Optimized key distribution system and method

Abstract

To provide an optimized key distribution system capable of utilizing a key more effectively.SOLUTION: A key distribution system includes: a storage unit 1 that stores a plurality of keys and an upper limit of the number of times of use per unit time, the upper limit corresponding to each of the plurality of keys; and a processing unit 2 that is connected to the storage unit 1. The processing unit 2 is configured to: receive a prompt; acquire the number of times used within the unit time corresponding to each of the plurality of keys; and, when at least one of the number of times used within the unit time does not reach the corresponding upper limit of the number of times of use per unit time, acquire a remaining number of times of use within the unit time corresponding to each of the keys by subtracting the corresponding number of times used within the unit time from the corresponding upper limit of the number of times of use per unit time, select, as a target key, a key corresponding to the largest one among the remaining number of times of use within the unit time, and transmit the prompt and the target key to a generative AI system 200.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an optimized key distribution system, and in particular to an optimized system for distributing authenticated keys. The present invention further relates to an optimized method for distributing authenticated keys. [Background technology]

[0002] In recent years, large-scale language models (LLMs) have been rapidly developing, and Patent Document 1 discloses an LLM. Furthermore, the number of users of generative AI systems (such as ChatGPT (registered trademark)) built using LLMs is also rapidly increasing. When sending a prompt to a generative AI system or receiving a response from the generative AI system, a key must be used to authenticate and authorize the user or invoke a program.

[0003] However, a key has a limit on the number of times it can be used per unit time. For example, in the case of ChatGPT, a limit is set on the number of times a key can be used per minute. If the limit on the number of times a key can be used per unit time is exceeded, the generation AI system cannot be used with that key. Also, for example, when a company enters into a corporate contract, the company has multiple keys, and the company's employees share multiple keys. The problem that the present invention aims to solve is how to use multiple keys more effectively while complying with the limit on the number of times each key can be used per unit time. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] U.S. Patent No. 8,332,207 Summary of the Invention

[0005] [Problem to be solved by the invention] It is therefore an object of the present invention to provide an optimized key distribution system and an optimized key distribution method.

[0006] [Means for solving the problem] According to one aspect of the present invention, an optimized key distribution system includes a storage unit configured to communicate with a generation AI system and storing multiple keys authenticated by the generation AI system and corresponding usage limits per unit time, and a processing unit connected to the storage unit. The processing unit is configured to receive a prompt, obtain the number of times each key has been used within a unit time corresponding to each of the multiple keys, determine whether each of the number of times each key has been used within the unit time has reached its corresponding usage limit per unit time, and if it determines that at least one of the number of times each key has been used within the unit time has not reached its corresponding usage limit per unit time, obtain the remaining number of times each key has been used within the unit time corresponding to each of the multiple keys by subtracting the corresponding number of times each key has been used within the unit time from the corresponding usage limit per unit time, select the key corresponding to the largest remaining number of times each key has been used within the unit time as a target key, send a response request including the prompt and the target key to the generation AI system, and receive a response result corresponding to the response request from the generation AI system.

[0007] According to another aspect of the present invention, an optimized key distribution method is performed by an optimized key distribution system, the optimized key distribution system including: a storage unit configured to communicate with a generation AI system, the storage unit storing a plurality of keys authenticated by the generation AI system and corresponding usage limits per unit time for each of the plurality of keys; The optimized key distribution method includes the steps of: (a) a processing unit receiving a prompt; (b) a processing unit obtaining the number of times each key has been used within a unit time corresponding to each of the multiple keys; (c) a processing unit determining whether each of the number of times each key has been used within the unit time has reached the corresponding upper limit of the number of times each key has been used per unit time; and (d) if the processing unit determines that at least one of the number of times each key has been used within the unit time has not reached the corresponding upper limit of the number of times each key has been used per unit time, obtaining the remaining number of times each key has been used within the unit time corresponding to each of the keys by subtracting the corresponding number of times each key has been used within the unit time from the corresponding upper limit of the number of times each key has been used per unit time, selecting the key corresponding to the largest of the remaining number of times each key has been used within the unit time as the target key, sending a response request including the prompt and the target key to the generation AI system, and receiving a response result corresponding to the response request from the generation AI system.

[0008] [Effects of the invention] The optimized key distribution system of the present invention obtains the remaining number of uses in a unit time for each of multiple keys by subtracting the corresponding number of uses in a unit time from the corresponding upper limit of the number of uses per unit time, and selects the key corresponding to the largest remaining number of uses in the unit time as the target key, thereby optimizing key distribution.

[0009] Other features and advantages of the present invention will become apparent from the following detailed description of the embodiments, which proceeds with reference to the accompanying drawings. [Brief explanation of the drawings]

[0010] [Figure 1]FIG. 1 is a block diagram illustrating an optimized key distribution system in communication with a generation AI system according to one embodiment of the present invention. [Figure 2] 1 is a flowchart illustrating an optimized key distribution method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] As used herein, the terms "couple" or "connect" mean a direct connection between two or more electrical devices / apparatus / facilities by means of a conductive material (e.g., electrical wires) or an indirect connection between two electrical devices / apparatus / facilities by means of one or more other devices / apparatus / facilities or wireless communication.

[0012] 1 illustrates an optimized key distribution system 100 according to an embodiment of the present invention. The optimized key distribution system 100 is configured to communicate with a generating AI system 200 (such as ChatGPT) and includes a storage unit 1 and a processing unit 2.

[0013] The storage unit 1 stores multiple keys authenticated by the generation AI system 200 and the upper limit of the number of times each key can be used per unit time. The upper limit of the number of times each key can be used per unit time is, for example, 20 times per minute, 30 times per minute, etc.

[0014] The storage unit 1 may be realized as a non-volatile storage device such as a hard disk drive or flash memory.

[0015] The processing unit 2 connects to the storage unit 1. The processing unit 2 may include, but is not limited to, at least one of a single-core processor, a multi-core processor, a dual-core mobile processor, a microprocessor, a microcontroller, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), and a radio frequency integrated circuit (RFIC).

[0016] 2 shows an optimized key distribution method according to an embodiment of the present invention, which is performed by an optimized key distribution system 100 and includes steps S01 to S08.

[0017] In step S01, the processing unit 2 receives a prompt, which may be received from a user-end electronic device, for example, by being input into the user-end electronic device by a user.

[0018] In step S02, the processing unit 2 acquires the number of times each key has been used within a unit time corresponding to each of the multiple keys. Specifically, the number of times each key has been used within a unit time may be acquired, for example, from the generation AI system 200, or may be acquired by the processing unit 2 by monitoring the usage status of the key.

[0019] In step S03, the processing unit 2 determines whether each of the number of times used within a unit time has reached the corresponding upper limit of the number of times used per unit time. If it is determined that all of the number of times used within a unit time have reached the corresponding upper limit of the number of times used per unit time, the processing unit 2 proceeds to step S04. If it is determined that the upper limit of the number of times used has not been reached, that is, if it is determined that at least one of the number of times used within a unit time has not reached the corresponding upper limit of the number of times used per unit time, the processing unit 2 proceeds to step S05.

[0020] If it is determined that all of the keys used within the unit time have reached their corresponding upper limit of usage per unit time, the processing unit 2 waits for a predetermined time (e.g., 10 seconds) in step S04. Then, the processing unit 2 returns to step S02. That is, steps S02 and S03 are executed again. By waiting, some of the multiple keys may reach the unit time, and the number of times they have been used within the unit time may be reset.

[0021] If it is determined that at least one of the number of times used within the unit time has not reached the corresponding upper limit of the number of times used per unit time, in step S05, the processing unit 2 obtains the remaining number of times used within the unit time corresponding to each of the multiple keys. Each of the remaining number of times used within the unit time is obtained by subtracting the corresponding number of times used within the unit time from the corresponding upper limit of the number of times used per unit time.

[0022] In step S06, the processing unit 2 selects, as the target key, the key corresponding to the largest remaining number of uses within the unit time.

[0023] In step S07, the processing unit 2 sends a response request including the prompt and the selection key to the generating AI system 200.

[0024] In step S08, the processing unit 2 receives a response result corresponding to the response request from the generation AI system 200.

[0025] In summary, the optimized key distribution system 100 of the present invention obtains the remaining number of uses in a unit time for each of multiple keys by subtracting the corresponding number of uses in a unit time from the corresponding upper limit of the number of uses per unit time, and selects the key corresponding to the largest one of the remaining number of uses in the unit time as the target key, thereby optimizing key distribution and reliably achieving the objective of the present invention.

[0026] In the above description, for purposes of explanation, numerous specific details are set forth to provide a thorough understanding of the embodiments. However, it will be apparent to one skilled in the art that one or more other embodiments may be practiced without these specific details. Furthermore, in the description of "one embodiment" or "one embodiment" herein, all references to "one embodiment" or "one embodiment" accompanied by an ordinal number or other designation should be understood to include specific aspects, structures, and features of the present invention. Furthermore, although multiple variations may be incorporated into one embodiment, drawing, or description thereof in this specification, this is for the purpose of streamlining the description and for the purpose of understanding the multifaceted aspects of the present invention. Furthermore, one or more features or specific embodiments of one embodiment may, where appropriate, be combined with one or more features or specific embodiments of other embodiments in the practice of the present invention.

[0027] Although the embodiments and variations of the present invention have been described above, the present invention is not limited to these and encompasses all modifications and equivalent configurations as various configurations falling within the spirit and scope of the broadest interpretation. [Explanation of symbols]

[0028] 100 Optimized Key Distribution System 1 storage unit 2 Processing Unit 200 Generative AI System S01-S08 steps

Claims

1. 1. An optimized key distribution system configured to communicate with a generation AI system, the key distribution system comprising: a storage unit that stores a plurality of keys authenticated by the generation AI system and an upper limit of the number of times each of the keys can be used per unit time; a processing unit coupled to the storage unit; The processing unit Receive a prompt, Obtaining the number of times each of the plurality of keys is used within a unit time corresponding to each of the plurality of keys; determining whether or not each of the number of times used within the unit time has reached the corresponding upper limit of the number of times used per unit time; When it is determined that at least one of the number of times used within the unit time has not reached the corresponding upper limit of the number of times used per unit time, the remaining number of times used within the unit time corresponding to each key is obtained by subtracting the corresponding number of times used within the unit time from the corresponding upper limit of the number of times used per unit time, and the key corresponding to the largest one of the remaining number of times used within the unit time is selected as a target key, a response request including the prompt and the target key is sent to the generation AI system, and a response result corresponding to the response request is received from the generation AI system. Key distribution system.

2. 2. The key distribution system of claim 1, wherein the processing unit is further configured to, when it determines that all of the usages within the unit time have reached their corresponding upper limit of usages per unit time, wait for a predetermined time, and then obtain the usages within the unit time again, and determine again whether each of the usages within the unit time has reached its corresponding upper limit of usages per unit time.

3. An optimized key distribution method executed by an optimized key distribution system, the optimized key distribution system including: a storage unit configured to communicate with a generation AI system, the storage unit storing a plurality of keys authenticated by the generation AI system and a plurality of usage limits per unit time corresponding to the plurality of keys; and a processing unit connected to the storage unit, the key distribution method comprising: (a) the processing unit receiving a prompt; (b) the processing unit acquiring the number of times each of the plurality of keys is used within a unit time corresponding to each of the plurality of keys; (c) the processing unit determining whether each of the number of times used within the unit time has reached a corresponding upper limit of the number of times used per unit time; (d) when the processing unit determines that at least one of the number of times used within the unit time has not reached the corresponding upper limit of the number of times used per unit time, subtracting the corresponding number of times used within the unit time from the corresponding upper limit of the number of times used per unit time to obtain the remaining number of times used within the unit time corresponding to each key, selecting the key corresponding to the largest one of the remaining number of times used within the unit time as a target key, sending a response request including the prompt and the target key to the generation AI system, and receiving a response result corresponding to the response request from the generation AI system; Key distribution method.

4. (e) if the processing unit determines that all of the uses within the unit time have reached the corresponding upper limit of uses per unit time, waiting for a predetermined time and then performing steps (b) and (c) again.

Images