Optimized key distribution system and optimized key distribution 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 more particularly to an optimized system for distributing authenticated keys. The present invention further relates to an optimized method for distributing authenticated keys.

Background Art

[0002] In recent years, large language models (LLMs) have been rapidly developing, and Patent Document 1 discloses an LLM. Also, the number of users of generative AI systems (such as ChatGPT (registered trademark), etc.) constructed using LLMs has been increasing rapidly. When sending a prompt to a generative AI system and receiving a response from the generative AI system, it is necessary to use a key to authenticate / authorize the user or call a program.

[0003] However, keys have a usage limit per unit time. For example, in the case of ChatGPT, the key has a usage limit per minute. If the usage limit per unit time is exceeded, the generative 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 employees of the company share multiple keys. Effectively using multiple keys while complying with the usage limit per unit time for each key is the problem to be solved by the present invention.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

[0005] [Problems to be Solved by the Invention] Accordingly, an object of the present invention is 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 generative AI system and store a plurality of keys authenticated by the generative AI system and an upper limit of the number of times of use per unit time corresponding to each of the plurality of keys, and a processing unit connected to the storage unit. The processing unit receives a prompt, obtains the number of times of use within the unit time corresponding to each of the plurality of keys, determines whether each of the number of times of use within the unit time reaches the corresponding upper limit of the number of times of use per unit time, and when it is determined that at least one of the number of times of use within the unit time does not reach the corresponding upper limit of the number of times of use per unit time, obtains the remaining number of times of use within the unit time corresponding to each key by subtracting the corresponding number of times of use within the unit time from the corresponding upper limit of the number of times of use per unit time, selects the key corresponding to the largest one of the remaining number of times of use within the unit time as the target key, generates a response request including the prompt and the target key and transmits it to the generative AI system, and is configured to receive a response result corresponding to the response request from the generative AI system.

[0007] According to another aspect of the present invention, the optimized key distribution method is executed by an optimized key distribution system. The optimized key distribution system includes a storage unit configured to communicate with a generation AI system and store a plurality of keys authenticated by the generation AI system and an upper limit of the number of times of use per unit time corresponding to each of the plurality of keys, and a processing unit connected to the storage unit. The optimized key distribution method includes: (a) a step in which the processing unit receives a prompt; (b) a step in which the processing unit obtains the number of times of use within a unit time corresponding to each of the plurality of keys; (c) a step in which the processing unit determines whether each of the number of times of use within a unit time reaches the corresponding upper limit of the number of times of use per unit time; and (d) when the processing unit determines that at least one of the number of times of use within a unit time does not reach the corresponding upper limit of the number of times of use per unit time, obtaining the remaining number of times of use within a unit time corresponding to each key by subtracting the corresponding number of times of use within a unit time from the corresponding upper limit of the number of times of use per unit time, selecting as a target key the key corresponding to the largest one of the remaining number of times of use within a unit time, transmitting 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] [Advantages of the Invention] The optimized key distribution system of the present invention can optimize key distribution by obtaining the remaining number of times of use within a unit time for each of the plurality of keys by subtracting the corresponding number of times of use within a unit time from the corresponding upper limit of the number of times of use per unit time, and selecting as a target key the key corresponding to the largest one of the remaining number of times of use within a unit time.

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

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

[0011] As used herein, the terms "coupled" or "connected" mean that between a plurality of electrical devices / apparatuses / facilities are directly connected by a conductive material (e.g., an electric wire), or that between two electrical devices / apparatuses / facilities are indirectly connected by one or more other devices / apparatuses / facilities or wireless communication.

[0012] FIG. 1 shows an optimized key distribution system 100 according to one embodiment of the present invention. The optimized key distribution system 100 is configured to communicate with a generative AI system 200 (e.g., ChatGPT, etc.) and includes a storage unit 1 and a processing unit 2.

[0013] The storage unit 1 stores a plurality of keys authenticated by the generative AI system 200 and an upper limit on the number of usage times per unit time corresponding to each of the plurality of keys. The upper limit on the number of usage times 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, a flash memory, etc.

[0015] The processing unit 2 is connected to the memory 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] FIG. 2 shows an optimized key distribution method according to one embodiment of the present invention. The optimized key distribution method is executed by an optimized key distribution system 100 and includes steps S01 to S08.

[0017] In step S01, the processing unit 2 receives a prompt. The prompt may be input by a user to a user terminal electronic device and received from the user terminal electronic device, for example.

[0018] In step S02, the processing unit 2 obtains the number of times each of a plurality of keys is used within a unit time. Specifically, the number of times used within a unit time may be obtained from, for example, the generation AI system 200, or may be obtained by the processing unit 2 monitoring the usage status of the keys.

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

[0020] 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 uses per unit time, in step S04, the processing unit 2 waits for a predetermined time (for example, 10 seconds, etc.). After that, it returns to step S02. That is, steps S02 and S03 are executed again. By waiting, some of those multiple keys may reach the unit time and the number of times used within the unit time may be reset.

[0021] 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 uses per unit time, in step S05, the processing unit 2 obtains the remaining number of uses within the unit time corresponding to each of the multiple keys. Each of the remaining number of uses 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 uses per unit time.

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

[0023] In step S07, the processing unit 2 transmits a response request including a prompt and a selection key to the generation 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 can optimize the key distribution by obtaining the remaining number of uses within the unit time of each of the multiple keys by subtracting the corresponding number of times used within the unit time from the corresponding upper limit of the number of uses per unit time, and selecting the key corresponding to the largest one among the remaining number of uses within the unit time as the target key, and can surely achieve the object of the present invention.

[0026] In the above description, for the purpose of explanation, numerous specific details have been set forth to provide a complete understanding of the embodiments. However, it will be apparent to those skilled in the art that one or more other embodiments may be practiced without these specific details. Also, in the description indicating "a certain embodiment" or "an embodiment" in this specification, it should be understood that all descriptions accompanied by indications such as ordinal numbers may be included in specific implementations of the present invention having specific aspects, structures, and features. Furthermore, in this specification, although multiple variations are sometimes incorporated into one embodiment, drawing, or their descriptions, this is for rationalizing this specification and is aimed at understanding the multifaceted nature of the present invention. Also, one or more features or specific examples in a certain embodiment may, where appropriate, be practiced together with one or more features or specific examples in other embodiments in the implementation of the present invention.

[0027] As described above, the embodiments and variations of the present invention have been explained, but the present invention is not limited thereto, and it shall include all modifications and equivalent configurations as various configurations included within the spirit and scope of the broadest interpretation.

Description of Reference Numerals

[0028] 100 Optimized Key Distribution System 1 Memory Unit 2 Processing Unit 200 Generation AI System S01 - S08 Steps

Claims

1. An optimized key distribution system configured to communicate with a generation AI system, the key distribution system comprising: a storage unit storing a plurality of keys authenticated by the generation AI system and an upper limit of the number of uses per unit time corresponding to each of the plurality of keys; a processing unit connected to the storage unit; wherein the processing unit: receives a prompt; obtains the number of times of use within each unit time corresponding to each of the plurality of keys; determines whether each of the number of times of use within the unit time has reached the corresponding upper limit of the number of uses per unit time; when it is determined that at least one of the number of times of use within the unit time has not reached the corresponding upper limit of the number of uses per unit time, obtains the remaining number of uses within the unit time corresponding to each key by subtracting the corresponding number of times of use within the unit time from the corresponding upper limit of the number of uses per unit time, selects the key corresponding to the largest one of the remaining number of uses within the unit time as the target key, transmits a response request including the prompt and the target key to the generation AI system, and receives a response result corresponding to the response request from the generation AI system; a key distribution system.

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

3. An optimized key distribution method executed by an optimized key distribution system, the optimized key distribution system being configured to communicate with a generation AI system and including a storage unit storing a plurality of keys authenticated by the generation AI system and a plurality of upper limits of the number of uses per unit time corresponding to each of the plurality of keys, and a processing unit connected to the storage unit, the key distribution method comprising: (a) a step in which the processing unit receives a prompt; (b) The step in which the processing unit obtains the number of times each of the plurality of keys is used within a unit time; (c) The step in which the processing unit determines whether each of the number of times used within the unit time has reached the corresponding upper limit of the number of uses 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 uses per unit time, by subtracting the corresponding number of times used within the unit time from the corresponding upper limit of the number of uses per unit time, obtaining the remaining number of uses within the unit time corresponding to each key, selecting the key corresponding to the largest one among the remaining number of uses 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; (d) A key distribution method. (e) When the processing unit determines that all of the number of times used within the unit time have reached the corresponding upper limit of the number of uses per unit time, further including the step of waiting for a predetermined time and then executing steps (b) and (c) again. The key distribution method according to claim 3. ​

Images