Information determination method and device, electronic equipment and storage medium

Abstract

The invention discloses an information determination method. The method comprises the following steps: transmitting first self-capability information to other equipment; acquiring second self-capability information broadcasted by other equipment, and determining the capability of the target equipment according to the difference between the first self-capability information and the second self-capability information; and determining a target device corresponding to the target device capability, and determining a connection path of the target device capability based on the matching degree of the second self-capability information of the target device and the first self-capability information. According to the technical scheme provided by the embodiment of the invention, the target equipment capability is determined according to the difference between the first self-capability information and the second self-capability information, so that the problem that the capability information among the equipment in the existing system is non-transparent can be solved; the connection path of the target equipment capability is determined based on the matching degree of the second self-capability information of the target equipment and the first self-capability information, so that adaptive optimization of the scheduling strategy can be realized, and stable and efficient operation of the system is ensured.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to an information determination method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the field of artificial intelligence, the Model Context Protocol (MCP) is a standardized protocol framework for enabling interaction between large language models and external tool application programming interfaces (APIs). In this framework, the tool provider runs as a server, providing a series of callable APIs (such as weather queries and navigation), while the large model or its client application acts as a MCP client, sending requests to the server and receiving results via the JSON-RPC (JavaScript Object Notation - Remote Procedure Call) protocol.

[0003] However, existing model context protocol (MFR) communication is typically based on fixed network configurations and lacks distributed capabilities. This results in the MFR capabilities of devices in distributed networks being invisible to each other, easily leading to problems such as low resource utilization, poor collaboration efficiency, and insufficient system adaptability. Therefore, how to design a MFR with automatic disclosure capabilities, mutual awareness, and dynamic cross-device collaboration has become a key technical problem that urgently needs to be solved in this field. Summary of the Invention

[0004] This invention provides an information determination method, apparatus, electronic device, and storage medium to address the problems of low resource utilization, poor collaboration efficiency, and lack of adaptability in existing model context protocols.

[0005] According to one aspect of the present invention, an information determination method is provided, the method comprising:

[0006] Transmit its own capability information to other devices;

[0007] Obtain second self-capability information broadcast by other devices, and determine the target device's capabilities based on the differences between the first self-capability information and the second self-capability information;

[0008] The target device corresponding to the target device capability is determined, and the connection path of the target device capability is determined based on the degree of matching between the second self-capability information and the first self-capability information of the target device.

[0009] According to another aspect of the present invention, an information determining apparatus is provided, the apparatus comprising:

[0010] The self-capability information transmission module is used to transmit the first self-capability information to other devices;

[0011] The target device capability determination module is used to obtain second self-capability information broadcast by other devices and determine the target device capability based on the difference between the first self-capability information and the second self-capability information.

[0012] A target device determination module is used to determine the corresponding target device based on the capabilities of the target device.

[0013] The connection path determination module is used to determine the connection path of the target device's capabilities based on the degree of matching between the second self-capability information and the first self-capability information of the target device.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the information determination method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute the information determination method described in any embodiment of the present invention.

[0019] The technical solution of this invention determines the capability of the target device based on the difference between the first and second self-capability information, which solves the problem of opaque capability information between devices in the existing system. By determining the connection path of the target device capability based on the matching degree between the second and first self-capability information of the target device, adaptive optimization of the scheduling strategy can be achieved, resulting in the beneficial effect of stable and efficient system operation.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of an information determination method provided according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of an information determination method provided according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a flowchart of an information determination method provided according to Embodiment 3 of the present invention;

[0025] Figure 4 This is a flowchart of an information determination method provided according to Embodiment 3 of the present invention;

[0026] Figure 5 This is a schematic diagram of an information determination device according to Embodiment 4 of the present invention;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the information determination method of Embodiment 5 of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart illustrating an information determination method provided in Embodiment 1 of the present invention. This embodiment is applicable to device model context protocol capability awareness and dynamic management in a distributed network environment. The method can be executed by an information determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S110, Transmit first self-capability information to other devices.

[0033] The first aspect, the device's own capabilities, includes various aspects of its capabilities, such as model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption, and task adaptability. Other devices include intelligent devices within or outside the network that have established connections with the current device; these intelligent devices include servers and user terminals.

[0034] Specifically, the device generates a description file of its own capabilities as its primary capability information. This capability description file may include model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption level, task adaptability, etc. This primary capability information is transmitted to other devices via wired or wireless communication methods, such as Bluetooth, cellular networks, and Ethernet.

[0035] S120: Obtain the second self-capability information broadcast by other devices, and determine the target device's capabilities based on the differences between the first self-capability information and the second self-capability information.

[0036] Among these, "other devices" includes intelligent devices within or outside the network that have established connections with the current device. Intelligent devices include servers, user terminals, etc. The second set of self-capability information includes various aspects of the device's capabilities broadcast by other devices. These capabilities include model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption levels, and task adaptability. The target device's capabilities can be determined by analyzing and comparing the current device's first set of self-capability information with the second set of self-capability information broadcast by other devices. This includes model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption levels, and task adaptability. Alternatively, it can be capabilities provided by other devices, including capabilities the current device lacks or capabilities it possesses that are less effective.

[0037] Specifically, the current device receives second self-capability information broadcast periodically or triggered by other devices through a communication interface. The broadcasting methods can include Bluetooth broadcasting, Wi-Fi broadcasting, etc. After acquiring the second self-capability information, the current device compares and analyzes the first self-capability information with the second self-capability information. This comparison and analysis can include comparing the magnitude, strength, and priority of capabilities, and then determining the target device's capabilities based on the differences between the first and second self-capability information.

[0038] S130. Determine the target equipment corresponding to the target equipment capability.

[0039] The target device's capabilities can be various aspects of capability information determined by analyzing and comparing the current device's primary capability information with the secondary capability information broadcast by other devices. These capabilities include model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption level, task adaptability, etc., or they can be capabilities provided by other devices, including capabilities that the current device does not possess or capabilities that the current device possesses but is less capable of. The target device may include other devices that provide the target device's capabilities.

[0040] Specifically, the current device selects one or more devices as the target device from other devices that have the capabilities of the target device. The selection process may include capability matching, logical operations, etc.

[0041] S140. Determine the connection path of the target device's capabilities based on the degree of matching between the target device's second self-capability information and its first self-capability information.

[0042] The matching degree can include the complementarity, consistency, or compatibility level of the first and second self-capability information in terms of functionality, performance, etc. The connection path can include the physical or logical channels traversed by the target device when transmitting data between other devices.

[0043] Specifically, the current device compares and analyzes its own first capability information with the acquired second capability information of the target device. This comparison and analysis may include comparing the magnitude, strength, and priority of capabilities. Then, based on the degree of matching, the current device selects the optimal path from multiple candidate paths as the connection path for the target device's capabilities.

[0044] The technical solution of this invention transmits first self-capability information to other devices, then obtains second self-capability information broadcast by the other devices, and determines the target device's capability based on the difference between the first and second self-capability information. This determines the target device corresponding to the target device's capability, and then determines the connection path of the target device's capability based on the matching degree between the second and first self-capability information. This technical solution, by determining the target device's capability based on the difference between the first and second self-capability information, solves the problem of opaque device capability information in existing systems. Furthermore, by determining the connection path of the target device's capability based on the matching degree between the second and first self-capability information, it enables adaptive optimization of scheduling strategies, ensuring stable and efficient system operation.

[0045] Example 2

[0046] Figure 2 This is a flowchart of an information determination method provided in Embodiment 2 of the present invention. This embodiment further refines the above embodiment:

[0047] like Figure 2 As shown, the method includes:

[0048] S210. Collect model context protocol capability information and running status information as its own capability information.

[0049] The model context protocol capability information may include a standardized protocol supported by the artificial intelligence model carried by the device, used in the model's runtime context. The runtime status information may include dynamic parameters reflecting the device's resource usage and performance during real-time operation, such as processor utilization, memory usage, model inference latency, or device temperature.

[0050] Specifically, the current device periodically or triggeredly collects the model context protocol capability information and operating status information as its own capability information through the device's built-in interface. The collection methods may include data reading, real-time status detection, etc.

[0051] S220: Broadcast its own capability information based on a preset standardized protocol.

[0052] The pre-defined standardized protocols can include predefined and uniformly standardized data exchange formats and communication rules, such as the JSON remote procedure call protocol and XML-based communication protocols. Broadcasting can include the process of sending data to all devices within the distributed network range in a one-to-one or one-to-many manner.

[0053] Specifically, the device broadcasts its own capability information based on a preset standardized protocol, which may include JSON remote procedure call protocol, XML-based communication protocol, etc., and the broadcast may include Bluetooth broadcast, Wi-Fi broadcast, etc.

[0054] S230: Obtain the second self-capability information broadcast by other devices, and determine the target device's capabilities based on the differences between the first self-capability information and the second self-capability information.

[0055] Other devices include intelligent devices within or outside the network that have established connections with the target device. These intelligent devices include servers, user terminals, etc. The second set of self-capability information can include various aspects of the device's capabilities broadcast by other devices, including model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption level, and task adaptability. The target device's capabilities can be determined by analyzing and comparing the current device's first set of self-capability information with the second set of self-capability information broadcast by other devices. This includes model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption level, and task adaptability. Alternatively, it can be capabilities provided by other devices, including capabilities the current device lacks or capabilities it possesses that are less effective.

[0056] Specifically, the current device receives second self-capability information broadcast periodically or triggered by other devices through a communication interface. The broadcasting methods can include Bluetooth broadcasting, Wi-Fi broadcasting, etc. After acquiring the second self-capability information, the current device compares and analyzes the first self-capability information with the second self-capability information. This comparison and analysis can include comparing the magnitude, strength, and priority of capabilities, and then determining the target device's capabilities based on the differences between the first and second self-capability information.

[0057] S240. For each type of target equipment capability, other equipment corresponding to the target equipment capability shall be recorded as target equipment.

[0058] Each category of target device capability can include different capability classifications across all devices, categorized by function, service type, or resource type. Target device capabilities can be various aspects of capability information determined by analyzing and comparing the current device's primary inherent capability information with the secondary inherent capability information broadcast by other devices. This includes model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption level, task adaptability, etc., or capabilities provided by other devices, including capabilities the current device does not possess or capabilities it possesses that are less effective. Target devices can include other devices that provide the target device capabilities.

[0059] Specifically, for each type of target device capability that has been determined, the current device iterates through all other devices in the device group and uses a matching algorithm to match and verify each type of target device capability with the target device capabilities of each other device. The matching and verification methods can include capability type matching, performance index matching, etc. When a certain other device is determined to be the most suitable to undertake a certain type of target device capability, it is recorded as the target device corresponding to that type of target device capability.

[0060] S250. Extract the second self-capability information and the operating status information carried by the first self-capability information of the target device respectively.

[0061] The extraction process can include obtaining operational status-related data from capability information data. Operational status information can include dynamic parameter information reflecting the device's resource usage and performance during real-time operation, such as processor utilization, memory usage, model inference latency, or device temperature.

[0062] Specifically, the current device extracts fields or data segments carrying operating status information from the first self-capability information and the second self-capability information of the target device, thereby obtaining the current operating status details. The extraction process may include extraction based on the JSON remote procedure call protocol, extraction based on the capability information of the XML communication protocol, etc.

[0063] S260. For each target device, determine the matching score between the second self-capability information and the first self-capability information according to the preset evaluation mechanism.

[0064] The preset evaluation mechanism may include a pre-defined scoring system for quantitatively evaluating the operational status information of different devices. The matching score may include the quantitative values ​​of the operational status information of the second self-capability information and the operational status information of the first self-capability information, calculated through the preset evaluation mechanism.

[0065] Specifically, for each identified target device, the operating status information from the second set of its own capability information and the operating status information from the first set of its own capability information are obtained respectively. Based on the preset evaluation mechanism, multiple parameters in the two sets of operating status information are compared and analyzed to obtain a quantitative matching score. The comparison and analysis may include comparison of capability size, comparison of capability strength, and comparison of priority.

[0066] S270. The target device with the highest matching score is designated as the optimal device, and the connection path of the optimal device is set as the connection path of the target device's capability.

[0067] The optimal device can be the specific device that best matches the current device's operating state among all candidate target devices after evaluation by a preset evaluation mechanism. The connection path can include the physical or logical channel traversed by the target device when transmitting data with the current device.

[0068] Specifically, the current device compares the matching scores of all target devices to determine the target device with the highest matching score and marks it as the optimal device; then the connection path of the optimal device is set as the connection path of the target device's capabilities, where the connection path may include physical channels, logical channels, etc.

[0069] The technical solution of this invention collects model context protocol capability information and operation status information as its own capability information and broadcasts its own capability information based on a preset standardized protocol. Then, it obtains the second self-capability information broadcast by other devices. Based on the difference between the first self-capability information and the second self-capability information, it determines the capability of the target device. Then, for each type of target device capability, it records the other devices corresponding to the target device capability as the target device. It extracts the second self-capability information and the operation status information carried by the first self-capability information of the target device. For each target device, it determines the matching score between the operation status information of the second self-capability information and the operation status information of the first self-capability information according to a preset evaluation mechanism. Then, the target device with the highest matching score is recorded as the optimal device, and the connection path of the optimal device is set as the connection path of the target device capability. The above technical solution, by determining the target device's capabilities based on the differences between the first and second self-capability information, can solve the problem of opaque capability information between devices in existing systems. By determining the matching score between the second and first self-capability information of each target device according to a preset evaluation mechanism, scheduling decisions can be made not only based on a single computing power parameter, but also by adopting multi-objective comprehensive optimization, thereby improving system robustness. By determining the connection path of the target device's capabilities based on the matching degree between the second and first self-capability information, adaptive optimization of the scheduling strategy can be achieved, ensuring stable and efficient system operation.

[0070] Furthermore, based on the above embodiments, obtaining second self-capability information broadcast by other devices, and determining the target device's capabilities based on the differences between the first and second self-capability information, includes:

[0071] Receive second capability information broadcast by other devices and extract the model context protocol capability information of the second capability information;

[0072] Compare the model context protocol capability information of the first capability information with the model context protocol capability information of the second capability information;

[0073] If the model context protocol capability information of the first capability information is different from the model context protocol capability information of the second capability information, then the model context protocol capability information of the second capability information is determined as the target device capability.

[0074] The model context protocol capability information may include a standardized protocol supported by the artificial intelligence model carried by the device, used in the model's runtime context.

[0075] Specifically, the current device receives the second capability information broadcast by other devices and extracts the model context protocol capability information of the second capability information; then it compares the model context protocol capability information of the first capability information with the model context protocol capability information of the second capability information, wherein the comparison may include comparison of capability size, capability strength, priority, etc.; if there is a difference in the comparison result, the model context protocol capability information contained in the second capability information is determined as the target device capability.

[0076] Furthermore, based on the above embodiments of the invention, the preset evaluation mechanism includes at least:

[0077] Negotiate communication with the target device based on a preset communication protocol to obtain communication latency and historical reliability.

[0078] Determine the computing power information carried by the operation status information of the first self-capability information and the second self-capability information respectively, and determine the computing power matching degree between the computing power information of the first self-capability information and the second self-capability information.

[0079] Extract the energy efficiency carried by the operating status information of the second self-capability information;

[0080] The matching score is a weighted sum of communication latency, historical reliability, computing power matching degree, and energy efficiency.

[0081] Communication latency can include the time difference between when the current device sends information and when the target device receives it. Historical reliability can include the proportion of sessions that successfully established a connection and completed data transmission with the target device in historical interaction records. Computational power matching can include the degree of matching between the current device and the target device in terms of computing power. Energy efficiency can include the energy consumed by the target device when processing a unit of computing task per unit of time.

[0082] Furthermore, based on the above embodiments of the invention, the operating status information includes:

[0083] At least one of the following: computing power information, memory capacity information, energy consumption level information, and task adaptation information.

[0084] The computing power information can include performance metrics of the device's computing capabilities, such as the core utilization of the central processing unit (CPU) and the floating-point arithmetic capability of the graphics processing unit (GPU). Memory capacity information can include the current available storage resources of the device, such as the remaining available space of RAM and the total available space of storage. Energy consumption information can include the power consumed by the device per unit time or when performing a specific task, such as current instantaneous power consumption and average power consumption. Task compatibility information can include the hardware or software configuration's support characteristics for specific types of tasks.

[0085] Specifically, operational status information is collected in real time or periodically through the device's built-in monitoring module or hardware sensors. The collected information may include computing power information, memory capacity information, energy consumption level information, and task adaptation information.

[0086] Furthermore, based on the above embodiments, the invention also includes at least one of the following:

[0087] Periodically acquire task performance information of the target device's capabilities, and adjust the connection path of the target device's capabilities based on the task performance information;

[0088] In response to device networking updates, adjust the connection path for the target device's capabilities.

[0089] The task performance information can include the actual performance metrics reflected when performing tasks corresponding to the target device's capabilities through the connection path. Device network update information can include information about changes in network topology or device membership, such as new devices joining, existing devices going offline, or device roles changing.

[0090] Example 3

[0091] Figure 3 and Figure 4 This is a flowchart of an information determination method provided in Embodiment 3 of the present invention.

[0092] For details, see Figure 3 and Figure 4 The flowchart of an information determination method described in this embodiment shows the steps of the information determination system to perform the information determination action as follows:

[0093] Each device automatically generates a capability description file upon joining the network and proactively broadcasts or registers it using a standardized protocol. This capability description file includes model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption levels, and task adaptability. During network deployment, devices proactively broadcast their capabilities and related information, allowing other devices in the network to collect new device descriptions and real-time operational status. Based on this information, devices can then filter out model context protocol capabilities they lack, constructing a device capability profile, which is updated in real-time according to operational status. Simultaneously, multi-dimensional metrics are used for quantitative modeling, including model context protocol capabilities, computing power utilization, latency, energy consumption, and historical task completion rates. Furthermore, a decentralized negotiation mechanism is employed, with devices negotiating and allocating tasks based on their capability profiles. A weighted scoring mechanism is introduced to help select the optimal path, with weighted scoring items including computing power matching degree, energy efficiency, network latency, and historical reliability, configured with adjustable weights. Finally, a periodic feedback mechanism learns from device task performance and optimizes scheduling strategies, while also supporting rapid reconstruction and updates when devices dynamically join or leave the network, ensuring network adaptability.

[0094] Example 4

[0095] Figure 5 This is a schematic diagram of an information determination device provided in Embodiment 4 of the present invention. Figure 5 As shown, the device includes: a self-capability information transmission module 510, a target device capability determination module 520, a target device determination module 530, and a connection path determination module 540; wherein,

[0096] The self-capability information transmission module 510 is used to transmit first self-capability information to other devices.

[0097] The target device capability determination module 520 is used to obtain second self-capability information broadcast by other devices and determine the target device capability based on the difference between the first self-capability information and the second self-capability information.

[0098] The target device determination module 530 is used to determine the corresponding target device based on the target device's capabilities.

[0099] The connection path determination module 540 is used to determine the connection path of the target device's capabilities based on the degree of matching between the target device's second self-capability information and its first self-capability information.

[0100] The technical solution of this invention transmits first self-capability information to other devices, then obtains second self-capability information broadcast by other devices, and determines the target device's capabilities based on the differences between the first and second self-capability information. It then determines the corresponding target device based on the target device's capabilities, and finally determines the connection path of the target device's capabilities based on the matching degree between the second and first self-capability information. This technical solution, by determining the target device's capabilities based on the differences between the first and second self-capability information, solves the problem of opaque capability information between devices in existing systems. Furthermore, by determining the connection path of the target device's capabilities based on the matching degree between the second and first self-capability information, it enables adaptive optimization of scheduling strategies, ensuring stable and efficient system operation.

[0101] Optional, the self-capability information transmission module 510 is specifically used for:

[0102] Transmit its own capability information to other devices.

[0103] Optionally, transmitting initial self-capability information to other devices includes:

[0104] Collect model context protocol capability information and runtime status information as its own capability information;

[0105] Broadcast its own capability information based on a pre-defined standardized protocol.

[0106] The model context protocol capability information can include a standardized protocol supported by the artificial intelligence model carried by the device, used in the model's runtime context. Runtime status information can include dynamic parameters reflecting the device's resource usage and performance during real-time operation, such as processor utilization, memory usage, model inference latency, or device temperature. Predefined standardized protocols can include predefined and uniformly standardized data exchange formats and communication rules, such as the JSON remote procedure call protocol or XML-based communication protocols. Broadcasting can include the process of sending data to all devices within the distributed network range in a one-to-one or one-to-many manner.

[0107] Specifically, the device periodically or triggeredly collects the model context protocol capability information and running status information as its own capability information through its built-in interface. The collection methods may include data reading, real-time status detection, etc. The device then broadcasts its own capability information based on a preset standardized protocol, which may include JSON remote procedure call protocol, XML-based communication protocol, etc. The broadcast may include Bluetooth broadcast, Wi-Fi broadcast, etc.

[0108] Optional, the target device capability determination module 520 is specifically used for:

[0109] Obtain second self-capability information broadcast by other devices and determine the target device's capabilities based on the differences between the first and second self-capability information.

[0110] Optionally, obtaining second self-capability information broadcast by other devices and determining the target device's capabilities based on the differences between the first and second self-capability information includes:

[0111] Receive second capability information broadcast by other devices and extract the model context protocol capability information of the second capability information;

[0112] Compare the model context protocol capability information of the first capability information with the model context protocol capability information of the second capability information;

[0113] If the model context protocol capability information of the first capability information is different from the model context protocol capability information of the second capability information, then the model context protocol capability information of the second capability information is determined as the target device capability.

[0114] The model context protocol capability information may include a standardized protocol supported by the artificial intelligence model carried by the device, used in the model's runtime context.

[0115] Specifically, the system receives second capability information broadcast by other devices and extracts the model context protocol capability information from the second capability information. Then, it compares the model context protocol capability information of the first capability information with the model context protocol capability information of the second capability information. The comparison may include comparison of capability size, capability strength, priority, etc. If there is a difference in the comparison result, the model context protocol capability information contained in the second capability information is determined as the target device capability.

[0116] Optionally, the target device determination module 530 is specifically used for:

[0117] The corresponding target equipment is determined based on the capabilities of the target equipment.

[0118] Optionally, the corresponding target device can be determined based on the capabilities of the target device, including:

[0119] For each type of target device capability, other devices corresponding to the target device capability are denoted as target devices.

[0120] Each category of target device capability can include different capability classifications across all devices, categorized by function, service type, or resource type. Target device capabilities can be various aspects of capability information determined by analyzing and comparing the current device's primary inherent capability information with the secondary inherent capability information broadcast by other devices. This includes model context protocol capabilities, CPU / GPU computing power, memory capacity, energy consumption level, task adaptability, etc., or capabilities provided by other devices, including capabilities the current device does not possess or capabilities it possesses that are less effective. Target devices can include other devices that provide the target device capabilities.

[0121] Specifically, for each type of target device capability that has been determined, all other devices in the device group are traversed, and a matching algorithm is used to match and verify each type of target device capability with the target device capabilities of each other device. The matching and verification methods can include capability type matching, performance index matching, etc. When a certain other device is determined to be the most suitable to undertake a certain type of target device capability, it is recorded as the target device corresponding to that type of target device capability.

[0122] Optionally, the connection path determination module 540 is specifically used for:

[0123] Connection paths used to determine the capabilities of a target device based on the degree of matching between the target device's second self-capability information and its first self-capability information.

[0124] Optionally, determining the connection path of the target device's capabilities based on the degree of matching between the target device's second self-capability information and its first self-capability information includes:

[0125] Extract the second self-capability information and the operating status information carried by the first self-capability information of the target device respectively;

[0126] For each target device, a matching score is determined between the second self-capability information and the first self-capability information based on a preset evaluation mechanism.

[0127] The target device with the highest matching score is designated as the optimal device, and the connection path of the optimal device is set as the connection path of the target device's capability.

[0128] The extraction process can include obtaining operational status-related data from capability information data. Operational status information can include dynamic parameter information reflecting the device's resource usage and performance during real-time operation, such as processor utilization, memory usage, model inference latency, or device temperature. The preset evaluation mechanism can include a pre-defined scoring system for quantitatively evaluating the operational status information of different devices. The matching score can include the quantitative values ​​of the operational status information of the second self-capability information calculated through the preset evaluation mechanism and the operational status information of the first self-capability information. The optimal device can include the specific device that best matches the current device's operational status among all candidate target devices after evaluation by the preset evaluation mechanism. The connection path can include the physical or logical channel traversed by the target device when transmitting data with its specific device.

[0129] Specifically, the current device extracts fields or data segments carrying operational status information from its first self-capability information and the target device's second self-capability information to obtain details of the device's current operational status. This extraction process may include extraction based on JSON remote procedure call protocol or capability information extraction based on XML communication protocol. Then, for each identified target device, the operational status information is obtained from both the second and first self-capability information. Based on a preset evaluation mechanism, multiple parameters in the two sets of operational status information are compared and analyzed to obtain a quantitative matching score. This comparison and analysis may include comparisons of capability size, capability strength, and priority. Next, the matching scores of all target devices are compared to determine the target device with the highest matching score, and this device is marked as the optimal device. Finally, the connection path of the optimal device is set as the connection path of the target device's capabilities, where the connection path may include physical channels, logical channels, etc.

[0130] The information determination device provided in the embodiments of the present invention can execute the information determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0131] Example 5

[0132] Figure 6A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0133] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0135] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as information determination methods.

[0136] In some embodiments, the information determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the information determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the information determination method by any other suitable means (e.g., by means of firmware).

[0137] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0139] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0141] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0142] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0143] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0144] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining information, characterized in that, The method includes: Transmit its own capability information to other devices; Obtain second self-capability information broadcast by other devices, and determine the target device's capabilities based on the differences between the first self-capability information and the second self-capability information; The target device corresponding to the target device capability is determined, and the connection path of the target device capability is determined based on the degree of matching between the second self-capability information and the first self-capability information of the target device.

2. The method according to claim 1, characterized in that, The transmission of the first self-capability information to other devices includes: The model context protocol capability information and runtime status information are collected as the self-capability information; Broadcast its own capability information based on a preset standardized protocol.

3. The method according to claim 1, characterized in that, The step of obtaining second self-capability information broadcast by other devices and determining the target device's capabilities based on the differences between the first self-capability information and the second self-capability information includes: Receive the second capability information broadcast by the other device, and extract the model context protocol capability information of the second capability information; Compare the model context protocol capability information of the first capability information with the model context protocol capability information of the second capability information; If the model context protocol capability information of the first capability information is different from the model context protocol capability information of the second capability information, then the model context protocol capability information of the second capability information is determined as the target device capability.

4. The method according to claim 1, characterized in that, The step of determining the target device corresponding to the target device capability and determining the connection path of the target device capability based on the matching degree between the second self-capability information of the target device and the first self-capability information includes: For each type of target device capability, the other devices corresponding to the target device capability are denoted as the target device; Extract the second self-capability information and the operating status information carried by the first self-capability information of the target device respectively; For each of the target devices, a matching score is determined between the operating status information of the second self-capability information and the operating status information of the first self-capability information according to a preset evaluation mechanism; The target device with the highest matching score is designated as the optimal device, and the connection path of the optimal device is set as the connection path of the target device's capability.

5. The method according to claim 4, characterized in that, The preset evaluation mechanism includes at least the following: The device negotiates communication with the target device based on a preset communication protocol to obtain communication latency and historical reliability. Determine the computing power information carried by the operating status information of the first self-capability information and the second self-capability information respectively, and determine the computing power matching degree between the computing power information of the first self-capability information and the second self-capability information; Extract the energy consumption efficiency carried by the operating status information of the second self-capability information; The weighted sum of the communication delay, historical reliability, computing power matching degree, and energy efficiency is used as the matching score.

6. The method according to any one of claims 2, 4, or 5, characterized in that, The operational status information includes at least one of the following: computing power information, memory capacity information, energy consumption level information, and task adaptation information.

7. The method according to claim 1, characterized in that, It also includes at least one of the following: Periodically acquire task performance information of the target device's capabilities, and adjust the connection path of the target device's capabilities based on the task performance information; In response to device networking update information, the connection path of the target device capability is adjusted.

8. An information determining device, characterized in that, The device includes: The self-capability information transmission module is used to transmit the first self-capability information to other devices; The target device capability determination module is used to obtain second self-capability information broadcast by other devices and determine the target device capability based on the difference between the first self-capability information and the second self-capability information. A target device determination module is used to determine the corresponding target device based on the capabilities of the target device. The connection path determination module is used to determine the connection path of the target device's capabilities based on the degree of matching between the second self-capability information and the first self-capability information of the target device.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the information determination method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to perform the information determination method according to any one of claims 1-7.

Images