Energy storage scheduling strategy determination method and device, equipment and storage medium
By using user voice interaction and a pre-trained energy dispatch model, energy storage dispatch strategies are automatically generated, solving the problems of low efficiency and poor flexibility of traditional energy storage dispatch strategies and improving accuracy and security in complex scenarios.
Patent Information
- Application Number
- CN202511396675.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-28
- Publication Date
- 2026-01-09
AI Technical Summary
Traditional energy storage scheduling strategies rely on manual experience or fixed scenario data, which is inefficient, inflexible, and cannot guarantee accuracy and safety in complex scenarios.
By acquiring the user's target voice information and inputting it into a pre-trained energy dispatching model, the model automatically generates energy storage dispatching strategies using a constraint recognition module, a dispatching function determination module, and a dispatching strategy determination module, thereby improving the flexibility and interpretability of the strategies.
It improves the accuracy, security, and operational efficiency of energy storage scheduling strategies in complex scenarios, and achieves efficient strategy generation and interpretability.
Smart Images

Figure CN121303672A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and medium for determining energy storage scheduling strategies. Background Technology
[0002] With the rapid development of energy storage equipment, the requirements for the accuracy and dynamic adaptability of energy dispatching of energy storage equipment have increased significantly. As the core means to achieve efficient operation of energy storage equipment, energy storage dispatching strategy directly affects the reliability and economy of energy storage equipment.
[0003] Currently, traditional methods for determining energy storage dispatch strategies often rely on manual experience rules or data-driven approaches based on fixed scenarios. However, these traditional methods suffer from low efficiency and flexibility, as well as poor interpretability, thus failing to guarantee the accuracy and security of energy storage dispatch in complex scenarios. Summary of the Invention
[0004] This invention provides a method, apparatus, device, and medium for determining energy storage scheduling strategies, so as to achieve efficient generation of energy storage scheduling strategies, improve the flexibility and interpretability of energy storage scheduling strategy determination, and thus ensure the accuracy and safety of energy storage scheduling in complex scenarios.
[0005] According to one aspect of the present invention, a method for determining an energy storage scheduling strategy is provided, the method comprising:
[0006] Obtain the user's target voice information;
[0007] The target speech information is input into a pre-trained energy dispatch model to generate a strategy, and the energy storage dispatch strategy is determined based on the output of the energy dispatch model.
[0008] The energy dispatching model includes a constraint identification module, a dispatching function determination module, and a dispatching strategy determination module. The constraint identification module is used to determine dispatching constraint information based on the target speech information. The dispatching function determination module is used to determine a target dispatching function based on the dispatching constraint information. The dispatching strategy determination module is used to generate a strategy based on the dispatching constraint information and the target dispatching function.
[0009] According to another aspect of the present invention, an energy storage scheduling strategy determination apparatus is provided, the apparatus comprising:
[0010] The information acquisition module is used to acquire the user's target voice information;
[0011] The strategy determination module is used to input the target voice information into a pre-trained energy dispatch model to generate a strategy, and determine the energy storage dispatch strategy based on the output of the energy dispatch model.
[0012] The energy dispatching model includes a constraint identification module, a dispatching function determination module, and a dispatching strategy determination module. The constraint identification module is used to determine dispatching constraint information based on the target speech information. The dispatching function determination module is used to determine a target dispatching function based on the dispatching constraint information. The dispatching strategy determination module is used to generate a strategy based on the dispatching constraint information and the target dispatching function.
[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0014] At least one processor; and
[0015] A memory communicatively connected to the at least one processor; wherein,
[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the energy storage scheduling strategy determination method according to any embodiment of the present invention.
[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the energy storage scheduling strategy determination method according to any embodiment of the present invention.
[0018] The technical solution of this invention provides a data foundation for subsequent processing by acquiring the user's target voice information. The target voice information is input into a pre-trained energy dispatch model for strategy generation. Based on the output of the energy dispatch model, an energy storage dispatch strategy is determined. The energy dispatch model includes a constraint identification module, a dispatch function determination module, and a dispatch strategy determination module. The constraint identification module determines dispatch constraints based on the target voice information. The dispatch function determination module determines a target dispatch function based on the dispatch constraints. The dispatch strategy determination module generates a strategy based on the dispatch constraints and the target dispatch function, improving the accuracy and flexibility of energy storage strategy determination. This invention analyzes user voice interaction using an energy dispatch model and determines energy storage dispatch strategies, improving the flexibility and interpretability of energy storage dispatch strategy determination, and significantly enhancing the accuracy, security, and operational efficiency of energy storage dispatch in complex scenarios.
[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a flowchart of a method for determining an energy storage scheduling strategy according to Embodiment 1 of the present invention;
[0022] Figure 2 This is a flowchart of a method for determining an energy storage scheduling strategy according to Embodiment 2 of the present invention;
[0023] Figure 3 This is a schematic diagram of the structure of an energy storage scheduling strategy determination device according to Embodiment 3 of the present invention;
[0024] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the energy storage scheduling strategy determination method of the present invention. Detailed Implementation
[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0026] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0027] Example 1
[0028] Figure 1This is a flowchart illustrating a method for determining an energy storage scheduling strategy according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the energy storage scheduling strategy for an energy storage device needs to be determined. This method can be executed by an energy storage scheduling strategy determination device, which can be implemented in hardware and / or software. This energy storage scheduling strategy determination device can be configured in an electronic device. Figure 1 As shown, the method includes:
[0029] S110, Obtain the user's target voice information.
[0030] The target voice information can refer to the voice signal input by the user through hardware devices such as microphones and smart terminals.
[0031] Specifically, it can respond to user voice input operations on hardware devices such as microphones and smart terminals, acquire the target voice information input by the user, and provide basic data for subsequent processing.
[0032] For example, S110 may include: in response to a user's voice input operation, acquiring the user's original voice information; performing preprocessing operations on the original voice information to obtain target voice information, wherein the preprocessing operations include at least one of noise reduction processing and sound enhancement processing.
[0033] Raw voice information can refer to unprocessed voice signals directly input by the user through hardware devices such as microphones and smart terminals.
[0034] Specifically, a high-sensitivity microphone array or the built-in microphone of a smart terminal (such as a mobile phone) can be used to acquire the user's original voice signal in real time when the user triggers a voice input operation. The original voice information is then subjected to noise reduction and sound enhancement processing to obtain pre-processed target voice information, which helps to improve the accuracy of voice recognition and provides high-quality input for subsequent constraint recognition and strategy generation, thereby ensuring the accuracy and safety of energy dispatching strategies.
[0035] S120. Input the target speech information into the pre-trained energy dispatch model to generate a strategy, and determine the energy storage dispatch strategy based on the output of the energy dispatch model. The energy dispatch model includes a constraint identification module, a dispatch function determination module, and a dispatch strategy determination module. The constraint identification module is used to determine the dispatch constraint information based on the target speech information. The dispatch function determination module is used to determine the target dispatch function based on the dispatch constraint information. The dispatch strategy determination module is used to generate a strategy based on the dispatch constraint information and the target dispatch function.
[0036] The energy dispatch model can refer to a neural network model, which is an intelligent system composed of a constraint recognition module, a dispatch function determination module, and a dispatch strategy determination module, achieving full automation from voice input to dispatch strategy generation. Dispatch constraint information can refer to the quantitative rules extracted from the target speech, used to restrict dispatch behavior, including the target of interest and operational boundaries. The target dispatch function can refer to the optimization objective function derived from the dispatch constraint information, used to quantify the energy storage dispatch effect. The energy storage dispatch strategy can refer to the control commands used to dispatch energy storage devices.
[0037] Specifically, the target speech information can be input into a pre-trained energy dispatching model. The energy dispatching model can perform semantic parsing and information extraction on the target speech information according to the constraint recognition module to obtain dispatching constraint information. The dispatching function determination module corresponding to the energy dispatching model generates a target dispatching function based on the dispatching constraint information. The dispatching constraint information and the target dispatching function are then input into the dispatching strategy determination module for optimization and solution to obtain the energy storage dispatching strategy. This greatly improves the interpretability of the energy storage dispatching strategy and significantly enhances the accuracy and safety of energy storage dispatching in complex scenarios.
[0038] In this embodiment, the user's target voice information is acquired to provide a data foundation for subsequent processing. The target voice information is input into a pre-trained energy dispatch model for strategy generation. The energy dispatch model's output determines the energy storage dispatch strategy. The energy dispatch model includes a constraint identification module, a dispatch function determination module, and a dispatch strategy determination module. The constraint identification module determines dispatch constraints based on the target voice information; the dispatch function determination module determines a target dispatch function based on the dispatch constraints; and the dispatch strategy determination module generates a strategy based on the dispatch constraints and the target dispatch function, improving the accuracy and flexibility of energy storage strategy determination. This invention analyzes user voice interaction using an energy dispatch model and determines energy storage dispatch strategies, improving the flexibility and interpretability of energy storage dispatch strategy determination, and significantly enhancing the accuracy, security, and operational efficiency of energy storage dispatch in complex scenarios.
[0039] Example 2
[0040] Figure 2 This is a flowchart of a method for determining an energy storage scheduling strategy according to Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes the step of "inputting the target voice information into a pre-trained energy scheduling model for strategy generation". Explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.
[0041] See Figure 2 The alternative method for determining energy storage scheduling strategy provided in this embodiment specifically includes the following steps:
[0042] S210, Obtain the user's target voice information.
[0043] S220. Input the target speech information into the constraint recognition module for information extraction and determine the scheduling constraint information corresponding to the target speech information.
[0044] Specifically, the target speech information can be input into the constraint recognition module, which can be built based on a large language model. The constraint recognition module performs word segmentation, entity recognition, and relation extraction on the target speech information to obtain the target keywords, priority information, and hard constraint information corresponding to the target speech information. The target keywords, priority information, and hard constraint information are then used as the scheduling constraint information corresponding to the target speech information, thereby reducing manual costs and improving efficiency.
[0045] For example, the constraint recognition module includes: a speech recognition unit and an information extraction unit; S220 may include: inputting the target speech information into the speech recognition unit for speech recognition to obtain target text information; inputting the target text information into the information extraction unit for information extraction to obtain scheduling constraint information corresponding to the target speech information.
[0046] Specifically, the target speech information is input to the speech recognition unit, which converts it into structured text (target text information) based on a speech recognition model. This target text information is then input to the information extraction unit, which performs word segmentation, part-of-speech tagging, and entity recognition on the received target text information using a large language model to obtain the scheduling constraint information corresponding to the target speech information. Through the collaborative work of the speech recognition unit and the information extraction unit, the constraint recognition module achieves efficient and accurate conversion from natural language speech to structured constraints, providing high-quality input for subsequent scheduling function determination and strategy generation, ultimately ensuring the accuracy and security of the energy scheduling strategy.
[0047] S230. Input the scheduling constraint information into the scheduling function determination module to determine the target scheduling function.
[0048] Specifically, scheduling constraint information can be input into the scheduling function determination module. The scheduling function determination module can use a weighted sum method to process the multi-objective problem (such as equipment life, economy, and carbon emission reduction) corresponding to the scheduling constraint information, and construct a weighted conformity function, i.e., the target scheduling function. This can avoid strategy failure caused by the disconnect between the target and the constraint, and improve security.
[0049] For example, the scheduling function determination module includes a weight mapping unit and a scheduling function determination unit; S230 may include: inputting scheduling constraint information into the weight mapping unit to perform weight mapping processing on multiple atomic objective functions to obtain a target weight sequence; inputting the target weight sequence into the scheduling function determination unit to perform weighted summation on multiple atomic objective functions to obtain a target scheduling function.
[0050] In energy scheduling, an atomic objective function can refer to a pre-normalized semantic expression defined to achieve a specific optimization objective. Each atomic objective function corresponds to a specific optimization dimension (such as economy, environmental friendliness, response speed, etc.). The objective weight sequence can refer to the sequence of weight values assigned to each atomic objective function in multi-objective optimization, reflecting the relative importance of different objectives in the overall optimization and dynamically adapting to scenario requirements.
[0051] Specifically, scheduling constraint information can be input into the weight mapping unit to perform weight mapping processing on multiple atomic objective functions, determining the weight corresponding to each atomic objective function and generating a target weight sequence. This target weight sequence is then input into the scheduling function determination unit, which linearly combines the target weight sequence output by the weight mapping unit with the multiple atomic objective functions to generate the target scheduling function. Through the collaborative work of the weight mapping unit and the scheduling function determination unit, the scheduling function determination module achieves intelligent transformation from constraint information to the target scheduling function, significantly improving the accuracy, safety, and operational efficiency of energy scheduling in complex scenarios.
[0052] For example, the weight mapping unit is specifically used to perform the following steps: determining the target priority sequence based on scheduling constraint information; performing weight mapping processing on multiple atomic objective functions based on the target priority sequence to obtain the original weight sequence; and normalizing the original weight sequence to obtain the target weight sequence.
[0053] The original weight sequence can refer to the set of initial weight values obtained after weight mapping of multiple atomic objective functions. This sequence has not been normalized, and the sum of the weights may not be 1. It can directly reflect the relative importance of each atomic objective function in multi-objective optimization.
[0054] Specifically, the target priority sequence can be determined based on scheduling constraint information; multiple atomic objective functions can be weighted according to their priority based on the target priority sequence to obtain the original weight sequence; and the weights of the same priority in the original weight sequence can be normalized to obtain the target weight sequence. This transforms subjective priority into objective weights and avoids weight allocation bias caused by human experience.
[0055] For example, the scheduling constraint information could be "prioritize economy, then battery life, SOC not less than 20%." In this case, the target keywords are determined to be economy and battery life. The target priority sequence is then: economy > battery life, and battery life > all other targets except the target keywords. It should be noted that each target corresponds to an atomic objective function. A preset weight allocation strategy can be used to map the weights of the atomic objective functions corresponding to each target in the target priority sequence to obtain the original weight sequence. For example, the original weight sequence might be economy. Battery life The remaining objectives are each assigned a weight of 0.1. After normalization, the objective weight sequence is the economic one. Battery life The weight of the sum of the remaining objectives is 0.1.
[0056] For example, the atomic objective function may include economy. ,life Multiple atomic objective functions.
[0057]
[0058] in, , , , For time step indexing (15-minute granularity). Energy storage power (discharge is positive, charging is negative, unit is MW). To purchase electricity, The selling price of electricity.
[0059]
[0060] in, Cost per unit cycle decay Rated capacity of the battery (in MWh).
[0061] S240. Input the scheduling constraint information and target scheduling function into the scheduling strategy determination module to generate a strategy and determine the energy storage scheduling strategy.
[0062] Specifically, scheduling constraint information and target scheduling function can be input into the scheduling strategy determination module for integration, generating a constrained optimization model, and solving the optimization model to obtain the global optimal solution, i.e., the energy storage scheduling strategy. This ensures the interpretability of the energy storage scheduling strategy and improves subsequent energy storage scheduling and security.
[0063] For example, the scheduling strategy determination module includes: a constraint generation unit and a strategy determination unit; S240 may include: inputting scheduling constraint information into the constraint generation unit for semantic transformation to generate a target constraint function; inputting the target constraint function and the target scheduling function into the strategy determination unit for scheduling strategy generation to determine the energy storage scheduling strategy.
[0064] Among them, the objective constraint function can refer to the core tool that transforms natural language or structured scheduling constraint information into mathematical expressions, and is the mathematical carrier of constraints in optimization solutions.
[0065] Specifically, scheduling constraint information can be input into the constraint generation unit for semantic transformation, converting the semantic constraints in the scheduling constraint information into linear inequalities to generate the objective constraint function. The objective constraint function and the objective scheduling function are then input into the strategy determination unit, where they are integrated into a constrained optimization problem and solved to obtain the energy storage scheduling strategy. This achieves the optimal solution of the objective function while satisfying all constraints, improving the interpretability of the energy storage scheduling strategy and determining its stability in dynamic environments.
[0066] For example, the target scheduling function can be as follows:
[0067]
[0068] in, The interpretability score for energy storage dispatch strategy. For the atomic objective function corresponding to economic efficiency, The atomic objective function corresponding to battery life. For objectives other than economy and battery life, the semantic constraint "SOC not less than 20%" in the scheduling constraint information can be converted into an objective constraint function. The power limit can be generated according to the nameplate value. Then, the objective constraint function and the objective scheduling function are integrated into a constrained optimization model, as shown below:
[0069]
[0070]
[0071]
[0072] in, Let be the state of charge (SOC) of the energy storage device at time t. Ultimately, the energy storage dispatch strategy can be: "This dispatch prioritizes economic gains with 60% weight, controls battery degradation with 30% weight, and ensures the SOC is not lower than 20%." The interpretable score of this strategy is... It should be noted that... The larger the value, the higher the overall efficiency of the energy storage dispatch strategy.
[0073] The technical solution of this embodiment extracts information from the target voice information by inputting it into the constraint recognition module, thereby determining the scheduling constraint information corresponding to the target voice information. This can replace manual configuration, reduce human configuration errors, and improve efficiency. Inputting the scheduling constraint information into the scheduling function determination module to determine the target scheduling function ensures the correlation between the target function and the constraints, avoiding strategy failure caused by a disconnect between the target and constraints, and improving scenario adaptability. Inputting the scheduling constraint information and the target scheduling function into the scheduling strategy determination module to generate a strategy and determine the energy storage scheduling strategy improves the interpretability and security of the energy storage scheduling strategy. This invention, through automated constraint recognition and energy storage scheduling strategy generation, can greatly improve the efficiency of energy storage scheduling strategy determination and significantly enhance the accuracy, security, and operational efficiency of energy storage scheduling in complex scenarios.
[0074] Example 3
[0075] Figure 3 This is a schematic diagram of an energy storage scheduling strategy determination device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an information acquisition module 310 and a strategy determination module 320;
[0076] Among them, the information acquisition module 310 is used to acquire the user's target voice information;
[0077] The strategy determination module 320 is used to input the target voice information into a pre-trained energy scheduling model to generate a strategy, and determine the energy storage scheduling strategy based on the output of the energy scheduling model.
[0078] The energy dispatching model includes a constraint identification module, a dispatching function determination module, and a dispatching strategy determination module. The constraint identification module is used to determine dispatching constraint information based on the target speech information. The dispatching function determination module is used to determine a target dispatching function based on the dispatching constraint information. The dispatching strategy determination module is used to generate a strategy based on the dispatching constraint information and the target dispatching function.
[0079] In this embodiment, the user's target voice information is acquired to provide a data foundation for subsequent processing. The target voice information is input into a pre-trained energy dispatch model for strategy generation. Based on the output of the energy dispatch model, an energy storage dispatch strategy is determined. The energy dispatch model includes a constraint identification module, a dispatch function determination module, and a dispatch strategy determination module. The constraint identification module determines dispatch constraints based on the target voice information. The dispatch function determination module determines a target dispatch function based on the dispatch constraints. The dispatch strategy determination module generates a strategy based on the dispatch constraints and the target dispatch function, improving the accuracy and flexibility of energy storage strategy determination. This invention analyzes user voice interaction using an energy dispatch model and determines energy storage dispatch strategies, improving the flexibility and interpretability of energy storage dispatch strategy determination, and significantly enhancing the accuracy, security, and operational efficiency of energy storage dispatch in complex scenarios.
[0080] Optionally, the information acquisition module 310 is specifically used to: in response to the user's voice input operation, acquire the user's original voice information; perform preprocessing operations on the original voice information to obtain target voice information, wherein the preprocessing operation includes at least one of noise reduction processing and sound enhancement processing.
[0081] Optionally, the strategy determination module 320 includes:
[0082] A constraint recognition unit is used to input the target speech information into the constraint recognition module for information extraction and to determine the scheduling constraint information corresponding to the target speech information.
[0083] The function determination unit is used to input the scheduling constraint information into the scheduling function determination module to determine the target scheduling function;
[0084] The strategy generation unit is used to input the scheduling constraint information and the target scheduling function into the scheduling strategy determination module to generate a strategy and determine the energy storage scheduling strategy.
[0085] Optionally, the constraint recognition module includes: a speech recognition unit and an information extraction unit; the constraint recognition unit is specifically used to: input the target speech information into the speech recognition unit for speech recognition to obtain target text information; input the target text information into the information extraction unit for information extraction to obtain scheduling constraint information corresponding to the target speech information.
[0086] Optionally, the scheduling function determination module includes a weight mapping unit and a scheduling function determination unit; the function determination unit is specifically used to: input the scheduling constraint information into the weight mapping unit to perform weight mapping processing on multiple atomic objective functions to obtain a target weight sequence; input the target weight sequence into the scheduling function determination unit to perform weighted summation on multiple atomic objective functions to obtain a target scheduling function.
[0087] Optionally, the weight mapping unit is specifically used to perform the following steps: determining a target priority sequence based on the scheduling constraint information; performing weight mapping processing on multiple atomic objective functions based on the target priority sequence to obtain an original weight sequence; and normalizing the original weight sequence to obtain a target weight sequence.
[0088] Optionally, the scheduling strategy determination module includes: a constraint generation unit and a strategy determination unit; the strategy generation unit is specifically used to: input the scheduling constraint information into the constraint generation unit for semantic transformation to generate a target constraint function; input the target constraint function and the target scheduling function into the strategy determination unit to generate a scheduling strategy and determine an energy storage scheduling strategy.
[0089] The above-described device can execute the energy storage scheduling strategy determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the energy storage scheduling strategy determination method.
[0090] Example 4
[0091] Figure 4 This is a schematic diagram of the structure of an electronic device implementing the energy storage scheduling strategy determination method of this invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0092] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0093] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0094] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the energy storage scheduling strategy determination method.
[0095] In some embodiments, the energy storage scheduling strategy determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the XX method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the energy storage scheduling strategy determination method by any other suitable means (e.g., by means of firmware).
[0096] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.
[0097] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0098] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0099] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0100] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0101] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0102] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0103] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0104] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for determining an energy storage dispatch strategy, characterized in that, include: Obtain the user's target voice information; The target speech information is input into a pre-trained energy dispatch model to generate a strategy, and the energy storage dispatch strategy is determined based on the output of the energy dispatch model. The energy dispatching model includes a constraint identification module, a dispatching function determination module, and a dispatching strategy determination module. The constraint identification module is used to determine dispatching constraint information based on the target speech information. The dispatching function determination module is used to determine a target dispatching function based on the dispatching constraint information. The dispatching strategy determination module is used to generate a strategy based on the dispatching constraint information and the target dispatching function.
2. The method according to claim 1, characterized in that, The acquisition of the user's target voice information includes: In response to the user's voice input, obtain the user's original voice information; The original speech information is preprocessed to obtain target speech information, wherein the preprocessing operation includes at least one of noise reduction processing and sound enhancement processing.
3. The method according to claim 1, characterized in that, The step of inputting the target speech information into a pre-trained energy scheduling model for policy generation includes: The target speech information is input into the constraint recognition module for information extraction to determine the scheduling constraint information corresponding to the target speech information; The scheduling constraint information is input into the scheduling function determination module to determine the target scheduling function; The scheduling constraint information and the target scheduling function are input into the scheduling strategy determination module to generate a strategy and determine the energy storage scheduling strategy.
4. The method according to claim 3, characterized in that, The constraint recognition module includes: a speech recognition unit and an information extraction unit; The step of inputting the target speech information into the constraint recognition module for information extraction and determining the scheduling constraint information corresponding to the target speech information includes: The target speech information is input into the speech recognition unit for speech recognition to obtain the target text information; The target text information is input into the information extraction unit for information extraction to obtain the scheduling constraint information corresponding to the target speech information.
5. The method according to claim 3, characterized in that, The scheduling function determination module includes: a weight mapping unit and a scheduling function determination unit; The step of inputting the scheduling constraint information into the scheduling function determination module to determine the target scheduling function includes: The scheduling constraint information is input into the weight mapping unit to perform weight mapping processing on multiple atomic objective functions to obtain the target weight sequence; The target weight sequence is input into the scheduling function determination unit to perform a weighted summation of multiple atomic objective functions to obtain the target scheduling function.
6. The method according to claim 5, characterized in that, The weight mapping unit is specifically used to perform the following steps: Based on the scheduling constraint information, a target priority sequence is determined; Based on the target priority sequence, multiple atomic objective functions are weighted and mapped to obtain the original weight sequence. The original weight sequence is normalized to obtain the target weight sequence.
7. The method according to claim 3, characterized in that, The scheduling strategy determination module includes: a constraint generation unit and a strategy determination unit; The step of inputting the scheduling constraint information and the target scheduling function into the scheduling strategy determination module to generate a strategy and determine the energy storage scheduling strategy includes: The scheduling constraint information is input into the constraint generation unit for semantic transformation to generate the target constraint function; The target constraint function and the target scheduling function are input into the strategy determination unit to generate a scheduling strategy and determine the energy storage scheduling strategy.
8. An energy storage scheduling strategy determination device, characterized in that, include: The information acquisition module is used to acquire the user's target voice information; The strategy determination module is used to input the target voice information into a pre-trained energy dispatch model to generate a strategy, and determine the energy storage dispatch strategy based on the output of the energy dispatch model. The energy dispatching model includes a constraint identification module, a dispatching function determination module, and a dispatching strategy determination module. The constraint identification module is used to determine dispatching constraint information based on the target speech information. The dispatching function determination module is used to determine a target dispatching function based on the dispatching constraint information. The dispatching strategy determination module is used to generate a strategy based on the dispatching constraint information and the target dispatching function.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the energy storage scheduling strategy determination method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the energy storage scheduling strategy determination method according to any one of claims 1-7.
