Equipment type selection method and system

Abstract

The invention relates to an equipment type selection method and system. The method comprises the following steps: acquiring equipment category information corresponding to equipment demand information; performing clustering analysis on the equipment category information to obtain an equipment application scene; and reasoning the equipment category information and the equipment application scene by the knowledge base to obtain target equipment meeting a preset type selection condition. By acquiring the equipment category information corresponding to the equipment demand information, the natural language input of the user can be automatically understood and processed, the demand of manual intervention is reduced, and the risk of human errors is reduced; the equipment type information is subjected to clustering analysis, so that accurate understanding of user requirements is ensured, an accurate equipment application scene is obtained, and a more reliable decision is made. The pre-trained knowledge base constructs the structured query condition according to the equipment category information and the equipment application scene, rapid reasoning and positioning can be carried out in mass information, the target equipment meeting the preset type selection condition is obtained, and therefore the use experience is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of computer-aided design technology, and in particular to a method and system for selecting an equipment. Background Art

[0002] Equipment selection is crucial in bidding and procurement within the coal mining industry. Traditional equipment selection methods rely on experience and manual search, resulting in inefficiency, fragmented information, high communication costs, and significant decision-making risks. Furthermore, the wide variety of equipment types and complex technical specifications, with relevant information scattered across multiple sources such as supplier catalogs, technical manuals, and industry standards, makes it difficult for users to quickly obtain comprehensive information.

[0003] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide an equipment selection method and system to solve the problems in the prior art of low equipment selection efficiency, high risk of errors due to information dispersion, long selection cycle and high communication costs.

[0005] In order to solve the above problems, the equipment selection method involved in this application adopts the following technical solutions:

[0006] Acquire device category information corresponding to device requirement information, wherein the device requirement information is represented based on a natural language form;

[0007] Performing cluster analysis on the device category information to obtain device application scenarios;

[0008] The device category information and the device application scenario are input into a pre-trained knowledge base, and the knowledge base is used for reasoning to obtain a target device that meets the preset selection conditions.

[0009] In order to solve the above problems, the equipment selection system involved in this application adopts the following technical solutions:

[0010] a first acquisition module, configured to acquire device category information corresponding to device requirement information, wherein the device requirement information is represented based on a natural language form;

[0011] a second acquisition module, configured to perform cluster analysis on the device category information to obtain device application scenarios;

[0012] The third acquisition module is used to input the device category information and the device application scenario into a pre-trained knowledge base, and perform reasoning based on the knowledge base to obtain a target device that meets the preset selection conditions.

[0013] In order to solve the above problems, the electronic device involved in this application adopts the following technical solutions:

[0014] It includes a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the device selection method involved in this application.

[0015] In order to solve the above problems, the non-transitory computer-readable storage medium involved in this application uses the following technical solutions:

[0016] When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the device selection method involved in this application.

[0017] The beneficial effects of this application are as follows:

[0018] By obtaining the device category information corresponding to device requirements, it can automatically understand and process the user's natural language input, reducing the need for manual intervention and the risk of human error. By performing cluster analysis on device type information, it ensures an accurate understanding of user needs and derives precise device application scenarios, enabling more reliable decision-making. The pre-trained knowledge base constructs structured query conditions based on device category information and device application scenarios, enabling rapid inference and location within massive amounts of information, resulting in target devices that meet the preset selection criteria, greatly improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments:

[0020] Figure 1 A schematic diagram of a flow chart of a device selection method provided in an embodiment of the present application;

[0021] Figure 2 A flow chart of another device selection method provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the structure of a device selection system provided in an embodiment of the present application;

[0023] Figure 4 The figure is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the technical objectives, technical solutions, and beneficial effects of this application more clear, the technical solutions of this application are further described below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. That is, the embodiments described herein are only some embodiments of this application, not all embodiments. Generally, the components of the embodiments of this application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0025] The terms used in the embodiments of this application are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of this application. The singular forms "a" and "the" used in the embodiments of this application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0026] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to a determination."

[0027] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be understood as limiting the present application.

[0028] In the coal mining industry, equipment selection is a critical step in the bidding and procurement process. However, traditional equipment selection methods often rely on manual experience and search, which inevitably leads to a series of problems such as low efficiency, fragmented information, high communication costs, and increased decision-making risks.

[0029] Coal mining equipment is diverse and complex in its technical specifications, with relevant information scattered across multiple sources such as supplier catalogs, technical manuals, and industry standards. This fragmented information makes it difficult for users to quickly and comprehensively obtain the required information, thus affecting the accuracy and efficiency of model selection.

[0030] What's even more unique is the extremely demanding operating environment of coal mining equipment. Underground equipment, for example, must meet a range of stringent technical requirements, including explosion-proof ratings, operating temperature ranges, and waterproof ratings. Non-professionals often struggle to assess and understand these specialized parameters, further increasing communication costs and decision-making risks during the selection process.

[0031] In practice, due to the limited understanding of equipment technical parameters by non-professionals, repeated communication with multiple suppliers and technical experts is often required. This communication not only consumes a lot of time and manpower, but can also lead to the selection of equipment that does not meet actual needs due to information asymmetry or insufficient expertise, ultimately increasing the risk and uncertainty of decision-making.

[0032] Therefore, a new device selection method is urgently needed to improve user experience, reduce the risk of human error, shorten the selection cycle, and reduce communication costs.

[0033] The following describes the equipment selection method and system of the embodiment of the present application with reference to the accompanying drawings.

[0034] Figure 1 A flow chart of an equipment selection method provided in an embodiment of the present application.

[0035] like Figure 1 As shown, the equipment selection method includes but is not limited to the following steps:

[0036] S101: Acquire device category information corresponding to device requirement information, wherein the device requirement information is represented based on a natural language form.

[0037] In a feasible implementation, to obtain corresponding device category information from device requirement information in natural language form, a text classification model (such as a deep learning model) can be used to classify the device requirement information; then, by extracting keywords from the device requirement information and combining it with predefined device category rules, the device category information can be quickly matched.

[0038] In a feasible implementation, classification standards can be established based on dimensions such as equipment type (such as mechanical equipment, electronic equipment, etc.), usage scenario (such as above-ground, underground, etc.), and equipment status (such as in use, standby, under maintenance); then a rule engine is set up to match the corresponding equipment analogy information based on keywords or features in the equipment demand information in natural language form.

[0039] In a feasible implementation, a device-related knowledge graph can be constructed to associate entities in the device requirement information (such as device name, function, and purpose) with device categories, and device category information can be obtained through graph reasoning.

[0040] S102: Perform cluster analysis on device category information to obtain device application scenarios.

[0041] In a feasible implementation, the device category information can be preprocessed first, such as removing duplicates, filling missing values, etc. The device category information is converted into features that can be used for cluster analysis. For example, the device name in the device category information can be segmented and keywords can be extracted as features; the technical parameters, usage frequency, etc. in the device category information can also be quantified into numerical features. Then, the device category information is clustered using a selected clustering algorithm (such as the K-Means algorithm, the self-organizing feature mapping algorithm, etc.) to obtain clustering results; and the clustering results are evaluated and optimized, such as evaluating the clustering effect through indicators such as the silhouette coefficient, and adjusting the clustering algorithm parameters to improve the clustering quality. Next, the common features of the devices in the clustering results are analyzed, such as functional similarity, technical parameter range, etc., to infer the device application scenarios.

[0042] S103: Input the device category information and device application scenario into a pre-trained knowledge base, and use the knowledge base to perform reasoning to obtain a target device that meets the preset selection criteria.

[0043] In one feasible implementation, a pre-trained knowledge base is a platform for centrally storing, managing, and sharing device-related knowledge. This typically includes device specifications, operating manuals, application scenarios, troubleshooting methods, and more. When building a knowledge base, it's important to clearly define its purpose, such as improving device selection efficiency and optimizing device management. The knowledge base also collects information about device categories, application scenarios, and technical parameters, and converts it into structured data.

[0044] In a feasible implementation, the equipment category information (such as equipment name, function, technical parameters, etc.) and equipment application scenarios (such as usage environment, usage frequency, expected life, etc.) are input into the knowledge base, and the knowledge base uses existing knowledge to generate new knowledge through inference rules. The knowledge base can use preset logical rules for reasoning. For example, if the equipment application scenario is "high humidity environment", a target device with waterproof function is recommended; the knowledge base can also use the relationships in the knowledge graph for reasoning. For example, the path sorting algorithm is used to find entities and relationships related to the target device. Then, based on the reasoning results, the target device that meets the selection criteria is output. For example, if the requirement is "high humidity environment, used for underground harmful gases", the knowledge base can infer "high humidity harmful gas detector".

[0045] In summary, the device selection method provided in the embodiments of the present application, by obtaining device category information corresponding to device requirement information, can automatically understand and process the user's natural language input, reducing the need for manual intervention and the risk of human error. By performing cluster analysis on device type information, it ensures an accurate understanding of user needs and obtains precise device application scenarios, thereby making more reliable decisions. The pre-trained knowledge base constructs structured query conditions based on device category information and device application scenarios, enabling rapid reasoning and positioning within massive amounts of information to obtain target devices that meet the preset selection criteria, thereby greatly improving the user experience.

[0046] Figure 2 A flowchart of another equipment selection method provided in an embodiment of the present application.

[0047] like Figure 2 As shown, the equipment selection method includes but is not limited to the following steps:

[0048] S201, obtaining equipment requirement information represented in natural language form.

[0049] In a feasible implementation, natural language text data containing equipment requirement information may be collected. Such data may come from user input, equipment maintenance records, production plan documents, and the like.

[0050] S202: Pre-process the equipment requirement information to obtain equipment category information.

[0051] In a feasible implementation, the device requirement information can be preprocessed to obtain features related to keywords, wherein the device requirement information can be text cleaned, for example, by removing unnecessary characters and stop words to ensure that only the required content is retained, thereby obtaining first intermediate data; then, the first intermediate data is segmented to divide the first intermediate data into words or phrases to obtain a set W consisting of multiple words, where W = {w1, w2, ..., w n Then we can use the TF-IDF method (Term Frequency-Inverse Document Frequency) to analyze the term frequency and inverse document frequency of the collection and get the feature TF-IDF (w i ),in, i is any integer between 1 and n; TF(w i ) is the word w i The frequency of occurrence; N is the total number of documents; DF(w i ) is a word containing the word w i The number of documents.

[0052] In a feasible implementation, a pre-trained language model is used to perform probability prediction based on features to obtain device category information, wherein the feature TF-IDF (w i ) performs BERT encoding (Bidirectional Encoder Representations from Transformers, a deep learning model based on the Transformers architecture) on a set of multiple words to obtain a first intermediate vector X; then the first intermediate vector X is input into a pre-trained language model, and the language model performs probability prediction on the first intermediate vector based on the device category to obtain multiple probability values ​​P(c|X), where c represents the device category; based on the probability distribution output by the language model, the most likely device category information is determined; the maximum target probability value can be selected from the multiple probability values, and the device category corresponding to the maximum target probability value is used as the device category information.

[0053] In some embodiments, multiple target probability values ​​less than or equal to a preset probability threshold θ can be screened out from multiple probability values; then, the maximum target probability value is selected from the multiple target probability values, and the device category corresponding to the maximum target probability value is used as the device category information.

[0054] S203: Perform cluster analysis on the device category information to obtain device application scenarios.

[0055] In one feasible implementation, a preset device application scenario library can be used to perform keyword matching on device category information to obtain an initial classification result. For example, relevant vocabulary can be extracted from resources such as industry literature, technical documents, user manuals, and expert opinions; the collected vocabulary is then organized into a device application scenario library (the device application scenario library can be a list or a database, and should be set up according to specific needs); each vocabulary is weighted to reflect its importance in the device application scenario library, and the weight can be related to factors such as word frequency and professionalism.

[0056] In a feasible implementation, a confidence assessment can be performed on the initial classification result to obtain a revised classification result, wherein a reasonable threshold T can be set based on industry literature, technical documents, user manuals, expert opinions, etc., and the confidence assessment of the initial classification result can be performed based on the threshold T.

[0057] In a feasible implementation, the device application scenario library performs cluster analysis on the modified classification results to obtain the device application scenario, wherein the classification information, usage frequency, application scenario description, performance indicators and other features about the device can be extracted from the device application scenario library; these features are combined with the clustering algorithm to analyze the modified classification results to obtain the device application scenario.

[0058] In some embodiments, the equipment application scenarios may include downhole, uphole, etc.

[0059] S204: Input the device category information and device application scenario into a pre-trained knowledge base, and use the knowledge base to perform reasoning to obtain a target device that meets the preset selection criteria.

[0060] In one feasible implementation, device category information and device application scenarios are input into a pre-trained knowledge base to obtain multiple candidate devices that meet the device selection criteria. It should be noted that the pre-trained knowledge base can be a structured database or a graph-based database, storing the relationship between device category information and device application scenarios. This knowledge base can be accessed through an enterprise's internal device management system, procurement records, and maintenance records. It can also be combined with the experience and knowledge of industry experts to annotate device application scenarios. It can also be obtained from technical documentation provided by device manufacturers, industry standards, user reviews, and so on.

[0061] In some embodiments, device category information and device application scenarios are used as input and formatted into structured data that can be understood by the knowledge base. Based on the input device category information and device application scenarios, a query is performed in the knowledge base to screen out multiple candidate devices that meet the selection criteria, wherein the query process may include matching device categories (searching for devices consistent with the input device category information in the knowledge base), screening application scenarios (further screening out qualified devices based on the conditions of the device application scenarios), sorting and recommending (sorting candidate devices based on factors such as device performance, price, and user reviews). It should be noted that the screened candidate devices can be output in the form of a list, including detailed information of the candidate devices, the degree of matching of the device application scenarios, reasons for recommendation, etc.

[0062] In some embodiments, a target device is obtained by performing a reasoning analysis on multiple candidate devices in combination with preset selection conditions (which may include explosion-proof level, operating temperature range, waterproof level, data transmission method, installation method, etc.), wherein the preset selection conditions are obtained based on technical parameters, performance requirements, and cost constraints. It should be noted that a scoring standard can be constructed based on the preset selection conditions, and a weight can be assigned to each condition. For example, the weight of the technical parameters is 0.4; the weight of the performance requirements is 0.3; and the weight of the cost constraints is 0.3. Then, based on the weights and the scores of each condition, a comprehensive score for each candidate device is determined. The candidate devices are then sorted according to the comprehensive score, and the candidate device with the highest comprehensive score is selected as the target device.

[0063] It should be noted that the results of the target device can be displayed through a web interface or through industrial mobile phones, industrial tablets, etc. The displayed content includes easy-to-read text content, pictures, voice files, etc., and should be set according to specific needs.

[0064] In summary, the device selection method provided in the embodiments of the present application, by obtaining device category information corresponding to device requirement information, can automatically understand and process the user's natural language input, reducing the need for manual intervention and the risk of human error. By performing cluster analysis on device type information, it ensures an accurate understanding of user needs and obtains precise device application scenarios, thereby making more reliable decisions. The pre-trained knowledge base constructs structured query conditions based on device category information and device application scenarios, enabling rapid reasoning and positioning within massive amounts of information to obtain target devices that meet the preset selection criteria, thereby greatly improving the user experience.

[0065] Figure 3 A schematic diagram of the structure of an equipment selection system provided in an embodiment of the present application.

[0066] like Figure 3 As shown, the equipment selection system 300 includes:

[0067] A first acquisition module 301 is used to acquire device category information corresponding to device requirement information, wherein the device requirement information is represented based on a natural language form;

[0068] The second acquisition module 302 is used to perform cluster analysis on the device category information to obtain device application scenarios;

[0069] The third acquisition module 303 is used to input device category information and device application scenarios into a pre-trained knowledge base, and use the knowledge base to perform reasoning to obtain target devices that meet preset selection conditions.

[0070] Figure 4 The figure is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. Figure 4 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0071] like Figure 4As shown, the electronic device 400 includes a processor 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the memory 406 into the random access memory (RAM) 403. Various programs and data required for the operation of the electronic device 400 are also stored in the RAM 403. The processor 401, ROM 402 and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0072] The following components are connected to the I / O interface 405: a memory 406 including a hard disk, etc.; and a communication part 407 including a network interface card such as a LAN (Local Area Network) card, a modem, etc., which performs communication processing via a network such as the Internet; a drive 408 is also connected to the I / O interface 405 as needed.

[0073] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 407. When the computer program is executed by the processor 401, the above-mentioned functions defined in the method of the present application are performed.

[0074] In an exemplary embodiment, a storage medium including instructions is further provided, such as a memory including instructions, and the instructions can be executed by the processor 401 of the electronic device 400 to perform the above method. Alternatively, the storage medium can be a non-transitory computer-readable storage medium, such as a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0075] In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate and not to limit the technical solutions of this application. Any equivalent replacements of this application and modifications or partial replacements that do not depart from the spirit and scope of this application should be included in the scope of protection of the claims of this application.

Claims

1. A method for selecting equipment, characterized in that: include: Acquire device category information corresponding to device requirement information, wherein the device requirement information is represented based on a natural language form; Performing cluster analysis on the device category information to obtain device application scenarios; The device category information and the device application scenario are input into a pre-trained knowledge base, and the knowledge base is used for reasoning to obtain a target device that meets the preset selection conditions.

2. The equipment selection method according to claim 1, characterized in that: The device category information corresponding to the device requirement information is obtained, including: Obtain equipment requirement information based on natural language representation; Preprocessing the equipment demand information to obtain features related to keywords; Based on the features, a pre-trained language model is used to perform probability prediction to obtain the device category information.

3. The equipment selection method according to claim 2, characterized in that: The preprocessing of the device demand information to obtain features related to keywords includes: Performing text cleaning on the device demand information to obtain first intermediate data; Performing word segmentation processing on the first intermediate data to obtain a set consisting of multiple words; Perform word frequency and inverse document frequency analysis on the collection to obtain features related to the keywords.

4. The equipment selection method according to claim 2, characterized in that: The performing probability prediction based on the features using a pre-trained language model to obtain the device category information includes: Performing BERT encoding on a set of multiple words based on the features to obtain a first intermediate vector; Inputting the first intermediate vector into a pre-trained language model, and having the language model perform probability prediction on the first intermediate vector based on device category to obtain multiple probability values; A maximum target probability value is selected from the multiple probability values, and the device category corresponding to the maximum target probability value is used as the device category information.

5. The equipment selection method according to claim 4, characterized in that: The selecting a maximum probability value from the multiple probability values, and using the device category corresponding to the maximum probability value as the device category information, includes: Filtering out a plurality of target probability values ​​that are less than or equal to a preset probability threshold from the plurality of probability values; A maximum target probability value is selected from the multiple target probability values, and the device category corresponding to the maximum target probability value is used as the device category information.

6. The equipment selection method according to claim 1, characterized in that: The cluster analysis of the device category information to obtain device application scenarios includes: Perform keyword matching on the device category information using a preset device application scenario library to obtain an initial classification result; Performing a confidence assessment on the initial classification result to obtain a revised classification result; The device application scenario library performs cluster analysis on the modified classification results to obtain the device application scenario.

7. The equipment selection method according to any one of claims 1 to 6, characterized in that: The step of inputting the device category information and the device application scenario into a pre-trained knowledge base, and performing reasoning based on the knowledge base to obtain a target device that meets preset selection criteria includes: Inputting the device category information and the device application scenario into a pre-trained knowledge base to obtain multiple candidate devices that meet the device selection criteria; In combination with preset selection conditions, the multiple candidate devices are subjected to reasoning analysis to obtain the target device, wherein the preset selection conditions are obtained based on technical parameters, performance requirements and cost constraints.

8. An equipment selection system, characterized in that: include: a first acquisition module, configured to acquire device category information corresponding to device requirement information, wherein the device requirement information is represented based on a natural language form; a second acquisition module, configured to perform cluster analysis on the device category information to obtain device application scenarios; The third acquisition module is used to input the device category information and the device application scenario into a pre-trained knowledge base, and perform reasoning based on the knowledge base to obtain a target device that meets the preset selection conditions.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the device selection method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the device selection method according to any one of claims 1 to 7.

Images