Research and development knowledge delivery methods, devices, electronic equipment and storage media

Abstract

This application discloses a method, device, electronic device, and computer-readable storage medium for pushing R&D knowledge of locomotive products. The method is applied to a locomotive R&D knowledge management system and includes: acquiring R&D knowledge entries, which include R&D experience information and R&D specification information of locomotive products; classifying the R&D knowledge entries based on preset keywords to obtain a set of R&D knowledge entries related to the corresponding keywords; and pushing the set of R&D knowledge entries related to the corresponding keywords to a client for display, thereby assisting in the R&D tasks of locomotive products. The solution of this application enables the locomotive R&D knowledge management system to push R&D knowledge entries to the client in a targeted manner.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method for pushing R&D knowledge of locomotive products, a device for pushing R&D knowledge of locomotive products, an electronic device, and a computer-readable storage medium. Background Technology

[0002] As external market competition intensifies and new technologies emerge both domestically and internationally, enterprises face a more complex and volatile market environment. Under these circumstances, the government also requires enterprises to undergo digital transformation, enabling them to develop better, higher-quality, more cost-effective, and more competitive new products more quickly through the deep integration of information technology and industrialization.

[0003] Currently, in the field of locomotive R&D, enterprises face the risk of losing knowledge and experience along with personnel changes, as well as the lack of systematic management and chaotic management of locomotive R&D knowledge. This results in internal personnel having no channels to obtain this locomotive R&D knowledge and experience, and the knowledge and experience they acquire being inconsistent, thus reducing the efficiency of locomotive R&D. Summary of the Invention

[0004] To address the aforementioned technical problems, embodiments of this application provide a method for pushing R&D knowledge of locomotive products, a device for pushing R&D knowledge of locomotive products, an electronic device, and a computer-readable storage medium.

[0005] According to one aspect of the embodiments of this application, a method for pushing R&D knowledge of locomotive products is provided. The method is applied to a locomotive R&D knowledge management system. The method includes: acquiring R&D knowledge items, which include R&D experience information and R&D specification information of locomotive products; classifying the R&D knowledge items based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords; and pushing the set of R&D knowledge items related to the corresponding keywords to a client to display the set of R&D knowledge items through the client to assist in the R&D tasks of locomotive products.

[0006] In an exemplary embodiment, the preset keywords include parent keywords and child keywords; the R&D knowledge items are classified based on the preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords, including: classifying the R&D knowledge items based on the preset parent keywords to obtain a set of R&D knowledge items related to the corresponding parent keywords; and classifying the R&D knowledge items in the set of R&D knowledge items related to the parent keywords based on the preset child keywords to obtain a set of R&D knowledge items related to the corresponding child keywords.

[0007] In one exemplary embodiment, the R&D knowledge items are classified based on preset keywords, including: obtaining text information of the R&D knowledge items; matching the text information with preset keywords; and if the match is successful, treating the R&D knowledge item as an element in a set of R&D knowledge items related to the corresponding keywords.

[0008] In one exemplary embodiment, matching text information with preset keywords includes: extracting features of the text information; calculating the similarity between the features and each preset keyword; and if the similarity between the features and the target keyword is greater than a preset threshold, then determining that the R&D knowledge item matches the target keyword.

[0009] In one exemplary embodiment, pushing a set of R&D knowledge items related to the corresponding keywords to the client includes: obtaining the search terms input in the client for retrieving the set of R&D knowledge items; determining the keywords that match the search terms; and pushing the set of R&D knowledge items related to the keywords to the client.

[0010] In an exemplary embodiment, before pushing the set of R&D knowledge entries related to the corresponding keyword to the client, the method includes, but is not limited to: calculating multiple similarities between the R&D knowledge entries related to the corresponding keyword obtained through classification and processing and each other R&D knowledge entry related to the corresponding keyword in the locomotive R&D knowledge management system; if the multiple similarities include a first similarity and the first similarity is greater than a first preset value, deleting the R&D knowledge entries related to the corresponding keyword obtained through classification and processing from the locomotive R&D knowledge management system.

[0011] In an exemplary embodiment, the method further includes: if multiple similarities include a second similarity, the second similarity is greater than a second preset value and less than a first preset value, and the second preset value is less than the first preset value; obtaining a target R&D knowledge entry whose similarity to the R&D knowledge entry related to the corresponding keyword obtained through classification processing is the second similarity; and updating the target R&D knowledge entry using the R&D knowledge entry related to the corresponding keyword obtained through classification processing.

[0012] According to one aspect of the embodiments of this application, a device for pushing product R&D knowledge is provided, comprising: an acquisition module for acquiring R&D knowledge items, the R&D knowledge items including R&D experience information and R&D specification information of locomotive products; a classification processing module for classifying the R&D knowledge items based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords; and a push module for pushing the set of R&D knowledge items related to the corresponding keywords to a client, so as to display the set of R&D knowledge items through the client to assist in the R&D tasks of locomotive products.

[0013] According to one aspect of the embodiments of this application, an electronic device is provided, including a processor and a memory, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the above-described method for pushing R&D knowledge of locomotive products is implemented.

[0014] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, on which computer-readable instructions are stored, which, when executed by a computer's processor, cause the computer to execute the locomotive product research and development knowledge push method provided above.

[0015] According to one aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the locomotive product research and development knowledge delivery method provided in the various optional embodiments described above.

[0016] In the technical solution provided by the embodiments of this application, on the one hand, the R&D knowledge items are classified and stored in the locomotive R&D knowledge management system, so that the locomotive R&D knowledge management system can push R&D knowledge items to the client in a targeted manner. On the other hand, this embodiment sends the R&D knowledge items to the client in a set manner, so that the client can obtain all R&D knowledge items related to the R&D task at once, which can avoid the waste of time and energy caused by R&D personnel searching for the required R&D knowledge items one by one from all the messy R&D knowledge items, thereby improving the efficiency of locomotive R&D.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0019] Figure 1 This is a functional schematic diagram of a locomotive R&D knowledge management system, as illustrated in an exemplary embodiment of this application.

[0020] Figure 2 This is a flowchart illustrating a method for pushing R&D knowledge of locomotive products, as shown in an exemplary embodiment of this application;

[0021] Figure 3 Is Figure 2 A flowchart illustrating an exemplary method for pushing R&D knowledge of locomotive products, based on the illustrated embodiment;

[0022] Figure 4 yes Figure 2 The flowchart of step S200 in the illustrated embodiment is a typical example.

[0023] Figure 5 yes Figure 2 The flowchart of step S220 in the illustrated embodiment is shown in an exemplary embodiment.

[0024] Figure 6 yes Figure 2 The flowchart of step S200 in the illustrated embodiment is a typical example.

[0025] Figure 7 yes Figure 2 The flowchart of step S300 in the illustrated embodiment is a typical example.

[0026] Figure 8 This is a block diagram of a product research and development knowledge dissemination device illustrated in an exemplary embodiment of this application;

[0027] Figure 9 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0028] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0031] It should also be noted that "multiple" as mentioned in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0032] Knowledge management is a new management concept and method in the knowledge economy era. It utilizes modern information technology combined with enterprise management ideas and methods to achieve modern management. Knowledge management is an important component of enterprise management. In knowledge management, knowledge can be divided into two parts: explicit knowledge and tacit knowledge. Explicit knowledge is knowledge expressed in the form of words, symbols, graphics, etc., such as work results; tacit knowledge refers to knowledge that is not expressed in the form of words, symbols, graphics, etc. This type of knowledge exists in the human brain, such as inspiration and practical experience. Currently, there is a lack of a systematic management system for the R&D resources of locomotive enterprises, which makes it difficult to collect, integrate, share, and innovate information related to product development within locomotive enterprises. This hinders the exchange and development of technology within locomotive enterprises and is detrimental to their long-term technological progress.

[0033] To address at least the aforementioned problems in the prior art, embodiments of this application propose a method for pushing R&D knowledge of locomotive products, a device for pushing R&D knowledge of locomotive products, an electronic device, and a computer-readable storage medium, which will be described in detail below.

[0034] First, it should be noted that the embodiments of this application relate to a locomotive R&D knowledge management system. This system can be understood as an information platform used to manage R&D knowledge items in the field of locomotive R&D, and it generally has functions such as data collection, processing, and display. See also... Figure 1 , Figure 1 This is a functional schematic diagram of a locomotive R&D knowledge management system illustrated in an exemplary embodiment of this application, such as... Figure 1 As shown, the locomotive R&D knowledge management system can manage various locomotive R&D knowledge items, including knowledge push, knowledge retrieval, knowledge evaluation, knowledge Q&A, knowledge subscription, knowledge statistics, knowledge display, knowledge upload, knowledge classification, knowledge navigation, knowledge import, and knowledge templates. Figure 1 In this context, "knowledge" refers to locomotive R&D knowledge items. The locomotive R&D knowledge management system supports system upgrades and iterative optimizations centered on locomotive R&D business processes, thereby forming a knowledge application system guided by locomotive product R&D processes.

[0035] This locomotive R&D knowledge management system takes the locomotive product R&D process as its core. It develops a set of hardware and software systems around different stages of product R&D, which can cover all aspects of locomotive enterprise R&D departments, from design input to design output, production and manufacturing, quality management, and after-sales service, to help R&D personnel make correct, advantageous and efficient decisions when planning designs or when outputting designs.

[0036] The method for disseminating R&D knowledge for this locomotive product involves the systematic organization, identification, management, and application of knowledge in locomotive system integration and various professional fields. This is achieved through the use of information technology tools and data applications, business optimization, and integration with relevant software platforms. This results in the systematic organization, accumulation, inheritance, sharing, and management of knowledge. It should be noted that the constructed locomotive R&D knowledge management system can be applied to the entire locomotive industry or to individual locomotive companies; no specific limitations are imposed here.

[0037] Please see Figure 2 , Figure 2 This is a flowchart illustrating an exemplary embodiment of the present application of a method for pushing R&D knowledge of locomotive products, which is applied to the locomotive R&D knowledge management system mentioned above. Figure 1 As shown, the method for pushing R&D knowledge of locomotive products provided in this embodiment includes steps S100-S300, which are described in detail below:

[0038] Step S100: Obtain R&D knowledge entries.

[0039] In this embodiment, R&D knowledge items are divided into two categories. The first category is R&D specification information, which refers to standard documents needed by R&D personnel during locomotive R&D. These standard documents are usually documents issued by authoritative organizations that are beneficial to locomotive R&D. R&D specification information is generally immutable for a period of time, such as textbooks related to locomotive R&D published by a certain publishing house, guiding documents related to locomotive R&D written by a certain locomotive company, standards, laws and regulations, technical papers, technical books, design specifications, etc., without specific limitations here. The second category is R&D experience information, which refers to knowledge beneficial to locomotive R&D summarized by R&D personnel during the practice of locomotive R&D. This type of knowledge may be highly variable with knowledge updates, experience accumulation, and the development of new technologies, new materials, and new requirements. Therefore, it may be updated in real time as needed during locomotive R&D practice. Examples include typical cases, project overviews, handling of inertial quality problems, and handling of source quality problems.

[0040] For example, since R&D experience information is mainly based on personal experience, it is difficult to summarize and categorize it into structured data. Simply storing these experience descriptions makes retrieval and utilization difficult. Therefore, in order to facilitate the retrieval and utilization of this R&D experience information, we can use eigenvalue induction to summarize and partially structure the R&D experience information, ultimately obtaining the R&D knowledge entries corresponding to the R&D experience information.

[0041] For example, a question-and-answer section can be set up within the locomotive R&D knowledge management system. This allows R&D personnel to post technical problems encountered in their work, which are then answered and analyzed by professionals. This fully utilizes and stores the tacit knowledge stored within the locomotive company's personnel. Additionally, R&D personnel can also post their summarized experience in locomotive product development in the question-and-answer section. Professionals will then assess its accuracy and relevance to the locomotive R&D process. Only if the information is accurate or valuable will the corresponding experience be recognized as a R&D knowledge item.

[0042] For example, R&D experience and specifications information for locomotive products can be input into the locomotive R&D knowledge management system in various formats, such as text, images, and audio. Furthermore, the R&D experience or specifications information may be presented in languages ​​other than Chinese, such as English or Korean; no specific limitations are made here. In this case, after receiving R&D experience and specifications information for locomotive products in different formats, the locomotive R&D knowledge management system needs to preprocess this information to obtain R&D knowledge entries that conform to the specified format. For example, uniformly converting the R&D experience and specifications information for locomotive products into Chinese text format requires text extraction from image or audio formats and converting text in other languages ​​into Chinese text.

[0043] Step S200: Classify the R&D knowledge items based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords.

[0044] In this embodiment, keywords are pre-set for classifying R&D knowledge items. Each keyword is treated as a category, and each R&D knowledge item is assigned to a set of R&D knowledge items related to the corresponding keyword based on the classification results. In this embodiment, keywords can be specified by professional R&D personnel or determined based on key information corresponding to the locomotive product. For example, the key information could be the key R&D focus information of a locomotive company.

[0045] For example, keywords for classification can be determined based on at least one of the following: the R&D stage, product type, and product structure of the locomotive product. For instance, if different categories of locomotive product names are used as keywords, the process of classifying R&D knowledge items involves determining which locomotive product name is most relevant to the R&D knowledge item and assigning it to the category of the most relevant locomotive product name.

[0046] For example, keywords can be used to represent different stages of locomotive development, such as the locomotive design and development planning stage, review stage, technical design stage, working drawing design stage, user assessment stage, and technical confirmation stage.

[0047] For example, different structures of locomotive products can be used as keywords, such as preset keywords like car body, bogie, grid-side high-voltage system, traction system, braking system, auxiliary system, ventilation system, control and communication system, on-board safety monitoring and testing equipment, electrical room, braking, electric transmission, etc. For example, preset keywords can also be related to standards and specifications, structural principles, experience cases, methods, and inspection and testing.

[0048] This embodiment classifies the acquired R&D knowledge items to obtain a set of R&D knowledge items related to the corresponding keywords, and then displays the R&D knowledge items in a more organized manner in the locomotive R&D knowledge management system in a set manner.

[0049] Step S300: Push the set of R&D knowledge items related to the corresponding keywords to the client so that the set of R&D knowledge items can be displayed through the client, thereby assisting in the R&D tasks of locomotive products.

[0050] In this embodiment, the client is a terminal device connected to the locomotive R&D knowledge management system. For example, in response to the push request from the client, the set of R&D knowledge items to be pushed in the push request is pushed to the client.

[0051] In this embodiment, the R&D knowledge items are categorized and stored in the locomotive R&D knowledge management system, enabling the client to selectively retrieve R&D knowledge items from the system. Furthermore, this embodiment sends the R&D knowledge items to the client in a set format, allowing the client to retrieve all R&D knowledge items related to the R&D task at once. This avoids the waste of time and effort for R&D personnel to search through a chaotic list of items, thereby improving locomotive R&D efficiency.

[0052] See Figure 3 , Figure 3 Is Figure 2The flowchart illustrates an exemplary method for pushing R&D knowledge of locomotive products, based on the illustrated embodiment. Figure 3 As shown, the method is in Figure 2 Based on the illustrated embodiment, before step S300, steps S10-S40 are further included, which are described in detail below:

[0053] Step S10: Calculate the similarity between the R&D knowledge entries related to the corresponding keywords obtained from the classification process and each other R&D knowledge entry related to the corresponding keywords in the locomotive R&D knowledge management system.

[0054] exist Figure 2 Based on the embodiments shown, the inventors of this application considered that if the R&D knowledge entries related to the corresponding keywords obtained after classification processing are duplicated with other R&D knowledge entries related to the corresponding keywords in the locomotive R&D knowledge management system, then to avoid unnecessary memory consumption, the R&D knowledge entries related to the corresponding keywords obtained after classification processing can be deleted from the locomotive R&D knowledge management system.

[0055] Based on this, this step first calculates multiple similarities between the R&D knowledge entries related to the corresponding keywords obtained through classification and processing and each other R&D knowledge entry related to the corresponding keywords in the locomotive R&D knowledge management system, so as to determine whether they are duplicates by obtaining multiple similarities between the R&D knowledge entries related to the corresponding keywords obtained through classification and processing and each other R&D knowledge entry related to the corresponding keywords.

[0056] For example, firstly, the first text information of the R&D knowledge entries related to the corresponding keywords, which has been classified, and the second text information of each other R&D knowledge entry related to the corresponding keywords in the locomotive R&D knowledge management system are obtained. Then, multiple similarities between the first text information and each second text information are calculated.

[0057] Step S20: If multiple similarities include the first similarity and the first similarity is greater than the first preset value, delete the R&D knowledge entries related to the corresponding keywords obtained from the classification process from the locomotive R&D knowledge management system.

[0058] In this embodiment, the first preset value can be set according to the fault tolerance requirements required in the actual application scenario, such as 80%, 90%, etc., without specific limitation.

[0059] In this embodiment, when the similarity between the R&D knowledge entries related to the corresponding keywords obtained through classification processing and other R&D knowledge entries related to the corresponding keywords in the locomotive R&D knowledge management system is greater than a first preset value, the R&D knowledge entries related to the corresponding keywords obtained through classification processing will be deleted from the locomotive R&D knowledge management system to avoid a large number of duplicate R&D knowledge entries occupying the memory space of the locomotive R&D knowledge management system.

[0060] For example, when the similarity between the R&D knowledge item related to the corresponding keyword obtained through classification processing and other R&D knowledge items related to the corresponding keyword in the locomotive R&D knowledge management system is greater than a first preset value, an abnormal signal is generated to characterize the possible duplication of the R&D knowledge item related to the corresponding keyword obtained through classification processing. The abnormal signal is then sent to the backend so that relevant personnel in the backend can confirm whether to delete the R&D knowledge item related to the corresponding keyword obtained through classification processing as needed, so as to avoid accidental deletion of the R&D knowledge item related to the corresponding keyword obtained through classification processing and improve the user experience.

[0061] For example, a signal is sent to the question and answer area of ​​the locomotive R&D knowledge management system to indicate that the similarity between the R&D knowledge entries related to the corresponding keywords obtained through classification processing and other R&D knowledge entries related to the corresponding keywords in the locomotive R&D knowledge management system is greater than a first preset value. This allows professionals to analyze the duplication of the R&D knowledge entries related to the corresponding keywords obtained through classification processing in the locomotive R&D knowledge management system, and then determine whether to delete the R&D knowledge entries related to the corresponding keywords obtained through classification processing based on the analysis results.

[0062] Step S30: If multiple similarities include a second similarity, the second similarity is greater than a second preset value and less than a first preset value.

[0063] In this embodiment, the second preset value is a value less than the first preset value. The second preset value can be flexibly set according to the actual application scenario, and is not specifically limited here, such as 50%, 60%, etc.

[0064] Step S40: Obtain the target R&D knowledge item whose similarity to the corresponding keyword obtained from the classification process is the second similarity.

[0065] Because locomotive R&D experience is constantly evolving, what was previously considered correct may be deemed incorrect in subsequent practice. Locomotive R&D experience gained in practice supplements previous experience in the same field. Therefore, in this step, when the matching value between the R&D knowledge entries related to the corresponding keywords obtained through classification and processing and other R&D knowledge entries related to the corresponding keywords in the locomotive R&D knowledge management system meets preset conditions, the R&D knowledge entries related to the corresponding keywords obtained through classification and processing are used to update other R&D knowledge entries related to the corresponding keywords in the locomotive R&D knowledge management system. This ensures the real-time nature and accuracy of the R&D knowledge entries in the locomotive R&D knowledge management system, thereby ensuring that R&D personnel can obtain more accurate R&D knowledge entries from the locomotive R&D knowledge management system for R&D work.

[0066] In this embodiment, the target R&D knowledge entry is one of other R&D knowledge entries related to the corresponding keyword from the locomotive R&D knowledge management system.

[0067] Step S50: Update the target R&D knowledge entries using the R&D knowledge entries related to the corresponding keywords obtained from the classification process.

[0068] For example, when the similarity of the R&D knowledge entries related to the corresponding keywords obtained through classification processing is greater than a second preset value and less than a first preset value, a signal is generated to indicate confirmation of updating the target R&D knowledge entry. This signal is then sent to the backend so that relevant personnel in the backend can confirm whether to update the target R&D knowledge entry using the R&D knowledge entries related to the corresponding keywords obtained through classification processing, or the signal can be sent to the question and answer area of ​​the locomotive R&D knowledge management system so that professionals can analyze the target R&D knowledge entry and determine whether to update the target R&D knowledge entry using the R&D knowledge entries related to the corresponding keywords obtained through classification processing based on the analysis results, thereby improving the user experience.

[0069] For example, in the locomotive R&D knowledge management system, the interface design format used to display the target R&D knowledge items is directly applied to the R&D knowledge items related to the corresponding keywords obtained through classification processing. Subsequently, the target R&D knowledge items are deleted from the locomotive R&D management system. For instance, the display position, size, font, etc., of the target R&D knowledge items are directly applied to the R&D knowledge items related to the corresponding keywords obtained through classification processing. This method eliminates the tedious operation of setting the format of the R&D knowledge items related to the corresponding keywords obtained through classification processing.

[0070] This embodiment updates the target R&D knowledge entries by using the R&D knowledge entries related to the corresponding keywords obtained through classification processing that meet the preset conditions. On the one hand, it can improve the orderliness of R&D knowledge entry management and ensure the accuracy of R&D knowledge entries in the locomotive R&D knowledge management system. On the other hand, it can promptly clean up duplicate or partially duplicate R&D knowledge entries in the locomotive R&D knowledge management system to avoid occupying unnecessary memory space in the locomotive R&D knowledge management system.

[0071] See Figure 4 , Figure 4 yes Figure 2 The flowchart of step S200 in the illustrated embodiment is as follows: Figure 4 As shown, step S200 may include steps S210-S220, which are described in detail below:

[0072] Step S210: Obtain the text information of the R&D knowledge entries.

[0073] In this embodiment, different methods for obtaining the text information of R&D knowledge items are selected according to their different forms. For example, if the R&D knowledge item is in image format, text extraction processing is performed on the image to obtain the corresponding text information of the R&D knowledge item. OCR (Optical Character Recognition) can be used to extract the text information of the R&D knowledge item. OCR refers to the process by which electronic devices (such as scanners or digital cameras) examine characters printed on paper, determine their shape by detecting dark and light patterns, and then translate the shape into computer text using character recognition methods. That is, for printed characters, optical methods are used to convert the text in paper documents into black and white dot matrix image files, and recognition software converts the text in the image into text format for further editing by word processing software. To improve the accuracy of text information extraction, this embodiment can also use machine learning to extract the text information of R&D knowledge items; this is not specifically limited here.

[0074] Step S220: Match the text information with preset keywords. If the match is successful, the R&D knowledge item is taken as an element in the set of R&D knowledge items related to the corresponding keyword.

[0075] In this embodiment, text information is matched with keywords to determine whether the text information is related to the keywords. If it is related, it is matched; otherwise, it is not matched. For example, the text of a research and development knowledge item is compared with each keyword. If the text of the research and development knowledge item includes a preset number of characters from the keyword, then the research and development knowledge item is determined to match the corresponding keyword. For example, if the text of the research and development knowledge item includes a preset number of characters from the keyword, and the order of these preset number of characters is the same as the order of the preset number of characters in the corresponding keyword, then the research and development knowledge item is determined to match the corresponding keyword. For example, if the text of the research and development knowledge item includes a preset number of consecutive characters from the keyword, and the order of these preset number of characters is the same as the order of the preset number of characters in the corresponding keyword, then the research and development knowledge item is determined to match the corresponding keyword.

[0076] For example, if the word "body" in the R&D knowledge item "Good body surface quality, the visible body surface shall not have defects that impair the surface perfection such as ripples, wrinkles, dents, scratches, edge scratches; decorative lines and decorative ribs shall be clear, flat, smooth, symmetrical and uniformly transitioned, and the joints of two covering parts shall fit together but may be uneven" matches the word "body" in the pre-set keyword "body manufacturing requirements", then the above R&D knowledge item shall be regarded as an element in the set of R&D knowledge items related to the keyword "body manufacturing requirements".

[0077] In some specific application scenarios, the R&D knowledge item does not include some or all of the text in the keyword, but it is still related to the keyword. For example, if the preset keyword is "R&D design stage", the R&D knowledge item is "The structure of the bogie should facilitate the installation of the spring damping device and have good damping characteristics to mitigate vehicle and track vibration and reduce dynamic stress, thereby improving vehicle stability and safety". This R&D knowledge item does not include any of the text in the above keyword, but this R&D knowledge item is indeed a knowledge point involved in the R&D design stage.

[0078] In this context, when matching R&D knowledge items with keywords, machine learning (ML) methods can be used to calculate the relevance between the R&D knowledge item and each keyword, and then determine whether the two match based on the relevance. Machine learning is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and many other disciplines. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instruction-based learning.

[0079] The method for pushing R&D knowledge of locomotive products proposed in this application involves machine learning technology, and the following will describe the embodiment in detail.

[0080] Specifically, see Figure 5 , Figure 5 yes Figure 2 The flowchart of step S220 in the illustrated embodiment is as follows: Figure 5 As shown, step S220 may include steps S221-S222, which are described in detail below:

[0081] Step S221: Extract the features of the textual information of the R&D knowledge entries.

[0082] In this step, by extracting the features of the textual information of the R&D knowledge items, more important information in the R&D knowledge items can be extracted. This information cannot be expressed by simple text, but is determined by the contextual semantic relationships between words, sentences, or words and sentences in the R&D knowledge items, which can more accurately obtain the information contained in the R&D knowledge items.

[0083] This embodiment utilizes the Word2vec model to extract features from the textual information of R&D knowledge entries. The Word2vec model is a related model used to generate word vectors. These models are shallow, two-layer neural networks that represent words and need to guess the input words in adjacent positions. Under the bag-of-words assumption in Word2vec, the order of words is unimportant. After training, the Word2vec model can map each word to a vector, representing the relationship between words. This vector is the hidden layer of the neural network. Specifically, Chinese Wikipedia (zhiwiki) can be used as training corpus to pre-train the Word2vec model. The textual information of R&D knowledge entries is then input into the Word2vec model, and the features of the textual information of the R&D knowledge entries are output. It should be noted that this embodiment can utilize all existing word embedding methods to obtain the feature vectors corresponding to word segmentation, such as the Global Vectors of Word Representation (GloVe) method, One-hot encoding, information retrieval techniques, distributed representation, etc., without specific limitations.

[0084] Step S222: Calculate the similarity between the features of the text information and each preset keyword. If the similarity between the features of the text information and the target keyword is greater than the preset threshold, then the research and development knowledge item is determined to match the target keyword.

[0085] For example, if there is more than one target keyword whose similarity to the text information is greater than a preset threshold, then the R&D knowledge item is included as an element in the set of R&D knowledge items related to the target keyword with the highest similarity.

[0086] For example, the cosine value or Euclidean distance between the features of the text information and each preset keyword is calculated, and then the cosine value or Euclidean distance is used as the similarity between the features of the text information and the corresponding keywords.

[0087] This embodiment first extracts features from textual information and calculates the similarity between these features and each preset keyword. If the similarity between a feature and a target keyword is greater than a preset threshold, the research and development knowledge item is determined to match the target keyword. This method accurately obtains the feature information of research and development knowledge items, thereby improving the accuracy of the keywords obtained that match the research and development knowledge items, and ultimately improving the accuracy of the classification of research and development knowledge items.

[0088] See Figure 6 , Figure 6 yes Figure 2 The flowchart of step S200 in the illustrated embodiment is as follows: Figure 6As shown, step S200 may include steps S230-S240, which are described in detail below:

[0089] In this embodiment, the preset keywords include parent keywords and their corresponding child keywords. In practical applications, there exists a special case where a research and development knowledge entry may be an element in a set of research and development knowledge entries related to two or more keywords. For example, a research and development knowledge entry may be an element in a set of research and development knowledge entries related to the keyword "early stage of research and development," and simultaneously an element in a set of research and development knowledge entries related to the keyword "vehicle body manufacturing requirements." In this case, these two or more keywords can be used as each other's parent and child keywords, and the research and development knowledge entry can be considered an element in a set of research and development knowledge entries related to both the parent and child keywords.

[0090] For example, the parent keyword is "locomotive structure," and the corresponding child keywords are car body, bogie, grid-side high-voltage system, traction system, braking system, auxiliary system, ventilation system, control and communication system, on-board safety monitoring system, etc. For example, the parent keyword is "car body," and the corresponding child keywords are "car body structure knowledge," "car body method knowledge," etc.

[0091] If there is more than one target keyword whose textual information features have a similarity greater than a preset threshold to the target keyword, then the target keyword with lower similarity is taken as the parent keyword, the target keyword with higher similarity is taken as the child keyword, and the R&D knowledge item is taken as an element in the set of R&D knowledge items related to the parent keyword and the child keyword.

[0092] Step S230: Classify the R&D knowledge items based on the preset parent keywords to obtain a set of R&D knowledge items related to the corresponding parent keywords.

[0093] In this embodiment, each keyword can have its corresponding child keywords set or not. A keyword can be the parent keyword of its child keywords and also the child keyword of another keyword. It can be seen that this keyword setting method has one or more root keywords. Root keywords do not have parent keywords, but they do have child keywords. Therefore, root keywords are also a type of parent keyword. In this way, keywords are displayed hierarchically, and then the R&D knowledge items are classified according to the hierarchical keywords.

[0094] In this embodiment, when classifying R&D knowledge items, they are first matched with each root-level keyword. If the match is successful, the R&D knowledge item is included as an element in the set of R&D knowledge items related to the corresponding root-level keyword.

[0095] For example, this embodiment classifies R&D knowledge items based on the classification processing method described in steps S210-S220 above, which will not be described in detail here.

[0096] Step S240: Based on the preset child-level keywords, classify the R&D knowledge items in the set of R&D knowledge items related to the parent-level keywords to obtain the set of R&D knowledge items related to the corresponding child-level keywords.

[0097] In this step, the R&D knowledge items are further categorized using the parent keywords corresponding to each keyword. Specifically, the R&D knowledge items in the set of R&D knowledge items related to the parent keywords corresponding to each keyword are categorized to obtain the set of R&D knowledge items related to the corresponding child keywords.

[0098] Since each keyword, including parent and child keywords, is matched with the R&D knowledge item only once, it does not actually increase the workload of classifying and processing the R&D knowledge items. However, in this way, all R&D knowledge items can be hierarchically divided and displayed in the locomotive R&D knowledge management system, which is beneficial for subsequent hierarchical push of the classified R&D knowledge items.

[0099] See Figure 7 , Figure 7 yes Figure 2 The flowchart of step S300 in the illustrated embodiment is shown as follows: Figure 7 As shown, step S300 may include steps S310-S330, which are described in detail below:

[0100] Step S310: Obtain the search terms entered in the client for retrieving the set of R&D knowledge items.

[0101] In this embodiment, the user enters search terms on the client to retrieve a set of R&D knowledge items, so that the locomotive R&D knowledge management system can determine the set of R&D knowledge items to be pushed based on the search terms.

[0102] For example, the search query entered by the user on the client is preprocessed to obtain search terms that meet the preset conditions. Preprocessing methods include word replacement, search query simplification, keyword extraction, semantic feature extraction, etc., which are not specifically limited here.

[0103] For example, the client pre-stores all the keywords used in the vehicle R&D knowledge management system for classifying R&D knowledge items, so that when users need to obtain R&D knowledge items, they can directly determine the set of R&D knowledge items to be pushed based on the keywords.

[0104] For example, the locomotive R&D knowledge management system obtains the R&D knowledge item retrieval request input by the client, and sends all the keywords in the locomotive R&D knowledge management system to the client according to the R&D knowledge item retrieval request, and the client directly determines the set of R&D knowledge items to be pushed according to the keywords.

[0105] Step S320: Identify keywords that match the search terms.

[0106] In this step, the obtained search terms are matched with each keyword to determine the keyword that best matches the search terms. In this embodiment, the keyword that best matches the search terms is the keyword that is most relevant to the search terms. Therefore, this embodiment can calculate the similarity between the search terms and each keyword, and then take the keyword with the highest similarity as the keyword that best matches the search terms.

[0107] For example, the matching value between the search term and each keyword is calculated, and the keyword corresponding to the matching value greater than a preset threshold is taken as the keyword that best matches the search term. If no keyword has a matching value greater than the preset threshold with the search term, a message indicating that the request failed is returned to the client.

[0108] Step S330: Push the set of R&D knowledge items related to the keywords to the client.

[0109] This embodiment pushes a set of R&D knowledge items based on the search terms entered by the client. Specifically, by combining the search terms with all keywords in the locomotive R&D knowledge management system, it can quickly obtain all R&D knowledge items related to the search terms, thereby improving the efficiency of pushing R&D knowledge items.

[0110] participate Figure 8 , Figure 8 This is a block diagram of a product research and development knowledge dissemination device illustrated in an exemplary embodiment of this application, such as... Figure 8 As shown, the product R&D knowledge push device 50 includes a first acquisition module 51, a classification processing module 52, and a push module 53.

[0111] The first acquisition module 51 is used to acquire R&D knowledge items, which include R&D experience information and R&D specification information of locomotive products; the classification processing module 52 is used to classify the R&D knowledge items based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords; the push module 53 is used to push the set of R&D knowledge items related to the corresponding keywords to the client so that the set of R&D knowledge items can be displayed through the client to assist in the R&D tasks of locomotive products.

[0112] In another exemplary embodiment, the preset keywords include parent keywords and child keywords, and the classification processing module 52 includes a first classification processing unit and a second classification processing unit. The first classification processing unit is used to classify R&D knowledge items based on the preset parent keywords to obtain a set of R&D knowledge items related to the corresponding parent keywords; the second classification processing unit is used to classify the R&D knowledge items in the set of R&D knowledge items related to the parent keywords based on the preset child keywords to obtain a set of R&D knowledge items related to the corresponding child keywords.

[0113] In another exemplary embodiment, the classification processing module 52 includes an acquisition unit and a matching unit, wherein the acquisition unit is used to acquire text information of R&D knowledge items; the matching unit is used to match the text information with preset keywords, and if the match is successful, the R&D knowledge item is taken as an element in a set of R&D knowledge items related to the corresponding keywords.

[0114] In another exemplary embodiment, the matching unit includes an extraction subunit and a calculation subunit, wherein the extraction subunit is used to extract features of text information; the calculation subunit is used to calculate the similarity between the features and each preset keyword, and if the similarity between the features and the target keyword is greater than a preset threshold, then it is determined that the R&D knowledge item matches the target keyword.

[0115] In another exemplary embodiment, the push module 53 includes a search term acquisition unit, a determination unit, and a push unit, wherein the search term acquisition unit is used to acquire the search terms input by the client for retrieving a set of R&D knowledge items; the determination unit is used to determine the keywords that match the search terms; and the push unit is used to push the R&D knowledge items related to the keywords to the client.

[0116] In another exemplary embodiment, the product R&D knowledge push device 50 further includes a matching function module and a deletion function module. The matching function module is used to match the R&D knowledge entries related to the corresponding keywords obtained through classification processing with other R&D knowledge entries related to the corresponding keywords in the locomotive R&D knowledge management system. The deletion function module is used to delete the R&D knowledge entries related to the corresponding keywords obtained through classification processing from the locomotive R&D knowledge management system if the matching value is greater than a first preset value.

[0117] In another exemplary embodiment, the product R&D knowledge push device 50 further includes a second acquisition module and an update module, wherein the second acquisition module is used to acquire a target R&D knowledge entry that matches the R&D knowledge entry related to the corresponding keyword obtained by classification processing if the matching value is greater than a second preset value and less than a first preset value, and the second preset value is less than the first preset value; the update module is used to update the target R&D knowledge entry using the R&D knowledge entry related to the corresponding keyword obtained by classification processing.

[0118] It should be noted that the apparatus provided in the above embodiments and the method provided in the above embodiments belong to the same concept, and the specific way in which each module and unit performs operations has been described in detail in the method embodiments, and will not be repeated here.

[0119] In another exemplary embodiment, this application provides an electronic device including a processor and a memory, wherein computer-readable instructions are stored on the memory, which, when executed by the processor, implement the asset proxy method as described above.

[0120] Figure 9 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 9 The computer system 1000 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 9 As shown, the computer system 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1002 or programs loaded from storage portion 1008 into Random Access Memory (RAM) 1003, such as executing the information recommendation method described in the above embodiments. Various programs and data required for system operation are also stored in RAM 1003. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. An Input / Output (I / O) interface 1005 is also connected to bus 1004.

[0122] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0123] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs various functions defined in the system of this application.

[0124] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0126] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0127] Another aspect of this application provides a computer-readable storage medium storing computer-readable instructions that, when executed by a processor, implement a method for pushing research and development knowledge of locomotive products as described in any of the preceding embodiments.

[0128] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the locomotive product research and development knowledge delivery method provided in the above embodiments.

[0129] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0132] The above description is merely a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be determined by the scope of protection claimed in the claims.

Claims

1. A method for pushing R&D knowledge of locomotive products, the method being applied to a locomotive R&D knowledge management system, characterized in that, The method includes: Acquire research and development knowledge items, which include research and development experience information and research and development specification information for locomotive products; The R&D knowledge items are classified based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords. The preset keywords include parent keywords and child keywords. The set of R&D knowledge items related to the corresponding keywords is pushed to the client so that the set of R&D knowledge items can be displayed through the client, thereby assisting in the R&D tasks of locomotive products; The R&D knowledge items are categorized based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords, including: The R&D knowledge items are classified based on preset parent keywords to obtain a set of R&D knowledge items related to the corresponding parent keywords. Based on the preset child-level keywords, the R&D knowledge items in the set of R&D knowledge items related to the parent-level keywords are classified and processed to obtain the set of R&D knowledge items related to the corresponding child-level keywords. If the R&D knowledge item is related to two or more keywords, then each of the two or more keywords is used as a parent keyword and a child keyword, and the R&D knowledge item is used as an element in the set of R&D knowledge items related to the parent keyword and the child keyword. Before pushing the set of R&D knowledge items related to the corresponding keywords to the client, the method further includes: The system obtains the first text information of the R&D knowledge entries related to the corresponding keywords after classification processing, and the second text information of each other R&D knowledge entry related to the corresponding keywords in the locomotive R&D knowledge management system. Then, it calculates multiple similarities between the first text information and each of the second text information. If the plurality of similarities includes a first similarity, and the first similarity is greater than a first preset value, the R&D knowledge entries related to the corresponding keywords obtained from the classification process are deleted from the locomotive R&D knowledge management system.

2. The method according to claim 1, characterized in that, The classification of the R&D knowledge items based on preset keywords includes: Obtain the textual information contained in the aforementioned R&D knowledge entries; The text information is matched with preset keywords. If the match is successful, the R&D knowledge item is taken as an element in the set of R&D knowledge items related to the corresponding keyword.

3. The method according to claim 2, characterized in that, The step of matching the text information with preset keywords includes: Extract the features of the text information; Calculate the similarity between the feature and each preset keyword. If the similarity between the feature and the target keyword is greater than a preset threshold, then determine that the R&D knowledge item matches the target keyword.

4. The method according to claim 1, characterized in that, The step of pushing the set of R&D knowledge items related to the corresponding keywords to the client includes: Obtain the search terms input from the client for retrieving the set of R&D knowledge items; Identify keywords that match the search terms; The set of R&D knowledge items related to the keywords will be pushed to the client.

5. The method according to claim 1, characterized in that, The method further includes: If the plurality of similarities includes a second similarity, the second similarity is greater than a second preset value and less than the first preset value, and the second preset value is less than the first preset value; The similarity between the R&D knowledge entries related to the corresponding keywords obtained from the classification process is used as the target R&D knowledge entry for the second similarity. The target R&D knowledge entries are updated using the R&D knowledge entries related to the corresponding keywords obtained from the classification process.

6. A device for pushing product research and development knowledge, characterized in that, include: The acquisition module is used to acquire R&D knowledge items, which include R&D experience information and R&D specification information of locomotive products. The classification processing module is used to classify the R&D knowledge items based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords. The preset keywords include parent keywords and child keywords. The step of classifying the R&D knowledge items based on preset keywords to obtain a set of R&D knowledge items related to the corresponding keywords includes: classifying the R&D knowledge items based on preset parent keywords to obtain a set of R&D knowledge items related to the corresponding parent keywords; classifying the R&D knowledge items in the set of R&D knowledge items related to the parent keywords based on preset child keywords to obtain a set of R&D knowledge items related to the corresponding child keywords; if the R&D knowledge item is related to two or more keywords, then each of the two or more keywords is used as a parent keyword and a child keyword, and the R&D knowledge item is used as an element in the set of R&D knowledge items related to the parent keywords and child keywords. The push module is used to push the set of R&D knowledge items related to the corresponding keywords to the client, so as to display the set of R&D knowledge items through the client to assist in the R&D tasks of locomotive products; The matching module is used to obtain the first text information of the R&D knowledge entries related to the corresponding keywords after classification processing, and the second text information of each other R&D knowledge entry related to the corresponding keywords in the locomotive R&D knowledge management system, and then calculate multiple similarities between the first text information and each second text information. The deletion function module is used to delete the R&D knowledge entries related to the corresponding keywords obtained from the classification process from the locomotive R&D knowledge management system if the plurality of similarities includes a first similarity and the first similarity is greater than a first preset value.

7. An electronic device, characterized in that, include: Memory, which stores computer-readable instructions; A processor reads computer-readable instructions stored in memory to perform the method described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that, when executed by the processor of a computer, cause the computer to perform the method described in any one of claims 1-5.

Images