Coal inspection information processing method, system and equipment based on artificial intelligence

Abstract

The invention provides a coal inspection information processing method, system and device based on artificial intelligence, and relates to the technical field of coal detection information processing, and the method comprises the steps: obtaining original coal inspection information of a client; on the basis of a preset database, supplementing the original coal inspection information to obtain complete coal inspection information; inputting the complete coal inspection information into a preset inspection model to obtain standard coal inspection information output by the preset inspection model; the standard coal inspection information is information sorted according to a preset format; the preset inspection model is a large language model; and recording the standard coal inspection information in a business system. The method has the advantages of high data processing efficiency, high processing result accuracy and low processing cost.

Description

Technical Field

[0001] The present invention relates to the technical field of coal detection information processing, and particularly relates to a method, system and device for processing coal inspection information based on artificial intelligence. Background Art

[0002] With the rapid development of AI (Artificial Intelligence) technology, its applications in various industries are becoming increasingly widespread. Especially in the field of information processing, AI technology has become an important force driving the development and transformation of the industry.

[0003] Currently, in the coal detection industry, customers send coal inspection information to the business personnel of coal detection units via text messages, WeChat, phone calls or emails. The coal inspection information includes the customer's inspection requirements and the basic information of the coal to be inspected (such as coal variety, detection items, sending unit and transportation vehicle information, etc.). Then, the business personnel organize the inspection information according to a preset format, decompose the information organization result into work tasks, and distribute them to the corresponding departments for execution. At the same time, the information organization result is entered into the business system.

[0004] However, the method of manual data processing has problems such as low data processing efficiency, low accuracy of processing results and high processing costs. Summary of the Invention

[0005] In view of this, a method, system and device for processing coal inspection information based on artificial intelligence are provided to solve the problems of low data processing efficiency, low accuracy of processing results and high processing costs existing in the prior art.

[0006] The present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for processing coal inspection information based on artificial intelligence, including:

[0008] Obtaining the original coal inspection information of the customer;

[0009] Based on a preset database, supplementing the original coal inspection information to obtain complete coal inspection information;

[0010] Inputting the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model; the standard coal inspection information is the information organized according to a preset format; the preset inspection model is a large language model;

[0011] Recording the standard coal inspection information in the business system.

[0012] Optionally, the preset database is a vector database;

[0013] Based on a preset database, supplement the original coal inspection information to obtain complete coal inspection information, specifically including:

[0014] Use a preset data processing / transformation technical framework to perform structured data conversion on the original coal inspection information to obtain structured coal inspection information;

[0015] Extract key information from the structured coal inspection information to obtain key coal inspection information;

[0016] Use a preset embedding model to perform vector transformation on the key coal inspection information to obtain key coal inspection vectors;

[0017] Based on the key coal inspection vectors, perform similar vector retrieval in the preset database to obtain target vectors similar to the key coal inspection vectors;

[0018] Recombine the key coal inspection vectors and the target vectors to obtain the complete coal inspection information.

[0019] Optionally, the construction process of the preset database includes:

[0020] Obtain professional knowledge in the coal industry and the testing industry;

[0021] Obtain the historical coal inspection information of customers;

[0022] Use the preset data processing / transformation technical framework to perform preset operations on the professional knowledge and the historical coal inspection information to obtain structured collected data, and construct a knowledge graph and a natural language semantic network based on the structured collected data;

[0023] Use a combination of a relational database and a graph database to store the structured collected data, the knowledge graph, and the natural language semantic network to obtain an intermediate database;

[0024] Use the preset embedding model to convert the data in the intermediate database into vector form and store it in a vector database to obtain the preset database.

[0025] Optionally, the preset operations include: data cleaning, word segmentation, stop word removal, auxiliary word deletion, and stemming.

[0026] Optionally, the construction process of the preset inspection model includes:

[0027] Obtain first model training data, where the first model training data includes multiple training samples, and each training sample includes actual complete coal inspection information and its corresponding actual standard coal inspection information;

[0028] Select the target base model;

[0029] In response to the developer's data conversion operation, convert the first model training data into a prompt-based learning paradigm according to preset rules to obtain second model training data;

[0030] Based on the LLaMA-Factory technical framework, use the second model training data to train the target base model to obtain the preset inspection model.

[0031] Optionally, after inputting the complete coal inspection information into the preset inspection model to obtain the standard coal inspection information output by the preset inspection model, the method for processing coal inspection information based on artificial intelligence of the present invention further includes:

[0032] When there is a problem with the standard coal inspection information, in response to the developer's modification operation, modify the standard coal inspection information;

[0033] Store the modified standard coal inspection information and its corresponding complete coal inspection information in a preset training database.

[0034] Optionally, the method for processing coal inspection information based on artificial intelligence of the present invention further includes:

[0035] Use the data in the preset training database to optimize the preset inspection model.

[0036] Optionally, after inputting the complete coal inspection information into the preset inspection model to obtain the standard coal inspection information output by the preset inspection model, the method for processing coal inspection information based on artificial intelligence of the present invention further includes:

[0037] Display the standard coal inspection information.

[0038] In a second aspect, the present invention also provides a system for processing coal inspection information based on artificial intelligence, including:

[0039] An acquisition module, configured to acquire the original coal inspection information of a customer;

[0040] A supplement module, configured to supplement the original coal inspection information based on a preset database to obtain complete coal inspection information;

[0041] An arrangement module, configured to input the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model; the standard coal inspection information is information arranged in a preset format; the preset inspection model is a large language model;

[0042] A recording module, configured to record the standard coal inspection information in a business system.

[0043] In a third aspect, the present invention further provides a coal inspection information processing device based on artificial intelligence, including:

[0044] At least one processor; and,

[0045] A memory and a display communicatively connected to the at least one processor; wherein,

[0046] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the above-mentioned coal inspection information processing method based on artificial intelligence;

[0047] The display is used to display the data sent by the at least one processor.

[0048] After obtaining the original coal inspection information of the customer, the present invention adopts the above technical solutions to supplement the original coal inspection information based on a preset database to obtain complete coal inspection information, so as to improve the accuracy of the inspection information processing result. Then, the complete coal inspection information is input into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model. The standard coal inspection information is the information sorted according to a preset format, and the preset inspection model is a large language model. The large language model is a kind of AI model, which can further improve the accuracy of the inspection information processing result. Finally, the standard coal inspection information is recorded in the business system. In this way, the automatic sorting and recording of the original coal inspection information are realized, thereby improving the data processing efficiency of the coal inspection information and reducing the labor cost. Therefore, the present invention has the advantages of high data processing efficiency, high accuracy of processing results, and low processing cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 is a flowchart of a coal inspection information processing method based on artificial intelligence provided by an embodiment of the present invention;

[0051] Figure 2 is a structural diagram of a coal inspection information processing system based on artificial intelligence provided by an embodiment of the present invention;

[0052] Figure 3It is a schematic structural diagram of a coal inspection information processing device based on artificial intelligence provided by an embodiment of the present invention. Detailed implementation manners

[0053] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation manners obtained by those of ordinary skill in the art without creative efforts shall fall within the scope protected by the present invention.

[0054] With the rapid development of AI technology, its applications in various industries are becoming increasingly widespread. Especially in the field of information processing, AI technology has become an important force driving the development and transformation of the industry.

[0055] Currently, in the coal detection industry, customers send coal inspection information to the business personnel of coal detection units in the forms of text messages, WeChat, phone calls or emails. The coal inspection information includes the inspection demands of customers and the basic information of the coal to be inspected (such as coal varieties, detection items, sending units and transportation vehicle information, etc.). Then, the business personnel sort out the inspection information according to a preset format, decompose the information sorting result into work tasks, dispatch them to the corresponding departments for execution, and at the same time input the information sorting result into the business system. However, the way of manually processing data has problems such as low data processing efficiency, low accuracy of processing results and high processing costs.

[0056] Based on this, in order to improve the efficiency of coal inspection information processing, the accuracy of processing results and reduce the processing costs, the present invention provides a coal inspection information processing method, system and device based on artificial intelligence. The technical solutions of the present invention will be described in detail below with reference to the accompanying drawings.

[0057] Figure 1 It is a schematic flowchart of a coal inspection information processing method based on artificial intelligence provided by an embodiment of the present invention. As Figure 1 shown, this process includes:

[0058] Step 101: Obtain the original coal inspection information of the customer.

[0059] Specifically, the original coal inspection information is the coal inspection information sent by the customer to the business personnel of the coal detection unit, including the inspection demands of the customer and the basic information of the coal to be inspected. The basic information is, for example, coal varieties, detection items, sending units and transportation vehicle information, etc.

[0060] Step 102: Based on a preset database, supplement the original coal inspection information to obtain complete coal inspection information.

[0061] Specifically, the original coal inspection information is often incomplete. Therefore, based on a preset database, the present invention supplements the original coal inspection information to obtain complete coal inspection information.

[0062] Step 103: Input the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model; the standard coal inspection information is the information organized according to a preset format; the preset inspection model is an LLM (Large Language Model).

[0063] In a specific example, some of the information in the standard coal inspection information is shown in Table 1 below:

[0064] Table 1

[0065]

[0066]

[0067] In the embodiment of the present invention, after obtaining the standard coal inspection information, corresponding work tasks can also be initiated according to the standard coal inspection information, such as sampling tasks and / or stack inspection tasks, etc., for subsequent work.

[0068] Step 104: Record the standard coal inspection information in the business system.

[0069] In the embodiment of the present invention, adopting the above technical solution, after obtaining the original coal inspection information of the customer, based on a preset database, the original coal inspection information is supplemented to obtain complete coal inspection information to improve the accuracy of the inspection information processing result. Then, the complete coal inspection information is input into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model. The standard coal inspection information is the information organized according to a preset format, and the preset inspection model is a large language model. The large language model is a type of AI model, which can further improve the accuracy of the inspection information processing result. Finally, the standard coal inspection information is recorded in the business system. In this way, the automatic sorting and recording of the original coal inspection information are realized, thereby improving the data processing efficiency of the coal inspection information and reducing the labor cost. Therefore, the present invention has the advantages of high data processing efficiency, high processing result accuracy, and low processing cost.

[0070] In the embodiment of the present invention, the preset database can be a vector database.

[0071] Based on the preset database, supplementing the original coal inspection information to obtain complete coal inspection information may specifically include:

[0072] (1) Use a preset data processing / transformation technology framework to perform structured data transformation on the original coal inspection information to obtain structured coal inspection information.

[0073] Specifically, the preset data processing / transformation technology framework can be LangChain. LangChain supports the Python programming language and the JavaScript programming language. It is a framework specifically for developing applications based on language models, with many advantages that can bring convenience to model development. In terms of components, a large number of components are integrated inside LangChain, and these components have good adaptability in cross-country use. On the one hand, this facilitates model development, and on the other hand, it also makes the combination of information retrieval models and text generation models easier. At the same time, its modular interface design allows developers to easily combine components to meet different development needs. In terms of performance optimization, LangChain adopts caching optimization technology and batch processing technology. These technologies can effectively optimize the response time of the model, improve data throughput, and thus improve the operating efficiency of the entire application. In terms of community support, the open-source community of LangChain is the most mature and active community in the current model development field. This community provides developers with best practices, plugins, and tools, strongly supporting the development of the RAG (Retrieval Augmented Generation) model.

[0074] In addition, the preset data processing / transformation technology framework can also be other data processing / transformation technology frameworks in the prior art. For example, Dust.tt, Semantic-Kernel, Fixie.ai, and Brancher AI. Among them, Dust.tt supports the Rust programming language and the TypeScript programming language, provides a simple and easy-to-use API (Application Programming Interface), and allows developers to quickly build their own LLM applications; Semantic-Kernel supports the TypeScript programming language and a lightweight SDK (Software Development Kit), which can integrate large language models with traditional programming languages; Fixie.ai supports the Python programming language and has the advantages of being open, free, simple, and multimodal; Brancher AI supports the Python programming language and the JavaScript programming language and has the advantage of linking all large models and quickly generating applications without code.

[0075] (2) Extract key information from the structured coal inspection information to obtain key coal inspection information.

[0076] (3) Use a preset embedding model to perform vector transformation on the key coal inspection information to obtain the key coal inspection vector.

[0077] Specifically, the specific technical means to implement the embedding model is the text embedding algorithm. The text embedding algorithm refers to the specific algorithm for converting text data into vector representations, including the following steps:

[0078] (a) Tokenization: Divide the text into individual words or phrases.

[0079] (b) Build a vocabulary: Build a vocabulary from the tokenized words or phrases and assign a unique number to each word or phrase.

[0080] (c) Calculate word embeddings: Use a pre-trained model or a self-trained model to map each word or phrase into a vector space.

[0081] (d) Calculate text embeddings: Take the average or weighted average of the vector representations of each word or phrase in the text to obtain the vector representation of the entire text.

[0082] Common text embedding algorithms include, but are not limited to, Word2Vec (Word to Vector, a word vector conversion tool), GloVe (Global Vectors for Word Representation), and FastText (Fast Text Classification). These algorithms map words or phrases into a low-dimensional vector space through pre-training or self-training, enabling convenient processing of text data on a computer.

[0083] The preset embedding model adopted in the embodiments of the present invention is an embedding model that supports Chinese natural language, so as to enable text embedding calculation for Chinese. For example, the preset embedding model can be the BoW (Bag of Words Model) in the prior art, ERNIE 3.0 Nano (ERNIE 3.0 Tiny-Nano Chinese Pre-trained Model), Text2Vec-Base-Chinese (CoSENT-based Chinese Sentence Vector Model), Text2Vec-Large-Chinese (LERT-based Large-scale Chinese Text Embedding Model), or M3E-Base (Moka Massive Mixed Embedding Base Model).

[0084] (4) Based on the key coal inspection vector, perform a similar vector retrieval in the preset database to obtain a target vector similar to the key coal inspection vector.

[0085] (5) Recombine the key coal inspection vector and the target vector to obtain the complete coal inspection information.

[0086] In the embodiments of the present invention, the construction process of the preset database may include:

[0087] (1) Obtain the professional knowledge of the coal industry and the testing industry.

[0088] Specifically, the professional knowledge may include industry terms, concepts, work processes, regulations, and cases, etc. Its data form has multimodal characteristics, including text, images, and voices. The professional knowledge can be derived from industry document materials, such as inspection and testing industry data information, coal industry information, and relevant information of industries that use coal as power or raw materials, such as the power, cement, paper, metallurgy, coal chemical industry, etc. industries.

[0089] (2) Obtain the historical coal inspection information of the customers.

[0090] Specifically, the separate inspection information of many customers can be collected as the historical coal inspection information of the present invention.

[0091] (3) Use a preset data processing / transformation technology framework to perform preset operations on professional knowledge and historical coal inspection information to obtain structured collected data, and construct a knowledge graph and a natural language semantic network based on the structured collected data.

[0092] Specifically, the preset operations may include data cleaning, word segmentation, stop word removal, auxiliary word deletion, and stemming. Data cleaning may include removing duplicate data, correcting incorrect data, and handling missing data. After obtaining the structured collected data, entity recognition and annotation, as well as relationship extraction, are performed on it. Then, using a knowledge graph construction tool, the identified entities and relationships are stored and displayed in the form of a graph to obtain a knowledge graph. Among them, in the knowledge graph, nodes represent entities and edges represent relationships.

[0093] Next, construct a natural language semantic network, including: based on the knowledge graph, perform semantic annotation on the vocabulary and sentences in industry texts. Specifically, use semantic role labeling technology to determine the semantic roles of each vocabulary in the sentence, such as the agent, patient, time, and location. Then, use a semantic similarity algorithm to calculate the semantic similarity between industry texts. By constructing a semantic similarity matrix, analyze the semantic associations between different texts to provide support for knowledge retrieval and recommendation. Finally, based on the knowledge graph and semantic annotation information, establish semantic inference rules to achieve knowledge inference and expansion.

[0094] (4) Use a combination of a relational database and a graph database to store the structured collected data, the knowledge graph, and the natural language semantic network to obtain an intermediate database.

[0095] Specifically, the relational database is used to store the structured collected data, and the graph database is used to store the knowledge graph and the natural language semantic network. In this way, efficient storage and query of data are achieved.

[0096] (5) Use a preset embedding model to convert the data in the intermediate database into vector form and store it in a vector database to obtain a preset database.

[0097] Specifically, converting the data in the intermediate database into vector form and storing it in a vector database is beneficial for constructing an efficient retrieval system and facilitating retrieval and calculation by a language model.

[0098] In the embodiments of the present invention, the preset inspection model may be a model using the Transformer architecture, and has the ability of Chinese natural language processing, and is a model that has been pre-trained with a large amount of data. These models include, but are not limited to, the existing technology models described in Table 2, and Table 2 is as follows:

[0099] Table 2

[0100]

[0101] The construction process of the preset inspection declaration model may include:

[0102] (1) Obtain the first model training data, where the first model training data includes multiple training samples, and each training sample includes the actual complete coal inspection declaration information and its corresponding actual standard coal inspection declaration information.

[0103] (2) Select a target base model.

[0104] (3) In response to the data conversion operation of the developer, convert the first model training data into the paradigm of Prompt (Prompt-based Learning) according to the preset rules to obtain the second model training data. Among them, Prompt is an instruction or question provided by the developer to the model to guide the model to generate the required response.

[0105] (4) Based on the LLaMA-Factory technical framework, use the second model training data to train the target base model to obtain a professional vertical AI model for coal inspection declaration recognition in the coal detection industry, that is, the preset inspection declaration model.

[0106] In the embodiment of the present invention, after inputting the complete coal inspection declaration information into the preset inspection declaration model and obtaining the standard coal inspection declaration information output by the preset inspection declaration model, the method for processing coal inspection declaration information based on artificial intelligence of the present invention may further include:

[0107] (1) When there is a problem with the standard coal inspection declaration information, modify the standard coal inspection declaration information in response to the modification operation of the developer.

[0108] Specifically, after obtaining the standard coal inspection declaration information output by the preset inspection declaration model, the standard coal inspection declaration information can be manually reviewed. If there is a problem with the manual review of the standard coal inspection declaration information, it can be modified, and the system responds to the modification operation of the developer to modify the standard coal inspection declaration information.

[0109] (2) Store the modified standard coal inspection declaration information and its corresponding complete coal inspection declaration information into the preset training database, so that the data in the preset training database can be used subsequently to optimize the preset inspection declaration model.

[0110] In the embodiment of the present invention, the method for processing coal inspection declaration information based on artificial intelligence of the present invention may further include:

[0111] Use the data in the preset training database to optimize the preset inspection declaration model.

[0112] In the embodiments of the present invention, after inputting the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model, the method for processing coal inspection information based on artificial intelligence of the present invention may further include:

[0113] Display the standard coal inspection information to facilitate the user to know the standard coal inspection information according to the displayed content.

[0114] Based on a general inventive concept, the present invention also provides a system for processing coal inspection information based on artificial intelligence. Figure 2 It is a schematic structural diagram of a system for processing coal inspection information based on artificial intelligence provided by an embodiment of the present invention. As Figure 2 shown, the system includes:

[0115] An acquisition module 21, configured to acquire the original coal inspection information of a customer.

[0116] A supplement module 22, configured to supplement the original coal inspection information based on a preset database to obtain complete coal inspection information.

[0117] An arrangement module 23, configured to input the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model; the standard coal inspection information is information arranged in a preset format; the preset inspection model is a large language model.

[0118] A recording module 24, configured to record the standard coal inspection information in a business system.

[0119] Optionally, the preset database is a vector database.

[0120] The supplement module 22 may specifically be configured to:

[0121] (1) Use a preset data processing / transformation technology framework to perform structured data conversion on the original coal inspection information to obtain structured coal inspection information.

[0122] (2) Extract key information from the structured coal inspection information to obtain key coal inspection information.

[0123] (3) Use a preset embedding model to perform vector transformation on the key coal inspection information to obtain a key coal inspection vector.

[0124] (4) Based on the key coal inspection vector, perform similar vector retrieval in the preset database to obtain a target vector similar to the key coal inspection vector.

[0125] (5) Recombine the key coal inspection vector and the target vector to obtain complete coal inspection information.

[0126] Optionally, the construction process of the preset database may include:

[0127] (1) Obtain professional knowledge in the coal industry and the testing industry.

[0128] (2) Obtain the historical coal inspection information of customers.

[0129] (3) Use the preset data processing / transformation technology framework to perform preset operations on the professional knowledge and historical coal inspection information to obtain structured collected data, and construct a knowledge graph and a natural language semantic network based on the structured collected data.

[0130] (4) Use a combination of a relational database and a graph database to store the structured collected data, the knowledge graph, and the natural language semantic network to obtain an intermediate database.

[0131] (5) Use the preset embedding model to convert the data in the intermediate database into vector form and store it in the vector database to obtain the preset database.

[0132] Optionally, the preset operations may include: data cleaning, word segmentation, stop word removal, auxiliary word deletion, and stemming.

[0133] Optionally, the construction process of the preset inspection model may include:

[0134] (1) Obtain the first model training data, where the first model training data includes multiple training samples, and each training sample includes the actual complete coal inspection information and its corresponding actual standard coal inspection information.

[0135] (2) Select a target base model.

[0136] (3) In response to the data conversion operation of the developer, convert the first model training data into a prompt-based learning paradigm according to the preset rules to obtain the second model training data.

[0137] (4) Based on the LLaMA-Factory technology framework, use the second model training data to train the target base model to obtain the preset inspection model.

[0138] Optionally, the artificial intelligence-based coal inspection information processing system according to the embodiments of the present invention may further include: a model optimization module, which is used for:

[0139] (1) When there is a problem with the standard coal inspection information, modify the standard coal inspection information in response to the modification operation of the developer.

[0140] (2) Store the modified standard coal inspection information and its corresponding complete coal inspection information in the preset training database.

[0141] (3) Optimize the preset inspection model by using the data in the preset training database.

[0142] Optionally, the artificial intelligence-based coal inspection information processing system according to an embodiment of the present invention may further include: a display module for displaying standard coal inspection information.

[0143] Based on a general inventive concept, the present invention also provides an artificial intelligence-based coal inspection information processing device. Figure 3 It is a schematic structural diagram of an artificial intelligence-based coal inspection information processing device provided by an embodiment of the present invention. As Figure 3 shown, the device 30 includes:

[0144] At least one processor 302; and,

[0145] A memory 301 and a display 303 communicatively connected to at least one processor 302; wherein,

[0146] The memory 301 stores a preset database and instructions executable by at least one processor 302. The instructions are executed by at least one processor 302 so that at least one processor 302 can implement the artificial intelligence-based coal inspection information processing method as described above. When the processor 302 implements the artificial intelligence-based coal inspection information processing method as described above, it will involve a preset data processing / transformation technology framework, a preset embedding model, a preset inspection model, and a business system.

[0147] The display 303 is used to display the data sent by at least one processor 302. For example, it displays standard coal inspection information.

[0148] It can be understood that the same or similar parts in the above embodiments can be referred to each other. For the content not detailed in some embodiments, reference can be made to the same or similar content in other embodiments.

[0149] It should be noted that in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0150] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the technical field to which the embodiments of the present invention belong.

[0151] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0152] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program. The said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0153] In addition, in each embodiment of the present invention, each functional unit can be integrated in a processing module, or each unit can exist physically alone, or two or more units can be integrated in one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0154] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disk, etc.

[0155] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0156] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for processing coal inspection information based on artificial intelligence, characterized in that, Including: Obtain the original coal inspection information of the customer; Based on a preset database, supplement the original coal inspection information to obtain complete coal inspection information; Input the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model; the standard coal inspection information is information organized in a preset format; The preset inspection model is a large language model; Record the standard coal inspection information in the business system.

2. The method for processing coal inspection information based on artificial intelligence according to claim 1, wherein The preset database is a vector database; Based on a preset database, supplement the original coal inspection information to obtain complete coal inspection information, specifically including: Use a preset data processing / transformation technical framework to perform structured data transformation on the original coal inspection information to obtain structured coal inspection information; Extract key information from the structured coal inspection information to obtain key coal inspection information; Use a preset embedding model to perform vector transformation on the key coal inspection information to obtain a key coal inspection vector; Based on the key coal inspection vector, perform similar vector retrieval in the preset database to obtain a target vector similar to the key coal inspection vector; Recombine the key coal inspection vector and the target vector to obtain the complete coal inspection information.

3. The method for processing coal inspection information based on artificial intelligence according to claim 2, characterized in that, The construction process of the preset database includes: Obtain professional knowledge in the coal industry and the testing industry; Obtain the historical coal inspection information of the customer; Use the preset data processing / transformation technical framework to perform preset operations on the professional knowledge and the historical coal inspection information to obtain structured collected data, and construct a knowledge graph and a natural language semantic network based on the structured collected data; Use a combination of a relational database and a graph database to store the structured collected data, the knowledge graph, and the natural language semantic network to obtain an intermediate database; Use the preset embedding model to convert the data in the intermediate database into vector form and store it in a vector database to obtain the preset database.

4. The method for processing coal inspection information based on artificial intelligence according to claim 3, characterized in that The preset operations include: data cleaning, word segmentation, stop word removal, auxiliary word deletion, and stemming.

5. The method for processing coal inspection information based on artificial intelligence according to claim 1, wherein The construction process of the preset inspection model includes: Obtain first model training data, where the first model training data includes multiple training samples, and each training sample includes actual complete coal inspection information and its corresponding actual standard coal inspection information; Select a target base model; In response to the data transformation operation of the developer, convert the first model training data into a prompt-based learning paradigm according to preset rules to obtain second model training data; Based on the LLaMA-Factory technical framework, use the second model training data to train the target base model to obtain the preset inspection model.

6. The method for processing coal inspection information based on artificial intelligence according to claim 1, wherein After inputting the complete coal inspection information into the preset inspection model to obtain the standard coal inspection information output by the preset inspection model, it further includes: When there is a problem with the standard coal inspection information, modify the standard coal inspection information in response to the modification operation of the developer. Store the modified standard coal inspection information and its corresponding complete coal inspection information in a preset training database.

7. The method for processing coal inspection information based on artificial intelligence according to claim 6, characterized in that, It further includes: Optimize the preset inspection model using the data in the preset training database.

8. The method for processing coal inspection information based on artificial intelligence according to claim 1, characterized in that After inputting the complete coal inspection information into the preset inspection model and obtaining the standard coal inspection information output by the preset inspection model, it further includes: Display the standard coal inspection information.

9. An artificial intelligence-based coal inspection information processing system, characterized in that, It includes: An acquisition module for acquiring the original coal inspection information of the customer; A supplement module for supplementing the original coal inspection information based on a preset database to obtain complete coal inspection information; An arrangement module for inputting the complete coal inspection information into a preset inspection model to obtain the standard coal inspection information output by the preset inspection model; The standard coal inspection information is information arranged in a preset format; The preset inspection model is a large language model; A recording module for recording the standard coal inspection information in a business system.

10. An artificial intelligence-based coal inspection information processing device, characterized in that, It includes: At least one processor; And, A memory and a display that are communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the artificial intelligence-based coal inspection information processing method according to any one of claims 1 to 8; The display is used for displaying the data sent by the at least one processor.

Images