Artificial intelligence charging device and charging method

Abstract

This invention provides an artificial intelligence charging device and charging method, relating to the field of charging technology. The device includes: an input interface, an output interface, a power management unit, and a computing and communication unit. The input interface is coupled to the power management unit, providing AC power from an external power source to the power management unit. The power management unit is coupled to the output interface and the computing and communication unit, with the output interface connected to a terminal device. The power management unit converts the AC power into DC power, provides the DC power to the terminal device through the output interface, and supplies power to the computing and communication unit. The computing and communication unit is coupled to the output interface, responding to a first computing service request sent by the terminal device, processing the first computing service request, and sending the processing result to the terminal device. This charging device not only meets the efficient charging needs in mobile scenarios but also provides localized AI services to terminal devices, realizing a localized computing node in mobile scenarios.

Description

Technical Field

[0001] This invention relates to the field of charging technology, and in particular to an artificial intelligence charging device and charging method. Background Technology

[0002] With the widespread adoption of mobile smart devices and the rapid iteration of Artificial Intelligence (AI) technology, AI applications are migrating from the cloud to the edge. The deep integration of edge computing (as opposed to cloud computing, where data collection and analysis occur near the local device and network where the data is generated) and AI is driving the evolution of smart terminals towards "edge-side intelligence." More and more data will be processed at the edge, with AI inference tasks accounting for a significant portion. Breakthroughs in lightweight models have made it possible to run complex AI tasks on small devices, while the widespread adoption of the Type-C interface (a USB interface standard primarily used in smart mobile devices) provides a unified standard for power supply and data transmission between multiple devices. It supports up to 130W of power transmission and 10Gbps data rates, simultaneously meeting the power supply needs of laptops and the data interaction requirements of AI services.

[0003] However, existing mobile devices face a dual challenge when running AI applications: on the one hand, the local computing power of terminals such as mobile phones and laptops is limited, and running large models requires a lot of memory and leads to shortened battery life; on the other hand, they are heavily dependent on network stability, and services are interrupted in weak or no network environments. For example, when users use programming assistance or document processing functions in weak or no network scenarios such as high-speed rail or outdoors, network latency often affects efficiency. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, embodiments of the present invention provide an artificial intelligence charging device and a charging method.

[0005] In a first aspect, embodiments of the present invention provide an artificial intelligence charging device, including: an input interface, an output interface, a power management unit, and a computing and communication unit;

[0006] The input interface is coupled to the power management unit, and the input interface provides AC power from an external power source to the power management unit.

[0007] The power management unit is coupled to the output interface, which is connected to the terminal device; the power management unit converts the AC power into DC power and provides the DC power to the terminal device through the output interface;

[0008] The power management unit is also coupled to the computing and communication unit, and the power management unit supplies power to the computing and communication unit;

[0009] The computing power and communication unit is coupled to the output interface. In response to receiving a first computing power service request sent by the terminal device through the output interface, the computing power and communication unit processes the first computing power service request and sends the processing result to the terminal device through the output interface.

[0010] Optionally, the computing power and communication unit includes a computing power unit, a storage unit, and a wired communication interface. The computing power unit is coupled to the storage unit and the wired communication interface, respectively. The storage unit stores at least one model, and the wired communication interface is coupled to the output interface.

[0011] In response to receiving a first computing power service request sent by the terminal device through the output interface, the computing power unit parses the first computing power service request, calls a target model corresponding to the first computing power service request from at least one model stored in the storage unit, processes the first computing power service request using the target model, and sends the processing result to the terminal device through the output interface.

[0012] Optionally, the computing power and communication unit includes a wireless communication interface; the computing power and communication unit is coupled to the terminal device through the wireless communication interface; in response to receiving a second computing power service request sent by the terminal device through the wireless communication interface, the computing power and communication unit processes the second computing power service request and sends the processing result to the terminal device through the wireless communication interface.

[0013] Optionally, the power management unit adjusts the power supply to the terminal device according to the working status of the computing and communication unit.

[0014] Optionally, the power management unit detects the load and / or power consumption of the computing and communication unit, and adjusts the power supply to the terminal device according to the load and / or power consumption.

[0015] Optionally, the AI ​​charging device further includes a human-computer interaction unit coupled to the power management unit, the power management unit supplying power to the human-computer interaction unit; the human-computer interaction unit responds to a received status query command by outputting data corresponding to the status query command.

[0016] Optionally, the human-computer interaction unit is coupled to the computing power and communication unit;

[0017] The human-computer interaction unit responds to the received function management instruction and manages the computing power services provided by the computing power and communication unit according to the function management instruction.

[0018] Optionally, the human-computer interaction unit includes a screen and / or buttons.

[0019] Optionally, the AI ​​charging device includes a battery coupled to the power management unit; the power management unit converts the DC power provided by the battery and outputs it to the terminal device.

[0020] Optionally, the power management unit includes an input stage unit, a power conversion stage unit, a status detection unit, and a status management unit;

[0021] The input stage unit is coupled to the input interface. The input stage unit receives AC power from the external power source or DC power from the battery and filters out interference from the AC power or DC power.

[0022] The power conversion stage unit is coupled to the input stage unit, the computing power and communication unit, and the output interface. The power conversion stage unit converts the AC or DC power output by the input stage unit to power the computing power and communication unit and the terminal device, respectively.

[0023] The state detection unit is coupled to the state management unit. The state detection unit collects specified information from the artificial intelligence charging device and sends the specified information to the state management unit.

[0024] The status management unit manages the working status of the AI ​​charging device based on the specified information sent by the status detection unit.

[0025] Optionally, the status detection unit detects the working status of the computing power and communication unit and sends the working status of the computing power and communication unit to the status management unit; the status management unit adjusts the power supply to the terminal device according to the working status of the computing power and communication unit.

[0026] And / or,

[0027] The status detection unit detects the temperature and / or current information of the power conversion stage unit and sends the temperature and / or current information to the status management unit; the status management unit adjusts the operating status of the power conversion stage unit according to the temperature and / or current information.

[0028] Secondly, embodiments of the present invention also provide a charging method, applied to the artificial intelligence charging device described in any embodiment of the present invention, the method comprising:

[0029] In response to the coupling of the input interface of the AI ​​charging device to an external power source and the coupling of the output interface to a terminal device, the AI ​​charging device charges the terminal device.

[0030] The AI ​​charging device responds to receiving a first computing power service request sent by the terminal device, processes the first computing power service request, and sends the processing result to the terminal device.

[0031] Optionally, the method further includes: in response to the AI ​​charging device being coupled to the terminal device via a wireless connection, the AI ​​charging device receiving a second computing power service request sent by the terminal device via the wireless connection, processing the second computing power service request, and sending the processing result to the terminal device via the wireless connection.

[0032] Optionally, the method further includes: the AI ​​charging device adjusting the power supply to the terminal device according to the working state of processing the first computing power service request.

[0033] Optionally, the method further includes: the AI ​​charging device responding to receiving a status query instruction by outputting data corresponding to the status query instruction.

[0034] Optionally, the method further includes: the AI ​​charging device responding to receiving a function management instruction, and managing the computing power services provided by the AI ​​charging device according to the function management instruction.

[0035] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects:

[0036] The artificial intelligence charging device provided in this embodiment of the invention includes: an input interface, an output interface, a power management unit, and a computing and communication unit; the input interface is coupled to the power management unit, and the input interface provides AC power input from an external power source to the power management unit; the power management unit is coupled to the output interface, and the output interface is connected to a terminal device; the power management unit converts AC power into DC power and provides DC power to the terminal device through the output interface; the power management unit is also coupled to the computing and communication unit, and the power management unit supplies power to the computing and communication unit; the computing and communication unit is coupled to the output interface, and in response to receiving a first computing power service request sent by the terminal device through the output interface, the computing and communication unit processes the first computing power service request and sends the processing result to the terminal device through the output interface. This invention restructures the function of charging devices for mobile terminals, such as chargers and power banks (also known as power banks), upgrading them from simple "power conversion devices" to "power conversion devices + AI computing nodes." This not only meets the high-efficiency charging needs in mobile scenarios but also provides localized AI services for terminal devices. It realizes localized computing nodes in mobile scenarios, solves the problem of service interruption in weak network / network environments, breaks through the functional boundaries of traditional charging devices, and resolves the contradiction between computing power and battery life of terminal devices. Furthermore, as a frequently used accessory for terminal devices, the functional expansion of charging devices will significantly improve user experience and user stickiness. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0038] Figure 1 A schematic diagram of the architecture of an artificial intelligence charging device according to an embodiment of the present invention is shown;

[0039] Figure 2 A flowchart illustrating a charging method for an artificial intelligence charging device according to an embodiment of the present invention is shown;

[0040] Figure 3 A schematic diagram of the architecture of an artificial intelligence charging device according to another embodiment of the present invention is shown;

[0041] Figure 4 A schematic diagram of the architecture of an artificial intelligence charging device according to another embodiment of the present invention is shown;

[0042] Figure 5 A schematic diagram illustrating the application of an artificial intelligence charging device according to an embodiment of the present invention is shown;

[0043] Figure 6 A schematic diagram of a sub-process of a charging method for an artificial intelligence charging device according to an embodiment of the present invention is shown;

[0044] Figures 7A-7D A schematic diagram illustrating an application scenario of the artificial intelligence charging device according to an embodiment of the present invention is shown. Detailed Implementation

[0045] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0046] With the widespread adoption of smart mobile devices such as AI smartphones and AI glasses, user demand for mobile computing power continues to grow, and more and more users expect smart mobile devices to provide a more intelligent interactive experience. Currently, charging devices such as chargers and power banks, based on gallium nitride (GaN) materials, have achieved high-power fast charging outputs of over 65W while maintaining a compact size. The focus on intelligent features is mainly on optimizing charging strategies, such as dynamic power allocation and battery health monitoring. However, these products are still limited to a "passive power supply" role and fail to fully utilize the computing power resources required in mobile scenarios.

[0047] In view of this, the embodiments of the present invention reconstruct the function of charging devices for smart mobile terminals, such as chargers and power banks (also known as power banks), upgrading them from a single "power conversion device" to a "power conversion device + AI computing node." This not only meets the efficient charging needs in mobile scenarios but also provides localized AI services for terminal devices, realizing a localized computing node in mobile scenarios. This solves the problem of service interruption in weak network / network environments, breaks through the functional boundaries of traditional charging devices, and resolves the contradiction between computing power and battery life of terminal devices. Furthermore, as a frequently used accessory for terminal devices, the functional expansion of charging devices will significantly improve user experience and user stickiness.

[0048] Figure 1 A schematic diagram of the structure of an artificial intelligence charging device according to an embodiment of the present invention is shown. Figure 1 As shown, the AI ​​charging device includes an input interface, an output interface, a power management unit, and a computing and communication unit.

[0049] The AI-powered charging device connects to an external power source via an input interface to receive alternating current (AC). The input interface is coupled to a power management unit (PMU), which provides the AC power from the external power source. The PMU is coupled to an output interface, which connects to the terminal device. The PMU converts the AC power from the external power source into direct current (DC) and provides the DC power to the terminal device through the output interface to charge the device. Optional examples include mains power or a power source capable of providing 100V-240V. The terminal device can be a mobile device such as a smartphone, tablet, or headset. The output interface can be a USB interface or a Type-C interface.

[0050] The power management unit is also coupled to the computing and communication unit. The power management unit supplies power to the computing and communication unit.

[0051] The computing and communication unit is coupled to the output interface. The output interface not only provides a channel for charging the terminal device, but also a data interaction channel. For example, in response to receiving a first computing service request sent by the terminal device through the output interface, the computing and communication unit processes the first computing service request and sends the processing result back to the terminal device through the output interface.

[0052] In this embodiment of the invention, the power management unit is responsible for converting the power provided by the external power source into DC power and outputting it to the terminal device. The computing and communication unit provides artificial intelligence computing power services. The artificial intelligence charging device supplies power to the terminal device through its output interface and also provides computing power services to the terminal device.

[0053] Figure 2 A flowchart illustrating a charging method for an artificial intelligence charging device according to an embodiment of the present invention is shown. Figure 2 As shown, the method includes:

[0054] Step S201: In response to the coupling of the input interface of the AI ​​charging device with an external power source and the coupling of the output interface with a terminal device, the AI ​​charging device charges the terminal device.

[0055] Step S202: The AI ​​charging device responds to the first computing power service request sent by the terminal device, processes the first computing power service request, and sends the processing result to the terminal device.

[0056] When a terminal device is connected to an AI charging device, the terminal device sends a first computing power service request (e.g., a code-assisted generation request) to the AI ​​charging device. This first computing power service request is transmitted to the computing power and communication unit of the AI ​​charging device through an output interface. The computing power and communication unit processes the first computing power service request (e.g., generates code snippets) and feeds back the processing result (e.g., the generated code snippets) to the terminal device through the output interface.

[0057] The AI-powered charging device provided in this invention restructures the functions of charging devices for smart mobile terminals, such as chargers and power banks (also known as power banks), upgrading them from a single "power conversion device" to a "power conversion device + AI computing node." This not only meets the efficient charging needs in mobile scenarios but also provides localized AI services to terminal devices, realizing a localized computing node in mobile scenarios. This solves the problem of service interruption in weak network / network environments, breaks through the functional boundaries of traditional charging devices, and resolves the contradiction between computing power and battery life of terminal devices. Furthermore, as a frequently used accessory for terminal devices, the functional expansion of the charging device will significantly improve user experience and user stickiness.

[0058] In an optional embodiment, the power management unit includes an input stage unit, a power conversion stage unit, a status detection unit, and a status management unit. The input stage unit is coupled to an input interface, the power conversion stage unit is coupled to the input stage unit, the computing and communication unit, and the output interface, and the status detection unit is coupled to the status management unit.

[0059] The input stage unit receives AC power from an external power source or DC power from a battery (with different voltages, such as 100V-240V) and filters out AC or DC interference. As an optional example, the input stage unit includes EMI filter circuitry, a rectifier bridge, and other circuitry.

[0060] The power conversion stage unit converts the AC or DC power output from the input stage unit to power the computing and communication units and terminal devices, respectively. The power conversion stage unit converts the electrical energy from the input stage unit into voltage and current that meet the device's requirements. If the input is AC, it is converted to DC (AC-DC). If the input is DC, it is converted to DC (DC-DC) through a buck or boost circuit. Optional examples of power conversion stage units include LLC resonant topologies and GaN power transistors.

[0061] The state detection unit collects specified information from the AI ​​charging device and sends this information to the state management unit. The state detection unit may include one or more sensors (e.g., temperature sensors, current sensors, etc.) to collect specified information (e.g., temperature information, current information) and send the collected information to the state management unit.

[0062] The state management unit manages the operating state of the AI ​​charging device based on the specified information sent by the state detection unit. As an optional example, the state management unit may include a power management chip, which manages the operating state of the AI ​​charging device based on the information transmitted by the state detection unit, such as adjusting the operating state of the power conversion stage unit, thereby realizing functions such as overvoltage protection, overcurrent protection, overheat protection, and dynamic power adjustment.

[0063] In an optional embodiment, the computing and communication unit includes a computing unit, a storage unit, and a wired communication interface. The computing unit is coupled to both the storage unit and the wired communication interface. The storage unit stores at least one model, and the wired communication interface is coupled to an output interface. In response to receiving a first computing service request sent by a terminal device through the output interface, the computing unit parses the request, retrieves a target model corresponding to the request from the at least one model stored in the storage unit, processes the request using the target model, and sends the processing result to the terminal device through the output interface. As an optional example, the computing unit may be an AI computing chip, the storage unit may be a storage chip, and the wired communication interface may be a USB interface or a Type-C interface. In other optional embodiments, the computing unit, storage unit, and wired communication interface may be a single system-on-a-chip integrating storage and communication functions. The model stored in the storage unit can provide AI computing services and handle AI inference tasks. As an optional example, the model stored in the storage unit can perform tasks including but not limited to code generation, summary generation, image person recognition, and text translation.

[0064] In optional embodiments, the computing and communication unit includes a wireless communication interface, such as a Wi-Fi interface or a Bluetooth interface. The computing and communication unit can connect to the terminal device and interact with it via the wireless communication interface. For example, the computing and communication unit is coupled to the terminal device via the wireless communication interface. In response to receiving a second computing service request from the terminal device via the wireless communication interface, the computing and communication unit processes the second computing service request and sends the processing result back to the terminal device via the wireless communication interface. It is worth noting that while the AI ​​charging device can connect to and interact with the terminal device via the wireless communication interface, it cannot charge the terminal device via the wireless communication interface.

[0065] In an optional embodiment, the power management unit adjusts the power supply to the terminal device based on the operating status of the computing and communication units, thereby intelligently balancing charging power and computing power consumption. During the inference calculation process of the computing and communication units, the power management unit, for example, a status detection unit, detects the operating status of the computing and communication units, such as detecting the computing load and power consumption of the computing and communication units, and sends the computing load and power consumption information of the computing and communication units to the status management unit. The status management unit automatically adjusts the charging power to the terminal device based on the computing load and power consumption of the computing and communication units. For example, when the load of the computing and communication units is less than a threshold, the charging power of the power management unit to the terminal device is a first preset value. When the load of the computing and communication units is greater than or equal to the threshold, the charging power of the power management unit to the terminal device is a second preset value, which is less than the first preset value. Optionally, when the computing and communication units are not working, the charging power of the power management unit to the terminal device is a third preset value, which is greater than or equal to the first preset value.

[0066] The AI ​​charging device provided in this invention offers three operating modes: simultaneous charging and inference mode, standalone charging mode, and standalone inference mode. When the AI ​​charging device is connected to the terminal device via its output interface and no computing power service request is received, the AI ​​charging device operates in standalone charging mode. When the AI ​​charging device is connected to the terminal device via its output interface and receives a computing power service request from the terminal device via its output interface, the AI ​​charging device operates in simultaneous charging and inference service mode. When the AI ​​charging device is connected to the terminal device via a wireless communication interface of the computing power and communication unit, the AI ​​charging device operates in standalone inference mode.

[0067] Figure 3 A schematic diagram of the architecture of an artificial intelligence charging device according to another embodiment of the present invention is shown. Figure 3 As shown, the AI ​​charging device includes an input interface, an output interface, a power management unit, a computing and communication unit, and a human-computer interaction unit. The input interface, output interface, power management unit, and computing and communication unit can be referenced from [reference needed]. Figure 1 The embodiments shown will not be described in detail here.

[0068] The human-machine interface (HMI) unit is coupled to the power management unit, which supplies power to the HMI unit. The HMI unit enables data interaction between the user and the AI ​​charging device. For example, in response to receiving a status query command from the user, the HMI unit outputs data corresponding to the status query command. Optionally, the HMI unit can provide a screen (e.g., a touchscreen) or buttons. The user initiates a query to the AI ​​charging device via the screen or buttons. In response to detecting the user's query operation (i.e., receiving a status query command), the HMI unit displays data corresponding to the status query command on the screen, such as charging status, computing load of the computing and communication units, and device connection status. Optionally, the HMI unit can also receive voice query commands and verbally announce the query results corresponding to the voice query command.

[0069] Optionally, the human-computer interaction unit is also coupled to the computing and communication unit. Upon receiving a function management command, the human-computer interaction unit manages the computing services provided by the computing and communication unit according to the command. Users manage the computing services provided by the computing and communication unit through the human-computer interaction unit, such as updating, deleting, or adding models stored in the computing and communication unit.

[0070] Figure 4 A schematic diagram of the architecture of an artificial intelligence charging device according to another embodiment of the present invention is shown. Figure 4 As shown, the AI ​​charging device includes an input interface, an output interface, a power management unit, a computing and communication unit, a human-computer interaction unit, and a battery. The input interface, output interface, power management unit, computing and communication unit, and human-computer interaction unit can be referenced from [reference needed]. Figure 1 , Figure 3 The embodiments shown are not described in detail here to avoid repetition.

[0071] The device is coupled to the input interface and the power management unit. When the AI ​​charging device is connected to an external power source via the input interface, the power management unit converts the power from the external power source and transfers it to the battery to charge it. When the AI ​​charging device is connected to a terminal device via the output interface, the power management unit converts the DC power supplied by the battery and outputs it to the terminal device.

[0072] Figure 5 A schematic diagram illustrating the application of an artificial intelligence charging device according to an embodiment of the present invention is shown. Figure 5 In the diagram, the blue line indicates the signal path, and the red line indicates the charging path.

[0073] like Figure 5As shown, the terminal device can connect to the AI ​​charging device via an output interface, which in turn connects to the wired communication interface of the computing and communication unit. The output interface provides both a charging path and a signal path. The AI ​​charging device charges the terminal device via the charging path and interacts with it via the signal path (e.g., receiving computing service requests and responding to request results). For example, the terminal device sends a computing service request to the AI ​​charging device. This request is transmitted to the computing unit of the computing and communication unit via the output interface and the wired communication interface. The computing unit then processes the request using the model in the storage unit and sends feedback to the terminal device via the wired communication interface and the output interface.

[0074] Terminal devices can also connect to each other via the wireless communication interface of the computing and communication unit and exchange data.

[0075] The power management unit's status detection unit, such as a sensor array, transmits the collected information to the human-machine interface (HMI) module. Through the HMI module, users can query information about the AI ​​charging device, such as charging status, computing load, device connection status, current, and temperature. They can also manage the computing services provided by the computing and communication units (e.g., adding, deleting, and updating models stored in the computing and communication units). Optionally, users can also manage the power management unit through the HMI module; for example, they can send control signals to the power management unit to manage it, such as turning off the power.

[0076] The power management unit's status detection unit, such as a sensor array, transmits the collected information to the status management unit. Based on the received information, the status management unit manages the operating status of the AI ​​charging device. As an optional example, the status management unit may include a power management chip that manages the operating status of the AI ​​charging device based on the information transmitted by the status detection unit. For example, the power management chip may adjust the operating status of the power conversion stage unit to achieve functions such as overvoltage protection, overcurrent protection, overheat protection, and dynamic power adjustment.

[0077] Figure 6 A schematic diagram of a sub-process of a charging method for an artificial intelligence charging device according to an embodiment of the present invention is shown. Figure 6 In the illustrated embodiment, code generation is used as an example to explain the process by which the AI ​​charging device provides computing power services. Figure 6As shown, the user equipment sends a computing power service request (e.g., code completion) through the output interface. After receiving the request, the computing power and communication unit parses the request type, calls the corresponding model (the model is stored in the storage unit within the computing power and communication unit), obtains the result through model inference calculation (in this example, the code snippet generated by the model), and returns the result through the output interface, thus completing this user request.

[0078] During the inference computation process of the computing and communication units, the power management unit can automatically adjust the charging power to the terminal device based on the computing load and power consumption of the computing and communication units. A typical implementation is that when the load of the computing and communication units exceeds a threshold (e.g., 80%), the charging power is automatically adjusted from a first preset value (e.g., 65W) to a second preset value (e.g., 45W), thereby intelligently balancing the charging power and computing power consumption.

[0079] Figures 7A-7D This invention demonstrates the application forms of the AI ​​charging device according to embodiments of the present invention. Embodiments of the present invention support multiple AI charging devices connecting to a single terminal device to achieve multi-device collaboration and concurrent connection, and also support multiple terminal devices connecting to a single charger to achieve multi-terminal device sharing of computing resources. The AI ​​charging device of the present invention can operate in charger mode (AI charging device connected to an external power source) or in power bank mode (AI charging device not connected to an external power source, AI charging device powers the terminal device through an internal battery).

[0080] Figure 7A The application example demonstrates multiple devices connected to the same AI charging device, where user device power supply and AI computing power services are both accomplished via wired connections (such as Type-C interfaces). Figure 7B and Figure 7A Similarly, but the charging and AI computing services are provided by the battery built into the charging device, which operates as a mobile power bank. Figure 7C and Figure 7D The document showcases application examples of charging devices providing AI computing power services to user devices via wireless communication interfaces. Figure 7C The charging device shown is operating in charger mode. Figure 7D The charging device shown operates in the form of a mobile power bank.

[0081] This invention integrates computing power and communication modules into an AI charging device, enabling an innovative "computing service while charging" model. This eliminates reliance on the computing power of the user's mobile phone / laptop, avoiding the problems of excessive CPU load and shortened battery life caused by running AI tasks on mobile phones and laptops. For example, in programming assistance scenarios, it can reduce the terminal's CPU usage by 80%, balancing device battery life and AI performance, effectively improving mobile office efficiency. Furthermore, the localized computing nodes in mobile scenarios incorporate edge AI chips, supporting the localized deployment of large AI models. Even in weak / no-network environments (such as high-speed rail or outdoors), it can still provide stable AI services (such as document assistants and assisted programming), filling the application gaps dependent on the cloud, and reducing response latency by more than 90% compared to pure cloud solutions.

[0082] The AI-powered charging device provided in this invention breaks through the functional boundaries of traditional chargers, resolves the conflict between computing power and battery life in terminal devices, realizes localized computing power nodes in mobile scenarios, and solves the problems of weak / no network coverage. Furthermore, it effectively reuses high-frequency accessories such as chargers. As an essential accessory for mobile phones / laptops, it transforms the charger from a "low-value consumable" into a "smart computing power entry point," increasing user stickiness. Due to the reusability of standardized interface ecosystems such as Type-C, it can seamlessly connect with mainstream terminal devices such as mobile phones and laptops and third-party AI applications, reducing ecosystem integration costs, providing developers with an open computing power service platform, and promoting the construction of a new device ecosystem where "chargers are computing power nodes."

[0083] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0084] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0085] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. An artificial intelligence charging device, characterized in that, include: Input interface, output interface, power management unit, computing and communication unit; The input interface is coupled to the power management unit, and the input interface provides AC power from an external power source to the power management unit. The power management unit is coupled to the output interface, which is connected to the terminal device; the power management unit converts the AC power into DC power and provides the DC power to the terminal device through the output interface; The power management unit is also coupled to the computing and communication unit, and the power management unit supplies power to the computing and communication unit; The computing power and communication unit is coupled to the output interface. In response to receiving a first computing power service request sent by the terminal device through the output interface, the computing power and communication unit processes the first computing power service request and sends the processing result to the terminal device through the output interface. The computing and communication unit includes a computing unit, a storage unit, and a wired communication interface. The computing unit is coupled to the storage unit and the wired communication interface. The storage unit stores at least one model, and the wired communication interface is coupled to the output interface. In response to receiving a first computing power service request sent by the terminal device through the output interface, the computing power unit parses the first computing power service request, calls a target model corresponding to the first computing power service request from at least one model stored in the storage unit, processes the first computing power service request using the target model, and sends the processing result to the terminal device through the output interface. The terminal device is a mobile terminal device, and the first computing power service is an artificial intelligence computing power service.

2. The artificial intelligence charging device according to claim 1, characterized in that, The computing and communication unit includes a wireless communication interface; The computing power and communication unit is coupled to the terminal device through the wireless communication interface. In response to receiving a second computing power service request sent by the terminal device through the wireless communication interface, the computing power and communication unit processes the second computing power service request and sends the processing result to the terminal device through the wireless communication interface.

3. The artificial intelligence charging device according to claim 1, characterized in that, The power management unit adjusts the power supply to the terminal device according to the working status of the computing and communication unit.

4. The artificial intelligence charging device according to claim 3, characterized in that, The power management unit detects the load and / or power consumption of the computing and communication unit, and adjusts the power supply to the terminal device according to the load and / or power consumption.

5. The artificial intelligence charging device according to claim 1, characterized in that, The AI ​​charging device also includes a human-computer interaction unit, which is coupled to the power management unit, and the power management unit supplies power to the human-computer interaction unit. The human-computer interaction unit responds to the received status query command by outputting data corresponding to the status query command.

6. The artificial intelligence charging device according to claim 5, characterized in that, The human-computer interaction unit is coupled to the computing and communication unit; The human-computer interaction unit responds to the received function management instruction and manages the computing power services provided by the computing power and communication unit according to the function management instruction.

7. The artificial intelligence charging device according to claim 5 or 6, characterized in that, The human-computer interaction unit includes a screen and / or buttons.

8. The artificial intelligence charging device according to claim 1, characterized in that, The AI ​​charging device includes a battery, which is coupled to the power management unit. The power management unit converts the DC power provided by the battery and outputs it to the terminal device.

9. The artificial intelligence charging device according to claim 8, characterized in that, The power management unit includes an input stage unit, a power conversion stage unit, a status detection unit, and a status management unit; The input stage unit is coupled to the input interface. The input stage unit receives AC power from the external power source or DC power from the battery and filters out interference from the AC power or DC power. The power conversion stage unit is coupled to the input stage unit, the computing power and communication unit, and the output interface. The power conversion stage unit converts the AC or DC power output by the input stage unit to power the computing power and communication unit and the terminal device, respectively. The state detection unit is coupled to the state management unit. The state detection unit collects specified information from the artificial intelligence charging device and sends the specified information to the state management unit. The status management unit manages the working status of the AI ​​charging device based on the specified information sent by the status detection unit.

10. The artificial intelligence charging device according to claim 9, characterized in that, The status detection unit detects the working status of the computing power and communication unit and sends the working status of the computing power and communication unit to the status management unit; the status management unit adjusts the power supply to the terminal device according to the working status of the computing power and communication unit. And / or, The status detection unit detects the temperature information and / or current information of the power conversion stage unit and sends the temperature information and / or current information to the status management unit; The status management unit adjusts the operating status of the power conversion stage unit based on the temperature information and / or current information.

11. A charging method, characterized in that, The method, applied to the artificial intelligence charging device according to any one of claims 1-10, comprises: In response to the coupling of the input interface of the AI ​​charging device to an external power source and the coupling of the output interface to a terminal device, the AI ​​charging device charges the terminal device. The AI ​​charging device responds to receiving a first computing power service request sent by the terminal device, processes the first computing power service request, and sends the processing result to the terminal device.

12. The method according to claim 11, characterized in that, The method further includes: In response to the AI ​​charging device being coupled to the terminal device via a wireless connection, the AI ​​charging device receives a second computing power service request sent by the terminal device via the wireless connection, processes the second computing power service request, and sends the processing result to the terminal device via the wireless connection.

13. The method according to claim 11, characterized in that, The method further includes: The AI ​​charging device adjusts the power supply to the terminal device according to its working status in processing the first computing power service request.

14. The method according to claim 11, characterized in that, The method further includes: The AI ​​charging device responds to a received status query command by outputting data corresponding to the status query command.

15. The method according to claim 14, characterized in that, The method further includes: The AI ​​charging device responds to receiving a function management instruction and manages the computing power services provided by the AI ​​charging device according to the function management instruction.

Images