Information retrieval method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to an information retrieval method and device, computer equipment and a storage medium. The method comprises the steps of obtaining abnormal alarm information, input through retrieval operation, of an energy storage power station, and determining a prompt word template corresponding to the abnormal alarm information; based on the prompt word template and the abnormal alarm information, performing knowledge retrieval processing on a knowledge base of the energy storage power station to obtain processing scheme information and obtaining path information for the abnormal alarm information; obtaining index description information associated with the processing scheme information based on the domain model of the energy storage power station; obtaining index data associated with the abnormal alarm information according to the obtaining path information and the index description information; and performing information fusion processing on the processing scheme information, the obtaining path information, the index description information and the index data to obtain a target retrieval result corresponding to the retrieval operation. By adopting the method, the information retrieval efficiency can be improved, and the information accuracy and readability of the target retrieval result obtained through retrieval are also improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an information retrieval method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] With the continuous development of the power industry, a large number of important research results have been accumulated. These results can promote the improvement of energy production efficiency, the improvement of grid operation stability, the improvement of equipment management efficiency, etc., and can also provide rich knowledge and experience for subsequent research.

[0003] However, when an abnormal situation occurs in an energy storage power station, a meeting is usually held to discuss the abnormal situation and a solution is developed based on the work experience of the operation and maintenance personnel. Due to the complexity of the knowledge system in the power field and its wide coverage, it takes a lot of time to fully search and query the knowledge of abnormal situations, which can easily delay the timing of maintenance. Therefore, it is currently difficult to fully utilize the existing knowledge in the power field to solve abnormal situations in energy storage power stations. Summary of the invention

[0004] Based on this, it is necessary to provide an information retrieval method, apparatus, computer device, computer-readable storage medium and computer program product to address the above technical issues.

[0005] In a first aspect, the present application provides an information retrieval method. The method comprises:

[0006] Acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information;

[0007] Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information;

[0008] Based on the domain model of the energy storage power station, obtaining indicator description information associated with the processing solution information;

[0009] Obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information;

[0010] Information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a target search result corresponding to the search operation.

[0011] In one embodiment, information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a target search result corresponding to the search operation, including:

[0012] By using a large model, information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a fusion search result;

[0013] The fused search results are input into the prompt word template, and the target search results are output.

[0014] In one embodiment, before the processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing by a large model to obtain the fused search result, the method further includes:

[0015] Performing fault diagnosis processing on the indicator data to obtain a fault diagnosis result of the indicator data;

[0016] The processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing by the large model to obtain the fused search result, and further includes:

[0017] Through the large model, the processing solution information, the acquisition path information, the indicator description information, the indicator data and the fault diagnosis result are subjected to information fusion processing to obtain the fused retrieval result.

[0018] In one embodiment, based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information, including:

[0019] Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the abnormality processing knowledge base of the energy storage power station to obtain the processing solution information;

[0020] Based on the prompt word template and the abnormal alarm information, knowledge extraction processing is performed on the indicator knowledge base of the energy storage power station to obtain the acquisition path information; the acquisition path information is used to characterize the query conditions of the indicator data.

[0021] In one embodiment, determining the prompt word template corresponding to the abnormal alarm information includes:

[0022] Performing semantic recognition processing on the abnormal alarm information of the energy storage power station to obtain semantic information of the abnormal alarm information;

[0023] Based on the semantic information, a prompt word template matching the abnormal alarm information is determined.

[0024] In one embodiment, based on the domain model of the energy storage power station, the indicator description information associated with the processing solution information is obtained, including:

[0025] Performing natural language processing on the processing solution information to obtain text analysis information of the processing solution information;

[0026] The indicator description information associated with the text parsing information is obtained through the association relationship in the domain model of the energy storage power station.

[0027] In a second aspect, the present application also provides an information retrieval device. The device comprises:

[0028] A prompt word acquisition module, used to acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information;

[0029] A knowledge base retrieval module, used to perform knowledge retrieval processing on the knowledge base of the energy storage power station based on the prompt word template and the abnormal alarm information, and obtain processing solution information and acquisition path information for the abnormal alarm information;

[0030] An indicator acquisition module, used to obtain indicator description information associated with the processing solution information based on the domain model of the energy storage power station;

[0031] A data retrieval module, used to obtain the indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information;

[0032] The result output module is used to perform information fusion processing on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain the target search result corresponding to the search operation.

[0033] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0034] Acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information;

[0035] Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information;

[0036] Based on the domain model of the energy storage power station, obtaining indicator description information associated with the processing solution information;

[0037] Obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information;

[0038] Information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a target search result corresponding to the search operation.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information;

[0041] Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information;

[0042] Based on the domain model of the energy storage power station, obtaining indicator description information associated with the processing solution information;

[0043] Obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information;

[0044] Information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a target search result corresponding to the search operation.

[0045] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0046] Acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information;

[0047] Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information;

[0048] Based on the domain model of the energy storage power station, obtaining indicator description information associated with the processing solution information;

[0049] Obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information;

[0050] Information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a target search result corresponding to the search operation.

[0051] The above-mentioned information retrieval method, device, computer equipment, storage medium and computer program product obtain the abnormal alarm information of the energy storage power station input through the retrieval operation, determine the prompt word template corresponding to the abnormal alarm information; based on the prompt word template and the abnormal alarm information, perform knowledge retrieval processing on the knowledge base of the energy storage power station to obtain the processing solution information and acquisition path information for the abnormal alarm information; based on the domain model of the energy storage power station, obtain the indicator description information associated with the processing solution information; according to the acquisition path information and the indicator description information, obtain the indicator data associated with the abnormal alarm information; perform information fusion processing on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain the target retrieval result corresponding to the retrieval operation. By adopting this method, through the knowledge base and domain model of the energy storage power station, more comprehensive information resources related to the abnormal alarm information can be retrieved, and the integration and refinement of various information resources can be realized. While improving the efficiency of information retrieval, the information accuracy and readability of the target retrieval results obtained by retrieval are also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is an application environment diagram of an information retrieval method in an embodiment;

[0053] Figure 2 is a flow chart of an information retrieval method in one embodiment;

[0054] Figure 3 A schematic flow chart of a target search result step for obtaining abnormal alarm information in an embodiment;

[0055] Figure 4 is a flow chart of an information retrieval method in another embodiment;

[0056] Figure 5 is a flowchart of an information retrieval method in yet another embodiment;

[0057] Figure 6 is a structural block diagram of an information retrieval device in one embodiment;

[0058] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] It should be noted that the user information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and power information (including but not limited to abnormal alarm information, processing plan information, acquisition method information, indicator data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0061] The information retrieval method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 10 is equipped with a knowledge base 101, a data platform 102, a large model 103, and a domain model 104. The terminal 10 is a terminal device used by a user, and the terminal 10 includes but is not limited to various personal computers, laptops, smart phones, tablet computers, Internet of Things devices, and portable wearable devices.

[0062] In one embodiment, Figure 1 As shown, an information retrieval method is provided. This embodiment takes the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0063] Step S201, obtaining abnormal alarm information of the energy storage power station input through a search operation, and determining a prompt word template corresponding to the abnormal alarm information.

[0064] The energy storage power station is a device system that stores, converts and releases cyclic electrical energy through electrochemical batteries or electromagnetic energy storage media. For example, the energy storage power station can be an electrochemical energy storage power station.

[0065] The abnormal alarm information is an alarm prompt information generated for abnormalities that occur during the operation of the energy storage power station. For example, the abnormal alarm information may be "temperature abnormality alarm message of the battery cluster of the energy storage subsystem of the electrochemical energy storage station numbered X".

[0066] Among them, the prompt word template is used to help the model and knowledge base identify key information. The prompt word template usually contains a series of keywords or phrases to guide the model and knowledge base to better understand the meaning and structure when processing abnormal alarm information.

[0067] Specifically, when a user wants to retrieve how to solve an abnormal situation in an energy storage power station, the user can enter the abnormal alarm information of the energy storage power station on the terminal. After receiving the abnormal alarm information, the terminal can perform semantic understanding of the abnormal alarm information to understand the alarm intent of the abnormal alarm information, and then match it with a corresponding prompt word template. For example, the prompt word template with the closest semantics can be obtained from multiple preset prompt word templates.

[0068] Step S202 , based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information.

[0069] The processing solution information refers to the content describing the solution to the abnormal alarm information.

[0070] The acquisition method information refers to the content describing the method of obtaining indicator data.

[0071] Specifically, based on the prompt word template, the terminal retrieves the knowledge related to the abnormal alarm information in the knowledge base of the energy storage power station, and finally retrieves the processing solution for the abnormal alarm information and the relevant knowledge of the acquisition method of the relevant indicator data, that is, the terminal obtains the processing solution information and the acquisition method information.

[0072] Step S203: obtaining indicator description information associated with the processing solution information based on the domain model of the energy storage power station.

[0073] The domain model is used to establish and provide the association between knowledge and data in the energy storage power station and power field. The indicator description information refers to the description content of the data indicator associated with the processing solution information. For example, the indicator description information can be the measurement point information and equipment information describing the data indicator.

[0074] Specifically, the terminal pre-builds a domain model of the energy storage power station based on the knowledge, indicator description, indicator data and other contents of the energy storage power station and the power field, as well as the association relationship between these contents. The terminal uses the association relationship of the domain model to query the indicator description information of the data indicators closely related to the processing solution information.

[0075] Step S204, obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information.

[0076] The indicator data refers to the operation data of the data indicator associated with the processing scheme information. For example, assuming that the abnormal alarm information is the abnormal temperature of the battery cluster, the indicator data may be the temperature data of the battery cluster.

[0077] Specifically, the terminal converts the associated indicator information and the acquisition path information into grammatical structure information; and then converts the grammatical structure information into query language information. The terminal queries the data middle station based on the query language information, and obtains the indicator data associated with the abnormal alarm information in the data middle station. Among them, the grammatical structure information refers to the content of the abstract grammatical structure that describes the code. The query language information refers to the computer statement instructions for querying abnormal indicator related data formed by a computer compiled language. For example, the query language information can be a SQL (Structured Query Language) statement.

[0078] In actual applications, the terminal can convert the associated indicator information and the acquisition path information into an Abstract Syntax Tree (AST). The terminal converts the abstract syntax tree into an SQL statement based on the grammatical rules of the query language of the data center. Furthermore, the terminal can also optimize the SQL statement, such as removing redundant conditions in the SQL statement, adjusting the order of query conditions, etc., to improve query efficiency. The terminal uses SQL statements to query the data center, and obtains the corresponding indicator data in the data center. Among them, the data center is used to collect, store, and process the operating data of the energy storage power station. It consists of three-layer models: ODS (Operational Data Store, data storage layer), DWD (Data Warehouse Database, data detail layer), and DWS (Data Warehouse Service, data service layer). The table structure of DWD carries the label of the domain information model.

[0079] Step S205, performing information fusion processing on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain the target search result corresponding to the search operation.

[0080] Among them, the target search result refers to the relevant knowledge retrieved for the search operation, which can provide abnormal alarm information in many aspects such as abnormal indicators, indicator data, and processing solutions.

[0081] Specifically, the terminal can also integrate and refine the acquired processing solution information, acquisition path information, indicator description information, indicator data and other information through natural language processing technology, and output it according to the prompt word template, and finally obtain the target search results that are easy to understand and highly readable. The terminal displays the target search results for users to view the target search results of their search operations, so that users can also quickly solve the abnormal alarm information of the energy storage power station according to the target search results, and speed up the abnormal processing efficiency.

[0082] In the above information retrieval method, a prompt word template corresponding to the abnormal alarm information of the energy storage power station is obtained; based on the prompt word template and the abnormal alarm information, the knowledge base of the energy storage power station is subjected to knowledge retrieval processing to obtain the processing solution information and the acquisition path information for the abnormal alarm information; based on the domain model of the energy storage power station, the indicator description information associated with the processing solution information is obtained; according to the acquisition path information and the indicator description information, the indicator data associated with the abnormal alarm information is obtained; the processing solution information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing to obtain the target retrieval result corresponding to the retrieval operation. By adopting this method, more comprehensive information resources related to the abnormal alarm information can be retrieved through the knowledge base and domain model of the energy storage power station, and the integration and refinement of various information resources can be realized. While improving the efficiency of information retrieval, the information accuracy and readability of the target retrieval results obtained by retrieval are also improved.

[0083] In one embodiment, Figure 3 As shown, in the above step S205, the processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing to obtain the target search result corresponding to the search operation, which specifically includes the following contents:

[0084] Step S301, through the big model, information fusion processing is performed on the processing solution information, acquisition path information, indicator description information and indicator data to obtain the fused search results.

[0085] The large model refers to a deep learning model with large-scale parameters and complex computing structure. For example, the large model can be a large language model in the field of natural language processing.

[0086] Specifically, the terminal pre-builds and trains a big model; the processing solution information, acquisition path information, indicator description information and indicator data are input into the big model, and the big model performs semantic understanding, classification, integration and information adjustment on the input processing solution information, acquisition path information, indicator description information and indicator data, so that the description of the processing solution information, acquisition path information, indicator description information and indicator data is more accurate, and then the big model outputs the fused retrieval results.

[0087] Step S302: input the fused search results into a prompt word template and output the target search results.

[0088] Specifically, the terminal inputs the fused search results into the prompt word template corresponding to the abnormal alarm information, so as to layout the fused search results again through the prompt word template, and finally output the target search results.

[0089] In this embodiment, the advantages of the large model's strong information comprehension ability and high processing accuracy are utilized to fully integrate the processing solution information, acquisition path information, indicator description information and indicator data, effectively improve the accuracy of the fusion retrieval results obtained after processing, and output the target retrieval results according to the prompt word template without the user having to manually query the knowledge related to the abnormal alarm information. While improving the retrieval efficiency of the knowledge related to the abnormal alarm information of the energy storage power station, it also improves the readability of the output target retrieval results, thereby improving the processing efficiency of retrieving the knowledge related to the abnormal alarm information of the energy storage power station.

[0090] In one embodiment, in the above step S301, the processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing through the large model to obtain the fusion search result, and the method further includes: performing fault diagnosis processing on the indicator data to obtain the fault diagnosis result of the indicator data. In the above step S301, the processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing through the large model to obtain the fusion search result, and the method further includes: performing information fusion processing on the processing scheme information, the acquisition path information, the indicator description information, the indicator data and the fault diagnosis result to obtain the fusion search result.

[0091] Among them, the fault diagnosis result is used to characterize the probability of whether the abnormal indicator will cause the power equipment of the energy storage power station to fail.

[0092] Specifically, the terminal performs fault diagnosis processing based on the indicator data, for example, it can be a fault prediction model obtained through training based on historical indicator data, perform fault prediction on the currently acquired indicator data, and output the fault diagnosis results of the indicator data. The terminal can input the processing solution information, acquisition path information, indicator description information, indicator data and fault diagnosis results into the big model, and the big model can perform semantic understanding, classification, integration and information adjustment on the input processing solution information, acquisition path information, indicator description information, indicator data and fault diagnosis results, and then the big model outputs the fusion retrieval results.

[0093] In this embodiment, through the large model, the processing solution information, acquisition path information, indicator description information, indicator data and fault diagnosis results are fully integrated, and various information resources are integrated and refined, which is conducive to improving the comprehensiveness of the retrieval results after integration.

[0094] In one embodiment, the above step S202, based on the prompt word template and the abnormal alarm information, performs knowledge retrieval processing on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information, specifically includes the following contents: based on the prompt word template and the abnormal alarm information, performs knowledge retrieval processing on the abnormal processing knowledge base of the energy storage power station to obtain processing solution information; based on the prompt word template and the abnormal alarm information, performs knowledge extraction processing on the indicator knowledge base of the energy storage power station to obtain acquisition path information; the acquisition path information is used to characterize the query conditions of the indicator data.

[0095] The processing solution information refers to the content describing the processing method for abnormal alarm information.

[0096] The knowledge base of the energy storage power station includes an exception handling knowledge base and an indicator knowledge base. The exception handling knowledge base stores information on multiple solutions for abnormal situations, while the indicator knowledge base stores information on how to obtain multiple data indicators.

[0097] Specifically, the terminal sets a first search task according to the abnormal alarm information, and uses the prompt word template to perform auxiliary search, so as to retrieve knowledge matching the first search task from the abnormal processing knowledge base, and finally retrieve the processing solution information. Similarly, the terminal also sets a second search task according to the abnormal alarm information and the processing solution information, and continues to use the prompt word template to perform auxiliary search, so as to retrieve knowledge matching the second search task from the indicator knowledge base, and the terminal obtains the acquisition path information.

[0098] In this embodiment, based on the prompt word template and the abnormal alarm information, the processing solution information for the abnormal alarm information is retrieved from the exception handling knowledge base, and the acquisition path information is retrieved from the indicator knowledge base, thereby realizing the rapid acquisition of different aspects of knowledge related to the abnormal alarm information and effectively improving the information retrieval efficiency.

[0099] In one embodiment, the above step S201, determining the prompt word template corresponding to the abnormal alarm information, specifically includes the following contents: performing semantic recognition processing on the abnormal alarm information of the energy storage power station to obtain semantic information of the abnormal alarm information; and determining the prompt word template matching the abnormal alarm information based on the semantic information.

[0100] The semantic information is used to represent the search intent corresponding to the abnormal alarm information input through the search operation.

[0101] Specifically, when the terminal wants to parse the search intention of the user's search operation, it can perform semantic recognition processing on the abnormal alarm information of the energy storage power station input through the search operation to obtain the semantic information of the abnormal alarm information, for example, the semantic information of the abnormal alarm information can be obtained by recognizing the abnormal alarm information through a natural language processing model. From the stored multiple preset prompt word templates, determine the prompt word template that matches the semantic information, and set the prompt word template as the prompt word template that matches the abnormal alarm information.

[0102] In this embodiment, by identifying the semantic information of the abnormal alarm information and then obtaining a prompt word template that matches the abnormal alarm information based on the semantic information, the intention of the user's retrieval operation is understood, so that subsequent steps can use the prompt word template to more accurately obtain knowledge that better matches the user's retrieval intention, thereby improving the accuracy of information retrieval.

[0103] In one embodiment, the above step S203, based on the domain model of the energy storage power station, obtains the indicator description information associated with the processing solution information, specifically including the following contents: performing natural language processing on the processing solution information to obtain text parsing information of the processing solution information; and obtaining the indicator description information associated with the text parsing information through the association relationship in the domain model of the energy storage power station.

[0104] The text analysis data refers to the text keywords analyzed from the processing solution information.

[0105] Specifically, the terminal performs natural language processing on the processing solution information, which may be lexical analysis, syntactic analysis, and semantic analysis. Then, the terminal obtains important elements such as keywords, verbs, and noun phrases in the processing solution information, and finally forms text parsing data of the processing solution information. The text parsing data is then used to query the association relationship in the domain model of the energy storage power station to obtain indicator description information closely related to the text parsing information.

[0106] In this embodiment, by analyzing the processing solution information, text analysis data of the processing solution information is obtained, and then based on the text analysis data, indicator description information closely related to the knowledge can be queried in the domain model, so that the indicator data can be accurately queried in subsequent steps, which is conducive to improving the comprehensiveness of the retrieval results.

[0107] In one embodiment, Figure 4 As shown, another information retrieval method is provided, which is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0108] Step S401, obtaining abnormal alarm information of the energy storage power station input through a search operation.

[0109] Step S402 , performing semantic recognition processing on the abnormal alarm information of the energy storage power station to obtain semantic information of the abnormal alarm information; based on the semantic information, determining a prompt word template that matches the abnormal alarm information.

[0110] Step S403: Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the abnormal processing knowledge base of the energy storage power station to obtain processing solution information.

[0111] Step S404, based on the prompt word template and the abnormal alarm information, the index knowledge base of the energy storage power station is subjected to knowledge extraction processing to obtain acquisition path information; the acquisition path information is used to characterize the query conditions of the index data.

[0112] Step S405 , performing natural language processing on the processing solution information to obtain text analysis information of the processing solution information; and obtaining indicator description information associated with the text analysis information through the association relationship in the domain model of the energy storage power station.

[0113] Step S406, obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information.

[0114] Step S407, performing fault diagnosis processing on the indicator data to obtain a fault diagnosis result of the indicator data.

[0115] Step S408, through the large model, information fusion processing is performed on the processing solution information, acquisition path information, indicator description information, indicator data and fault diagnosis results to obtain the fused retrieval results.

[0116] Step S409: input the fused search results into the prompt word template and output the target search results.

[0117] The above information retrieval method can achieve the following beneficial effects: through the knowledge base and domain model of the energy storage power station, more comprehensive information resources related to abnormal alarm information can be retrieved, and the integration and refinement of various information resources can be realized. While improving the efficiency of information retrieval, it also improves the information accuracy and readability of the target retrieval results obtained.

[0118] In order to more clearly illustrate the information retrieval method provided by the embodiment of the present disclosure, the above-mentioned information retrieval method is specifically described below with a specific embodiment. Figure 5 As shown, another information retrieval method is provided, which can be applied to Figure 1 The terminal in the package includes the following contents:

[0119] (1) Input: The terminal receives the input abnormal alarm information of "abnormal temperature alarm of battery cluster of energy storage subsystem of electrochemical energy storage station No. X".

[0120] (2) Retrieval intent understanding: Determine the prompt word template that best matches the abnormal alarm information.

[0121] (3) Abnormal processing knowledge base of electrochemical energy storage station: Retrieve knowledge related to battery cluster temperature abnormality from the abnormal processing knowledge base of electrochemical energy storage station.

[0122] (4) Obtaining matching reference knowledge: Retrieve information on the treatment plan for abnormal battery cluster temperature; the treatment plan information includes the operating procedures of the battery cluster, the emergency treatment plan for abnormal battery cluster temperature, and the content on the treatment of abnormal battery cluster temperature in the technical manual.

[0123] (5) Index knowledge base of electrochemical energy storage station: Retrieve the battery cluster temperature index from the index knowledge base of electrochemical energy storage station.

[0124] (6) Obtain matching reference knowledge: retrieve the data acquisition method of the battery cluster temperature indicator.

[0125] (7) Generate query statements: Generate SQL query statements based on the domain model.

[0126] (8) Query the data center: execute SQL query statements in the data center.

[0127] (9) Obtaining data: Query and obtain the temperature data of the battery cluster of the energy storage subsystem of the electrochemical energy storage station numbered X.

[0128] (10) Data calculation task: Based on the queried temperature data, perform fault diagnosis calculation on the equipment status of the electrochemical energy storage station to obtain the fault diagnosis results.

[0129] (11) Output: Through the large model, summarize and refine the above search results (including the treatment plan information of battery cluster temperature anomalies, the data acquisition method of battery cluster temperature indicators, temperature data and fault diagnosis results), and output the target search results (such as output time, indicator name, indicator value, fault diagnosis suggestions, and emergency response methods) according to the prompt word template requirements.

[0130] In this embodiment, through the coordinated application of technologies such as knowledge base, data middle platform, big model, domain model, etc., the implementation process of knowledge organization, retrieval and output is completed, the relevant information between different fields is effectively integrated, the retrieval efficiency and retrieval accuracy are improved, and users can be provided with more comprehensive, intuitive and easy-to-understand information resources, which provides strong support for users to solve abnormal situations of electrochemical energy storage stations.

[0131] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0132] Based on the same inventive concept, the embodiment of the present application also provides an information retrieval device for implementing the above-mentioned information retrieval method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more information retrieval device embodiments provided below can refer to the limitations on the information retrieval method above, and will not be repeated here.

[0133] In one embodiment, Figure 6 As shown, an information retrieval device 600 is provided, comprising: a prompt word acquisition module 601, a knowledge base retrieval module 602, an indicator acquisition module 603, a data retrieval module 604 and a result output module 605, wherein:

[0134] The prompt word acquisition module 601 is used to acquire the abnormal alarm information of the energy storage power station input through the search operation, and determine the prompt word template corresponding to the abnormal alarm information.

[0135] The knowledge base search module 602 is used to perform knowledge search processing on the knowledge base of the energy storage power station based on the prompt word template and the abnormal alarm information, and obtain the processing solution information and acquisition path information for the abnormal alarm information.

[0136] The indicator acquisition module 603 is used to obtain indicator description information associated with the processing solution information based on the domain model of the energy storage power station.

[0137] The data retrieval module 604 is used to obtain the indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information.

[0138] The result output module 605 is used to perform information fusion processing on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain the target search result corresponding to the search operation.

[0139] In one embodiment, the result output module 605 is also used to perform information fusion processing on the processing solution information, the acquisition path information retrieval operation correspondence and the indicator data through a large model to obtain a fused retrieval result; input the fused retrieval result into a prompt word template to output the target retrieval result.

[0140] In one embodiment, the information retrieval device 600 further includes a fault diagnosis module for performing fault diagnosis processing on the indicator data to obtain the fault diagnosis result of the indicator data. The result output module 605 is also used to perform information fusion processing on the processing solution information, the corresponding retrieval operation of the acquisition path information, the indicator data and the fault diagnosis result through the large model to obtain the fusion retrieval result.

[0141] In one embodiment, the knowledge base retrieval module 602 is also used to perform knowledge retrieval processing on the abnormal processing knowledge base of the energy storage power station based on the prompt word template and the abnormal alarm information to obtain processing solution information; based on the prompt word template and the abnormal alarm information, perform knowledge extraction processing on the indicator knowledge base of the energy storage power station to obtain acquisition path information; the acquisition path information is used to characterize the query conditions of the indicator data.

[0142] In one embodiment, the prompt word acquisition module 601 is further used to perform semantic recognition processing on the abnormal alarm information of the energy storage power station to obtain semantic information of the abnormal alarm information; based on the semantic information, determine the prompt word template matching the abnormal alarm information.

[0143] In one embodiment, the language generation module 603 is also used to perform natural language processing on the processing solution information to obtain text analysis information of the processing solution information; and obtain indicator description information associated with the text analysis information through the association relationship in the domain model of the energy storage power station.

[0144] Each module in the above information retrieval device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0145] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an information retrieval method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0146] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0148] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0149] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0150] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0151] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An information retrieval method, characterized in that: The method comprises: Acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information; Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the knowledge base of the energy storage power station to obtain processing solution information and acquisition path information for the abnormal alarm information; Based on the domain model of the energy storage power station, obtaining indicator description information associated with the processing solution information; Obtaining indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information; Information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a target search result corresponding to the search operation.

2. The method according to claim 1, characterized in that The performing information fusion processing on the processing scheme information, the acquisition path information, the indicator description information and the indicator data to obtain the target search result corresponding to the search operation includes: By using a large model, information fusion processing is performed on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain a fusion search result; The fused search results are input into the prompt word template, and the target search results are output.

3. The method according to claim 2, characterized in that Before the processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing by the large model to obtain the fused search result, the method further includes: Performing fault diagnosis processing on the indicator data to obtain a fault diagnosis result of the indicator data; The processing scheme information, the acquisition path information, the indicator description information and the indicator data are subjected to information fusion processing by the large model to obtain the fused search result, and further includes: Through the large model, the processing solution information, the acquisition path information, the indicator description information, the indicator data and the fault diagnosis result are subjected to information fusion processing to obtain the fused retrieval result.

4. The method according to claim 1, characterized in that: Based on the prompt word template and the abnormal alarm information, the knowledge base of the energy storage power station is subjected to knowledge retrieval processing to obtain processing solution information and acquisition path information for the abnormal alarm information, including: Based on the prompt word template and the abnormal alarm information, a knowledge search process is performed on the abnormality processing knowledge base of the energy storage power station to obtain the processing solution information; Based on the prompt word template and the abnormal alarm information, knowledge extraction processing is performed on the indicator knowledge base of the energy storage power station to obtain the acquisition path information; the acquisition path information is used to characterize the query conditions of the indicator data.

5. The method according to claim 1, characterized in that The step of determining a prompt word template corresponding to the abnormal alarm information includes: Performing semantic recognition processing on the abnormal alarm information of the energy storage power station to obtain semantic information of the abnormal alarm information; Based on the semantic information, a prompt word template matching the abnormal alarm information is determined.

6. The method according to claim 1, characterized in that The indicator description information associated with the processing scheme information is obtained based on the domain model of the energy storage power station, including: Performing natural language processing on the processing solution information to obtain text analysis information of the processing solution information; The indicator description information associated with the text parsing information is obtained through the association relationship in the domain model of the energy storage power station.

7. An information retrieval device, characterized in that: The device comprises: A prompt word acquisition module, used to acquire abnormal alarm information of the energy storage power station input through a search operation, and determine a prompt word template corresponding to the abnormal alarm information; A knowledge base retrieval module, used to perform knowledge retrieval processing on the knowledge base of the energy storage power station based on the prompt word template and the abnormal alarm information, and obtain processing solution information and acquisition path information for the abnormal alarm information; A language generation module, used to obtain indicator description information associated with the processing solution information based on the domain model of the energy storage power station; A data retrieval module, used to obtain the indicator data associated with the abnormal alarm information according to the acquisition path information and the indicator description information; The result output module is used to perform information fusion processing on the processing solution information, the acquisition path information, the indicator description information and the indicator data to obtain the target search result corresponding to the search operation.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images