Resource allocation method and system based on artificial intelligence gateway

Abstract

The invention is suitable for the technical field of data processing, and provides a resource allocation method and system based on an artificial intelligence gateway, and the method comprises the steps: firstly responding to a call request instruction, obtaining historical operation text information of a target user and historical throughput record information of a target system, and then according to the historical throughput record information, carrying out resource allocation on the target user according to the historical throughput record information; and quickly generating overload time period information according to the historical operation text information, and finally automatically generating a calling control instruction according to the historical operation text information, the overload time period information and a preset word extraction algorithm. According to the method, the AI gateway can be dynamically adjusted according to the specific condition of each user, the user experience is remarkably improved, multiple optimization and safety functions are fused, all-around support is provided for users and developers, resource allocation is intelligently optimized through computing power scheduling in the aspects of resource management and efficiency optimization, and the user experience is improved. According to the method, on-demand execution of all tasks is guaranteed, resource waste is effectively reduced, and it is guaranteed that a user can obtain smooth and high-quality use experience.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular, to a resource configuration method and system based on an artificial intelligence gateway. Background Art

[0002] The Artificial Intelligence (AI) gateway is the core bridge between enterprise applications and large internal and external models. It not only acts as a hub for data flow, but also restricts access to ensure that interactions with AI models are secure and efficient.

[0003] At present, artificial intelligence gateways usually adopt a unified current limiting strategy when the system is busy, which causes the access speed of all users to slow down or the requests to be rejected. It cannot be dynamically adjusted according to the specific circumstances of each user, resulting in a poor user experience, which needs further improvement. Summary of the invention

[0004] Based on this, the embodiment of the present application provides a resource configuration method and system based on an artificial intelligence gateway to solve the problem of poor user experience in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a resource configuration method based on an artificial intelligence gateway, the method comprising: In response to the call request instruction, obtaining historical operation text information of the target user and historical throughput record information of the target system; Generate overload period information according to the historical throughput record information; A call control instruction is generated according to the historical operation text information, the overload period information and a preset word extraction algorithm, wherein the call control instruction is a call free instruction or a call current limiting instruction.

[0006] Compared with the prior art, the beneficial effect is that the resource configuration method based on the artificial intelligence gateway provided in the embodiment of the present application, the terminal device can first respond to the call request instruction, obtain the historical operation text information of the target user and the historical throughput record information of the target system, and then quickly generate the overload period information based on the historical throughput record information, and finally automatically generate the call control instruction based on the historical operation text information, the overload period information and the preset word extraction algorithm, so as to realize dynamic adjustment of the AI ​​gateway according to the specific situation of each user, improve the user experience, and solve the problem of poor user experience of the current users to a certain extent.

[0007] In a second aspect, an embodiment of the present application provides a resource configuration system based on an artificial intelligence gateway, the system comprising: A historical operation text information acquisition module: used to obtain the historical operation text information of the target user and the historical throughput record information of the target system in response to the call request instruction; An overload period information generating module: used to generate overload period information according to the historical throughput record information; A call control instruction generation module is used to generate a call control instruction according to the historical operation text information, the overload period information and a preset word extraction algorithm, wherein the call control instruction is a call free instruction or a call current limiting instruction.

[0008] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0010] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0012] Figure 1 It is a flowchart of a resource configuration method provided by an embodiment of the present application; Figure 2 is a flowchart of step S200 in the resource configuration method provided in an embodiment of the present application; Figure 3 It is a flowchart of step S300 in the resource configuration method provided in an embodiment of the present application; Figure 4 It is a flowchart before step S350 in the resource configuration method provided in an embodiment of the present application; Figure 5 It is a flowchart after step S360 in the resource configuration method provided in one embodiment of the present application; Figure 6 It is a module block diagram of a resource configuration system provided by an embodiment of the present application; Figure 7 It is a schematic diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0014] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0015] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0016] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0017] See also Figure 1 , Figure 1 : is a flow chart of a resource configuration method based on an artificial intelligence gateway provided in an embodiment of the present application. In this embodiment, the execution subject of the resource configuration method is a terminal device. It is understandable that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptops, ultra-mobile personal computers (Ultra-Mobile Personal Computer, UMPC), netbooks, personal digital assistants (Personal Digital Assistant, PDA), etc., and the embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0018] See also Figure 1 The resource configuration method provided in the embodiment of the present application includes but is not limited to the following steps: In S100 , in response to the call request instruction, historical operation text information of the target user and historical throughput record information of the target system are obtained.

[0019] Specifically, the terminal device can first respond to the call request instruction to obtain the historical operation text information of the target user and the historical throughput record information of the target system, wherein the call request instruction is used to describe the request initiated by the target user to call the AI ​​model; the target user is used to describe the user who initiated the request to call the AI ​​model. The historical operation text information is used to describe the text content of the target user in the historical operation, such as the question content that the target user has sent to the AI ​​model in the history.

[0020] In one possible implementation, the target system may be an AI interactive system for coordinating users and AI models. In one possible implementation, the target system may also be an AI interface system for coordinating users and AI models. The historical throughput record information is used to describe the throughput record of the target system in history, wherein the historical throughput record information includes multiple throughput information and sampling time information corresponding to each throughput information; the throughput information is used to describe the throughput of the target system, that is, the number of requests processed at a certain moment; the sampling time information is used to describe the occurrence time corresponding to the throughput information.

[0021] In S200, overload period information is generated according to historical throughput record information.

[0022] Specifically, after the terminal device obtains the historical operation text information and the historical throughput record information, the terminal device can effectively generate the overload period information according to the historical throughput record information, wherein the overload period information is used to describe the time period when the target system is in an overloaded state; the terminal device can use the existing technology to determine whether the target system is in an overloaded state, so it is not elaborated; the overload state of the target system can be pre-defined by the operation and maintenance personnel. For example, the operation and maintenance personnel can pre-define that when the throughput information is greater than 90% of the maximum throughput of the target system, the target system is in an overloaded state.

[0023] In some possible implementations, in order to effectively generate overload period information, see Figure 2 Step S200 includes but is not limited to the following steps: In S210, for each sampling time information in the historical throughput record information: based on the preset sampling period information, generate sampling period information.

[0024] Specifically, the terminal device can perform this processing for each sampling time information in the historical throughput record information: based on the preset sampling period information, generate sampling period information, wherein the specific value of the sampling period information can be customized by the operation and maintenance personnel; the sampling period information is used to describe the time period with the sampling time information as the starting time and the sampling period information as the duration.

[0025] For example, when a sampling time information in the historical throughput record information is 9:00 on January 1 and the sampling period information is two hours, the sampling period information can be a time period with 9:00 on January 1 as the starting time and 11:00 on January 1 as the ending time.

[0026] In S220, for each sampling period information: generate throughput sum information according to a plurality of throughput information corresponding to the sampling period information.

[0027] Specifically, after the terminal device generates the sampling period information, the terminal device can perform this processing for each sampling period information: based on the sum of multiple throughput information located in the sampling period information at the time of occurrence, quickly generate the throughput sum information, wherein the throughput sum information is used to describe the sum of multiple throughput information corresponding to the sampling period information.

[0028] In S230, it is determined whether the throughput sum information is greater than the preset throughput limit value information.

[0029] Specifically, after the terminal device generates the total throughput information, the terminal device can determine whether the total throughput information is greater than the preset throughput limit value information, wherein the specific value of the throughput limit value information can be customized by the operation and maintenance personnel according to the specific target system; the throughput limit value information can be the maximum throughput threshold information of a specified multiple, and the maximum throughput threshold information is used to describe the maximum throughput of the target system, and the specific value of the specified multiple can be any positive number between 0.85 and 0.9.

[0030] In S240, if the throughput sum information is greater than the throughput limit value information, it is determined that the sampling period information corresponding to the throughput sum information is the overload period information.

[0031] Specifically, if the throughput sum information is greater than the throughput limit value information, it indicates that the target system in the sampling period information is in an overload state, and the terminal device can effectively determine that the sampling period information corresponding to the throughput sum information is the overload period information.

[0032] In S300, a call control instruction is generated according to the historical operation text information, the overload period information and the preset word extraction algorithm.

[0033] Specifically, after the terminal device generates overload period information, the terminal device can effectively generate call control instructions based on historical operation text information, overload period information and preset word extraction algorithm, so as to realize dynamic adjustment according to the specific situation of the user, optimize the allocation of computing resources, and improve the user experience.

[0034] Without loss of generality, the call control instruction is a call free instruction or a call current limiting instruction, wherein the call free instruction is used to describe that the target user does not limit the amount of data when initiating a request to call the AI ​​model, so that the target user can still freely call the AI ​​model when the target system is busy. The call current limiting instruction is used to describe the limit on the amount of data when the target user initiates a request to call the AI ​​model, so that the target user's access speed is slowed down or the request is rejected when the target system is busy.

[0035] In some possible implementations, in order to improve the user experience, please refer to Figure 3 Step S300 includes but is not limited to the following steps: In S310, based on the overload period information, the historical operation text information is filtered and processed to generate historical operation sub-text information.

[0036] Specifically, the terminal device can filter and process the historical operation text information based on the overload period information, filter out all the texts whose operation time is within the overload period information in the historical operation text information, and quickly generate historical operation sub-text information, wherein the historical operation sub-text information is used to describe part of the historical operation text information whose operation time is within the overload period information.

[0037] In S320, based on a preset word extraction algorithm, word extraction processing is performed on the historical operation sub-text information to generate a plurality of word information to be detected.

[0038] Specifically, after the terminal device generates the historical operation sub-text information, the terminal device can perform word extraction processing on the historical operation sub-text information based on a preset word extraction algorithm, extract all words in the historical operation sub-text information, and generate multiple word information to be detected, wherein the word extraction algorithm can be a TextRank algorithm or a RAKE (Rapid Automatic Keyword Extraction) algorithm; the word information to be detected is used to describe the words extracted from the historical operation sub-text information.

[0039] In S330, for each piece of word information to be detected: based on a preset first sensitive word database, it is determined whether the word information to be detected is the same as any piece of sensitive word information of the first category.

[0040] Specifically, after the terminal device generates multiple pieces of word information to be detected, the terminal device can perform this processing for each piece of word information to be detected: based on a preset first sensitive word database, determine whether the word information to be detected is the same as any one of the first category of sensitive word information, wherein the first sensitive word database stores multiple first category of sensitive word information, and the specific value of a category of sensitive word information can be customized by the operation and maintenance personnel. For example, the operation and maintenance personnel can pre-customize inappropriate or non-compliant words as a category of sensitive word information, and pre-store the first category of sensitive word information in the first sensitive word database.

[0041] In S340, if the word information to be detected is the same as any sensitive word information of the first category, the word information to be detected is determined to be trigger word information.

[0042] Specifically, if the word information to be detected is the same as any Class I sensitive word information, the terminal device can quickly determine that the word information to be detected is trigger word information, where the trigger word information is used to describe words extracted from historical operation sub-text information and is the same as any Class I sensitive word information.

[0043] In S350 , trigger quantity information is generated according to the total quantity of trigger word information.

[0044] Specifically, after the terminal device determines whether all the word information to be detected is the same as any Class I sensitive word information, the terminal device can generate trigger quantity information based on the total number of trigger word information, where the trigger quantity information is used to describe the total number of trigger word information.

[0045] In S360, if the trigger quantity information is greater than or equal to the preset trigger threshold information, a call current limiting instruction is generated, otherwise a call free instruction is generated.

[0046] Specifically, if the trigger quantity information is greater than or equal to the preset trigger threshold information, it means that the target user has mentioned inappropriate or non-compliant words many times when the target system is busy. The target system should dispatch the computing power resources allocated to the target user to other users when it is busy to reduce the waste of computing power resources. Therefore, the terminal device can generate a call to limit the flow.

[0047] Without loss of generality, if the trigger quantity information is less than the preset trigger threshold information, it means that the target user did not mention inappropriate or non-compliant words multiple times when the target system was busy. The target system can give priority to ensuring the user experience of the target user, so the terminal device can generate a call free instruction.

[0048] In some possible implementations, to further optimize resource allocation, see Figure 4Before step S350, the method further includes but is not limited to the following steps: In S351, for each piece of word information to be detected: based on a preset second sensitive word database, it is determined whether the word information to be detected is the same as any second-category sensitive word information.

[0049] Specifically, the terminal device can perform this processing for each word information to be detected: based on the preset second sensitive word database, determine whether the word information to be detected is the same as any second-category sensitive word information, wherein the second sensitive word database stores multiple second-category sensitive word information, and the second-category sensitive word information is used to describe the homonyms of the first-category sensitive word information, and the specific value of the second-category sensitive word information can be customized by the operation and maintenance personnel.

[0050] In S352, if the word information to be detected is the same as any second-category sensitive word information, the word information to be detected is determined to be trigger word information.

[0051] Specifically, if the word information to be detected is the same as any second-category sensitive word information, the terminal device can determine that the word information to be detected is trigger word information.

[0052] In some possible implementations, to further adapt to high-concurrency application scenarios, see Figure 5 If a call free instruction is generated, after step S360, the method further includes but is not limited to the following steps: In S361, the target user's cumulative free calling duration information is obtained.

[0053] Specifically, the terminal device may first obtain the target user's cumulative free calling duration information, wherein the cumulative free calling duration information is used to describe the cumulative duration when the trigger quantity information is less than the trigger threshold information.

[0054] In S362, the free cumulative duration information is compared with the preset cumulative duration threshold information; Specifically, after the terminal device obtains the free cumulative duration information of the call, the terminal device can compare the free cumulative duration information of the call with the preset cumulative duration threshold information, wherein the specific value of the cumulative duration threshold information can be customized by the operation and maintenance personnel.

[0055] In S363, if the call free cumulative duration information is greater than or equal to the cumulative duration threshold information, the target user is marked as a priority user.

[0056] Specifically, if the free cumulative call duration information is greater than or equal to the cumulative duration threshold information, it indicates that the target user is a high-quality user, so the terminal device can mark the target user as a priority user, where the priority user is used to describe the target user who is given priority in scheduling computing resources.

[0057] The implementation principle of the resource configuration method based on the artificial intelligence gateway in the embodiment of the present application is as follows: the terminal device can first respond to the call request instruction, obtain the historical operation text information of the target user and the historical throughput record information of the target system, and then quickly generate the overload period information based on the historical throughput record information. Finally, based on the historical operation text information, the overload period information and the preset word extraction algorithm, the call control instruction is automatically generated, thereby realizing dynamic adjustment of the AI ​​gateway according to the specific circumstances of each user and improving the user experience.

[0058] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0059] The embodiment of the present application also provides a resource configuration system based on an artificial intelligence gateway. For ease of description, only the parts related to the present application are shown, such as Figure 6 As shown, the system 60 includes: The historical operation text information acquisition module 61 is used to obtain the historical operation text information of the target user and the historical throughput record information of the target system in response to the call request instruction; Overload period information generating module 62: used to generate overload period information according to historical throughput record information; The call control instruction generation module 63 is used to generate a call control instruction according to the historical operation text information, the overload period information and the preset word extraction algorithm, wherein the call control instruction is a call free instruction or a call current limiting instruction.

[0060] Optionally, the historical throughput record information includes multiple throughput information and sampling time information corresponding to each throughput information; the overload period information generating module 62 includes: The sampling period information generation submodule is used for generating sampling period information for each sampling moment information in the historical throughput record information based on the preset sampling period information, wherein the sampling period information is used to describe a time period starting from the sampling moment information and having the sampling period information as the duration; The throughput sum information generating submodule is used for generating the throughput sum information according to the multiple throughput information corresponding to the sampling period information for each sampling period information, wherein the throughput sum information is used to describe the sum of the multiple throughput information corresponding to the sampling period information; The throughput sum information judgment submodule is used to judge whether the throughput sum information is greater than the preset throughput limit value information, wherein the throughput limit value information is the maximum throughput threshold information of the specified multiple; The overload period information determination submodule is used to determine that the sampling period information corresponding to the throughput sum information is the overload period information if the throughput sum information is greater than the throughput limit value information.

[0061] Optionally, the above-mentioned call control instruction generation module 63 includes: A historical operation sub-text information generation sub-module: used to filter and process the historical operation text information based on the overload period information to generate historical operation sub-text information, wherein the historical operation sub-text information is used to describe part of the historical operation text information whose operation time is within the overload period information; Multiple to-be-detected word information generation submodule: used to perform word extraction processing on the historical operation subtext information based on a preset word extraction algorithm to generate multiple to-be-detected word information; The submodule for judging the word information to be detected is used to judge, for each word information to be detected, whether the word information to be detected is the same as any first-class sensitive word information based on a preset first sensitive word database, wherein the first sensitive word database stores a plurality of first-class sensitive word information; Trigger word information determination submodule: used to determine the word information to be detected as trigger word information if the word information to be detected is the same as any sensitive word information of the first category; The trigger quantity information generation submodule is used to generate the trigger quantity information according to the total quantity of the trigger word information; The submodule for generating a call current limiting instruction is used to generate a call current limiting instruction if the trigger quantity information is greater than or equal to the preset trigger threshold information, otherwise a call free instruction is generated.

[0062] Optionally, the system 60 further includes: The module for judging the word information to be detected is used to judge, for each word information to be detected, whether the word information to be detected is the same as any second-category sensitive word information based on a preset second sensitive word database, wherein the second sensitive word database stores a plurality of second-category sensitive word information, and the second-category sensitive word information is used to describe homophones of the first-category sensitive word information; Trigger word information determination module: used to determine that the word information to be detected is trigger word information if the word information to be detected is the same as any second-category sensitive word information.

[0063] Optionally, if a call free instruction is generated, the system 60 further includes: The free call cumulative time information acquisition module is used to obtain the free call cumulative time information of the target user, wherein the free call cumulative time information is used to describe the cumulative time when the trigger quantity information is less than the trigger threshold information; Call free cumulative duration information comparison module: used to compare the call free cumulative duration information with the preset cumulative duration threshold information; Target user marking module: used to mark the target user as a priority user if the free cumulative duration information of the call is greater than or equal to the cumulative duration threshold information, where the priority user is used to describe the target user for priority scheduling of computing resources.

[0064] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0065] The present application also provides a terminal device, such as Figure 7 As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. When the processor 71 executes the computer program 73, the steps in the above resource configuration method embodiment are implemented, for example Figure 1 Steps S100 to S300 shown; or, when the processor 71 executes the computer program 73, the functions of each module in the above device are realized, for example Figure 6 The historical operation text information acquisition module 61, the overload period information generation module 62 and the call control instruction generation module 63 shown have corresponding functions.

[0066] The terminal device 70 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server, and the terminal device 70 includes but is not limited to a processor 71 and a memory 72. Those skilled in the art will appreciate that Figure 7 It is only an example of the terminal device 70 and does not constitute a limitation of the terminal device 70. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 70 may also include input and output devices, network access devices, buses, etc.

[0067] Among them, the processor 71 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0068] The memory 72 may be an internal storage unit of the terminal device 70, such as a hard disk or memory of the terminal device 70, or the memory 72 may be an external storage device of the terminal device 70, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 70; further, the memory 72 may include both an internal storage unit and an external storage device of the terminal device 70, and the memory 72 may also store a computer program 73 and other programs and data required by the terminal device 70, and the memory 72 may also be used to temporarily store data that has been output or is to be output.

[0069] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form, etc.; the computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0070] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the methods, principles, and structures of the present application should be included in the protection scope of the present application.

Claims

1. A resource configuration method based on artificial intelligence gateway, characterized in that: The method comprises: In response to the call request instruction, obtaining historical operation text information of the target user and historical throughput record information of the target system; Generate overload period information according to the historical throughput record information; A call control instruction is generated according to the historical operation text information, the overload period information and a preset word extraction algorithm, wherein the call control instruction is a call free instruction or a call current limiting instruction.

2. The method according to claim 1, characterized in that The historical throughput record information includes a plurality of throughput information and sampling time information corresponding to each of the throughput information; The generating overload period information according to the historical throughput record information includes: For each sampling time information in the historical throughput record information: based on the preset sampling period information, generate sampling period information, wherein the sampling period information is used to describe a time period starting from the sampling time information and having the sampling period information as the duration; For each of the sampling period information: generating throughput sum information according to the plurality of throughput information corresponding to the sampling period information, wherein the throughput sum information is used to describe the sum of the plurality of throughput information corresponding to the sampling period information; Determine whether the throughput sum information is greater than preset throughput limit value information, wherein the throughput limit value information is a maximum throughput threshold information of a specified multiple; If the throughput sum information is greater than the throughput limit value information, it is determined that the sampling period information corresponding to the throughput sum information is the overload period information.

3. The method according to claim 2, characterized in that The generating of the call control instruction according to the historical operation text information, the overload period information and a preset word extraction algorithm includes: Based on the overload period information, the historical operation text information is filtered and processed to generate historical operation sub-text information, wherein the historical operation sub-text information is used to describe a portion of the historical operation text information whose operation time is within the overload period information; Based on a preset word extraction algorithm, the historical operation sub-text information is subjected to word extraction processing to generate a plurality of word information to be detected; For each of the word information to be detected: based on a preset first sensitive word database, determine whether the word information to be detected is the same as any one of the first category of sensitive word information, wherein the first sensitive word database stores a plurality of the first category of sensitive word information; If the word information to be detected is the same as any one of the sensitive word information of the first category, determining that the word information to be detected is trigger word information; Generate trigger quantity information according to the total quantity of the trigger word information; If the trigger quantity information is greater than or equal to the preset trigger threshold information, the call current limiting instruction is generated, otherwise the call free instruction is generated.

4. The method according to claim 3, characterized in that Before generating trigger quantity information according to the total quantity of the trigger word information, the method further includes: For each of the word information to be detected: based on a preset second sensitive word database, determine whether the word information to be detected is the same as any second-category sensitive word information, wherein the second sensitive word database stores a plurality of the second-category sensitive word information, and the second-category sensitive word information is used to describe homophones of the first-category sensitive word information; If the word information to be detected is the same as any one of the second-category sensitive word information, the word information to be detected is determined to be trigger word information.

5. The method according to claim 4, characterized in that If the call free instruction is generated, if the trigger quantity information is greater than or equal to the preset trigger threshold information, then the call current limiting instruction is generated; otherwise, after the call free instruction is generated, the method further includes: Acquire the target user's call free cumulative duration information, wherein the call free cumulative duration information is used to describe the cumulative duration during which the trigger quantity information is less than the trigger threshold information; Comparing the free cumulative duration information of the call with the preset cumulative duration threshold information; If the cumulative free call duration information is greater than or equal to the cumulative duration threshold information, the target user is marked as a priority user, wherein the priority user is used to describe the target user to whom computing resources are preferentially scheduled.

6. A resource configuration system based on artificial intelligence gateway, characterized in that: The system comprises: A historical operation text information acquisition module: used to obtain the historical operation text information of the target user and the historical throughput record information of the target system in response to the call request instruction; An overload period information generating module: used to generate overload period information according to the historical throughput record information; A call control instruction generation module is used to generate a call control instruction according to the historical operation text information, the overload period information and a preset word extraction algorithm, wherein the call control instruction is a call free instruction or a call current limiting instruction.

7. The system according to claim 6, characterized in that The historical throughput record information includes a plurality of throughput information and sampling time information corresponding to each of the throughput information; The overload period information generating module comprises: A sampling period information generating submodule: for each sampling moment information in the historical throughput record information: based on the preset sampling period information, generating sampling period information, wherein the sampling period information is used to describe a time period starting from the sampling moment information and having the sampling period information as the duration; The throughput sum information generating submodule is used for generating throughput sum information for each sampling period information according to the plurality of throughput information corresponding to the sampling period information, wherein the throughput sum information is used to describe the sum of the plurality of throughput information corresponding to the sampling period information; The throughput sum information judgment submodule is used to judge whether the throughput sum information is greater than the preset throughput limit value information, wherein the throughput limit value information is the maximum throughput threshold information of the specified multiple; An overload period information determination submodule is used to determine that the sampling period information corresponding to the throughput sum information is the overload period information if the throughput sum information is greater than the throughput limit value information.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images