Operation and maintenance alarm data query method and device, medium, electronic equipment and product

Abstract

The invention discloses an operation and maintenance alarm data query method and device, a medium, electronic equipment and a product. The method comprises the steps that an interaction control of an intelligent object is displayed in an operation and maintenance alarm page; in response to a trigger operation for the interaction control, displaying an intelligent object page; in response to an input operation in a natural language form in the intelligent object page, sending an input content corresponding to the input operation to a first machine learning model, so that the first machine learning model generates a query statement at least according to the input content, the database knowledge and the query statement knowledge, the query statement is used for querying in an operation and maintenance alarm database based on at least one data dimension to obtain target alarm data; and displaying the target alarm data returned by the operation and maintenance alarm database on the intelligent object page. Therefore, the alarm data can be queried from multiple dimensions, the query operation of the alarm data is simplified, the query efficiency of the alarm data is improved, and the statistical analysis efficiency of the alarm data is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to an operation and maintenance alarm data query method, device, medium, electronic equipment and product. Background Art

[0002] Monitoring and alarming are an important part of operation and maintenance work, identifying potential problems through continuous information collection, data integration and data analysis. The monitoring and alarming system generates a large number of alarms every day, and each alarm may involve dozens of related fields, resulting in a huge amount of alarm data.

[0003] In the related art, when performing statistical analysis on alarm data, it is usually necessary to manually search and select accurate fields from massive data and fields to filter, screen and aggregate the alarm data layer by layer, which is cumbersome and inefficient. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a method for querying operation and maintenance alarm data, the method comprising: Display interactive controls of smart objects in the operation and maintenance alarm page; In response to a trigger operation on the interactive control, a smart object page is displayed, wherein the smart object page is used for interaction between a user and the smart object; In response to an input operation in a natural language form in the smart object page, an input content corresponding to the input operation is sent to a first machine learning model, so that the first machine learning model generates a query statement at least according to the input content, database knowledge, and query statement knowledge, wherein the query statement is used to query and obtain target alarm data based on at least one data dimension in an operation and maintenance alarm database, and the database knowledge includes field information of fields in the operation and maintenance alarm database; The target alarm data returned by the operation and maintenance alarm database is displayed on the smart object page.

[0006] In a second aspect, the present disclosure provides an operation and maintenance alarm data query device, the device comprising: A first display module is used to display the interactive controls of the smart object in the operation and maintenance alarm page; A second display module, configured to display a smart object page in response to a trigger operation on the interactive control, wherein the smart object page is used for interaction between a user and the smart object; a sending module, configured to respond to an input operation in a natural language form in the smart object page, and send input content corresponding to the input operation to a first machine learning model, so that the first machine learning model generates a query statement at least according to the input content, database knowledge, and query statement knowledge, wherein the query statement is used to query and obtain target alarm data based on at least one data dimension in an operation and maintenance alarm database, and the database knowledge includes field information of fields in the operation and maintenance alarm database; The third display module is used to display the target alarm data returned by the operation and maintenance alarm database on the smart object page.

[0007] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when the program is executed by a processing device.

[0008] In a fourth aspect, the present disclosure provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the method in the first aspect.

[0009] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0010] Through the above technical solution, by responding to the input operation in the form of natural language in the smart object page, the input content corresponding to the input operation is sent to the first machine learning model, so that the first machine learning model generates a query statement at least according to the input content, database knowledge and query statement knowledge, and the operation and maintenance alarm database can query the operation and maintenance alarm database to obtain the target alarm data by executing the query statement, and finally display the target alarm data returned by the operation and maintenance alarm database on the smart object page. By adopting this method, by converting the input content in the form of natural language in the smart object page into a query statement, multi-dimensional query of alarm data can be realized, without manually searching and selecting accurate fields from massive data and fields for data query, simplifying the query operation of alarm data, improving the query efficiency of alarm data, and thus improving the statistical analysis efficiency of alarm data.

[0011] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 is a schematic diagram of an interface of a monitoring alarm system according to an exemplary embodiment of the present disclosure; Figure 2 It is a flowchart of a method for querying operation and maintenance alarm data according to an exemplary embodiment of the present disclosure; Figure 3 is a schematic diagram of a smart object page according to an exemplary embodiment of the present disclosure; Figure 4 is a schematic diagram of another smart object page according to an exemplary embodiment of the present disclosure; Figure 5 is a schematic diagram of database knowledge according to an exemplary embodiment of the present disclosure; Figure 6 This is a front-end and back-end interaction diagram of a method for querying operation and maintenance alarm data according to an exemplary embodiment of the present disclosure; Figure 7 It is a structural block diagram of an operation and maintenance alarm data query device according to an exemplary embodiment of the present disclosure; Figure 8 It is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0014] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0015] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] like Figure 1 As shown, when performing statistical analysis of alarm data, it is usually necessary to manually select query fields to filter, screen and aggregate the alarm data layer by layer, and select the corresponding chart type for display. Among them, the accuracy of data query depends on the accuracy of field selection. If the user is not familiar with the monitoring alarm platform, the alarm data may not be accurately screened out, which in turn affects the accuracy of alarm data analysis. In addition, it is necessary to manually select the data aggregation method, such as aggregating statistics by day or device dimension, and manually determine the chart type and other chart-related settings, so that the screened alarm data can be displayed in different types of charts.

[0025] Therefore, in the complete process of alarm data analysis, it is necessary to rely on users to manually and accurately filter fields, select data aggregation methods, determine chart types and other settings. The operation steps are cumbersome, resulting in low efficiency in alarm data query and analysis.

[0026] In view of this, the present disclosure provides an operation and maintenance alarm data query method, device, medium, electronic device and product to solve the above technical problems.

[0027] The embodiments of the present disclosure are further explained below with reference to the accompanying drawings.

[0028] Figure 2 is a flowchart of a method for querying operation and maintenance alarm data according to an exemplary embodiment of the present disclosure, referring to Figure 2 , the method may include the following steps: S201: Displaying interactive controls of smart objects in the operation and maintenance alarm page.

[0029] Among them, the operation and maintenance alarm page is a page of the monitoring alarm platform, which can be a homepage or a page used to display, manage, query, and analyze alarm data. That is to say, the smart object can be displayed on any page of the monitoring alarm platform, or on a page related to the alarm data. It can be set according to specific needs, and this disclosure does not impose any restrictions on this.

[0030] S202: In response to a trigger operation on an interactive control, a smart object page is displayed, where the smart object page is used for interaction between a user and a smart object.

[0031] S203: In response to an input operation in natural language form in the smart object page, the input content corresponding to the input operation is sent to the first machine learning model, so that the first machine learning model generates a query statement based on at least the input content, database knowledge and query statement knowledge, and the query statement is used to obtain target alarm data based on at least one data dimension in the operation and maintenance alarm database, and the database knowledge includes field information of fields in the operation and maintenance alarm database.

[0032] For example, Figure 3 As shown, input operations are performed in natural language on the smart object page. For example, if you need to query the "daily trend of XX events last month", it is equivalent to querying the number of XX events that occurred daily within the time range of "last month", generating the corresponding query statement, and then querying the operation and maintenance alarm database to obtain the target alarm data.

[0033] Among them, the type of query statement can be specifically determined according to the operation and maintenance alarm database, which can be an ES (Elasticsearch, a highly scalable distributed full-text search engine) query statement or an SQL (Structured Query Language, structured query language) query statement, and the present disclosure does not impose any restrictions on this.

[0034] In a possible manner, the target alarm data is obtained by automatically connecting to an operation and maintenance alarm database so that the operation and maintenance alarm database executes a query statement, obtains the target alarm data, and returns the target alarm data.

[0035] For example, after generating a query statement based on the input content, the operation and maintenance alarm database can be automatically connected and the query statement can be executed, simplifying the operation steps and improving the efficiency of data query. In addition, multi-dimensional data dimension query is supported, such as site, entity, alarm name, device name, time, region, etc., which is determined according to the actual business scenario and is not limited by this disclosure.

[0036] It should be noted that the source of the alarm data in the operation and maintenance alarm database can be the business system monitored by operation and maintenance, or it can be an external system that has business associations with the business system. That is to say, the data fields in the operation and maintenance alarm database can include business fields and alarm fields of the business system, and can also include alarm label fields of the external system related to operation and maintenance alarms. The specific determination is based on the actual business scenario, and the present disclosure does not impose any restrictions on this.

[0037] S204: Displaying the target alarm data returned by the operation and maintenance alarm database on the smart object page.

[0038] For example, specific data retrieved from a query statement can be displayed on a smart object page, such as Figure 3As shown, the target warning data may be displayed in a table format, which is not limited in the present disclosure.

[0039] By adopting the above method, multi-dimensional query of alarm data can be realized by converting the natural language input content in the smart object page into query statements. There is no need to manually search and select accurate fields from massive data and fields for data query, which simplifies the query operation of alarm data, improves the query efficiency of alarm data, and thus improves the statistical analysis efficiency of alarm data.

[0040] In a possible manner, the method also includes: sending the input content to a second machine learning model so that the second machine learning model extracts chart keywords from the input content, and determines the target chart type corresponding to the chart keywords from the correspondence between the keywords and the chart types; receiving the target chart type returned by the second machine learning model, and displaying the chart data corresponding to the target alarm data under the target chart type in the smart object page.

[0041] For example, the second machine learning model can extract the chart keywords of the input content, and determine the target chart type corresponding to the chart keywords from the correspondence between the keywords and the chart types. For example, the keyword "trend" can be a line chart, the keyword "ranking" can be a bar chart, the keyword "proportion" can be a pie chart, the keyword "quantity" can be a panel data, etc. The specific settings can be based on the needs, and the present disclosure does not limit this. Figure 4 As shown, the chart data corresponding to the target alarm data under the target chart type can be displayed in the smart object page.

[0042] There is no need to manually set the chart type. The corresponding chart can be automatically generated to intuitively aggregate and display the alarm data, enabling rapid query and visual display of the alarm data.

[0043] In addition, the first machine learning model generates a query statement based on the input content and the second machine learning model determines the target chart type based on the input content, which can be processed in parallel. The parallel processing method can reduce the time consumption caused by serial processing, thereby improving the efficiency of alarm data analysis. Of course, it is also possible to generate a query statement first and then determine the chart type, or to determine the chart type first and then generate a query statement, and the present disclosure does not limit this.

[0044] It should be understood that by reasonably setting the mechanism and order of calling machine learning models, the time spent from user input to chart generation can be effectively reduced, thereby improving the efficiency of alarm data analysis.

[0045] In a possible manner, the method also includes: sending the input content and target alarm data to a third machine learning model, so that the third machine learning model extracts data features of the target alarm data and semantic features of the input content, and generates data description content in natural language form based on the data features and semantic features; receiving the data description content returned by the third machine learning model, and displaying the data description content on the smart object page.

[0046] For example, after obtaining the target alarm data, the data features of the target alarm data and the semantic features of the input content can be extracted through the third machine learning model to generate data description content in natural language form and display it on the smart object page, for example, the target alarm data is summarized or summarized to display Figure 4 The summary description in natural language form shown is equivalent to a summary answer to the question in the input content, thereby improving the readability of the alarm data and facilitating user understanding and data analysis.

[0047] In a possible manner, the method further includes at least one of the following: displaying a query statement on a smart object page; determining query information corresponding to the query statement, and displaying the query information on the smart object page, wherein the query information includes at least one of a query dimension and a query indicator.

[0048] For example, Figure 4 As shown, the query statement can be displayed on the smart object page to facilitate operation and maintenance personnel to check whether the query statement is correct, or copy it to the alarm database for data query, etc. The query indicators and / or query dimensions corresponding to the query statement can also be determined and displayed, similar to Figure 1 The displayed information such as indicators, dimensions, and filter ranges facilitates ordinary users to intuitively understand the query indicators and / or query dimensions of the alarm data, thereby improving the readability of the alarm data.

[0049] In a possible manner, the first machine learning model generates a query statement in the following manner: at least based on input content, query statement knowledge and database knowledge, a target prompt word is constructed according to a preset prompt word template; at least based on the target prompt word and the first machine learning model, a query statement is generated.

[0050] For example, prompt words can be constructed according to a preset prompt word template based on input content, query statement knowledge and database knowledge, and query statements can be generated based on the prompt words through a first machine learning model. The prompt word template can be set according to needs, and the present disclosure does not limit this.

[0051] It should be noted that the first machine learning model, the second machine learning model and the third machine learning model of the present disclosure may be the same model or different models, for example, a neural network model or a large language model (LLM), and the present disclosure does not limit this. The machine learning model may be trained by constructing corresponding sample data according to actual needs to obtain machine learning models with different capabilities, and the present disclosure does not limit this.

[0052] In addition, in the embodiments of the present disclosure, the front-end display process and the machine learning model processing process can be executed by the same device, or the front-end device can be responsible for the front-end display, and the back-end server deploys the machine learning model and performs model processing. The present disclosure does not impose any restrictions on this.

[0053] In a possible manner, the database knowledge includes at least one of the following field information: field name, field value example, field description, field note, field matching logic description, and error-prone field matching description of the field in the operation and maintenance alarm database. Figure 5 As shown, all alarm fields and alarm label fields can be systematically organized, such as field names, field value examples, Chinese and English descriptions, notes, and other information, so that the first machine learning model can automatically match the correct alarm field or alarm label field based on the keywords in the input content. For example, if the user enters the Chinese name of an event, and the operation and maintenance alarm database stores the field with the English name, the corresponding field can be correctly matched based on the database knowledge.

[0054] For example, by setting the matching logic description of some special fields and emphasizing the matching error-prone fields, the first machine learning model can understand the field content and matching logic of the operation and maintenance alarm database, thereby improving the accuracy of field matching and the accuracy of alarm data query.

[0055] In a possible manner, at least based on input content, query statement knowledge and database knowledge, a target prompt word is constructed according to a preset prompt word template, including: based on input content, query statement knowledge, database knowledge and query statement examples, a target prompt word is constructed according to a preset prompt word template.

[0056] For example, query statement examples may also be added to the prompt words so that the first machine learning model can generate more standardized and accurate query statements based on the query statement examples, thereby further improving the accuracy and efficiency of the query of the alarm data.

[0057] In a possible manner, a query statement is generated based at least on a target prompt word and a first machine learning model, including: inputting the target prompt word into the first machine learning model so that the first machine learning model extracts field keywords of the input content in the target prompt word, performing field matching between the field keywords and database knowledge, determining a first field that matches the field keywords, and generating a query statement based on the first field and the query statement knowledge in the target prompt word; wherein the first field is a data field in the operation and maintenance alarm database.

[0058] For example, the first machine learning model can extract field keywords of the input content in the target prompt word, and then perform field matching on the field keywords and database knowledge to obtain the first field, and then generate a query statement based on the first field and query statement knowledge through the first machine learning model, thereby realizing automatic generation of query statements.

[0059] In a possible manner, a query statement is generated based at least on a target prompt word and a first machine learning model, including: obtaining operation and maintenance alarm domain knowledge; inputting the target prompt word and the operation and maintenance alarm domain knowledge into the first machine learning model so that the first machine learning model extracts field keywords of the input content in the target prompt word, determines the domain keywords based on the field keywords and the operation and maintenance alarm domain knowledge, performs field matching on the domain keywords and database knowledge, determines a second field that matches the domain keywords, and generates a query statement based on the second field and the query statement knowledge in the target prompt word; wherein the second field is a data field in the operation and maintenance alarm database.

[0060] For example, the domain knowledge of operation and maintenance alarms can be systematically sorted out in advance. When calling the first machine learning model to generate a query statement, the prompt word and the domain knowledge of operation and maintenance alarms can be simultaneously input into the first machine learning model so that the first machine learning model can understand the domain knowledge of operation and maintenance alarms and correctly extract domain keywords. For example, when the input content includes "CSW", the first machine learning model can determine that "CSW" represents the core switch (coreswitch) based on the domain knowledge of operation and maintenance alarms, and then perform field matching based on the domain keywords and database knowledge, such as matching the fields associated with core-switch, and finally generate a query statement based on the query statement knowledge in the second field and the target prompt word. This helps the first machine learning model to generate query statements more accurately, thereby improving the query efficiency and analysis efficiency of alarm data.

[0061] In a possible manner, a query statement is generated based at least on a target prompt word and a first machine learning model, including: obtaining preset content and preset keywords corresponding to the preset content; inputting the target prompt word and the preset example content into the first machine learning model, so that the first machine learning model semantically matches the input content and the preset content in the target prompt word, determines the target preset content in the preset content that semantically matches the input content, and performs field matching based on the target preset keywords corresponding to the target preset content and database knowledge, determines a third field that matches the target preset keywords, and generates a query statement based on the third field and the query statement knowledge in the target prompt word; wherein the third field is a data field in the operation and maintenance alarm database.

[0062] It should be understood that different users have different expression habits or different levels of understanding of data, so the input content of different users varies greatly. For example, if the input content is "query the alarm data of event XXYY last month", the query time and the queried event can be clearly stated, and keywords can be accurately extracted and field matching can be performed. If the input content is "query the alarm data of YY last month", the keywords may not be accurately extracted.

[0063] For example, preset content and preset keywords corresponding to the preset content can be pre-set. For example, with the authorization of the user, the alarm data frequently queried by the user can be summarized and sorted, and the input content of the user's historical input can be obtained and summarized and sorted. In this way, the alarm data actually to be queried by the user can be determined based on the user's common expressions. For example, if the preset content is "YY's alarm data", the corresponding preset keyword is "XXYY event", and the corresponding preset keyword "XXYY event" can be determined based on the successful semantic match between the input content and the preset content, and then the alarm data corresponding to the "XXYY event" can be queried. Thereby improving the query accuracy and efficiency of the alarm data.

[0064] The following is an example of the processing logic of the front-end and back-end in conjunction with the accompanying drawings. In which, the first machine learning model, the second machine learning model and the third machine learning model are the same machine learning model as an example.

[0065] like Figure 6As shown, the front-end device receives the input content entered by the user in the form of natural language, and then requests the back-end server to generate a query statement based on the input content. The back-end server builds a prompt word based on the input content, database knowledge, query statement knowledge, and query statement examples and inputs it into the machine learning model. The machine learning model can be called twice in parallel to generate query statements and determine the chart type respectively, and then automatically connect to the operation and maintenance alarm database to execute the query statement to obtain the target alarm data, and then return the target alarm data and chart type to the front-end device. The front-end device displays the data in an intuitive chart based on the queried target alarm data and the chart type determined by the machine learning model, so as to realize rapid query and visual display of the data. The target alarm data can also be re-input into the machine learning model to obtain a text description summarizing the target alarm data, and the text description is sent to the front-end device for display.

[0066] By calling the machine learning model in parallel to generate query statements and determine the chart type, and summarizing and describing the queried alarm data, the time consumption caused by serial calls can be reduced, and the time required for users to input the corresponding alarm data and chart data to the front-end display can be effectively reduced, effectively improving the query efficiency and analysis efficiency of alarm data.

[0067] Based on the same concept, the embodiment of the present disclosure provides an operation and maintenance alarm data query device, such as Figure 7 As shown, the operation and maintenance alarm data query device 700 includes: The first display module 701 is used to display the interactive controls of the smart object in the operation and maintenance alarm page; A second display module 702 is used to display a smart object page in response to a trigger operation on the interactive control, where the smart object page is used for the user to interact with the smart object; A sending module 703 is used to send input content corresponding to the input operation to the first machine learning model in response to an input operation in a natural language form in the smart object page, so that the first machine learning model generates a query statement based on at least the input content, database knowledge, and query statement knowledge, where the query statement is used to query the operation and maintenance alarm database based on at least one data dimension to obtain target alarm data, and the database knowledge includes field information of fields in the operation and maintenance alarm database; The third display module 704 is used to display the target alarm data returned by the operation and maintenance alarm database on the smart object page.

[0068] Optionally, the first machine learning model generates the query statement through the following modules: A construction module, configured to construct a target prompt word according to a preset prompt word template based at least on the input content, the query sentence knowledge and the database knowledge; A generation module is used to generate the query statement based on at least the target prompt word and the first machine learning model.

[0069] Optionally, the generating module is used to: Inputting the target prompt word into the first machine learning model so that the first machine learning model extracts field keywords of the input content in the target prompt word, performs field matching on the field keywords and the database knowledge, determines a first field matching the field keywords, and generates the query statement according to the first field and the query statement knowledge in the target prompt word; Among them, the first field is a data field in the operation and maintenance alarm database.

[0070] Optionally, the generating module is used to: Acquire domain knowledge of operation and maintenance alarms; Inputting the target prompt word and the operation and maintenance alarm domain knowledge into the first machine learning model, so that the first machine learning model extracts field keywords of the input content in the target prompt word, determines domain keywords based on the field keywords and the operation and maintenance alarm domain knowledge, performs field matching on the domain keywords and the database knowledge, determines a second field matching the domain keywords, and generates the query statement according to the second field and the query statement knowledge in the target prompt word; Among them, the second field is a data field in the operation and maintenance alarm database.

[0071] Optionally, the generating module is used to: Acquire preset content and preset keywords corresponding to the preset content; Inputting the target prompt word and the preset example content into the first machine learning model, so that the first machine learning model performs semantic matching on the input content and the preset content in the target prompt word, determines the target preset content in the preset content that semantically matches the input content, performs field matching based on the target preset keyword corresponding to the target preset content and the database knowledge, determines a third field that matches the target preset keyword, and generates the query statement based on the third field and the query statement knowledge in the target prompt word; Among them, the third field is a data field in the operation and maintenance alarm database.

[0072] Optionally, the building block is used to: Based on the input content, the query statement knowledge, the database knowledge and the query statement example, the target prompt word is constructed according to a preset prompt word template.

[0073] Optionally, the dimension alarm data query device 700 further includes a first sending submodule, and the first sending submodule is used to: Sending the input content to a second machine learning model so that the second machine learning model extracts chart keywords from the input content and determines a target chart type corresponding to the chart keyword from a correspondence between the keyword and the chart type; Receive the target chart type returned by the second machine learning model, and display chart data corresponding to the target alarm data under the target chart type in the smart object page.

[0074] Optionally, the dimension alarm data query device 700 further includes a second sending submodule, and the second sending submodule is used to: Sending the input content and the target alarm data to a third machine learning model, so that the third machine learning model extracts data features of the target alarm data and semantic features of the input content, and generates data description content in natural language form based on the data features and the semantic features; Receive the data description content returned by the third machine learning model, and display the data description content on the smart object page.

[0075] Optionally, the database knowledge includes at least one type of field information including field names, field value examples, field descriptions, field notes, field matching logic descriptions, and matching descriptions of error-prone fields in the operation and maintenance alarm database.

[0076] Optionally, the target alarm data is obtained in the following manner: The operation and maintenance alarm database is automatically connected so that the operation and maintenance alarm database executes the query statement, obtains the target alarm data, and returns the target alarm data.

[0077] Optionally, the dimension alarm data query device 700 further includes at least one of the following modules: A fourth display module, configured to display the query statement on the smart object page; The fifth display module is used to determine the query information corresponding to the query statement and display the query information on the smart object page, wherein the query information includes at least one of a query dimension and a query indicator.

[0078] Based on the same concept, an embodiment of the present disclosure further provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the above-mentioned operation and maintenance alarm data query method are implemented.

[0079] Based on the same concept, the present disclosure also provides an electronic device, which may include: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the above-mentioned operation and maintenance alarm data query method.

[0080] Based on the same concept, an embodiment of the present disclosure also provides a computer program product, including a computer program, which implements the steps of the above-mentioned operation and maintenance alarm data query method when executed by a processor.

[0081] Reference below Figure 8 , which shows a schematic diagram of the structure of an electronic device 800 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0082] like Figure 8 As shown, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0083] Typically, the following devices may be connected to the I / O interface 805: an input device 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 800 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0084] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0085] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with 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 disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may 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 may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0086] In some embodiments, the front-end device and the back-end server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0087] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0088] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: displays the interactive control of the smart object in the operation and maintenance alarm page; displays the smart object page in response to a trigger operation on the interactive control, and the smart object page is used for the user to interact with the smart object; in response to an input operation in natural language form in the smart object page, the input content corresponding to the input operation is sent to a first machine learning model, so that the first machine learning model generates a query statement based on at least one data dimension in the operation and maintenance alarm database, and the database knowledge includes field information of fields in the operation and maintenance alarm database; and displays the target alarm data returned by the operation and maintenance alarm database on the smart object page.

[0089] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0090] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a module does not, in some cases, limit the module itself.

[0092] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0093] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0094] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0095] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0096] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A method for querying operation and maintenance alarm data, characterized in that: The method comprises: Display interactive controls of smart objects in the operation and maintenance alarm page; In response to a trigger operation on the interactive control, a smart object page is displayed, wherein the smart object page is used for interaction between a user and the smart object; In response to an input operation in a natural language form in the smart object page, an input content corresponding to the input operation is sent to a first machine learning model, so that the first machine learning model generates a query statement at least according to the input content, database knowledge, and query statement knowledge, wherein the query statement is used to query and obtain target alarm data based on at least one data dimension in an operation and maintenance alarm database, and the database knowledge includes field information of fields in the operation and maintenance alarm database; The target alarm data returned by the operation and maintenance alarm database is displayed on the smart object page.

2. The operation and maintenance alarm data query method according to claim 1 is characterized in that: The first machine learning model generates the query statement in the following manner: At least based on the input content, the query sentence knowledge and the database knowledge, construct a target prompt word according to a preset prompt word template; The query statement is generated based at least on the target prompt word and the first machine learning model.

3. The operation and maintenance alarm data query method according to claim 2 is characterized in that: The step of generating the query statement based at least on the target prompt word and the first machine learning model includes: Inputting the target prompt word into the first machine learning model so that the first machine learning model extracts field keywords of the input content in the target prompt word, performs field matching on the field keywords and the database knowledge, determines a first field matching the field keywords, and generates the query statement according to the first field and the query statement knowledge in the target prompt word; Among them, the first field is a data field in the operation and maintenance alarm database.

4. The operation and maintenance alarm data query method according to claim 2 is characterized in that: The step of generating the query statement based at least on the target prompt word and the first machine learning model includes: Acquire domain knowledge of operation and maintenance alarms; Inputting the target prompt word and the operation and maintenance alarm domain knowledge into the first machine learning model, so that the first machine learning model extracts field keywords of the input content in the target prompt word, determines domain keywords based on the field keywords and the operation and maintenance alarm domain knowledge, performs field matching on the domain keywords and the database knowledge, determines a second field matching the domain keywords, and generates the query statement according to the second field and the query statement knowledge in the target prompt word; Among them, the second field is a data field in the operation and maintenance alarm database.

5. The operation and maintenance alarm data query method according to claim 2 is characterized in that: The step of generating the query statement based at least on the target prompt word and the first machine learning model includes: Acquire preset content and preset keywords corresponding to the preset content; Inputting the target prompt word and the preset example content into the first machine learning model, so that the first machine learning model performs semantic matching on the input content and the preset content in the target prompt word, determines the target preset content in the preset content that semantically matches the input content, performs field matching based on the target preset keyword corresponding to the target preset content and the database knowledge, determines a third field that matches the target preset keyword, and generates the query statement based on the third field and the query statement knowledge in the target prompt word; Among them, the third field is a data field in the operation and maintenance alarm database.

6. The operation and maintenance alarm data query method according to claim 2 is characterized in that: The step of constructing a target prompt word according to a preset prompt word template based at least on the input content, the query sentence knowledge and the database knowledge includes: Based on the input content, the query statement knowledge, the database knowledge and the query statement example, the target prompt word is constructed according to a preset prompt word template.

7. The operation and maintenance alarm data query method according to any one of claims 1 to 6, characterized in that: The method further comprises: Sending the input content to a second machine learning model so that the second machine learning model extracts chart keywords from the input content and determines a target chart type corresponding to the chart keyword from a correspondence between the keyword and the chart type; Receive the target chart type returned by the second machine learning model, and display chart data corresponding to the target alarm data under the target chart type in the smart object page.

8. The operation and maintenance alarm data query method according to any one of claims 1 to 6, characterized in that: The method further comprises: Sending the input content and the target alarm data to a third machine learning model, so that the third machine learning model extracts data features of the target alarm data and semantic features of the input content, and generates data description content in natural language form based on the data features and the semantic features; Receive the data description content returned by the third machine learning model, and display the data description content on the smart object page.

9. The operation and maintenance alarm data query method according to any one of claims 1 to 6, characterized in that: The database knowledge includes at least one field information of the field name, field value example, field description, field remark, field matching logic description and error-prone field matching description of the field in the operation and maintenance alarm database.

10. The operation and maintenance alarm data query method according to any one of claims 1 to 6, characterized in that: The target warning data is obtained in the following manner: The operation and maintenance alarm database is automatically connected so that the operation and maintenance alarm database executes the query statement, obtains the target alarm data, and returns the target alarm data.

11. The operation and maintenance alarm data query method according to any one of claims 1 to 6, characterized in that: The method further comprises at least one of the following: Displaying the query statement on the smart object page; Determine query information corresponding to the query statement, and display the query information on the smart object page, wherein the query information includes at least one of a query dimension and a query index.

12. An operation and maintenance alarm data query device, characterized in that: The device comprises: A first display module is used to display the interactive controls of the smart object in the operation and maintenance alarm page; A second display module, configured to display a smart object page in response to a trigger operation on the interactive control, wherein the smart object page is used for interaction between a user and the smart object; a sending module, configured to respond to an input operation in a natural language form in the smart object page, and send input content corresponding to the input operation to a first machine learning model, so that the first machine learning model generates a query statement at least according to the input content, database knowledge, and query statement knowledge, wherein the query statement is used to query and obtain target alarm data based on at least one data dimension in an operation and maintenance alarm database, and the database knowledge includes field information of fields in the operation and maintenance alarm database; The third display module is used to display the target alarm data returned by the operation and maintenance alarm database on the smart object page.

13. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 11 are implemented.

14. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 11.

15. 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 11 are implemented.

Images