment 100 for progressive artificial intelligence assistant avatar appearance generation according to one embodiment of the present invention is shown;

[0010] Figure 2 An architectural diagram of a system 200 for progressively generating an artificial intelligence assistant avatar appearance according to one embodiment of the present invention is shown;

[0011] Figure 3 A trend graph showing changes in the proportion of user facial information in the initial generation and subsequent updates of an avatar's appearance according to one embodiment of the present invention;

[0012] Figure 4 A flowchart of a method 400 for progressive artificial intelligence assistant avatar appearance generation according to one embodiment of the present invention is shown; and

[0013] Figure 5 A block diagram of an exemplary computing device according to one embodiment of the present invention is shown. DETAILED DESCRIPTION

[0014] The present invention will be described in detail below with reference to the accompanying drawings, and the features of the present invention will be further apparent in the following specific description.

[0015] The following detailed description refers to the accompanying drawings that illustrate exemplary embodiments of the present invention. However, the scope of the present invention is not limited to these embodiments, but is defined by the appended claims. Therefore, embodiments other than those shown in the drawings, such as modifications of the illustrated embodiments, are still encompassed by the present invention.

[0016] References in this specification to "one embodiment," "an embodiment," "an example embodiment," etc., mean that the embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes that particular feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it should be understood that it is within the knowledge of those skilled in the relevant art that the particular feature, structure, or characteristic can be implemented in conjunction with other embodiments, whether or not explicitly described.

[0017] For ease of explanation, this document only describes in detail an embodiment in which the technical solution of the present invention is applied to a "vehicle." However, those skilled in the art will fully understand that the technical solution of the present invention can be applied to any means of transportation, such as trains, subways, airplanes, and ships. Unless otherwise specified, the term "A or B" used in this specification refers to "A and B" and "A or B," and does not mean that A and B are exclusive.

[0018] Terminology Introduction:

[0019] IVI (In-Vehicle Infotainment) is an integrated in-vehicle information processing system that utilizes a dedicated onboard central processor, a vehicle bus system, and internet services. IVI enables a range of applications, including 3D navigation, real-time traffic conditions, IPTV, assisted driving, fault detection, vehicle information, vehicle body control, mobile office, wireless communications, and online entertainment, significantly enhancing the vehicle's electronic, networked, and intelligent capabilities.

[0020] AIaaS (Artificial Intelligence as a Service) is a cloud-based offering that allows individuals and organizations to take advantage of AI tools and services without having to build and maintain AI infrastructure and expertise in-house.

[0021] Overall, the solution of this application enables the intelligent personal assistant avatar to present a more human-like appearance. Specifically, in this application, the appearance of the intelligent personal assistant avatar is customized based on user-provided prompts and the user's actual facial information. Furthermore, the appearance of the intelligent personal assistant avatar can be regularly changed based on the increase in mileage and changes in the user's facial information.

[0022] Figure 1 An architectural diagram of an environment 100 for progressive artificial intelligence assistant avatar (hereinafter referred to as “avatar”) appearance generation according to one embodiment of the present invention is shown.

[0023] In this environment 100, when a user initially generates an avatar appearance (e.g., when registering the in-vehicle system, when enabling the avatar appearance generation function, when first updating the default avatar appearance of the in-vehicle system, etc.), the user can interact with the vehicle's IVI service 101 (e.g., through the microphone 105 and the speaker 106) to provide the IVI service 101 with prompts related to avatar appearance generation. These prompts can indicate the user's customization preferences for the avatar appearance. In addition, the in-vehicle camera 104 can capture the user's facial information and provide the facial information to the IVI service 101. The IVI service 101 can then provide both the collected user prompts and the user's facial information to the AlaaS service 102. The AlaaS service 102 can generate an avatar appearance based on the received user prompts and the user's facial information, and return the generated avatar appearance to the IVI service 101 for presentation to the user on the display 103. After the initial generation of the avatar appearance, the IVI service 101 can re-acquire the user's facial information according to certain rules and pass it to the AlaaS service 102, so that the AlaaS service 102 can gradually increase the weight of the user's facial information when generating the updated avatar appearance, making the avatar appearance closer and closer to the user himself, providing the user with a sense of intimacy.

[0024] Figure 2 An architectural diagram of a system 200 for progressive artificial intelligence assistant avatar appearance generation according to one embodiment of the present invention is shown.

[0025] See also Figure 2 It can be seen that system 200 primarily includes an information collection module 201 and an avatar appearance generation module 202. Those skilled in the art will readily appreciate that the above module division is merely for the sake of clarity. The functionality of one or more of the above modules may be combined into a single module or split into multiple modules. Furthermore, one or more of the above modules may be implemented using software, hardware, or a combination thereof. Furthermore, data flow between modules may be performed using methods known in the art and is not covered by this disclosure.

[0026] Specifically, the information collection module 201 can be instantiated as the IVI service 101 described above, and the avatar appearance generation module 202 can be instantiated as the AlaaS service 102 described above. In practice, the information collection module 201 can communicate with the AlaaS service 102 via communication technologies such as the Internet.

[0027] According to one embodiment of the present invention, the information collection module 201 may be configured to collect user-provided prompts and user facial information. In one example, the user may provide prompts through voice interaction, touch interaction with the display screen, gesture interaction, etc. These prompts may, for example, indicate preferences regarding the avatar's appearance. For example, these preferences may include, but are not limited to: the category of the avatar's appearance (e.g., cartoon, animal, robot, etc.), the avatar's human-like personality (e.g., gentle, optimistic, reserved, etc.), the avatar's clothing type (e.g., casual, formal, sportswear, pants, skirt, etc.), and the avatar's physical characteristics (e.g., thin, overweight, muscular, long hair, short hair, etc.). The above preferences are merely illustrative, and a variety of preferences related to avatar appearance can be provided for use by AI technology. In practice, these prompts may or may not match the user's actual characteristics. Through these prompts, the generated avatar's appearance is more customized to the user.

[0028] In another example, the information collection module 201 may call an onboard camera to scan the user's face to capture the user's facial information.

[0029] According to one embodiment of the present invention, the information collection module 201 may be configured to re-collect the user's facial information according to predetermined rules. In one example, the predetermined rules may include, but are not limited to: vehicle mileage reaching a predetermined distance (e.g., every 1,000 miles); reaching a predetermined time (e.g., every three months); receiving a user-initiated avatar appearance update request, etc.

[0030] According to one embodiment of the present invention, the avatar appearance generation module 202 may be configured to generate the avatar appearance based on the user prompts and the user's facial information collected by the information collection module 201. In one example, when the avatar appearance of the user is generated for the first time, the role played by the user's facial information in generating the avatar appearance may have a predetermined initial ratio. For example, user facial information / (user prompts + user facial information) = a predetermined initial ratio (e.g., 50%). Afterwards, based on the predetermined rules as described above, with each re-collection of the user's facial information, the role played by the re-collected user facial information in updating the user's avatar appearance becomes increasingly higher until it approaches a predetermined target ratio (e.g., 90%).

[0031] In one example, the predetermined initial ratio and the predetermined target ratio may be set by a user, by a manufacturer, etc., and the specific setting method is not limited by the present invention.

[0032] For example, Figure 3 A trend chart shows the changing proportion of user facial information during the initial generation and subsequent updates of an avatar's appearance, according to one embodiment of the present invention. For example, point A represents a predetermined initial proportion, and point B represents a predetermined target proportion. As vehicle mileage increases, the proportion of user facial information gradually increases from the initial proportion until it approaches the predetermined target proportion. As the proportion of user facial information increases, the proportion of user prompts collected during the initial generation of the avatar's appearance decreases during subsequent updates of the avatar's appearance, causing the avatar's appearance to increasingly resemble the user's physical characteristics. That is, user prompts are only collected from the user during the initial generation of the avatar's appearance. With each subsequent update of the avatar's appearance, prompts are no longer collected from the user, and only the user's facial information is recollected.

[0033] For example, assuming the predetermined initial ratio is 50%, then in the initial generation of the avatar appearance, the initially collected user facial information accounts for 50% of the total of the user facial information and user prompts. When the vehicle's mileage reaches 1,000 miles for the first time, the vehicle may recollect the user's facial information and update the initially generated avatar appearance. In this first update, the ratio of the newly collected user facial information to the total of the newly collected user facial information and the initially collected user prompts may increase compared to the initial ratio, for example, to 60%. Thereafter, when the vehicle's mileage reaches 1,000 miles for the second time, the vehicle may recollect the user's facial information for a second time and update the avatar appearance after the first update. In this second update, the ratio of the newly collected user facial information to the total of the newly collected user facial information and the initially collected user prompts may continue to increase, for example, to 65%. After that, every time the vehicle reaches 1,000 miles, the avatar appearance after the previous update can be updated again, and the proportion of user facial information collected in each update gradually increases until it approaches the predetermined target proportion (for example, 90%).

[0034] The way in which the proportion of user facial information increases in each update can be defined according to actual needs, for example, linear, step-by-step, curved, etc.

[0035] Figure 4 A flowchart of a method 400 for progressive artificial intelligence assistant avatar appearance generation according to one embodiment of the present invention is shown.

[0036] At 405, user prompts and user facial information are initially collected, wherein the user prompts may indicate the user's preference for the avatar appearance.

[0037] At 410 , an avatar appearance is initially generated based on both the initially collected user prompts and the user facial information, wherein the user facial information accounts for an initial proportion of the user facial information and the user prompts in the initial generation.

[0038] At 415 , according to a predetermined rule, the user's facial information is recollected to update the avatar's appearance, wherein with each update, the proportion of the recollected user's facial information in the update relative to the recollected user's facial information and the user prompt is progressively increased without exceeding a predetermined target proportion.

[0039] Figure 5 A block diagram of an exemplary computing device according to one embodiment of the present invention is shown, which is one example of a hardware device applicable to various aspects of the present invention.

[0040] refer to Figure 5 A computing device 500 will now be described, which is an example of a hardware device applicable to various aspects of the present invention. Computing device 500 can be any machine configured to perform processing and / or computing, and can be, but is not limited to, a workstation, server, desktop computer, laptop computer, tablet computer, personal digital assistant, smartphone, in-vehicle computer, or any combination thereof. The various methods / apparatus / server / client devices described above can be implemented in whole or in part by computing device 500 or similar devices or systems.

[0041] The computing device 500 may include components that can be connected or communicated via one or more interfaces and a bus 502. For example, the computing device 500 may include a bus 502, one or more processors 504, one or more input devices 506, and one or more output devices 508. The one or more processors 504 may be any type of processor and may include, but are not limited to, one or more general-purpose processors and / or one or more special-purpose processors (e.g., specialized processing chips). The input device 506 may be any type of device capable of inputting information to the computing device and may include, but are not limited to, a mouse, keyboard, touch screen, microphone, and / or remote controller. The output device 508 may be any type of device capable of presenting information and may include, but are not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The computing device 500 may also include or be connected to a non-transient storage device 510, which may be any storage device that is non-transient and capable of storing data, and may include, but is not limited to, a disk drive, an optical storage device, a solid-state memory, a floppy disk, a floppy disk, a hard disk, a magnetic tape or any other magnetic medium, an optical disk or any other optical medium, a ROM (read-only memory), a RAM (random access memory), a cache memory, and / or any memory chip or cassette, and / or any other medium from which a computer can read data, instructions, and / or code. The non-transient storage device 510 may be detachable from the interface. The non-transient storage device 510 may have data / instructions / code for implementing the above-described methods and steps. The computing device 500 may also include a communication device 512. The communication device 512 can be any type of device or system that can communicate with internal devices and / or with a network and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication device and / or a chipset, such as a Bluetooth device, an IEEE 1302.11 device, a WiFi device, a WiMax device, a cellular communication device and / or the like.

[0042] When the computing device 500 is used as an in-vehicle device, it can also be connected to external devices (e.g., a GPS receiver, sensors for sensing various environmental data (such as accelerometers, wheel speed sensors, gyroscopes, etc.)). In this way, the computing device 500 can receive, for example, positioning data and sensor data indicating the vehicle's tread condition. When the computing device 500 is used as an in-vehicle device, it can also be connected to other devices for controlling the vehicle's travel and operation (e.g., engine systems, wipers, anti-lock brake systems, etc.).

[0043] In addition, the non-transitory storage device 510 may contain map information and software components so that the processor 504 can implement route guidance processing. In addition, the output device 506 may include a display for displaying an avatar appearance, displaying a map, displaying a vehicle's location marker, and displaying an image indicating the vehicle's driving status. The output device 506 may also include a speaker or headphone jack for audio guidance.

[0044] The bus 502 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus. Specifically, for in-vehicle devices, the bus 502 may also include a Controller Area Network (CAN) bus or other architectures designed for automotive applications.

[0045] The computing device 500 may also include a working memory 514 , which may be any type of working memory capable of storing instructions and / or data that facilitate the operation of the processor 504 and may include, but is not limited to, random access memory and / or read-only storage devices.

[0046] Software components may be located in the working memory 514, including but not limited to an operating system 516, one or more application programs 518, drivers, and / or other data and code. Instructions for implementing the aforementioned methods and steps may be included in the one or more application programs 518, and the modules, units, and components of the aforementioned various devices / servers / client devices may be implemented by the processor 504 reading and executing the instructions of the one or more application programs 518.

[0047] It should also be appreciated that variations may be made based on specific needs. For example, custom hardware may also be used, and / or specific components may be implemented in hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. In addition, connections to other computing devices, such as network input / output devices, etc., may be employed. For example, some or all of the disclosed methods and apparatus may be implemented using logic and algorithms according to the present invention using programming hardware (e.g., programmable logic circuits including field programmable gate arrays (FPGAs) and / or programmable logic arrays (PLAs)) in assembly language or a hardware programming language (e.g., VERILOG, VHDL, C++).

[0048] Although various aspects of the present invention have been described so far with reference to the accompanying drawings, the above-described methods, systems, and devices are merely examples, and the scope of the present invention is not limited to these aspects, but is defined solely by the appended claims and their equivalents. Various components may be omitted or replaced by equivalent components. In addition, the steps described may be performed in an order different from that described in the present invention. Furthermore, the various components may be combined in various ways. It is also important to note that as technology develops, many of the components described may be replaced by equivalent components that become available later.

Claims

1. A method for progressively generating an avatar appearance for an artificial intelligence assistant, comprising: Initially collecting user prompts and user facial information; Initially generating the avatar appearance based on both the initially collected user prompts and the user facial information, wherein the user facial information accounts for an initial proportion of the user facial information and the user prompts in the initial generation; as well as According to predetermined rules, the user's facial information is collected again to update the avatar appearance.

2. The method according to claim 1, wherein With each update, the proportion of the re-collected user facial information in the update compared to the re-collected user facial information and the user prompt is gradually increased without exceeding a predetermined target proportion.

3. The method according to claim 1, wherein The user prompt indicates a user preference for the avatar's appearance.

4. The method according to claim 3, wherein The preference includes at least one of the following: a category of the avatar appearance, a humanoid personality of the avatar appearance, a clothing type of the avatar appearance, and a physical feature of the avatar appearance.

5. The method according to claim 1, wherein The predetermined rule includes at least one of the following: the vehicle mileage reaches a predetermined distance; a predetermined time is reached; the user actively initiates an avatar appearance update request.

6. A system for progressively generating an avatar appearance for an artificial intelligence assistant, comprising: An information collection module, wherein the information collection module is configured to: Initially collecting user prompts and user facial information; Re-collect user facial information according to predetermined rules; an avatar appearance generation module, wherein the avatar appearance generation module is configured to: Initially generating the avatar appearance based on both the initially collected user prompts and the user facial information, wherein the user facial information accounts for an initial proportion of the user facial information and the user prompts in the initial generation; as well as The avatar appearance is updated based on the re-collected user facial information and the user prompt.

7. The system according to claim 6, wherein: With each update, the proportion of the re-collected user facial information in the update compared to the re-collected user facial information and the user prompt is gradually increased without exceeding a predetermined target proportion.

8. The system according to claim 6, wherein: The user prompt indicates a user preference for the avatar's appearance.

9. The system according to claim 6, wherein: The predetermined rule includes at least one of the following: the vehicle mileage reaches a predetermined distance; a predetermined time is reached; the user actively initiates an avatar appearance update request.

10. The system according to claim 6, wherein: The information collection module is the in-vehicle infotainment system IVI, and the avatar appearance generation module is artificial intelligence as a service AlaaS.

Images