Comprehensive energy management system number asking method based on big language model and intelligent companion assistant

Abstract

The invention discloses a big language model-based comprehensive energy management system number asking method and an intelligent companion assistant. The comprehensive energy management system number asking method based on the large language model comprises the steps that consultation information input by a user is received, and the consultation information is used for requesting target data from a comprehensive energy management system; analyzing the consultation information to obtain corresponding prompt words; inputting the cue word into a pre-trained consultation model, so that the consultation model obtains the target data from the comprehensive energy management system according to the cue word; and providing the target data to the user. According to the method and the device, the user can be helped to quickly and directly find the required data or indexes from the comprehensive energy management system, the operation and management work complexity and complexity are reduced, the data query speed and convenience are improved, and then the management efficiency can be improved.

Description

Technical Field

[0001] This application generally relates to the technical field of energy enterprise management, and specifically relates to a method for querying data in an integrated energy management system based on a large language model and an intelligent companion assistant. Background Art

[0002] Energy enterprise management, especially the management of multi-category energy operations, involves various aspects such as daily production operations, energy allocation, operation and maintenance management, and personnel management. In the integrated energy management system of an enterprise, relevant personnel need to find the corresponding business module in the integrated energy management system and then find the specified page in the corresponding business module to view the required data and metrics. In addition, there are often many business modules in the integrated energy management system, and the system also includes a lot of pages. Especially for those who are not familiar with the system, it is very difficult to find the specified page. Even for those who are familiar with the system, they need to find the corresponding business module and then further start from that business module to find the specified page to query data, which is inconvenient to operate. As a result, the daily operations and management work are cumbersome and complex, and the management efficiency is low. Summary of the Invention

[0003] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method for querying data in an integrated energy management system based on a large language model and an intelligent companion assistant, which can help users quickly and directly find the required data or metrics from the integrated energy management system, reduce the cumbersome and complex degree of operation and management work, improve the query speed and convenience of data, and thus can improve management efficiency.

[0004] In a first aspect, an embodiment of the present application provides a method for querying data in an integrated energy management system based on a large language model, including:

[0005] Receiving the consultation information input by the user, where the consultation information is used to request target data from the integrated energy management system;

[0006] Parsing the consultation information to obtain corresponding prompt words;

[0007] Inputting the prompt words into a pre-trained consultation model so that the consultation model obtains the target data from the integrated energy management system according to the prompt words;

[0008] Providing the target data to the user.

[0009] In some examples, the parsing the consultation information to obtain corresponding prompt words includes:

[0010] Parsing the consultation information to determine the business attribute theme corresponding to the consultation information;

[0011] Retrieve the corresponding prompt word from a pre - released list of prompt words according to the business attribute theme, where the prompt words in the list of prompt words are pre - written and released.

[0012] In some examples, the inputting the prompt word into a pre - trained consultation model so that the consultation model obtains the target data from the integrated energy management system according to the prompt word includes:

[0013] Input the prompt word into a pre - trained consultation model;

[0014] Retrieve the corresponding service interface according to the prompt word;

[0015] Query the target data from the integrated energy management system based on the service interface.

[0016] In some examples, before retrieving the corresponding service interface according to the prompt word, it further includes:

[0017] Obtain the relevant service data of the integrated energy management system;

[0018] Provide a service interface according to the relevant service data.

[0019] In some examples, before inputting the prompt word into a pre - trained consultation model, it further includes:

[0020] Input a sample of prompt words into an initial consultation model, and train the initial consultation model according to the loss between the output of the initial consultation model and the target to obtain the consultation model.

[0021] In some examples, the providing the target data to the user includes:

[0022] Present the target data to the user; and / or,

[0023] Provide a query interface for the target data.

[0024] In some examples, the providing the query interface for the target data includes:

[0025] Provide a display interface for the target data; and / or,

[0026] Provide a query link for the target data.

[0027] In a second aspect, an embodiment of the present application provides a Zhiban assistant, including:

[0028] A receiving module, configured to receive consultation information input by a user, where the consultation information is used to request target data from an integrated energy management system;

[0029] A parsing module for parsing the consultation information to obtain corresponding prompt words;

[0030] A consultation module for inputting the prompt words into a pre-trained consultation model, so that the consultation model can obtain the target data from the integrated energy management system according to the prompt words;

[0031] A providing module for providing the target data to the user.

[0032] In a third aspect, an embodiment of the present application provides a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The feature is that when the processor executes the program, it implements the integrated energy management system question number method based on a large language model described in the embodiment of the first aspect of the application.

[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the integrated energy management system question number method based on a large language model described in the embodiment of the first aspect of the present application.

[0034] The integrated energy management system question number method and intelligent companion assistant proposed in the embodiment of the present application receive the consultation information input by the user, parse the consultation information to obtain prompt words, input the prompt words into a pre-trained consultation model, and the consultation model can obtain corresponding target data from the integrated energy management system according to the prompt words, and finally provide the target data to the user. Thus, it can help the user quickly and directly find the required data or indicators from the integrated energy management system, without the user having to find the corresponding business module from the integrated energy management system and then find the corresponding page from the business module to query the required data or indicators. Therefore, it reduces the complexity and tediousness of operation and management, improves the query speed and convenience of data, and further can improve the management efficiency.

[0035] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objects, and advantages of the present application will become more obvious:

[0037] Figure 1 It is a schematic flowchart of the integrated energy management system question number method based on a large language model according to an embodiment of the present application;

[0038] Figure 2Schematic diagram of the application of the method for querying numbers in an integrated energy management system based on a large language model according to an embodiment of the present application;

[0039] Figure 3 Another process schematic diagram of the method for querying numbers in an integrated energy management system based on a large language model according to an embodiment of the present application;

[0040] Figure 4 Block diagram of the structure of the intelligent companion assistant according to an embodiment of the present application;

[0041] Figure 5 Shows a schematic diagram of the structure of a computing device suitable for implementing the embodiments of the present application. Detailed implementation manners

[0042] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, rather than limiting the application. In addition, it should be noted that, for the sake of convenience of description, only parts related to the application are shown in the drawings.

[0043] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and embodiments.

[0044] The following combines the attached Figure 1 Describe the method for querying numbers in an integrated energy management system based on a large language model and the intelligent companion assistant according to the embodiments of the present application.

[0045] Figure 1 Is a flowchart of the method for querying numbers in an integrated energy management system based on a large language model according to an embodiment of the present application. Among them, the method for querying numbers in an integrated energy management system based on a large language model according to the embodiment of the present application can be applied in the intelligent companion assistant, and this component can be an application, such as: the energy and carbon intelligent companion, such as Figure 2 As shown, the energy and carbon intelligent companion can be simply referred to as the intelligent companion.

[0046] Such as Figure 1 As shown, according to the method for querying numbers in an integrated energy management system based on a large language model according to an embodiment of the present application, the following steps are included:

[0047] S101: Receive the consultation information input by the user, where the consultation information is used to request target data from the integrated energy management system.

[0048] Combined with Figure 2As shown, at the front end of the integrated energy management system, the user poses a question to be consulted through the Energy and Carbon Intelligent Assistant, that is: the consultation information, which can be a conversation or text. After the front end of the integrated energy management system obtains the question the user wants to consult, it transmits it to the Energy and Carbon Intelligent Assistant. In a specific example, for instance, the consultation information is transmitted to the Energy and Carbon Intelligent Assistant in the form of the websocket network communication protocol.

[0049] In the above description, the question the user wants to consult can be a query for specific data or a query for specific metrics.

[0050] S102: Parse the consultation information to obtain the corresponding prompt words.

[0051] In an embodiment of the present application, parsing the consultation information to obtain the corresponding prompt words includes: parsing the consultation information to determine the business attribute theme corresponding to the consultation information; according to the business attribute theme, retrieving the corresponding prompt words from a pre-published prompt word list, where the prompt words in the prompt word list are pre-written and published.

[0052] Specifically, as shown in Figure 3 the Energy and Carbon Intelligent Assistant (Intelligent Assistant) parses the consultation information and judges the business attribute theme of the consultation information. Determine the business attribute theme and retrieve the corresponding Prompt (prompt words).

[0053] In a specific application, different energy types can correspond to different business attribute themes. For example: natural gas energy corresponds to one business attribute theme, and electric energy corresponds to one business attribute theme.

[0054] It should be noted that the prompt words in the prompt word list are pre-written and published. For example: the writing and publishing of the prompt words for the integrated energy management system are completed based on a large language model technology platform (such as the consultation model in the present application).

[0055] S103: Input the prompt words into a pre-trained consultation model so that the consultation model obtains the target data from the integrated energy management system according to the prompt words.

[0056] In an embodiment of the present application, inputting the prompt words into a pre-trained consultation model so that the consultation model obtains the target data from the integrated energy management system according to the prompt words includes: inputting the prompt words into a pre-trained consultation model; retrieving the corresponding business interface according to the prompt words; based on the business interface, querying the target data from the integrated energy management system.

[0057] It should be noted that before retrieving the corresponding service interface according to the prompt, it includes: obtaining the relevant service data of the integrated energy management system; providing a service interface according to the relevant service data.

[0058] Combined with Figure 2 and Figure 3 As shown, the large language model (i.e., the consultation model) obtains the prompt, parses the key parameter information, and returns it to the energy and carbon intelligent assistant. That is, the energy and carbon intelligent assistant retrieves the relevant service interface according to the parameter information returned by the large language model; the service interface executes an interface query based on the input parameters and returns the relevant data / metric information.

[0059] Specifically, the relevant service data of the integrated energy management system is pre-organized, that is, a data interface is provided. After the user completes the corresponding role setting in the integrated energy management system, the user uses the energy and carbon intelligent assistant in the integrated energy management system. For example, when the user inputs the data, metrics, etc. they want to know, the energy and carbon intelligent assistant applies the large language model to semantically understand the user's input requirements, determine the intention, and retrieve the corresponding service interface to query the data, metrics, etc. After the energy and carbon intelligent assistant completes the service interface query through the large model technology, it obtains the target data such as the data and metrics returned by the integrated energy management system.

[0060] In the above description, the consultation model is pre-trained. Therefore, in an embodiment of the present application, a training method for the consultation model is also provided. Specifically, before inputting the prompt into the pre-trained consultation model, it further includes: inputting the prompt sample into the initial consultation model, and training the initial consultation model according to the loss between the output of the initial consultation model and the target to obtain the consultation model. That is, training samples and sample labels are provided in advance, and then the model is trained according to the training samples and labels, and the model parameters are continuously adjusted until the loss between the output of the consultation model and the label meets the expectation, and then the model training is completed. Among them, the loss between the output of the consultation model and the label can be calculated through the loss function of the model.

[0061] S104: Provide the target data to the user.

[0062] In a specific example, providing the target data to the user includes: presenting the target data to the user; and / or providing a query interface for the target data.

[0063] In this example, providing a query interface for the target data includes: providing a display interface for the target data; and / or providing a query link for the target data.

[0064] Combined with Figure 2 andFigure 3 As shown, the Nengtan Zhiban intelligent assistant sorts and renders all information and instructions for opening the business system page; among them, the prompt words Prompt corresponding to different themes carry specified business attributes and are associated with the page information parameters in the business system.

[0065] The Nengtan Zhiban intelligent assistant receives the information and completes the rendering and display, and can also open the specified business system page according to the instructions. The Nengtan Zhiban intelligent assistant completes the business interface query through the large model technology, obtains the returned data and indicators, echoes them in the Nengtan Zhiban, and opens the system interface where they are located according to the indicator data for the customer to further understand and analyze the data.

[0066] According to the method for querying data of the integrated energy management system based on the large language model in the embodiments of the present application, the user input consultation information is received, the consultation information is parsed to obtain the prompt words, the prompt words are input into the pre-trained consultation model, and the consultation model can obtain the corresponding target data from the integrated energy management system according to the prompt words, and finally the target data is provided to the user. Thus, it can help the user quickly and directly find the required data or indicators from the integrated energy management system, without the user having to find the corresponding business module from the integrated energy management system and then find the corresponding page from the business module to query the required data or indicators. Therefore, it reduces the tediousness and complexity of operation and management, improves the query speed and convenience of data, and further improves the management efficiency.

[0067] Furthermore, as Figure 4 shown, the embodiments of the present application also provide a Zhiban assistant, including: a receiving module 410, a parsing module 420, a consultation module 430, and a providing module 440, where:

[0068] The receiving module 410 is configured to receive the consultation information input by the user, where the consultation information is used to request target data from the integrated energy management system;

[0069] The parsing module 420 is configured to parse the consultation information to obtain the corresponding prompt words;

[0070] The consultation module 430 is configured to input the prompt words into the pre-trained consultation model so that the consultation model can obtain the target data from the integrated energy management system according to the prompt words;

[0071] The providing module 440 is configured to provide the target data to the user.

[0072] The intelligent companion assistant according to the embodiments of the present application receives the consultation information input by the user, parses the consultation information to obtain a prompt word, inputs the prompt word into a pre-trained consultation model, and the consultation model can obtain corresponding target data from the integrated energy management system according to the prompt word, and finally provides the target data to the user. Thus, it can help the user quickly and directly find the required data or metrics from the integrated energy management system, without the user having to find the corresponding business module in the integrated energy management system and then find the corresponding page in the business module to query the required data or metrics. Therefore, it reduces the complexity and tediousness of operation and management, improves the query speed and convenience of data, and further improves the management efficiency.

[0073] It should be noted that the specific implementation manner of the intelligent companion assistant in the embodiments of the present application is similar to the specific implementation manner of the integrated energy management system question answering method based on the large language model in the embodiments of the present application. For details, please refer to the description in the method part and will not be elaborated here.

[0074] The following refers to Figure 5 , Figure 5 shows a schematic structural diagram of a computing device suitable for implementing the embodiments of the present application,

[0075] As Figure 5 shown, the computer system includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage part 1008 into the random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation instructions of the system are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other through a bus 1004. The input / output (I / O) interface 1005 is also connected to the bus 1004.

[0076] The following components are connected to the I / O interface 1005; an input part 1006 including a keyboard, a mouse, etc.; an output part 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and speakers, etc.; a storage part 1008 including a hard disk, etc.; and a communication part 1009 including a network interface card such as a LAN card, a modem, etc. The communication part 1009 performs communication processing via a network such as the Internet. The drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed so that the computer program read from it can be installed into the storage part 1008 as needed.

[0077] Specifically, according to the embodiments of the present application, the above refers to the flowchartFigure 1 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program code for performing the method shown in the flowchart. In such an embodiment, the computer program contains program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above functions defined in the system of the present application are performed.

[0078] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in conjunction with an instruction execution system, apparatus, or device. And in the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operation instructions of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a portion of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that executes the specified functions or operation instructions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0080] The units or modules involved in the embodiments described in the present application may be implemented in software or in hardware. The described units or modules may also be provided in a processor. Among them, the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0081] On the other hand, the present application also provides a computer-readable storage medium, which may be included in the computing device described in the above embodiments, or may exist separately without being assembled into the computing device. The above computer-readable storage medium stores one or more programs, and when the above programs are executed by one or more processors to perform the method for querying data of the integrated energy management system based on a large language model described in the present application, for example, performing: receiving consultation information input by a user, where the consultation information is used to request target data from the integrated energy management system;

[0082] analyzing the consultation information to obtain corresponding prompt words;

[0083] inputting the prompt words into a pre-trained consultation model so that the consultation model obtains the target data from the integrated energy management system according to the prompt words;

[0084] providing the target data to the user.

[0085] As another aspect, the present application also provides a computer program product, which may be included in the computing device described in the above embodiments, or may exist independently without being assembled into the computing device. The above computer program product stores one or more programs, and when the above programs are executed by one or more processors to perform the method for querying data of the integrated energy management system based on the large language model described in the present application. For example, execute: receiving consultation information input by a user, wherein the consultation information is used to request target data from the integrated energy management system;

[0086] Analyzing the consultation information to obtain corresponding prompt words;

[0087] Inputting the prompt words into a pre-trained consultation model so that the consultation model obtains the target data from the integrated energy management system according to the prompt words;

[0088] Providing the target data to the user.

[0089] The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present application.

Claims

1. A method for querying an integrated energy management system based on a large language model, characterized in that: include: Receiving inquiry information input by a user, wherein the inquiry information is used to request target data from the integrated energy management system; Parsing the consulting information to obtain corresponding prompt words; Inputting the prompt word into a pre-trained consulting model so that the consulting model obtains the target data from the integrated energy management system according to the prompt word; The target data is provided to a user.

2. The method for querying an integrated energy management system based on a large language model according to claim 1 is characterized in that: The step of parsing the consulting information to obtain corresponding prompt words includes: Parsing the consulting information to determine the business attribute subject corresponding to the consulting information; According to the business attribute theme, the corresponding prompt word is retrieved from a pre-published prompt word list, wherein the prompt words in the prompt word list are pre-written and published.

3. The method for querying an integrated energy management system based on a large language model according to claim 1 is characterized in that: The step of inputting the prompt word into a pre-trained consulting model so that the consulting model obtains the target data from the integrated energy management system according to the prompt word comprises: Inputting the prompt words into a pre-trained consultation model; Calling the corresponding service interface according to the prompt word; Based on the business interface, the target data is queried from the integrated energy management system.

4. The method for querying an integrated energy management system based on a large language model according to claim 3 is characterized in that: Before calling the corresponding service interface according to the prompt word, the method further includes: Obtaining relevant business data of the integrated energy management system; A business interface is provided according to the relevant business data.

5. The method for querying an integrated energy management system based on a large language model according to any one of claims 1 to 4, characterized in that: Before inputting the prompt words into the pre-trained consultation model, the method further includes: The prompt word samples are input into the initial consultation model, and the initial consultation model is trained according to the loss between the output of the initial consultation model and the target to obtain the consultation model.

6. The method for querying an integrated energy management system based on a large language model according to claim 1 is characterized in that: Providing the target data to the user comprises: presenting the target data to the user; and / or, A query interface for the target data is provided.

7. The method for querying an integrated energy management system based on a large language model according to claim 6 is characterized in that: The query interface for providing the target data includes: Providing a display interface for the target data; and / or, A query link for the target data is provided.

8. A smart companion assistant, characterized in that: include: A receiving module, used for receiving consultation information input by a user, wherein the consultation information is used for requesting target data from the integrated energy management system; A parsing module, used for parsing the consulting information to obtain corresponding prompt words; A consulting module, used for inputting the prompt word into a pre-trained consulting model, so that the consulting model obtains the target data from the integrated energy management system according to the prompt word; A providing module is used to provide the target data to a user.

9. A computing device, characterized in that The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for querying an integrated energy management system based on a large language model according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for querying an integrated energy management system based on a large language model according to any one of claims 1 to 7 is implemented.

Images