Bridge steel structure technical file intelligent retrieval method and device based on embedded model

Abstract

The invention relates to the technical field of natural language processing, in particular to a bridge steel structure technical file intelligent retrieval method and device based on an embedded model, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring query input information of a target object; analyzing the query input information based on a preset information analysis model to obtain a query input vector corresponding to the query input information; based on the query input vector, performing retrieval comparison in a pre-constructed vector database to obtain a matched data vector meeting a preset matching condition; performing reverse positioning according to the matched data vector to obtain target file data associated with the matched data vector; and responding to the query input information of the target object based on the target file data. By adopting the method, the retrieval efficiency of the technical file and the accuracy of the retrieval result can be improved.

Description

Technical Field

[0001] The present application relates to the field of natural language processing technology, and in particular to an embedded model-based intelligent retrieval method, device, computer equipment, storage medium and computer program product for technical documents of bridge steel structures. Background Art

[0002] Bridge steel structure is a widely used structural form in modern bridge construction. It is mainly made of steel and has the advantages of high strength, light weight, good seismic resistance and short construction period. The technical documents of bridge steel structure usually include professional documents in many aspects, which specify in detail the technical requirements of each stage such as design, construction, acceptance and maintenance. The technical documents of bridge steel structure usually include: design documents, construction technical documents, quality control documents, safety management documents, maintenance and management documents, post-evaluation documents and various reference standard documents.

[0003] In the related technology, there are traditional information retrieval systems based on natural language processing and keyword matching. These systems usually rely on Boolean matching of keywords or simple statistical models to find relevant documents. The workflow of this type of system mainly uses Boolean logic to connect keywords using Boolean retrieval models. The search results are based on precise matching of conditions, and users can filter information by combining search conditions. On the other hand, the system will calculate the importance of documents through statistical models such as word frequency and inverse document frequency. Commonly used algorithms such as TF-IDF (Term Frequency-Inverse Document Frequency) are to statistically analyze the distribution of keywords in documents and the entire corpus.

[0004] However, the current retrieval method has the following technical problems:

[0005] Traditional technologies perform poorly when processing complex queries and have difficulty understanding the deep semantics in user input, especially when the query contains ambiguous, context-dependent technical terms. The relevance of retrieval results is often low. In addition, such systems find it difficult to accurately analyze unstructured technical documents, resulting in low retrieval efficiency. Summary of the invention

[0006] Based on this, it is necessary to provide an intelligent retrieval method, device, computer equipment, computer-readable storage medium and computer program product for bridge steel structure technical documents based on an embedded model, which can improve the retrieval efficiency of technical documents and the accuracy of retrieval results in response to the above technical problems.

[0007] In a first aspect, the present application provides an intelligent retrieval method for bridge steel structure technical documents based on an embedded model. The method comprises:

[0008] Get the query input information of the target object;

[0009] Parsing the query input information based on a preset information parsing model to obtain a query input vector corresponding to the query input information;

[0010] Based on the query input vector, a search and comparison is performed in a pre-built vector database to obtain a matching data vector that meets a preset matching condition;

[0011] Perform reverse positioning according to the matching data vector to obtain target file data associated with the matching data vector;

[0012] The query input information of the target object is responded to based on the target file data.

[0013] In one embodiment, the method comprises:

[0014] Acquire raw data to be processed, where the raw data is unstructured data, parse the raw data, and convert it into vector data;

[0015] The vector database is constructed based on the vector data.

[0016] In one embodiment, the obtaining of raw data to be processed, where the raw data is unstructured data, parsing the raw data, and converting the raw data into vector data includes:

[0017] Acquire the data format of the original data, and match the corresponding associated database based on the data format;

[0018] Parsing the original data based on the associated database;

[0019] and / or;

[0020] Based on preset recognition rules, a pre-built machine learning model is called to recognize text elements in the raw data;

[0021] Parsing the text elements based on a preset hierarchical clustering algorithm to determine the chapter structure and hierarchical relationship in the original data;

[0022] and / or;

[0023] Semantic analysis is performed on the unconventional objects in the original data to obtain associated semantic data, wherein the unconventional objects include images and tables.

[0024] In one embodiment, the obtaining of raw data to be processed, where the raw data is unstructured data, parsing the raw data, and converting the raw data into vector data includes:

[0025] After the original data is parsed, a unique identifier is generated for the parsed data element, and the unique identifier is used to trace and reference the data element.

[0026] In one embodiment, before responding to the query input information of the target object based on the target file data, the method further includes:

[0027] Calculate the matching index between the target file data and the query input information based on the preset matching index calculation rules;

[0028] The target file data is sorted and output based on the matching index.

[0029] In one embodiment, responding to the query input information of the target object based on the target file data includes:

[0030] Acquire demand information of a target object, wherein the demand information includes request terminal information of the target object;

[0031] The target file data is adjusted based on the requirement information so that the target file data matches the requirement information.

[0032] In a second aspect, the present application also provides an intelligent retrieval device for bridge steel structure technical documents based on an embedded model. The device comprises:

[0033] A query input module is used to obtain query input information of a target object;

[0034] A query parsing module, used to parse the query input information based on a preset information parsing model to obtain a query input vector corresponding to the query input information;

[0035] A vector matching module, used to perform a search and comparison in a pre-built vector database based on the query input vector to obtain a matching data vector that meets a preset matching condition;

[0036] A file positioning module, used for performing reverse positioning according to the matching data vector to obtain target file data associated with the matching data vector;

[0037] A query response module is used to respond to the query input information of the target object based on the target file data.

[0038] In one embodiment, the device comprises:

[0039] The raw data module is used to obtain the raw data to be processed, which is unstructured data, analyze the raw data, and convert it into vector data;

[0040] A database module is used to construct the vector database based on the vector data.

[0041] In one embodiment, the raw data module includes:

[0042] A matching module, used for obtaining the data format of the original data and matching the corresponding associated database based on the data format;

[0043] A parsing module, used for parsing the original data based on the associated database;

[0044] and / or;

[0045] A recognition module, used to recognize text elements in the raw data based on preset recognition rules and calling a pre-built machine learning model;

[0046] A hierarchical module, used to parse the text elements based on a preset hierarchical clustering algorithm to determine the chapter structure and hierarchical relationship in the original data;

[0047] and / or;

[0048] The semantic module is used to perform semantic analysis on the unconventional objects in the original data to obtain associated semantic data, wherein the unconventional objects include images and tables.

[0049] In one embodiment, the raw data module includes:

[0050] The identification module is used to generate a unique identifier for the parsed data element after the original data is parsed, and the unique identifier is used to trace and reference the data element.

[0051] In one embodiment, before the query response module, it also includes:

[0052] A matching module, used to calculate a matching index between the target file data and the query input information based on a preset matching index calculation rule;

[0053] A sorting module is used to sort and output the target file data based on the matching index.

[0054] In one embodiment, the query response module includes:

[0055] The request terminal module obtains the demand information of the target object, wherein the demand information includes the request terminal information of the target object;

[0056] The file adjustment module is used to adjust the target file data based on the demand information so that the target file data matches the demand information.

[0057] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps in the intelligent retrieval method for bridge steel structure technical documents based on an embedded model as described in any embodiment of the first aspect.

[0058] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for intelligent retrieval of technical documents of bridge steel structures based on an embedded model as described in any one of the embodiments in the first aspect.

[0059] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps in the intelligent retrieval method for bridge steel structure technical documents based on an embedded model as described in any one of the embodiments in the first aspect are implemented.

[0060] The above-mentioned intelligent retrieval method, device, computer equipment, storage medium and computer program product of bridge steel structure technical documents based on embedded model can achieve the beneficial effects of corresponding technical problems in the background technology by deducing the technical features in the exclusive right:

[0061] The present application provides an intelligent retrieval method for bridge steel structure technical documents based on an embedded model, and the steps mainly include the contents recorded in the application documents. In implementation, after obtaining the query input information of the target object, the query input information can be first parsed according to the preset information parsing model to obtain a query input vector corresponding to the query input information. At this time, the query input vector processed by vectorization can get rid of the limitation of the original format of the data, so that the core content and key data of the query data information can be obtained, reducing the possibility of incorrect query results due to errors in the query input information. Subsequently, the query input vector is used as the retrieval basis, and a search and comparison is performed in the pre-constructed vector database to obtain a matching data vector that meets certain matching requirements. In this way, the target file data associated with the matching data vector can be determined by reverse positioning, and finally the query input information is responded to with the obtained target file data, breaking through the limitation that the traditional system cannot effectively process unstructured data, and ensuring the relevance and comprehensiveness of the retrieval results. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 An application environment diagram of an embedded model-based intelligent retrieval method for technical documents of bridge steel structures in one embodiment;

[0064] Figure 2 It is a first flow chart of a method for intelligent retrieval of technical documents of bridge steel structures based on an embedded model in one embodiment;

[0065] Figure 3 A second flow chart of an intelligent retrieval method for technical documents of bridge steel structures based on an embedded model in another embodiment;

[0066] Figure 4 A third flow chart of an intelligent retrieval method for technical documents of bridge steel structures based on an embedded model in another embodiment;

[0067] Figure 5 A fourth flow chart of an intelligent retrieval method for technical documents of bridge steel structures based on an embedded model in another embodiment;

[0068] Figure 6 A fifth flow chart of an intelligent retrieval method for technical documents of bridge steel structures based on an embedded model in another embodiment;

[0069] Figure 7 A sixth flow chart of an intelligent retrieval method for technical documents of bridge steel structures based on an embedded model in another embodiment;

[0070] Figure 8 It is a structural block diagram of an intelligent retrieval device for bridge steel structure technical documents based on an embedded model in one embodiment;

[0071] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] In the related technology, there are traditional information retrieval systems based on natural language processing and keyword matching. These systems usually rely on Boolean matching of keywords or simple statistical models to find relevant documents. The workflow of this type of system mainly uses Boolean logic to connect keywords using Boolean retrieval models. The search results are based on precise matching of conditions, and users can filter information by combining search conditions. On the other hand, the system will calculate the importance of documents through statistical models such as word frequency and inverse document frequency. Commonly used algorithms such as TF-IDF (Term Frequency-Inverse Document Frequency) are to statistically analyze the distribution of keywords in documents and the entire corpus.

[0074] However, the current retrieval method has the following technical problems:

[0075] Traditional technologies perform poorly when processing complex queries and have difficulty understanding the deep semantics in user input, especially when the query contains ambiguous, context-dependent technical terms. The relevance of retrieval results is often low. In addition, such systems find it difficult to accurately analyze unstructured technical documents, resulting in low retrieval efficiency.

[0076] Based on this, the embodiment of the present application provides an intelligent retrieval method for bridge steel structure technical documents based on an embedded model, which can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0077] In one embodiment, Figure 2 As shown in the figure, an intelligent retrieval method for bridge steel structure technical documents based on embedded model is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0078] Step 202: Obtain query input information of the target object;

[0079] Step 204: parsing the query input information based on a preset information parsing model to obtain a query input vector corresponding to the query input information;

[0080] Step 206: Based on the query input vector, search and compare in a pre-built vector database to obtain a matching data vector that meets a preset matching condition;

[0081] Step 208: performing reverse positioning according to the matching data vector to obtain target file data associated with the matching data vector;

[0082] Step 2010: Respond to the query input information of the target object based on the target file data.

[0083] In the above-mentioned intelligent retrieval method for bridge steel structure technical documents based on embedded model, reasonable deduction is performed in combination with the technical features in the embodiment to achieve the beneficial effect of solving the technical problems raised in the background technology:

[0084] The present application provides an intelligent retrieval method for bridge steel structure technical documents based on an embedded model, and the steps mainly include the contents recorded in the application documents. In implementation, after obtaining the query input information of the target object, the query input information can be first parsed according to the preset information parsing model to obtain a query input vector corresponding to the query input information. At this time, the query input vector processed by vectorization can get rid of the limitation of the original format of the data, so that the core content and key data of the query data information can be obtained, reducing the possibility of incorrect query results due to errors in the query input information. Subsequently, the query input vector is used as the retrieval basis, and a search and comparison is performed in the pre-constructed vector database to obtain a matching data vector that meets certain matching requirements. In this way, the target file data associated with the matching data vector can be determined by reverse positioning, and finally the query input information is responded to with the obtained target file data, breaking through the limitation that the traditional system cannot effectively process unstructured data, and ensuring the relevance and comprehensiveness of the retrieval results.

[0085] In one embodiment, if Figure 3 As shown, the method includes:

[0086] Step 302: obtaining raw data to be processed, the raw data being unstructured data, parsing the raw data, and converting the raw data into vector data;

[0087] Step 304: constructing the vector database based on the vector data.

[0088] In this embodiment, during the execution of this solution, the original data to be processed can be obtained, and the original data as unstructured data can be parsed and processed so that the multi-source and multi-structured original data can be converted into unified vector data, thereby constructing a vector database to provide support for the retrieval of technical documents.

[0089] In one embodiment, if Figure 4 As shown, step 302 includes:

[0090] Step 402: Acquire the data format of the original data, and match the corresponding associated database based on the data format;

[0091] Step 404: parsing the original data based on the associated database;

[0092] and / or;

[0093] Step 406: Based on preset recognition rules, a pre-built machine learning model is called to recognize text elements in the original data;

[0094] Step 408: parsing the text elements based on a preset hierarchical clustering algorithm to determine the chapter structure and hierarchical relationship in the original data;

[0095] and / or;

[0096] Step 4010: Perform semantic analysis on the unconventional objects in the original data to obtain associated semantic data, wherein the unconventional objects include images and tables.

[0097] In this embodiment, the processing of the original data includes identifying the format, performing preliminary parsing through a matching library, and then performing hierarchical processing of text elements through a hierarchical clustering algorithm combined with a model, which helps to implement the parsing and processing of text data, thereby parsing unstructured data into data elements that meet unified standards. Semantic analysis of unconventional objects helps to obtain relevant semantic data, and improves the processing and analysis efficiency of such data objects with the help of the readability of semantic data.

[0098] In one embodiment, if Figure 5 As shown, step 302 includes:

[0099] Step 502: After the original data is parsed, a unique identifier is generated for the parsed data element, and the unique identifier is used to trace and reference the data element.

[0100] In this embodiment, after obtaining the data elements through parsing, a unique identifier is generated for the parsed data, which helps to trace and reference the data elements and improves the efficiency and accuracy of intelligent retrieval.

[0101] In one embodiment, if Figure 6 As shown, before step 2010, the method further includes:

[0102] Step 602: Calculate the matching index between the target file data and the query input information based on a preset matching index calculation rule;

[0103] Step 604: sort and output the target file data based on the matching index.

[0104] In this embodiment, after the target file data is obtained, the target file data is secondary sorted and output based on the matching degree, which helps to improve the retrieval efficiency of the target object and improve the user experience.

[0105] In one embodiment, if Figure 7 As shown, the step 2010 includes:

[0106] Step 702: Acquire the target object's demand information, where the demand information includes the target object's request terminal information;

[0107] Step 704: Adjust the target file data based on the demand information to make the target file data match the demand information.

[0108] In this embodiment, before outputting the target file data, the target file data is adjusted according to the demand information, thereby improving the adaptability of the target file data display, which helps to enhance the compatibility and scalability of the search result display.

[0109] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0110] Based on the same inventive concept, the embodiment of the present application also provides an embedded model-based intelligent retrieval device for bridge steel structure technical documents for realizing the above-mentioned embedded model-based intelligent retrieval method for bridge steel structure technical documents. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the embedded model-based intelligent retrieval device for bridge steel structure technical documents provided below can be referred to the above-mentioned limitations on the embedded model-based intelligent retrieval method for bridge steel structure technical documents, and will not be repeated here.

[0111] In one embodiment, Figure 8 As shown, an intelligent retrieval device for bridge steel structure technical documents based on an embedded model is provided, comprising: a query input module, a query parsing module, a vector matching module and a file positioning module, wherein:

[0112] A query input module is used to obtain query input information of a target object;

[0113] A query parsing module, used to parse the query input information based on a preset information parsing model to obtain a query input vector corresponding to the query input information;

[0114] A vector matching module, used to perform a search and comparison in a pre-built vector database based on the query input vector to obtain a matching data vector that meets a preset matching condition;

[0115] A file positioning module, used for performing reverse positioning according to the matching data vector to obtain target file data associated with the matching data vector;

[0116] A query response module is used to respond to the query input information of the target object based on the target file data.

[0117] In one embodiment, the device comprises:

[0118] The raw data module is used to obtain the raw data to be processed, which is unstructured data, analyze the raw data, and convert it into vector data;

[0119] A database module is used to construct the vector database based on the vector data.

[0120] In one embodiment, the raw data module includes:

[0121] A matching module, used for obtaining the data format of the original data and matching the corresponding associated database based on the data format;

[0122] A parsing module, used for parsing the original data based on the associated database;

[0123] and / or;

[0124] A recognition module, used to recognize text elements in the raw data based on preset recognition rules and calling a pre-built machine learning model;

[0125] A hierarchical module, used to parse the text elements based on a preset hierarchical clustering algorithm to determine the chapter structure and hierarchical relationship in the original data;

[0126] and / or;

[0127] The semantic module is used to perform semantic analysis on the unconventional objects in the original data to obtain associated semantic data, wherein the unconventional objects include images and tables.

[0128] In one embodiment, the raw data module includes:

[0129] The identification module is used to generate a unique identifier for the parsed data element after the original data is parsed, and the unique identifier is used to trace and reference the data element.

[0130] In one embodiment, before the query response module, it also includes:

[0131] A matching module, used to calculate a matching index between the target file data and the query input information based on a preset matching index calculation rule;

[0132] A sorting module is used to sort and output the target file data based on the matching index.

[0133] In one embodiment, the query response module includes:

[0134] The request terminal module obtains the demand information of the target object, wherein the demand information includes the request terminal information of the target object;

[0135] The file adjustment module is used to adjust the target file data based on the demand information so that the target file data matches the demand information.

[0136] Each module in the above-mentioned intelligent retrieval device for technical documents of bridge steel structures based on embedded models can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0137] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an intelligent retrieval method for technical documents of bridge steel structures based on an embedded model is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0138] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0141] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0143] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An intelligent retrieval method for bridge steel structure technical documents based on embedded model, characterized in that: The method comprises: Get the query input information of the target object; Parsing the query input information based on a preset information parsing model to obtain a query input vector corresponding to the query input information; Based on the query input vector, a search and comparison is performed in a pre-built vector database to obtain a matching data vector that meets a preset matching condition; Perform reverse positioning according to the matching data vector to obtain target file data associated with the matching data vector; The query input information of the target object is responded to based on the target file data.

2. The method according to claim 1, characterized in that The method comprises: Acquire raw data to be processed, where the raw data is unstructured data, parse the raw data, and convert it into vector data; The vector database is constructed based on the vector data.

3. The method according to claim 2, characterized in that The obtaining of raw data to be processed, where the raw data is unstructured data, parsing the raw data, and converting the raw data into vector data includes: Acquire the data format of the original data, and match the corresponding associated database based on the data format; Parsing the original data based on the associated database; and / or; Based on preset recognition rules, a pre-built machine learning model is called to recognize text elements in the raw data; Parsing the text elements based on a preset hierarchical clustering algorithm to determine the chapter structure and hierarchical relationship in the original data; and / or; Semantic analysis is performed on the unconventional objects in the original data to obtain associated semantic data, wherein the unconventional objects include images and tables.

4. The method according to claim 3, characterized in that The obtaining of raw data to be processed, where the raw data is unstructured data, parsing the raw data, and converting the raw data into vector data includes: After the original data is parsed, a unique identifier is generated for the parsed data element, and the unique identifier is used to trace and reference the data element.

5. The method according to any one of claims 1 to 4, characterized in that: Before responding to the query input information of the target object based on the target file data, the method further includes: Calculate the matching index between the target file data and the query input information based on the preset matching index calculation rules; The target file data is sorted and output based on the matching index.

6. The method according to claim 5, characterized in that The responding to the query input information of the target object based on the target file data includes: Acquire demand information of a target object, wherein the demand information includes request terminal information of the target object; The target file data is adjusted based on the requirement information so that the target file data matches the requirement information.

7. An intelligent retrieval device for bridge steel structure technical documents based on embedded model, characterized in that: The device comprises: A query input module is used to obtain query input information of a target object; A query parsing module, used to parse the query input information based on a preset information parsing model to obtain a query input vector corresponding to the query input information; A vector matching module, used to perform a search and comparison in a pre-built vector database based on the query input vector to obtain a matching data vector that meets a preset matching condition; A file positioning module, used for performing reverse positioning according to the matching data vector to obtain target file data associated with the matching data vector; A query response module is used to respond to the query input information of the target object based on the target file data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images