Nuclear power data recommendation method and device and electronic equipment

Abstract

The invention is suitable for the technical field of nuclear power data processing, and provides a nuclear power data recommendation method and device and electronic equipment, and the method comprises the steps: obtaining user information of a user in a nuclear power station, the user information comprising project information of a nuclear power station project currently served by the user and professional information of a professional to which the user belongs; obtaining document information edited by a user at present; the project information, the professional information and the document information serve as input of a trained recommendation model, nuclear power data output by the recommendation model are obtained, and the recommendation model is used for searching nuclear power data matched with the project information, the professional information and the document information from stored nuclear power data and sending the nuclear power data to the project information, the professional information and the document information. And outputting the searched nuclear power data. Through the method, the accuracy of the recommended nuclear power data can be improved.

Description

Technical Field

[0001] The present application belongs to the field of nuclear power data processing technology, and in particular, relates to a nuclear power data recommendation method, device and electronic equipment. Background Art

[0002] A nuclear power plant is a facility that uses a nuclear reactor to convert nuclear energy into electrical energy. Since nuclear power plants generate a large amount of heat energy by controlling the fission reaction of radioactive materials, they have potential risks such as nuclear waste, nuclear accidents, and nuclear proliferation. In order to improve the safety of nuclear power plants, the design, construction, and operation of nuclear power plants must comply with established safety standards and regulations, which are usually reflected in engineering documents or structured data.

[0003] From construction to operation and maintenance, nuclear power plants usually accumulate hundreds of thousands of engineering documents and millions of structured data. With the increase in the number of nuclear power plants, the nuclear power data involved in nuclear power plants will grow explosively. How to mine the value of these nuclear power data and achieve efficient use, knowledge inheritance, and capability reuse of a large amount of heterogeneous nuclear power data is of great value and significance to the high-quality construction and operation of the entire nuclear power plant.

[0004] However, due to the large amount of historical nuclear power data and poor correlation, it is difficult to obtain effective nuclear power data from historical nuclear power data in practical applications. Summary of the invention

[0005] The embodiments of the present application provide a nuclear power data recommendation method, device and electronic equipment, which can solve the problem that it is difficult to obtain effective nuclear power data from historical nuclear power data.

[0006] In a first aspect, an embodiment of the present application provides a nuclear power data recommendation method, comprising:

[0007] Acquire user information of the user in the nuclear power plant, the user information including project information of the nuclear power plant project currently served by the user and professional information of the profession to which the user belongs;

[0008] Get the document information currently edited by the user;

[0009] The project information, the professional information and the document information are used as inputs of a trained recommendation model to obtain nuclear power data output by the recommendation model. The recommendation model is used to find nuclear power data that matches the project information, the professional information and the document information from the stored nuclear power data, and output the found nuclear power data.

[0010] In a second aspect, an embodiment of the present application provides a nuclear power data recommendation device, including:

[0011] A user information acquisition module, used to acquire the user information of the user in the nuclear power plant, the user information including the project information of the nuclear power plant project currently served by the user and the professional information of the profession to which the user belongs;

[0012] The document information acquisition module is used to obtain the document information currently edited by the user;

[0013] A nuclear power data recommendation module is used to use the project information, the professional information and the document information as inputs of a trained recommendation model to obtain nuclear power data output by the recommendation model. The recommendation model is used to search for nuclear power data that matches the project information, the professional information and the document information from the stored nuclear power data, and output the found nuclear power data.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, wherein when the computer program is executed, the method described in the first aspect is executed.

[0017] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0018] In the embodiment of the present application, the recommended nuclear power data is determined based on the project information, professional information and document information, that is, the recommended nuclear power data is not only related to the document information, but also to the project information and professional information, and the nuclear power data of different nuclear power plant projects and different professions are usually different. Therefore, the nuclear power data recommended according to the above method is more accurate, that is, the acquired nuclear power data is more effective. In addition, since the recommended nuclear power data is determined according to the recommendation model, that is, the user does not need to actively search, thus simplifying the user's operation and improving the user's good experience.

[0019] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0021] Figure 1 It is a flowchart of a nuclear power data recommendation method provided by an embodiment of the present application;

[0022] Figure 2 This is a schematic diagram of displaying nuclear power data recommended when editing a document on a web page, provided by an embodiment of the present application;

[0023] Figure 3 It is a schematic diagram of generating a quality assurance audit report in Word format from a quality assurance audit report in Excel format provided by an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of a nuclear power data recommendation device provided by an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of an electronic device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0028] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0030] A nuclear power plant is a facility that uses a nuclear reactor to convert nuclear energy into electrical energy. Due to its advantages such as high energy density, low fuel consumption, and low greenhouse gas emissions, the number of nuclear power plants is increasing.

[0031] Each newly built nuclear power plant is equivalent to a newly built nuclear power plant project. During the implementation of the nuclear power plant project, multiple disciplines need to be involved, such as civil engineering, electrical engineering, instrumentation and control, systems, conventional islands, etc., and different disciplines will generate corresponding nuclear power data. Since there are usually some differences in the nuclear power data corresponding to different nuclear power plant projects and different disciplines, that is, different nuclear power data may have poor correlation, therefore, with the accumulation of a large amount of nuclear power data, it is becoming increasingly difficult to search for effective nuclear power data from a large amount of historical nuclear power data.

[0032] In order to increase the probability of searching for accurate nuclear power data from historical nuclear power data, an embodiment of the present application provides a nuclear power data recommendation method.

[0033] In the nuclear power data recommendation method, the corresponding nuclear power data is recommended to the user according to the user information of the user in the nuclear power plant and the document information currently edited by the user. Since the recommended nuclear power data is determined not only according to the document information currently edited by the user, but also according to the user information, it is equivalent to making the recommended nuclear power data filtered by the project information and professional information contained in the document information and the user information, thereby improving the accuracy of the recommended nuclear power data.

[0034] The nuclear power data recommendation method provided in the embodiment of the present application is described below with reference to the accompanying drawings.

[0035] Figure 1 A schematic flow chart of a nuclear power data recommendation method provided in an embodiment of the present application is shown. The method can be applied to a nuclear power system, and is described in detail as follows:

[0036] S11, obtaining user information of the user in the nuclear power plant, the user information including project information of the nuclear power plant project currently served by the user and professional information of the profession to which the user belongs.

[0037] The users here refer to users who serve nuclear power plants. One user can serve one nuclear power plant project or multiple nuclear power plant projects, which is not limited here.

[0038] The nuclear power plant project here corresponds to a nuclear power plant, one nuclear power plant corresponds to one nuclear power plant project, and the project information includes the identifier of the nuclear power plant (such as name, code, etc.).

[0039] The professional information here includes the name or code of the major, etc. The professional information can be determined according to the user's graduation major. For example, the user's graduation major (usually the last major studied by the user) is matched with various majors pre-set by the nuclear power plant, and the major that best matches the pre-set majors is selected as the user's major, and then the corresponding professional information is determined according to the selected major. Of course, the professional information can also be determined according to the content of the user's current work, which is not limited here.

[0040] In the embodiment of the present application, the user information may also include one or more of the user's name, ID number, work number in the nuclear power plant, etc., which are not limited here.

[0041] S12, obtaining information of the document currently being edited by the user.

[0042] The document information here includes the name of the document and / or the title of the document.

[0043] Specifically, it is detected whether the cursor appears in the document. If the cursor appears in the document, it can be determined that the user is editing the current document, and the document information of the document where the cursor is located is obtained. The document here includes a document in Word format and a document in PDF format. It only needs to be in an editable state, which is not limited here.

[0044] In the embodiment of the present application, "editing" includes input operations on a document that does not contain any document information, and also includes input operations on a document that already has document information, such as including modification operations on existing document information.

[0045] S13, taking the above-mentioned project information, the above-mentioned professional information and the above-mentioned document information as the input of the trained recommendation model, obtaining the nuclear power data output by the above-mentioned recommendation model, and the above-mentioned recommendation model is used to find the nuclear power data matching the above-mentioned project information, the above-mentioned professional information and the above-mentioned document information from the stored nuclear power data, and output the above-mentioned nuclear power data found.

[0046] Specifically, a recommendation model capable of making recommendations based on project information, professional information and document information is pre-trained. The recommendation model can use natural language processing (NLP) to identify document information, and search for required nuclear power data in the stored nuclear power data corresponding to the project information and professional information according to the identification result. Optionally, the recommendation model is a large model, that is, the recommendation model is a machine learning model with large-scale parameters and complex computing structure, which is constructed by a deep neural network. Since a large model is used as the recommendation model, the expression ability and prediction performance of the recommendation model are improved.

[0047] In the embodiment of the present application, the recommended nuclear power data is determined based on the project information, professional information and document information, that is, the recommended nuclear power data is not only related to the document information, but also to the project information and professional information, and the nuclear power data of different nuclear power plant projects and different professions are usually different. Therefore, the nuclear power data recommended according to the above method is more accurate, that is, the acquired nuclear power data is more effective. In addition, since the recommended nuclear power data is determined according to the recommendation model, that is, the user does not need to actively search, thus simplifying the user's operation and improving the user's good experience.

[0048] In some embodiments, the above S11 includes:

[0049] A1. When detecting that a user is logged in, obtain the user's login information.

[0050] A2. According to a preset login mapping relationship, search for project information and professional information corresponding to the login information, wherein the login mapping relationship is used to record the corresponding relationship between the user's login information and the project information and professional information.

[0051] In the embodiment of the present application, in order to improve the security of nuclear power data, the user is usually required to log in to the nuclear power system before accessing the nuclear power system, where the nuclear power system refers to a system related to a nuclear power plant. When it is detected that a user has logged in to the nuclear power system, the user's login information is obtained, where the login information includes the user's login account, and each login account uniquely identifies a user. After the user's login information is obtained, the login information is compared with the login information in the preset login mapping relationship. If the login information that is exactly the same as the acquired login information is found in the preset login mapping relationship, the project information and professional information corresponding to the login information found in the login mapping relationship are used as the user's project information and professional information.

[0052] It is introduced above that the user's project information and professional information can be determined based on the login information. In actual situations, the user's project information and professional information can also be determined based on other methods, such as through the project information and professional information currently entered by the user, which is not limited here.

[0053] In some embodiments, after the user information is obtained, the user information may change, for example, the logged-in user is changed. For example, when the user serves more than one nuclear power plant project, at this time, whether the logged-in user is changed or the same user updates his project information, the user information obtained by the nuclear power system will change. At this time, in order to ensure the accuracy of the user information obtained by the nuclear power system, after the above S11, it also includes:

[0054] If a modification operation of the user is detected, the acquired project information and / or professional information is modified to obtain the modified project information and / or modified professional information.

[0055] Specifically, if a change in the login account is detected, it is determined that a user modification operation is detected, and the acquired project information and professional information are replaced with the project information and professional information corresponding to the changed login account; if a change in the project information and / or professional information of the currently logged-in user is detected, it is determined that a user modification operation is detected, and if the modification operation only modifies the project information, the acquired project information is modified accordingly, if the modification operation only modifies the professional information, the acquired professional information is modified accordingly, and if the modification operation modifies both the project information and the professional information, the acquired project information and the acquired professional information are modified accordingly. After obtaining the modified project information and the modified professional information, the subsequent recommendation module will recommend the corresponding nuclear power data based on the modified project information and the modified professional information.

[0056] In the embodiment of the present application, the user may edit the document information through a text input device such as a mouse or a keyboard, or may edit the document information through a voice input device such as a microphone. In some embodiments, when the user edits the document information through a voice input device, the above S12 includes:

[0057] B1. When the user edits the document information by voice, the user's voice information is obtained.

[0058] Specifically, it is detected whether the voice input device collects voice information, and if so, the voice information is obtained.

[0059] B2. Recognize the above voice information to obtain a voice recognition result.

[0060] Specifically, the voice information is recognized as text information to obtain a voice recognition result.

[0061] B3. Use the stored nuclear power data to correct the above voice recognition result to obtain a corrected voice recognition result, and the above corrected voice recognition result is used as the document information currently edited by the user.

[0062] Specifically, considering that different characters may have the same pronunciation, when users of a nuclear power plant edit document information, the document information is likely to be related to the nuclear power data of the nuclear power plant. For example, the laws and regulations involved in the document information are usually laws and regulations related to the nuclear power plant. Therefore, when the speech recognition results are corrected in combination with the stored nuclear power data, it is beneficial to improve the accuracy of the final document information.

[0063] In an embodiment of the present application, after obtaining the speech recognition result, the nuclear power data closest to the speech recognition result can be searched from the stored nuclear power data, and then the speech recognition result can be corrected according to the closest nuclear power data. For example, assuming that the document information that the user actually wants to edit is "1RCP0001", but after the nuclear power system recognizes the voice information, the speech recognition result obtained is "ERCP0001". After regular comparison, it is found that the first digit before the system code "RCP" is mostly a number. Therefore, "E" is automatically replaced with "1", that is, the above-mentioned "ERCP0001" is corrected to "1RCP0001". It should be pointed out that the process of correcting the speech recognition result can be implemented using a trained correction model, which is not limited here.

[0064] In some embodiments, considering that users with different roles usually want to obtain different recommended information, before the above S13, the following is further included:

[0065] Obtain the role information of the user, where the role information is used to reflect the role of the user.

[0066] Correspondingly, the above S13 includes:

[0067] The project information, the professional information, the document information and the role information are used as inputs of the trained recommendation model to obtain the nuclear power data output by the recommendation model.

[0068] The role information includes the name of the role and / or the description information of the role. The role name may be at least one of the following: newbie, programmer, translator, general professional, quality assurance professional.

[0069] Among them, the description information of a newbie can be: As a newbie, I am still learning and exploring in [field / skill]; I have just started to get in touch with [thing / technology] and there are still many things I don’t understand, please give me more advice; As a newbie, I am well aware of my shortcomings, and I hope that the seniors can give me guidance; For [problem / task], as a newbie, I may still have many questions, and I hope to get your help.

[0070] The description of a programmer can be: I am a programmer who focuses on the development of [programming language / technical field]. As a programmer, I love programming and am good at solving various technical problems. As a programmer, I have a very high pursuit of code quality and am committed to writing efficient and maintainable code. In past projects, I successfully completed [project name] as a programmer and received praise from customers.

[0071] The description of the translator can be: I am a translator who is good at translating between [languages]. As a translator, I am committed to accurately conveying the meaning of the original text and maintaining the fluency and accuracy of the language. In my many years of career as a translator, I have accumulated rich translation experience and can handle various complex translation tasks. As a translator, I have participated in the translation of [important meetings / documents] and have been recognized by relevant parties.

[0072] The description of the overall professional can be: I have overall professional knowledge and skills in [field / profession]. As an overall professional, I can fully grasp the overall direction and key points of the project or task. My overall professional ability is not only reflected in theoretical knowledge, but also in practical operations and project management. With the quality of overall professionalism, I can quickly adapt to new environments and solve various complex problems.

[0073] The description of the quality assurance profession can be: I am a quality assurance professional who focuses on product quality control and assurance. As a quality assurance professional, I am familiar with various quality standards and testing methods and can ensure that products meet relevant requirements. In the field of quality assurance, I always adhere to the principle of quality first and strive to improve the overall quality level of products. Through the work of quality assurance, I have successfully reduced the failure rate of products and improved customer satisfaction.

[0074] In the embodiment of the present application, since the recommendation model determines the recommended nuclear power data based on project information, professional information, document information and role information, the screening dimension is increased, thereby improving the accuracy of the recommended nuclear power data. For example, for the role of "novice", the detail of the recommended nuclear power data can be increased, and for the role of "programmer", the nuclear power data related to the code can be recommended first.

[0075] In some embodiments, after the above S13, the method further includes:

[0076] When the above-mentioned document information is displayed on a web page, the above-mentioned nuclear power data is displayed on the display interface where the above-mentioned document information is located, but the above-mentioned nuclear power data and the above-mentioned document information are not on the same display page.

[0077] Specifically, when a user edits a document on a web page, the document information of the document is displayed on the web page. At this time, the nuclear power data output by the recommendation model is displayed on the same display interface as the document information, but is not displayed on the same display page as the document information. Since the nuclear power data and the document information are not on the same display page, editing the document information will not affect the recommended nuclear power data. Similarly, changes to the recommended nuclear power data will not affect the displayed document information. In addition, since both the document information and the recommended nuclear power data are displayed on the same display interface, the user can view the document information and the recommended nuclear power data at the same time without switching the display interface.

[0078] Optionally, the recommendation model can also be used to retrieve according to the search information input by the user. Specifically, the recommendation model searches for corresponding nuclear power data from the stored nuclear power data according to the search information input by the user and the acquired project information and professional information. Since the search information is information actively input by the user, the above method is conducive to obtaining more accurate nuclear power data.

[0079] like Figure 2 As shown, assuming that the document information is displayed on the first display page, the nuclear power data output by the recommended model will be displayed on the second display page. Figure 2 In the data, the design input, the information corresponding to 1, 2, and 3 under the design input (such as 1.ANXXXXXXXXXX001), and the laws and regulations, the information corresponding to 1, 2, and 3 under the laws and regulations (such as 1.GBXXXXXXXXXX001) all belong to the nuclear power data found by the recommendation model based on the document information. When the user hopes to obtain search results that match the search information entered by the user, the user can enter the search information in the input box corresponding to "Please enter" on the second display page. The recommendation model searches for the corresponding nuclear power data from the stored nuclear power data based on the search information entered by the user and the project information and professional information of the user that has been obtained. When the nuclear power data is found, the searched nuclear power data will be displayed on the display page where the "Knowledge Questions and Answers" are located. From Figure 2 It can be seen that the first display page and the second display page both belong to the same display interface, that is, the user can view the first display page and the second display page at the same time without switching the display interface.

[0080] The above describes how to display the nuclear power data determined by the recommendation model when the document information is displayed on the web page. Considering that in actual situations, the document information may also be edited locally, at this time, the nuclear power data determined by the recommendation model may be displayed on the display interface corresponding to the input method, that is, in some embodiments, after the above S13, it also includes:

[0081] When the above-mentioned document information is displayed locally and the recommendation function is turned on, the above-mentioned nuclear power data is displayed on the display interface corresponding to the input method currently used.

[0082] Specifically, the recommendation model can be associated with the input method, such as adding a "recommendation function module" in the input method. The recommendation function module is used to implement the recommendation function. When the recommendation function is turned on, the display interface corresponding to the input method can display the nuclear power data determined by the recommendation model.

[0083] After the user turns on the recommendation function corresponding to the recommendation model in the input method, the recommendation model can display the nuclear power data it has searched for on the display interface of the currently used input method, so that the user can quickly insert the displayed nuclear power data into the document information he is editing. For example, after the user enters the title of the document through the input method (such as using the character information in the first line of the document as the title of the document), the recommendation model obtains the title of the document, and searches for nuclear power data based on the title and the acquired project information and professional information, obtains the found nuclear power data, and displays the found nuclear power data on the display interface corresponding to the input method. Assuming that in the display interface, the number corresponding to the nuclear power data is 1, after the user clicks "1", the nuclear power system inserts the nuclear power data corresponding to "1" into the position of the cursor of the document, thereby realizing the rapid insertion of nuclear power data.

[0084] In some embodiments, the recommendation model of the embodiment of the present application can be trained in the following manner. That is, before the above S13, it also includes:

[0085] C1. Obtain at least two types of raw data.

[0086] The raw data here refers to data related to nuclear power technology. For example, it may include data obtained from completing one or more nuclear power plant projects, and may also include data corresponding to papers and reports related to nuclear power technology. In the embodiment of the present application, the type of raw data can be divided according to the format of the raw data. For example, the raw data in Word format can be used as one type of raw data, the raw data in PDF format can be used as another type of raw data, the raw data in picture format can be used as another type of raw data, and so on. Of course, the type of the raw data can also be divided according to the profession to which the content it contains belongs, which is not limited here.

[0087] Optionally, the number of raw data of each type may be determined according to actual needs. For example, when the actual needs of the user are that the format of the searched nuclear power data is as much as possible in Word format, the number of raw data in Word format to be obtained may be set to be the largest. For example, when the actual needs of the user are that there is no restriction on the format of the searched nuclear power data, the number of raw data of each type to be obtained may be set to be the same.

[0088] C2. parse the original data using a parsing method corresponding to the type of the original data to extract metadata of the original data, where the metadata includes project information and professional information corresponding to the original data.

[0089] Specifically, when the type of raw data is divided according to the format of the raw data, the raw data can be parsed according to a format that matches the format of the raw data. For example, when the format of the raw data is Word format, the raw data can be parsed according to a parsing method corresponding to the Word format, such as parsing out the title and / or content of the raw data, and obtaining metadata of the raw data according to the parsing result. The metadata includes project information and professional information corresponding to the raw data, and in addition, may also include at least one information such as author, creation date, version number, copyright, etc.

[0090] Optionally, parsing the original data may also include parsing the structural layout of the original data to obtain a corresponding structural layout, which includes the title and subtitle of the original data, and may also include the font, page margins, etc. of the original data, which will not be repeated here.

[0091] C3. Obtaining the user information of the user and the behavior data of the user when using the original data, wherein the behavior data includes the data of viewing the nuclear power data.

[0092] The use of original data here includes viewing original data and / or editing original data.

[0093] The behavior data here refers to the data corresponding to the behavior related to nuclear power data generated by the user when using the original data. For example, assuming that the user views nuclear power data m when editing the original data 1, the behavior data of the user when using the original data 1 includes viewing nuclear power data m. The behavior data also includes the user's preference data. For example, when the above behavior is viewing, the corresponding preference data includes data such as which author or which professional nuclear power data the user prefers to view when viewing nuclear power data.

[0094] Optionally, the above-mentioned behavior data may also include data on copying and / or clicking on nuclear power data, that is, the behavior data involved in the embodiment of the present application may include not only viewing, but also copying and / or clicking, etc., which will not be repeated here.

[0095] C4. Train the recommendation model to be trained according to the metadata of the original data, the user information and the behavior data to obtain the trained recommendation model.

[0096] Specifically, training the recommendation model to be trained based on metadata, user information and behavior data is equivalent to determining the correspondence between metadata, user information and behavior data, so that the trained recommendation model can input user information and document information and the determined correspondence to output corresponding nuclear power data.

[0097] In an embodiment of the present application, since the types of original data for training the recommendation model include at least two types, the trained recommendation model can search in at least two types of nuclear power data corresponding to the training, thereby improving the accuracy of the nuclear power data determined by the recommendation model.

[0098] It should be pointed out that there may be only one type of original data for training the recommendation model. In this case, the trained recommendation model can only be searched in nuclear power data corresponding to this type.

[0099] In some embodiments, if after parsing the original data, the parsing result also includes the structural layout of the original data, then step C4 will train the recommendation model to be trained based on the metadata, user information, behavior data and structural layout of the original data. At this time, when the trained recommendation model (i.e., the trained recommendation model) obtains the document information currently edited by the user, the obtained document information also includes the structural layout of the document, and determines the corresponding nuclear power data based on the obtained structural layout of the document, thereby further improving the accuracy of the output nuclear power data.

[0100] In some embodiments, if the behavior data of the embodiment of the present application also includes user preference data, the trained recommendation model may give priority to outputting nuclear power data that matches the user's preference data. Since nuclear power data that matches the user's preference data is given priority, and the user's preference usually does not change over a period of time, when outputting nuclear power data in the above manner, it is beneficial to improve the accuracy of the output nuclear power data.

[0101] In some embodiments, after obtaining the trained recommendation model, the method further includes:

[0102] D1. Obtain user feedback.

[0103] The feedback information here includes information actively collected by the nuclear power system, such as after the recommendation model outputs the nuclear power data, the nuclear power system actively collects the nuclear power data selected (such as clicked) by the user to obtain the corresponding feedback information. The above feedback information may also include information actively input by the user, such as after the recommendation model outputs the nuclear power data, the user inputs the corresponding evaluation according to the output nuclear power data, and the nuclear power system can determine the above feedback information according to the evaluation input by the user.

[0104] D2. Optimize the trained recommendation model according to the feedback information to obtain an optimized trained recommendation model.

[0105] In the embodiment of the present application, since the feedback information is related to the user, optimizing the trained recommendation model according to the user's feedback information is conducive to obtaining a more accurate recommendation model, that is, it is conducive to improving the accuracy of the nuclear power data output by the optimized trained recommendation model.

[0106] In some embodiments, considering that nuclear power data may change over time, in order to improve the accuracy of the nuclear power data output by the recommendation model, it is necessary to optimize the trained recommendation model according to the changed original data. At this time, after obtaining the trained recommendation model, the following is further included:

[0107] E1. Obtain the adjusted original data.

[0108] Among them, the adjusted original data includes adjustments to existing original data, such as deleting existing original data, or changing part of the existing original data, where the partial data includes at least one of the version number, parameter name, parameter value, structural layout, etc. of the original data; the adjusted original data also includes adjustments to non-existing original data, such as newly added original data.

[0109] E2. parse the adjusted original data using a parsing method corresponding to the type of the adjusted original data to extract metadata of the adjusted original data to obtain adjusted metadata.

[0110] The process of obtaining the adjusted metadata is similar to the process of obtaining the metadata in the above step C2, and will not be repeated here.

[0111] E3. Obtaining the user information of the user, and obtaining the behavior data of the user when using the adjusted original data, to obtain the adjusted behavior data.

[0112] The process of obtaining the adjusted behavior data is similar to the process of obtaining the behavior data in the above step C3, which will not be repeated here.

[0113] E4. Optimize the trained recommendation model according to the adjusted metadata, the user information and the adjusted behavior data to obtain an optimized trained recommendation model.

[0114] The process of optimizing the trained recommendation model is similar to the process of training the recommendation model to be trained, which will not be described in detail here.

[0115] In the embodiment of the present application, since the trained recommendation model is optimized in combination with the adjusted original data, and the accuracy of the adjusted original data is usually higher than the original data before the adjustment, the accuracy of the optimized trained recommendation model is improved after optimization through the above method.

[0116] In some embodiments, after the above S12, the method further includes:

[0117] Perform error correction on the above document information.

[0118] Specifically, the nuclear power system can send the acquired document information to the recommendation model for processing, and the recommendation model analyzes whether the expression of the document information matches the expression of the project information and professional information corresponding to the document information. If not, the document information is prompted to be wrong. For example, when the recommendation model determines that the parameter value in the document information is different from the parameter value of the nuclear power data determined by it, an error reminder can be given for the parameter value; for example, when it is determined that the laws and regulations referenced by the document information are different from the pre-stored laws and regulations, an error reminder can be given for the referenced laws and regulations; for another example, when it is determined that the version number of the document referenced by the document information is not the latest version number, an error reminder can be given for the version number. Among them, the expression of the project information and professional information corresponding to the document information can be determined based on the expression of the corresponding project information and professional information in the stored nuclear power data.

[0119] In the embodiment of the present application, since the document information is error corrected, it is helpful to improve the accuracy of the final document.

[0120] In some embodiments, the error correction processing of the document information includes:

[0121] Perform error correction processing on the document information corresponding to the edited current sentence, and / or perform error correction processing on the document information corresponding to the edited paragraph.

[0122] Specifically, it is possible to determine whether the current sentence has been edited by the user based on the punctuation marks in the document information. If so, error correction is performed on the document information corresponding to the sentence that has been edited.

[0123] The edited paragraphs in the document information refer to the paragraphs corresponding to all the document information that have been edited by the user.

[0124] In the embodiment of the present application, the error correction process includes: identifying whether there are sentences with grammatical errors, for example, identifying whether the prepositions and time adverbials in the sentence are used accurately, and identifying whether the key information such as the subject, predicate, and object are missing in the sentence. If there are sentences with grammatical errors, and the existing grammatical errors cannot be deduced based on the context and logical inference, an error prompt is given, for example, "[]" is used to prompt at the location where the error exists. If there are sentences with grammatical errors, but the existing grammatical errors can be deduced based on the context and logical inference, the sentences with grammatical errors are modified. Furthermore, the modified sentences are prompted.

[0125] In the embodiment of the present application, since different error correction processing modes can be selected for error correction processing, the flexibility of the error correction processing is improved.

[0126] Optionally, a corresponding error correction processing method may be selected according to the editing time of the document information. For example, when the editing time (i.e., the time corresponding to the current time and the time when the editing starts) is less than a preset time threshold, error correction processing is selected for the document information corresponding to the edited paragraph, and when the editing time is not less than the time threshold, error correction processing is selected for the document information corresponding to the edited current sentence.

[0127] Since the document information corresponding to the edited paragraph is usually small when the editing time is short, the error correction time required for the document information corresponding to the edited paragraph is also short, which makes the error correction process timely. When the editing time is long, the document information corresponding to the edited paragraph is usually large. At this time, the document information corresponding to the current sentence that has been edited is selected for error correction, which can reduce the amount of data involved in a single error correction process, thereby shortening the error correction time required for a single error correction process, and further improving the timeliness of the error correction process.

[0128] Optionally, considering that the documents of the nuclear power plant may contain information marked with special symbols, and the probability of error of such information is low, it is not necessary to correct the information of the specified symbols, that is, before the error correction process is performed, the information of the specified symbols is first filtered out, and then the error correction process is performed on the filtered document information. For example, assuming that the specified symbols include "[ ]", "()", "《》", then during the error correction process, there is no need to delete or simplify the content contained in the "[ ]", "()", "《》" in the sentence, nor to add any new information or explanation.

[0129] Optionally, the information to be filtered out may also include project name, file number and version, chapter title, etc., which are not limited here.

[0130] In some embodiments, considering that the document information of the same document of the nuclear power plant may be edited by different users, the error correction process for the document information includes:

[0131] When it is detected that the document information has been edited by at least two users, error correction processing is performed on all the document information after editing.

[0132] For example, when it is detected that the document information has been edited by at least two users, error correction processing is performed on the document information corresponding to the current sentence after editing is completed. For another example, when it is detected that the document information has been edited by at least two users, error correction processing is performed on the document information corresponding to the paragraph after editing is completed.

[0133] Specifically, considering that different users may have different editing habits, for example, different users may use different symbols to represent the same parameter, therefore, in order to improve the accuracy of the obtained document, it is necessary to perform unified error correction processing on all document information after editing. The unified error correction processing here includes: after using NLP technology to perform semantic recognition on all document information, determine whether the expression of the same parameter in all document information is consistent, determine whether there are differences in parameter values ​​under the same parameter, determine whether there are inconsistencies in the description of the same event, and so on.

[0134] In an embodiment of the present application, it is detected whether a document has been edited. If it is detected that the document has been edited, the information of the editing user is counted. It is determined whether the same document has been edited by at least two users based on the counted editing user information. If it is determined that the same document has been edited by at least two users, error correction processing is performed on all document information after the editing is completed. Since error correction processing is performed on all document information after the editing is completed, that is, error correction processing is performed on document information at different locations, it is beneficial to improve the consistency of the description of the same document information, thereby improving the accuracy of the obtained document.

[0135] In some embodiments, after the above S12, the method further includes:

[0136] F1. Determine the keywords of the above document information.

[0137] Specifically, considering that nouns and verbs can reflect most of the information of an event, the keywords of the document information can be determined according to the nouns and verbs of the document information.

[0138] Optionally, when there are a large number of nouns (or verbs), whether the noun (or verb) is a keyword of the document information can be determined based on the frequency of occurrence of the noun (or verb). For example, when the frequency of occurrence of a noun is higher than a preset frequency threshold, the noun is used as a keyword of the document information.

[0139] F2. Determine the structural layout corresponding to the keywords of the document information, the project information and the professional information according to a preset structural layout mapping relationship, wherein the structural layout mapping relationship is used to record the correspondence between the structural layout and the keywords, project information and professional information.

[0140] F3. Determine the filling content of the above structure layout according to the above document information.

[0141] Specifically, the correspondence between the structure layout and the keywords, project information, and professional information is preset. After the keywords are obtained from the document information, if it is determined that the document (or report) does not have a structure layout, the keywords are parsed from the report name, and the corresponding structure layout is searched in the preset structure layout mapping relationship table according to the keywords, the project information in the user information, and the professional information, and then a document with the searched structure layout is generated. Furthermore, the obtained document information can be filled into the corresponding structure layout of the generated document.

[0142] In the embodiment of the present application, since the corresponding structural layout can be matched according to the keywords in the document information, the acquired project information and the professional information, and a document with the structural layout can be generated, it is beneficial to improve the consistency of the structural layout of similar documents.

[0143] In some embodiments, the above F3 includes: directly filling the document information into the determined structural layout, and also includes processing the document information before filling it into the determined structural layout. For example, assuming that a quality assurance inspection report in Word format needs to be generated based on the document information of the quality assurance inspection report in an Excel table, the list names of each list are extracted from the list in the Excel table, and these list names are equivalent to the keywords of the document information in the Excel table. According to the keyword, the acquired project information and professional information, the corresponding structural layout is matched, and the corresponding processing method is selected for the document information corresponding to each keyword, and the processed document information is filled into the matching structural layout.

[0144] like Figure 3 As shown, it is assumed that the Excel table includes three lists, namely, report F elements, F content, and report F element problem type F content. Among them, the document information corresponding to the report F element is usually used to describe the cause of event failure, the document information corresponding to the F content is usually used to describe the event itself, and the document information corresponding to the report F element problem type F content is usually used to describe the cause of event failure, the problem, and the event itself.

[0145] Assuming that the three keywords of report F element, F content and report F element problem type F content, and the structural layout determined according to the project information and professional information corresponding to the report include F basis documents, corrective action requirements (or improvement actions) and summary. Then, the F basis documents can be generated for the document information corresponding to the F element, that is, the relevant laws and regulations and other information can be searched according to the document information corresponding to the F element, and the documents corresponding to the laws and regulations and other information found are used as the document information corresponding to the F basis documents; the document information corresponding to the F content can be generated for the corrective action requirements or improvement actions; the document information corresponding to the summary can be generated for the document information corresponding to the report F element problem type F content.

[0146] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0147] Corresponding to the nuclear power data recommendation method described in the above embodiment, Figure 4 A structural block diagram of a nuclear power data recommendation device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0148] Reference Figure 4 The nuclear power data recommendation device 4 includes: a user information acquisition module 41, a document information acquisition module 42, and a nuclear power data recommendation module 43, wherein:

[0149] The user information acquisition module 41 is used to acquire the user information of the user in the nuclear power plant, wherein the user information includes the project information of the nuclear power plant project currently served by the user and the professional information of the profession to which the user belongs;

[0150] The document information acquisition module 42 is used to acquire the document information currently edited by the user;

[0151] The nuclear power data recommendation module 43 is used to use the above-mentioned project information, the above-mentioned professional information and the above-mentioned document information as the input of the trained recommendation model to obtain the nuclear power data output by the above-mentioned recommendation model. The above-mentioned recommendation model is used to find the nuclear power data matching the above-mentioned project information, the above-mentioned professional information and the above-mentioned document information from the stored nuclear power data, and output the above-mentioned nuclear power data found.

[0152] In the embodiment of the present application, the recommended nuclear power data is determined based on the project information, professional information and document information, that is, the recommended nuclear power data is not only related to the document information, but also to the project information and professional information, and the nuclear power data of different nuclear power plant projects and different professions are usually different. Therefore, the nuclear power data recommended according to the above method is more accurate, that is, the acquired nuclear power data is more effective. In addition, since the recommended nuclear power data is determined according to the recommendation model, that is, the user does not need to actively search, thus simplifying the user's operation and improving the user's good experience.

[0153] In some embodiments, the user information acquisition module 41 includes:

[0154] The login information acquisition unit is used to acquire the user's login information when detecting that the user is logged in.

[0155] The project information and professional information search unit is used to search for the project information and professional information corresponding to the above login information according to a preset login mapping relationship, wherein the above login mapping relationship is used to record the correspondence between the user's login information and the project information and professional information.

[0156] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0157] The modified user information acquisition module is used to modify the acquired project information and / or professional information if a user modification operation is detected after the user information of the user in the nuclear power plant is acquired, so as to obtain the modified project information and / or the modified professional information.

[0158] In some embodiments, the document information acquisition module 42 includes:

[0159] The voice information acquisition unit is used to acquire the user's voice information when the user edits the document information by voice.

[0160] The voice information recognition unit is used to recognize the above voice information and obtain a voice recognition result.

[0161] The speech recognition result correction unit is used to correct the speech recognition result using the stored nuclear power data to obtain a corrected speech recognition result, and the corrected speech recognition result is used as the document information currently edited by the user.

[0162] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0163] A role information acquisition module, used to acquire the role information of the user before taking the project information, the professional information and the document information as inputs of the trained recommendation model to obtain the nuclear power data output by the recommendation model, wherein the role information is used to reflect the role of the user;

[0164] Correspondingly, the nuclear power data recommendation module 43 is specifically used for:

[0165] The project information, the professional information, the document information and the role information are used as inputs of the trained recommendation model to obtain the nuclear power data output by the recommendation model.

[0166] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application also includes: after outputting the above-mentioned nuclear power data found, and when the above-mentioned document information is displayed on the web page, the above-mentioned nuclear power data is displayed on the display interface where the above-mentioned document information is located, but the above-mentioned nuclear power data and the above-mentioned document information are not on the same display page.

[0167] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application also includes: after outputting the above-mentioned nuclear power data found, and when the above-mentioned document information is displayed locally and the recommendation function is turned on, the above-mentioned nuclear power data is displayed on the display interface corresponding to the input method currently used.

[0168] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0169] The raw data acquisition module is used to acquire at least two types of raw data before using the project information, the professional information and the document information as inputs of the trained recommendation model.

[0170] The metadata extraction module is used to parse the original data using a parsing method corresponding to the type of the original data to extract metadata of the original data, wherein the metadata includes project information and professional information corresponding to the original data.

[0171] The behavior data acquisition module is used to obtain the user information of the user and the behavior data of the user when using the original data, wherein the behavior data includes the data of viewing the nuclear power data.

[0172] The recommendation model training module is used to train the recommendation model to be trained according to the metadata of the original data, the user information and the behavior data to obtain the trained recommendation model.

[0173] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0174] The feedback information acquisition module is used to obtain user feedback information after obtaining the above-mentioned trained recommendation model.

[0175] The first optimization module of the recommendation model is used to optimize the trained recommendation model according to the feedback information to obtain the optimized trained recommendation model.

[0176] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0177] The adjusted original data acquisition module is used to obtain the adjusted original data after the trained recommendation model is obtained.

[0178] The adjusted metadata acquisition module is used to parse the adjusted original data using a parsing method corresponding to the type of the adjusted original data to extract metadata of the adjusted original data to obtain adjusted metadata.

[0179] The adjusted behavior data acquisition module is used to acquire the user information of the user, and to acquire the behavior data of the user when using the adjusted original data, so as to obtain the adjusted behavior data.

[0180] The second optimization module of the recommendation model is used to optimize the trained recommendation model according to the adjusted metadata, the user information and the adjusted behavior data to obtain the optimized trained recommendation model.

[0181] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0182] The error correction processing module is used to perform error correction processing on the document information currently edited by the user after obtaining the document information currently edited by the user.

[0183] In some embodiments, the error correction processing module is specifically used to:

[0184] Perform error correction processing on the document information corresponding to the edited current sentence, and / or perform error correction processing on the document information corresponding to the edited paragraph.

[0185] In some embodiments, the error correction processing module is specifically used to:

[0186] When it is detected that the document information has been edited by at least two users, error correction processing is performed on all the document information after editing.

[0187] In some embodiments, the nuclear power data recommendation 4 provided in the embodiment of the present application further includes:

[0188] The keyword determination module is used to determine the keywords of the document information after obtaining the document information currently edited by the user.

[0189] The structural layout determination module is used to determine the structural layout corresponding to the keywords of the above-mentioned document information, the above-mentioned project information and the above-mentioned professional information according to the preset structural layout mapping relationship, wherein the above-mentioned structural layout mapping relationship is used to record the correspondence between the structural layout and the keywords, project information and professional information.

[0190] A filling module is used to determine the filling content of the above structure layout based on the above document information.

[0191] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0192] Figure 5 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 5 As shown, the electronic device 5 of this embodiment includes: at least one processor 50 ( Figure 5 Only one processor is shown in the figure), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, wherein the processor 50 implements the steps in any of the above-mentioned method embodiments when executing the computer program 52.

[0193] The electronic device 5 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 It is only an example of the electronic device 5 and does not constitute a limitation on the electronic device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0194] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0195] In some embodiments, the memory 51 may be an internal storage unit of the electronic device 5, such as a hard disk or memory of the electronic device 5. In other embodiments, the memory 51 may also be an external storage device of the electronic device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the electronic device 5. The memory 51 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0196] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0197] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0198] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0199] An embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0200] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0201] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0202] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0203] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0204] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0205] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A nuclear power data recommendation method, characterized in that: include: Acquire user information of the user in the nuclear power plant, the user information including project information of the nuclear power plant project currently served by the user and professional information of the profession to which the user belongs; Get the document information currently edited by the user; The project information, the professional information and the document information are used as inputs of a trained recommendation model to obtain nuclear power data output by the recommendation model. The recommendation model is used to find nuclear power data that matches the project information, the professional information and the document information from the stored nuclear power data, and output the found nuclear power data.

2. The nuclear power data recommendation method according to claim 1, characterized in that: The obtaining of user information of the user in the nuclear power plant includes: When a user is detected to be logged in, obtain the user's login information; According to a preset login mapping relationship, the project information and professional information corresponding to the login information are searched, wherein the login mapping relationship is used to record the corresponding relationship between the user's login information and the project information and professional information.

3. The nuclear power data recommendation method according to claim 1, characterized in that: After obtaining the user information of the user in the nuclear power plant, the method further includes: If a modification operation of the user is detected, the acquired project information and / or the professional information is modified to obtain the modified project information and / or the modified professional information.

4. The nuclear power data recommendation method according to claim 1, characterized in that: The obtaining of the document information currently edited by the user includes: When the user edits the document information by voice, obtaining the user's voice information; Recognizing the voice information to obtain a voice recognition result; The speech recognition result is corrected using the stored nuclear power data to obtain a corrected speech recognition result, and the corrected speech recognition result is used as the document information currently edited by the user.

5. The nuclear power data recommendation method according to claim 1, characterized in that: Before taking the project information, the professional information and the document information as inputs of the trained recommendation model to obtain the nuclear power data output by the recommendation model, the method further includes: Acquire role information of the user, where the role information is used to reflect the role of the user; The step of using the project information, the professional information and the document information as inputs of the trained recommendation model to obtain the nuclear power data output by the recommendation model includes: The project information, the professional information, the document information and the role information are used as inputs of a trained recommendation model to obtain nuclear power data output by the recommendation model.

6. The nuclear power data recommendation method according to claim 1, characterized in that: After obtaining the nuclear power data output by the recommendation model, the method further includes: When the document information is displayed on a web page, the nuclear power data is displayed on a display interface where the document information is located, but the nuclear power data and the document information are not on the same display page.

7. The nuclear power data recommendation method according to claim 1, characterized in that: After obtaining the nuclear power data output by the recommendation model, the method further includes: When the document information is displayed locally and the recommendation function is turned on, the nuclear power data is displayed on a display interface corresponding to the input method currently in use.

8. The nuclear power data recommendation method according to claim 1, characterized in that: Before taking the project information, the professional information and the document information as inputs of the trained recommendation model, the method further includes: Obtain at least two types of raw data; Parsing the original data using a parsing method corresponding to the type of the original data to extract metadata of the original data, wherein the metadata includes project information and professional information corresponding to the original data; Acquire user information of the user and behavior data of the user when using the original data, wherein the behavior data includes data of the behavior of viewing nuclear power data; The recommendation model to be trained is trained according to the metadata of the original data, the user information, and the behavior data to obtain the trained recommendation model.

9. The nuclear power data recommendation method according to claim 8, characterized in that: After obtaining the trained recommendation model, the method further includes: Get feedback from users; The trained recommendation model is optimized according to the feedback information to obtain an optimized trained recommendation model.

10. The nuclear power data recommendation method according to claim 8, characterized in that: After obtaining the trained recommendation model, the method further includes: Obtain adjusted raw data; Parsing the adjusted original data using a parsing method corresponding to the type of the adjusted original data to extract metadata of the adjusted original data to obtain adjusted metadata; Acquire user information of the user, and acquire behavior data of the user when using the adjusted original data to obtain adjusted behavior data; The trained recommendation model is optimized according to the adjusted metadata, the user information and the adjusted behavior data to obtain an optimized trained recommendation model.

11. The nuclear power data recommendation method according to any one of claims 1 to 10, characterized in that: After obtaining the document information currently edited by the user, the method further includes: Perform error correction processing on the document information corresponding to the edited current sentence, and / or perform error correction processing on the document information corresponding to the edited paragraph.

12. The nuclear power data recommendation method according to claim 11, characterized in that: The error correction processing of the document information corresponding to the edited current sentence includes: when it is detected that the document information has been edited by at least two users, error correction processing of the document information corresponding to the current sentence after editing is completed; The error correction processing of the document information corresponding to the edited paragraph includes: when it is detected that the document information has been edited by at least two users, error correction processing of the document information corresponding to the paragraph after editing is completed.

13. The nuclear power data recommendation method according to any one of claims 1 to 10, characterized in that: After obtaining the document information currently edited by the user, the method further includes: Determining keywords of the document information; Determine the structural layout corresponding to the keywords of the document information, the project information and the professional information according to a preset structural layout mapping relationship, wherein the structural layout mapping relationship is used to record the correspondence between the structural layout and the keywords, the project information and the professional information; The filling content of the structural layout is determined according to the document information.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 13 is implemented.

15. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 13 is implemented.

16. A computer program product, characterized in that The invention comprises a computer program, which, when being executed, enables the method according to any one of claims 1 to 13 to be performed.

Images