Method, apparatus, computer device, storage medium and program product of invoking a generative artificial intelligence
A knowledge graph and AI waiter system facilitates sustainable generative AI operations by providing customers with customized options based on their preferences and environmental impact, addressing the high energy consumption and sustainability concerns of generative AI.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2026-04-02
AI Technical Summary
The high energy consumption and environmental impact of generative AI technologies pose challenges in effectively involving customers in sustainable AI operations.
A system and method that utilizes a knowledge graph and AI waiter to generate customized menus for customers based on their sustainability preferences, business considerations, and carbon footprint monitoring, enabling them to choose AI services with optimal energy consumption methods.
Enables customers to make informed decisions about AI usage based on energy efficiency and sustainability, reducing carbon footprint while ensuring efficient and sustainable AI operations.
Smart Images

Figure CN2024121904_02042026_PF_FP_ABST
Abstract
Description
METHOD, APPARATUS, COMPUTER DEVICE, STORAGE MEDIUM AND PROGRAM PRODUCT OF INVOKING A GENERATIVE ARTIFICIAL INTELLIGENCETECHNICAL FIELD
[0001] Embodiments of the application relate to the technical field of artificial intelligence, and particularly relates to a method, an apparatus, an electronic device, a storage medium and a program product of invoking a generative artificial intelligence.BACKGROUND
[0002] The advent of generative Artificial Intelligence (AI) technologies, such as ChatGPT, or Midjourney, has make AI to a new capability level and brings many opportunities to transform how we live and work every day. However, its high energy cost and side-effect to the environment has raised more concerns when the popularity of generative AI increases.SUMMARY
[0003] The contents section of the present invention is provided to introduce in simplified form selected concepts which will be further described in the specific embodiments section below. The contents section of the invention is not intended to identify any key features or essential features of the claimed subject matter, nor is it intended to be used to assist in determining the scope of the claimed subject matter.
[0004] At least one of the embodiments of:
[0005] the application provides a method of invoking a generative artificial intelligence, wherein, comprising: receiving a target demand from a user; generating options corresponding to said target demand; providing feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option.
[0006] By above means, it is enabled to let user to choose the option to the artificial intelligence and give a selection of invoking artificial intelligence by economic and suitable energy consumption method.
[0007] In some embodiment, wherein generating options corresponding to said target demand comprises: generating a selection menu for said target demand, said selection menu comprising said corresponding options.
[0008] By above means, it is enabled to let user to choose based on this demand and give feedback to decided which option to invoking the artificial intelligence.
[0009] In some embodiment, wherein generating options corresponding to said target demand, comprises: generating said options based on a knowledge graph and said target demand; wherein said knowledge graph comprises an energy conserving method subgraph, a generative artificial intelligence model subgraph and a customer application subgraph.
[0010] By above means, it is provided different knowledge graph, and in the knowledge graph the different information and instruction are stored to use for involving the artificial intelligence appropriately and efficiently.
[0011] In some embodiment, wherein at least one of the following is further comprised: registering, as well as updating, said generative artificial intelligence model based on said generative artificial intelligence model subgraph; recommending energy conserving solutions based on said energy conserving method subgraph; generating a cost billing for said generative artificial intelligence invocation based on said target demand.
[0012] By above means, the information related to artificial intelligence are well stored and managed in the knowledge graph and later used for invoking the artificial intelligence and give the user a predicated billing cost for proposed target demand.
[0013] In some embodiment, generating options corresponding to said target demand, comprises: generating options corresponding to said target demand based on identification, location, capacity, energy type and availability of said generative artificial intelligence model.
[0014] By above means, the detailed information of generative artificial intelligence would be transformed or shared into the selection menu generation and option selection purpose.
[0015] In some embodiment, wherein providing feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option comprises: providing feedback on said target demand based on solar or wind energy consumption.
[0016] By above means, it can use green energy to invoking artificial intelligence and with less carbon dioxide emission and easy carbon footprint to follow and record.
[0017] The application also discloses a generative artificial intelligence invocation apparatus, wherein, comprising:
[0018] a waiter service module for receiving a target demand from a user;
[0019] a count service module for generating options corresponding to said target demand;
[0020] an artificial intelligence farm module for providing feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option
[0021] The application also provides a computer device comprising a memory and a processor, said memory storing a computer program, wherein said processor implements above said method when said computer program is executed by said processor.
[0022] The application also provides a computer readable storage medium having a computer program stored thereon, wherein said computer program implements above said method when executed by the processor.
[0023] The application also provides a computer program product, said computer program product being tangibly stored on a computer-readable medium and comprising computer-executable instructions, said computer-executable instructions when executed causing at least one processor to perform above said method as described above.DESCRIPTION OF DRAWINGS
[0024] To more clearly describe technical solutions in embodiments of the present disclosure or the prior art, drawings to be used in the description of the embodiments or the prior art will be briefly introduced below. Apparently, the drawings in the description below are merely some embodiments disclosed in the embodiments of the present disclosure. For those of ordinary skills in the art, other drawings may also be obtained based on these drawings.
[0025] FIG. 1 is schematic flowchart of a method of invoking a generative artificial intelligence provided in an embodiment of the present disclosure.
[0026] FIG. 2 is a schematic diagram of an apparatus of invoking a generative artificial intelligence provided in an embodiment of the present disclosure.
[0027] FIG. 3 is a schematic diagram of a computer device of invoking a generative artificial intelligence provided in an embodiment of the present disclosure.
[0028] FIG. 4 is a schematic diagram of customer comprehensive needs provided in an embodiment of the present disclosure.
[0029] FIG. 5 is a schematic diagram of layers for invoking a generative artificial intelligence provided in an embodiment of the present disclosure.
[0030] FIG. 6 is a schematic diagram of generative AI knowledge graph provided in an embodiment of the present disclosure.
[0031] FIG. 7 is a schematic diagram of three key steps to understand the customer comprehensive needs provided in an embodiment of the present disclosure.
[0032] FIG. 8 is a schematic diagram of workflow of AI waiter provided in an embodiment of the present disclosure.
[0033] List of reference numerals:
[0034] S101-S103: method steps
[0035] 200: apparatuses
[0036] 201: a waiter service module
[0037] 202: a count service module
[0038] 203: an artificial intelligence farm module
[0039] 300: computer device
[0040] 302: processor
[0041] 304: memory
[0042] 401: regular business considerations
[0043] 402: sustainability preferences
[0044] 403: carbon footprint monitoring / reporting
[0045] 404: customer comprehensive needs
[0046] 501: Generative AI model farm
[0047] 502: Counter service
[0048] 503: Waiter service
[0049] 504: Customer service
[0050] 600: generative AI model graph
[0051] 601: energy conserving method subgraph
[0052] 602: generative AI models subgraph
[0053] 603: customer application sub-graph
[0054] 701: collecting sustainability preference
[0055] 702: collecting regular business consideration
[0056] 703: collecting carbon footprint monitoring and reporting needs
[0057] 704: regular business considerations
[0058] 705: sustainability preferences
[0059] 706: carbon footprint monitoring / reporting
[0060] 707: customer comprehensive needs
[0061] S801-S817: method stepsDETAILED DESCRIPTION
[0062] In the following specification, many specific details are set forth for explanatory purposes. However, it will be appreciated that the realization of the present invention can be carried out without these specific details. In other examples, well-known circuits, structures, and techniques are not shown in detail so as not to affect the understanding of the specification.
[0063] Throughout the specification, there are references to “an embodiment” , “realization” , “exemplary embodiment” , “some embodiments” , “various embodiments” , “various embodiments” , “various embodiments” , “various embodiments” , “various embodiments” , and “various embodiments” , References to “an implementation” , “implementation” , “exemplary implementation” , “some implementations” , “various implementations” , etc., throughout the specification indicate that the described implementations of the present invention may include particular features, structures, or characteristics, however, it is not necessary for each implementation to include these particular features, structures, or characteristics. In addition, some implementations may have some, all, or none of the features described with respect to other implementations.
[0064] The scenario of this application is to build a method or apparatus to invoke generative artificial intelligence to process user demand based on reasonable energy consumption, business factor such as speed, accuracy and so on to finally give user an option or menu to choose and then feedback the result with generative artificial intelligence processing or other non AI processing.
[0065] As shown in FIG. 1, the method may include the following steps:
[0066] S101: receiving a target demand from a user;
[0067] The target demand also could be called customer demand. The individual customer demand can be illustrated in Figure 4. In some embodiments, customer demand is comprehensive, including three different aspects: regular business considerations 401 including price, performance and speed; sustainability preferences 402 including evaluation first, more solar energy, more winder energy and accept higher price; and carbon footprint monitoring / reporting 403. The intersection of three above mentioned circles is customer comprehensive needs 404, or in other words, is the target demand. In addition, the accuracy, speed and other aspect also need to be satisfied.
[0068] In some embodiment, the target demand receiving from users could be “wants to have a weather forecast report of next week” or “wants to have an advertise image from generative service” or “wants a report of a vertical market” . In this process of embodiment, chatting would be built for user to receive the target demand or get the customer application.
[0069] S102: generating options corresponding to said target demand;
[0070] In this step, the evaluation would be built for target demand, and evaluated whether suitable for invoking generative AI. If suitable to invoking generative AI, information of sustainability preferences, regular business considerations and carbon footprint monitoring / report would be collected for option generation. Furthermore, the speed, accuracy and other information would be collected for option generation and later selection. Based on such mentioned information, option could be generated to users.
[0071] In some embodiment, generating options corresponding to said target demand comprises: generating a selection menu for said target demand, said selection menu comprising said corresponding options.
[0072] In some embodiment, information of the collected customer demand will be sent to menu generation unit to create a customized menu for the customer. The customized menu will include: the available generative AI model services, the detail information of performance, response speed, energy source, accuracy and prices.
[0073] By above means, it is enabled to let user to choose options based on this listed condition and decide which option to employ to invoke the artificial intelligence.
[0074] In some embodiment, wherein generating options corresponding to said target demand, comprises: generating said options based on a knowledge graph and said target demand; wherein said knowledge graph comprises an energy conserving method subgraph, a generative artificial intelligence model subgraph and a customer application subgraph.
[0075] In Fig. 6, information of generative models which can be used for target demand are maintained in the generative AI model graph 600. Furthermore, the knowledge of customer applications is included in customer application sub-graph 603. The customer application sub-graph 603 could be used to process the information of target demand and to analyze the target demand into plurality of specific point to cooperate with the energy conserving method subgraph 601 and generative AI models subgraph 602. As a result, recommendations by generative AI models can be given according to the customer application subgraph.
[0076] In some embodiment, wherein at least one of the following is further comprised: registering, as well as updating, said generative artificial intelligence model based on said generative artificial intelligence model subgraph; recommending energy conserving solutions based on said energy conserving method subgraph; generating a cost billing for said generative artificial intelligence invocation based on said target demand.
[0077] In some embodiments, some functions could be implemented as below:
[0078] Generative AI model registration: to register a generative AI model so that it will be managed in this layer;
[0079] Generative AI model status updating: After registration, the status of the generative AI model in graph will be updated continuously.
[0080] Energy-conserving solution recommendation: create recommendation of energy-conserving solution with collected customer demand;
[0081] Menu generation: create customized menu for the customer with collected customer demand to support the customers’ decision-making;
[0082] Order creation: create an order based on the order application from the AI waiter to invoke generative AI to process the customer demand.
[0083] Connecting and billing: compete the connecting between customer and selected generative AI model and the billing of generative AI service according to customer order;
[0084] Customer activity monitoring and reporting: the sustainability activity will be recorded to help the customer monitor their sustainability activity or report the activity to an external monitoring system.
[0085] By above means, it is provided different knowledge graph, and different knowledge graph has different responsibility. Moreover, in the knowledge graph the different information and instruction are stored to use for involving the artificial intelligence appropriately and efficiently.
[0086] In some embodiment, generating options corresponding to said target demand, comprises: generating options corresponding to said target demand based on identification, location, capacity, energy type and availability of said generative artificial intelligence model.
[0087] In some embodiment, the generative AI models will be characterized by next parameters:
[0088] 1. Identity and locations: the generative AI model identity and its location;
[0089] 2. Capability: the domain (chatting generation, image generation, or engineering design generation) it works on, the performance, the speed to complete the task;
[0090] 3. Energy sources and percentage: The types of the sustainable source (solar, wind power) , and the percentage of the energy sources;
[0091] 4. Availability: the time it can work for the customer (current status and prediction) .
[0092] By above means, the detailed parameter related to generative AI would be transformed or shared along with the selection menu to customer for option display and selection.
[0093] S103: providing feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option.
[0094] In some embodiment, based on the selection of the option, generative AI would be invoked to process the target demand and give the feedback for the target demand based on the procession result of generative AI.
[0095] In some embodiment, wherein providing feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option comprises: providing feedback on said target demand based on solar or wind energy.
[0096] In some embodiment, solar energy or wind energy are green energy so it is environment friendly and with low carbon emissions or footprint to achieve the sustainable goal.
[0097] By above means, it is enabled to let user to choose the option to the artificial intelligence and give a selection of invoking artificial intelligence by economic and suitable energy consumption method.
[0098] In some embodiment, the scope of this invention disclosure will focus on sustainable generative AI operation in inference phase, and next ones are applicable in this innovation:
[0099] Use energy-conserving computational methods;
[0100] Be discerning about when you use generative AI;
[0101] Evaluate the energy sources of your cloud provider and data center;
[0102] Include AI activities in your carbon monitoring.
[0103] All the above actions items cannot be done without the involvement of customers. The challenge is that the customer demand of generative AI is comprehensive, and the technical problem here is how can we effectively invite and involve massive customers to use generative AI in a sustainable way.
[0104] In some embodiment, inspired by the restaurant’s way to meet diverse individual customer needs by the waiters to understand individual customer needs, and to serve them for a satisfactory dining, a system and method that in some degree like the restaurant is proposed to achieve a sustainable generative AI operation by involving customer individually in sustainability actions.
[0105] The technical problem can be reviewed again from the point of view of the generative AI customer:
[0106] As a customer, the transparency of energy consumption in computational methods and energy source is insufficient for decision-making to consider sustainability. As a customer, he or she need support in evaluation and monitoring of AI activities for sustainability goal.
[0107] As a result, the technical solution that is put forward is illustrated in Figure 5. The technical solution contained 4 layers and it can run like a restaurant to invite the guide the customers to use generative AI in a sustainable way.
[0108] Top layer 501 (Generative AI model farm) : The top layer is generative AI model farm layer in which generative AI models are located and run. Sustainability energies, such as solar power or winder power, can be used by the generative model to help achieve the sustainable goal.
[0109] Second layer 502 (Counter service) : The second layer is the counter service layer. Like the counter in the restaurant where the information and deal are centrally processed, this is the layer that manages information and business deal activity centrally. The core of the counter service layer is generative AI knowledge graph which is illustrated in Figure 6. Moreover, knowledge of energy-conserving methods, such as TinyML which is less computationally expensive to serve the customer application, is included in energy-conserving method sub-graph. With this sub-graph, an evaluation can be made for the customer on whether there’s an energy-conserving method available for the customer demand. In this layer, it contains function of generative AI model registration, Generative AI model status updating, energy-conserving solution recommendation, menu generation, order generation, connecting and billing and sustainability activity monitoring / reporting. The sustainability activity monitoring / reporting could further connect to external monitoring system.
[0110] Third layer 503 (waiter service) : The third layer is waiter service layer where the AI waiter is realized to serve the customer of generative AI. In this layer, AI waiter will chat with the customer to understand customer needs of generative AI, including: regular business considerations: e.g., generative AI service types to generate a text, or an image, or engineering design, etc., performance and speed requirements; their sustainability preferences; carbon footprint monitoring and reporting.
[0111] Customer can make a choice with the customized menu to meet their needs. The AI waiter then will help the customer to put an order to realize customer’s choice by sending an order application to counter service layer and start to use the generative model.
[0112] Bottom layer 504 (customer service) : The bottom layer is the customer layer where the customers are located to find the service of generative AI and at the same time their sustainability needs are met. In this layer, customer with sustainability awareness could receive customized menu and response the customer needs or customer demand.
[0113] In Figure 7, the three key steps to understand the customer comprehensive demand at the core of the three circles. For example, step of collecting sustainability preference 701 is corresponding to circle of sustainability preferences 705; step of collecting regular business consideration 702 is corresponding to circle of regular business considerations 704; step of collecting carbon footprint monitoring and reporting needs 703 is corresponding to circle of carbon footprint monitoring and reporting 706. And the interaction of three circle is customer comprehensive needs 707. The workflow of AI waiter to implement the three key steps is illustrated in Figure 8. For example, S801 is that customer comes, S802 is that AI waiter stat chat with customer, S803 is that get the customer application, S804 is that evaluation of application for generative AI. If not suitable, goes to S803 that recommend the customer to use energy-conserving method, S806 is that customer whether agree. If agree, goes to S807 that support to use energy-conserving method. If not agree, from S806 goes to S808 that collect sustainability preference. And S809 is that collect regular business considerations, S810 is that collect carbon footprint monitoring / reporting needs. And S811 is that formulate customer sustainability needs, S812 is that request a customized menu for customer, S813 is that show the menu to customer, S814 is that help the customer to make a choice in the menu, S815 is that put an order application for the customer, S816 is that tell the customer the information on the order execution, S817 is that say thanks to customer for sustainability behavior.
[0114] In detail, the AI waiter will chat with the customer (this can be well supported in current technology, as that used in Apple Siri) . In this workflow, when the demand of the customer is collected, the evaluation will be done to check if the demand is more suitable for an energy-conserving method. Based on the evaluation, an energy-conserving method might be recommended. After that, the customer’s sustainability preferences, and performance / speed / price needs will be collected. All the information will be used to generate a customized menu so that the most relevant offers of generative AI service can be included. The customer can make a choice with the menu, and the AI waiter can help to place an order for customer’s choice. Then, the AI waiter will tell the customer the information about following order execution and sustainability activity reporting to guarantee the customer satisfaction.
[0115] In summary, the AI waiter plays an important role to support the customer to realize their needs and sustainable goals, and to ensure that the sustainable generative AI operation can be achieved with the high involvement of customers.
[0116] Next use cases describe how to use this innovation to effectively involve customers to achieve sustainable generative AI operation by providing an individual offer to them:
[0117] Use case 1: the customer wants to have a weather forecast report of next week and was informed by AI waiter after evaluation that there’s no need to use generative AI because this information is available in website A. The customer is glad to be guided to website A. Short summary: Avoid the unnecessary use of generative AI.
[0118] Use case 2: the customer wants to have an advertise image from generative service. AI waiter showed the customized menu to the customer with two options:
[0119] Option1: get the result in 1 minutes with non-sustainable energy and high price.
[0120] Option2: get the result in 8 hours with solar power energy and with lower price.
[0121] The customer can wait for 8 hours and is glad to select the option 2 with low-carbon footprint recorded. Short summary: Customer can select a low-carbon offer with tradeoff between acceptable long waiting time and sustainability choice.
[0122] Use case 3: the customer wants a report of a vertical market from a generative AI. The AI waiter showed the menu to the customer with three options:
[0123] Option1: get the result in 10 minutes with non-sustainable energy and regular price.
[0124] Option2: get the result in 10 minutes with winder power energy and 20%higher price than option1.
[0125] Option3: get the result in 1 day with solar power energy, with lower price than option1.
[0126] The customer needs this market report right now but would like to pay more for using sustainable power. As a result, option 2 is selected. Short summary: Customer would like to pay higher price to have both a low-carbon offer and a short waiting time.
[0127] The technical effect of this application compared with the current solution has the following: use knowledge graph as single source to manage the capability and status of generative AI model; use AI waiter to collect the customer’s comprehensive needs; use customized menu to give the customized sustainable offers to customer.
[0128] The way to detect whether this application being used could follow next steps: check whether an AI waiter is used to interact with customer to collect the needs, including information about sustainability preferences; check if a customized menu is generated based on the customer input to give the suitable offers; check if knowledge graph is used to manage the generative AI models.
[0129] Although the individual steps in the flowchart of FIG. 1 are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless expressly stated herein, there is no strict order limitation on the execution of these steps, and the steps may be executed in other orders. Moreover, at least a portion of the steps of FIG. 1 may include multiple steps or multiple stages, which are not necessarily executed to completion at the same moment, but may be executed at different moments, and the order in which these steps or stages are executed is not necessarily sequential, but may be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps
[0130] As shown in FIG. 2, the application provides a generative artificial intelligence invocation apparatus 200, wherein, comprising:
[0131] a waiter service module 201 for receiving a target demand from a user;
[0132] a count service module 202 for generating options corresponding to said target demand;
[0133] an artificial intelligence farm module 203 for providing feedback on said target demand based on an energy consumption method of the artificial intelligence and selection of said option.
[0134] It is noted that the device may comprise more or fewer modules to perform the described functions. For example, at least one of the modules of FIG. 2 may be further divided into plural distinct sub-modules, each of which is used to perform at least a portion of the operations described herein in conjunction with the corresponding module. In addition, in some examples, the device 200 may include additional modules for performing other operations already described in the specification. In addition, it will be understood by those skilled in the art that the exemplary device 200 may be implemented with software, hardware, firmware, or any combination thereof.
[0135] FIG. 3 provides a computer device. According to one embodiment, the computer device 300 may include a processor 302, the processor 302 executing a computer program stored in a memory 304. The computer program is executed by the processor to implement the method described above.
[0136] It will be understood by one of ordinary skill in the art that the structure illustrated in FIG. 3, which is only a block diagram of a portion of the structure related to the embodiments of the present application, does not constitute a limitation on the computer device to which the present application is applied, and that a specific computer device may include more or fewer components than those shown in the drawings, or a combination of some of the components, or have a different arrangement of components.
[0137] A person of ordinary skill in the art may understand that all or part of the processes in the methods for realizing the above embodiments are possible to be accomplished by a computer program for instructing the relevant hardware, and that said computer program may be stored in a non-volatile computer-readable storage medium, which computer program, when executed, may comprise processes such as the processes of the embodiments of each of the above-described methods. Among other things, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include Read-Only Memory (ROM) , magnetic tape, floppy disk, flash memory, or optical memory. Volatile memory may include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, the RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM) , and the like.
[0138] The present application also provides a computer readable storage medium having a computer program stored thereon, said computer program realizing the above steps when executed by a processor.
[0139] The present application also provides a computer program product, said computer program product being tangibly stored on a computer-readable medium and comprising computer-executable instructions, said computer-executable instructions when executed causing at least one processor to perform said method.
[0140] Further, said computer program may be stored, run in the cloud for execution of said method. Further, components of said program may be laid out on multiple devices, on the cloud, e.g. the corresponding steps may be laid out, run on a local or local computer, or run on different cloud devices, transmitting signals via a communication connection, or may also be laid out, run on a local or local computer. The present application does not limit the described ways or methods, and the corresponding techniques can be flexibly laid out and deployed to fully utilize the cloud, big data, supercomputing power, and other devices and techniques for the execution and completion of the methods.
[0141] Some implementations of the present disclosure may include artifacts. The artifacts may include a storage medium, which is used to store logic. Examples of storage media may include one or more types of computer-readable storage media capable of storing electronic data, including volatile memory or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or rewritable memory, and the like. Examples of logic may include various software units, such as software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (APIs) , instruction sets, computational code, computer code, code segments, computer code segments, words, value, symbol, or any combination thereof. In some implementations, for example, the article may store executable computer program instructions that, when executed by the processor, cause the processor to perform the methods and / or operations described herein. The executable computer program instructions may include any suitable type of code, e.g., source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. The executable computer program instructions may be implemented according to a predefined computer language, manner, or syntax for commanding a computer to perform a particular function. Said instructions may be implemented using any suitable high-level, low-level, object-oriented, visual, compiled, and / or interpreted programming language.
[0142] What has been described above includes examples of the disclosed architecture. It is certainly not possible to describe every conceivable combination of components and / or methods, but those skilled in the art can appreciate that many other combinations and arrangements are possible. Accordingly, the novel architecture is intended to cover all such substitutions, modifications, and variations that fall within the spirit and scope of the appended claims.
[0143] Independent of the grammatical term usage, individuals with male, female or other gender identities are included within the term.
Claims
A method (100) of invoking a generative artificial intelligence, wherein, comprises:receiving (S101) atarget demand from a user;generating (S102) options corresponding to said target demand;providing (S103) feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option.The method (100) according to claim 1, wherein generating (S102) options corresponding to said target demand comprises:generating a selection menu for said target demand, said selection menu comprising said corresponding option.The method (100) according to claim 1, wherein generating (S102) options corresponding to said target demand, comprises:generating said options based on a knowledge graph and said target demand; wherein said knowledge graph comprises an energy conserving method subgraph, a generative artificial intelligence model subgraph, and a customer application subgraph.The method (100) according to claim 3, wherein at least one of the following is further comprised:registering, as well as updating, said generative artificial intelligence model based on said generative artificial intelligence model subgraph;recommending energy conserving solutions based on said energy conserving method subgraph;generating a cost billing for said generative artificial intelligence invocation based on said target demand.The method (100) according to claim 1, wherein generating (S102) options corresponding to said target demand, comprises:generating options corresponding to said target demand based on identification, location, capacity, energy type and availability of said generative artificial intelligence model.The method (100) according to claim 1, wherein providing (S103) feedback on said target demand based on an energy consumption method of said generative artificial intelligence and selection of said option comprises:providing feedback on said target demand based on solar or wind energy.A generative artificial intelligence invocation apparatus (200) , wherein, comprises:a waiter service module (201) for receiving a target demand from a user;a count service module (202) for generating options corresponding to said target demand;an artificial intelligence farm module (203) for providing feedback on said target demand based on an energy consumption method of the artificial intelligence and selection of said option.A computer device comprising a memory and a processor, said memory storing a computer program, wherein said processor realizes the steps of the method described in any one of claims 1 to 6 when said computer program is executed by said processor.A computer readable storage medium, wherein having stored a computer program, said computer program executed by the processor implements the steps of any one of claims 1 to 6.A computer program product, said computer program product being tangibly stored on a computer-readable medium and comprising computer-executable instructions, said computer-executable instructions executed causing at least one processor to perform the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Data processing method and apparatus
CN108268313A
Optimal carbon emission calculation unloading method and system of multi-energy supply edge system
CN114816584A
AI intelligent computing platform management method and system
CN118171743A
Algorithm model intelligent calling method and system
CN118227743A
Resource allocation and pricing method and system for new energy edge server calculation
CN118426946A