Technical protocol generation method and device, electronic equipment and storage medium
By acquiring multimodal data and utilizing large models to generate technical protocols, the problem of low efficiency in manual programming is solved, and efficient and reliable automatic generation of technical protocols is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA MOBILE GROUP DESIGN INST
- Filing Date
- 2025-12-31
- Publication Date
- 2026-05-19
AI Technical Summary
In existing technologies, the drafting of technical protocols for industrial equipment relies on manual methods, which leads to low efficiency and susceptibility to human factors.
By acquiring multimodal data, including technical protocol generation requirements information, parameter documents, and industrial equipment images, we perform identification and parameter extraction to determine the target technical protocol template and generate the technical protocol using a large model.
It improves the efficiency and reliability of technical protocol generation, reduces human error, and enhances the accuracy and consistency of protocols.
Smart Images
Figure CN122069306A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, electronic device, and storage medium for generating technical protocols. Background Technology
[0002] Currently, technical protocols for industrial equipment are typically written manually. However, this manual method is time-consuming and susceptible to human error, resulting in low efficiency. Therefore, finding a convenient way to obtain technical protocols is a pressing technical problem that needs to be solved. Summary of the Invention
[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for generating technical protocols.
[0004] In a first aspect, this disclosure provides a method for generating a technical protocol, the method comprising: acquiring multimodal data, wherein the multimodal data includes: technical protocol generation requirement information, parameter documents, and industrial equipment images; recognizing the industrial equipment images to obtain equipment identification information of the industrial equipment in the industrial equipment images; extracting parameters from the technical protocol generation requirement information, the parameter documents, and the equipment identification information to obtain first parameter information; determining a corresponding target technical protocol template based on the first parameter information; and generating a technical protocol corresponding to the technical protocol generation requirement information using a large model, based on the first parameter information and the target technical protocol template.
[0005] Secondly, this disclosure provides a technical protocol generation apparatus, the apparatus comprising: a first acquisition module, configured to acquire multimodal data, wherein the multimodal data includes: technical protocol generation requirement information, parameter document, and industrial equipment image; an identification module, configured to identify the industrial equipment image to obtain equipment identification information of the industrial equipment in the industrial equipment image; a parameter extraction module, configured to extract parameters from the technical protocol generation requirement information, the parameter document, and the equipment identification information to obtain first parameter information; a first determination module, configured to determine a corresponding target technical protocol template based on the first parameter information; and a generation module, configured to generate a technical protocol corresponding to the technical protocol generation requirement information using a large model, based on the first parameter information and the target technical protocol template.
[0006] Thirdly, this disclosure provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the technical protocol generation method disclosed in the embodiments of this disclosure.
[0007] Fourthly, this disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the technical protocol generation method disclosed in the embodiments of this disclosure.
[0008] Fifthly, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the technical protocol generation method disclosed in the embodiments of this disclosure.
[0009] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: After acquiring the technical protocol generation requirements information, parameter documents, and industrial equipment images, the industrial equipment images are identified to obtain equipment identification information. Parameters are extracted from the technical protocol generation requirements information, parameter documents, and equipment identification information to obtain first parameter information. Based on the first parameter information, the corresponding target technical protocol template is determined. Then, using a large model, the technical protocol corresponding to the technical protocol generation requirements information is generated based on the first parameter information and the target technical protocol template. Thus, by combining the parameter documents and industrial equipment images, a technical protocol that meets the technical protocol generation requirements information is automatically generated, which helps improve the efficiency and reliability of obtaining the technical protocol. Attached Figure Description
[0010] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0011] Figure 1 This is a flowchart illustrating a method for generating a technology protocol according to an exemplary embodiment; Figure 2 This is a detailed flowchart illustrating step 104 according to an exemplary embodiment; Figure 3 A flowchart illustrating another method for generating a technical protocol according to an exemplary embodiment; Figure 4 A flowchart illustrating another method for generating a technical protocol according to an exemplary embodiment; Figure 5 A flowchart illustrating another method for generating a technical protocol according to an exemplary embodiment; Figure 6 This is a schematic diagram illustrating the structure of a technology protocol generation apparatus according to an exemplary embodiment; Figure 7 This is a structural block diagram of an electronic device according to an exemplary embodiment.
[0012] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0014] The technical solutions of this disclosure and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this disclosure will now be described with reference to the accompanying drawings.
[0015] First, combine Figure 1 The present disclosure provides an exemplary description of the technical protocol generation method provided in the embodiments.
[0016] Figure 1 This is a flowchart illustrating a method for generating a technology protocol according to an exemplary embodiment.
[0017] It should be noted that the technical protocol generation method provided in this disclosure can be executed by a technical protocol generation device, which can be implemented by software and / or hardware. The technical protocol generation device can be an electronic device, or it can be configured within an electronic device.
[0018] It should be noted that the electronic device can be any device with computing capabilities, such as a terminal device or a server. This embodiment does not specifically limit the electronic device.
[0019] like Figure 1 As shown, the method for generating this technical protocol includes the following steps: Step 101: Obtain multimodal data, which includes: technical protocol generation requirements information, parameter documents, and industrial equipment images.
[0020] The aforementioned industrial equipment images were obtained by acquiring images of industrial equipment.
[0021] The industrial equipment in this embodiment may include, but is not limited to, hydraulic control equipment, servo drives, or pneumatic actuators.
[0022] For example, if the industrial equipment is a hydraulic control device, the image of the industrial equipment can be obtained by acquiring images of the hydraulic control device.
[0023] The aforementioned industrial equipment images can be one or more.
[0024] When there are multiple images of the aforementioned industrial equipment, the perspectives of these multiple industrial equipment can be different.
[0025] In this embodiment, the parameter document can be in various formats, such as .docx, .txt, .xlsx, .csv, etc. This embodiment does not impose specific limitations on the format of the parameter document.
[0026] In some embodiments, the requirement information generated by the above-described technical protocol can be input by the user through natural language text.
[0027] The technical protocol generation requirement information is input by the user and describes the specific requirements of the electronic control technology protocol that needs to be generated. For example, the technical protocol generation requirement information can be "Generate a national standard non-shunt with shear FKDQ-1200-9 technical protocol".
[0028] In some embodiments, when a user has a need to generate a technical protocol, the user can trigger a technical protocol generation control. Correspondingly, a corresponding interactive interface can be displayed, and a technical protocol generation requirement description box can be displayed on the interactive interface. Correspondingly, the user can enter the technical protocol generation requirement information in the technical protocol generation requirement description box. Correspondingly, a document upload control can also be displayed on the interactive interface to facilitate the user to upload parameter documents and industrial equipment images, etc., required for generating the technical protocol.
[0029] Step 102: Recognize the industrial equipment image to obtain the equipment identification information of the industrial equipment in the industrial equipment image.
[0030] In some embodiments, device identification information refers to device-related information obtained by identifying images of industrial equipment.
[0031] In some embodiments, an image quality score is performed on the industrial equipment image to obtain an image quality score of the industrial equipment image. If the image quality score exceeds a preset quality score threshold, target recognition is performed on the industrial equipment image to obtain the region of interest (ROI) of the target in the industrial equipment image, and the ROI is identified to obtain the equipment identification information of the industrial equipment image.
[0032] In other embodiments, if the image quality score does not exceed a preset quality score threshold, a prompt message may be output, indicating that the industrial equipment image does not meet the requirements and a new image should be provided.
[0033] In some embodiments, the quality score of an industrial equipment image can be obtained by scoring the image quality based on multiple image quality dimensions.
[0034] Image quality dimensions may include, but are not limited to, sharpness, exposure and contrast range, occlusion ratio, and percentage of highly reflective area.
[0035] As an example, the region of interest (ROI) can be scaled and contrast-normalized, and adaptive gamma / spectrum suppression and background noise reduction can be applied to ensure that details remain distinguishable under different lighting and oil conditions. Correspondingly, the processed ROI is input into a fine-grained classification feature model to obtain the fine-classification features of interest, and the device identification information is determined based on the fine-classification features.
[0036] In cases where the equipment identification information includes the equipment model, the equipment model can be identified based on the fine classification features to obtain the target equipment model of the industrial equipment in the industrial equipment image.
[0037] The equipment identification information may include, but is not limited to, equipment model, equipment type, equipment nameplate information, and interface information of industrial equipment.
[0038] The interface information may include information such as interface type, interface diameter, and number of interface holes.
[0039] Step 103: Extract parameters from the technical protocol generation requirements information, parameter document, and device identification information to obtain the first parameter information.
[0040] In some embodiments, parameters can be extracted from the technical protocol generation requirement information to obtain a first parameter extraction result; parameters can be extracted from the parameter document to obtain a second parameter extraction result; parameters can be extracted from the device identification information to obtain a third parameter extraction result; the first parameter extraction result, the second parameter extraction result, and the third parameter extraction result are merged to obtain the first parameter information.
[0041] In some embodiments, after receiving the technical protocol generation requirement information, the intent of the technical protocol generation requirement information can be identified to obtain the intent identification result. If the intent identification result indicates an intent to generate a technical protocol, parameters can be extracted from the technical protocol generation requirement information, parameter document, and device identification information to obtain the first parameter information.
[0042] In some embodiments, a trained intent recognition model can be used to identify the intent of the technical protocol generation requirement information to obtain the intent recognition result. Thus, the intent recognition result of the technical protocol generation requirement information can be quickly obtained through the intent recognition model, facilitating subsequent processing based on the intent recognition result.
[0043] In some embodiments, one possible implementation of extracting parameters from the technical protocol generation requirement information to obtain the first parameter extraction result is as follows: performing word segmentation on the technical protocol generation requirement information to obtain the word segmentation result; performing semantic representation on the word segmentation result to obtain the semantic representation of the word segmentation result; performing entity recognition on the semantic representation of the word segmentation result to obtain the entity recognition result, and extracting parameter information for technical protocol template selection from the entity recognition result.
[0044] As an example, the tokenization function Tokenize() can be used to segment the requirement information S generated by the technical protocol to obtain the segmentation result W, which can be represented as:
[0045] in, wi is a word element, and pi is a part-of-speech tag.
[0046] The semantic representation of each word is obtained by using a transformer-based bidirectional encoder to represent the BERT model:
[0047] Combined into a semantic matrix:
[0048] By combining industry-specific dictionaries and named entity recognition models, entity recognition results related to technical protocols are identified.
[0049]
[0050] For example: E={Standard Type: National Standard, Diversion: None, Shearing: Yes, Model: FKDQ-1200-9, Document Type: Technical Agreement}.
[0051] In some embodiments, the identified entities can be mapped to a standardized parameter structure P within the system:
[0052] in: STD∈{Chinese Standard, American Standard, API...}, DIV∈{with shunting, without shunting...}, CUT∈{with cutting, without cutting...}, MODEL∈{FKDQ...}, DOC∈{technical protocol, design datasheet...}.
[0053] In some embodiments, during the word segmentation of the technical protocol generation requirement information S, model information is identified in the technical protocol generation requirement information S. If model information exists, the signal information is divided into a word unit. Thus, it can be ensured that the model information in the word segmentation result is intact.
[0054] In addition, in this embodiment, by mapping the identified entities to standardized parameters within the system, the accuracy of the resulting technical protocol can be improved by avoiding inconsistencies in units, symbols, and synonyms when adding parameter information to the technical protocol template.
[0055] In some embodiments, one possible implementation of extracting parameters from a parameter document to obtain a second parameter extraction result is as follows: the parameter document can be structurally identified to obtain a structured identification result, and parameters can be extracted from the structured identification result to obtain a second parameter extraction result.
[0056] As an example, a possible implementation of performing structure recognition on the parameter document to obtain a structured recognition result, and then extracting parameters from the structured recognition result to obtain a second parameter extraction result, can be: parsing the parameter document using the text reading function ReadDoc() to obtain a UTF-8 encoded string T in a uniform format, where T can be represented as: T = ReadDoc(D), D ∈{docx,doc,xlsx,csv,...} Then, irrelevant information is removed and the format is standardized (e.g., removing extra spaces, control characters, HTML tags, special characters, etc.) from the UTF-8 string T to obtain the processed UTF-8 string. ,in, It can be represented as:
[0057] Using rule-based and machine learning-based structural analysis algorithms, to Document structure recognition is performed to obtain document recognition result S. The document recognition result can include the recognition of different document structural elements such as headings, paragraphs, and columns. The document recognition result S can be represented as:
[0058] Each structural unit si consists of the following attributes:
[0059] Type ∈ {TITLE, PARAGRAPH, LIST, TABLE, CAPTION, NOTE} Content is the text content of this structure block; Position is the sequential position index in the document; Then, domain parameters are extracted from the Content portion of the document recognition result S. This is combined with Named Entity Recognition (NER) and regular expression matching rules to obtain the identified technical parameters E. The identified technical parameters E can be expressed as:
[0060] Where R is an industry-specific set of parameter matching rules (such as "pressure rating", "medium type", "model", "temperature range" etc.).
[0061] The extracted result is a set of parameters: ,in, This represents the p-th parameter in parameter set E. This represents the value of the p-th parameter.
[0062] In some embodiments, in order to eliminate the differences in parameter writing in different ways (e.g., unifying "MPa" and "megapascal" into the same unit), the system normalizes the parameter values; The normalized parameter values are then mapped to the system's internal normalized structure P, which can be expressed as:
[0063] in, This indicates that the value of the p-th parameter is mapped to the standardized parameter value within the system.
[0064] Step 104: Determine the corresponding target technology protocol template based on the first parameter information.
[0065] In some embodiments, a target technical protocol template matching the first parameter information is obtained from a preset technical protocol template library based on the first parameter information.
[0066] Step 105: Using the large model, based on the first parameter information and the target technical protocol template, generate the technical protocol corresponding to the technical protocol generation requirement information.
[0067] In some embodiments, the first parameter information and the target technical protocol template can be input into the large model to generate the technical protocol corresponding to the requirement information through the large model.
[0068] Among them, the technical agreement is a written agreement on non-commercial terms such as the technical performance, functional requirements, interface standards, and acceptance methods of industrial equipment, and serves as the technical basis for the design, manufacturing, inspection, and acceptance of industrial equipment.
[0069] In some embodiments, the technical protocol may include, but is not limited to, an overview of the industrial equipment, technical parameters, interface specifications, standards and certifications, inspection and acceptance, and functional requirements. The overview of the industrial equipment may include, but is not limited to, its name, purpose, and application scenarios.
[0070] It is understandable that after obtaining the technical agreement, operations, production supervision, inspection and acceptance can be carried out based on the technical agreement.
[0071] The format of the electronic document of the technical protocol obtained from the large model may include, but is not limited to, Word document format, PDF format, etc. This embodiment does not specifically limit the format of the electronic document of the technical protocol.
[0072] In some embodiments, prompt words can be generated based on the first parameter information and the target technical protocol template. These prompt words instruct the generation of a technical protocol based on the first parameter information and the target technical protocol template. Correspondingly, the prompt words are input into the large model, enabling the large model to generate the corresponding technical protocol based on the prompt words. Thus, the prompt words guide the large model, allowing it to accurately generate the technical protocol.
[0073] The technical protocol generation method provided in this disclosure, after acquiring technical protocol generation requirement information, parameter documents, and industrial equipment images, identifies the industrial equipment images to obtain equipment identification information of the industrial equipment in the images. It then extracts parameters from the technical protocol generation requirement information, parameter documents, and equipment identification information to obtain first parameter information. Based on the first parameter information, it determines the corresponding target technical protocol template and generates the technical protocol corresponding to the technical protocol generation requirement information using a large model, based on the first parameter information and the target technical protocol template. Thus, by combining the parameter documents and industrial equipment images, a technical protocol that meets the technical protocol generation requirement information is automatically generated, which helps improve the efficiency and reliability of obtaining the technical protocol.
[0074] In some embodiments, in order to clearly understand the process of determining the corresponding target technology protocol template based on the first parameter information, the following is combined with Figure 2 An exemplary description is provided of one possible implementation method for determining the corresponding target technical protocol template based on the first parameter information.
[0075] Figure 2 This is a detailed flowchart illustrating step 104 according to an exemplary embodiment.
[0076] like Figure 2 As shown, the method may include: Step 201: Determine the core parameter information required for selecting the technical protocol template from the first parameter information.
[0077] The core parameter information may include, but is not limited to, equipment model and standard system, and may also protect other information, such as traffic distribution and equipment clusters.
[0078] Step 202: Obtain candidate technical protocol templates that match the core parameter information from the preset technical protocol template library.
[0079] Step 203: Based on the rule matching results between the first parameter information and the candidate technical protocol template, and the semantic similarity between the first parameter information and the candidate technical protocol template, determine the comprehensive matching score between the candidate technical protocol template and the first parameter information.
[0080] In some embodiments, the rule matching result between the first parameter information and the candidate technical protocol template can be determined; the semantic similarity between the first parameter information and the candidate technical protocol template can be determined; and the rule matching result and the semantic similarity can be weighted and summed to obtain the comprehensive matching score between the candidate technical protocol template and the first parameter information.
[0081] For example, there are multiple candidate technology protocol templates. For the i-th candidate technology protocol template among these multiple candidate technology protocol templates, assume that t i This represents the i-th candidate technology protocol template, used to obtain the comprehensive matching score between the i-th candidate technology protocol template and the first parameter information. can be represented as:
[0082] It should be noted that in the formula... Indicates to The weights used, where, Indicates to The weights used This represents the rule matching result between the first parameter information and the i-th candidate technology protocol template; This represents the semantic similarity between the i-th candidate technology protocol template and the first parameter information, where, This indicates the information of the first parameter.
[0083] Step 204: Select the candidate technical protocol template with the highest comprehensive matching score from the candidate technical protocol templates as the target technical protocol template.
[0084] In this embodiment, by combining core parameter information, the technical protocol template library is matched to quickly narrow down the candidate technical protocol templates. Then, the comprehensive matching score between the first parameter information and the candidate technical protocol templates is determined, and the candidate technical protocol template with the highest comprehensive matching score is selected as the target technical protocol template. Thus, the target technical protocol template can be determined quickly and accurately.
[0085] Based on the above embodiments, in order to ensure that the first parameter information can include the parameter values of each parameter required by the second parameter information in the target technical protocol template, correspondingly, in some embodiments, after step 204, such as Figure 3 As shown, the method may include the following steps: Step 301: Determine the parameter matching degree between the second parameter information and the first parameter information in the target technical protocol template.
[0086] In some embodiments, the second parameter information in the target technical protocol template can be obtained, and the parameter matching degree between the second parameter information and the parameters in the first parameter information can be determined.
[0087] Step 302: If the parameter matching degree is less than the matching degree threshold, the first target parameter missing in the first parameter information is determined by comparing the second parameter information and the first parameter information.
[0088] The matching degree threshold is a pre-set matching degree threshold based on actual needs. This embodiment does not specifically limit the value of the matching degree threshold.
[0089] In some embodiments, if the parameter matching degree is greater than or equal to the matching degree threshold, then there is no need to supplement the first parameter information.
[0090] Step 303: Add the first target parameter and its corresponding value to the first parameter information.
[0091] An example of how the value of the first target parameter is obtained can be: In some embodiments, when it is determined that there is a constraint relationship between the second target parameter and the first target parameter in the first parameter information, the parameter value of the first target parameter is estimated based on the constraint relationship and the parameter value of the second target parameter to obtain the parameter value of the first target parameter. A first label is then used to annotate the parameter value of the first target parameter, wherein the first label indicates that the parameter value of the first target parameter is an estimated value. Therefore, the parameter value of the first target parameter can be obtained through engineering constraints, greatly simplifying the document production process and reducing repetitive work and human error.
[0092] In some embodiments, when it is determined that the parameter value of the first target parameter is calculated from the third target parameter in the first parameter information through a preset functional relationship, the parameter value of the first target parameter is calculated based on the preset functional relationship and the parameter value of the third target parameter. Thus, by combining the existing parameter value of the third target parameter and the preset function, the parameter value of the first target parameter is accurately calculated, greatly simplifying the document production process and reducing repetitive work and human error.
[0093] In other embodiments, if it is determined that there is no constraint relationship between the parameters in the first parameter information and the first target parameter, and there is no functional relationship between the parameters in the first parameter information and the first target parameter, the parameter value of the first target parameter is set as a preset placeholder, and a second marker is used to annotate the parameter value of the first target parameter. The second marker indicates that the parameter value of the first target parameter requires manual confirmation. This allows the user to determine the requirement for manual confirmation of the first target parameter by using the second marker after obtaining the generated technical protocol.
[0094] In this embodiment, the second parameter information in the target technical protocol template is used to supplement the parameters in the first parameter information, which helps to further improve the accuracy of the technical protocol generated subsequently.
[0095] Based on any of the above embodiments, in order to automatically verify the compliance of each parameter in the first parameter information, in some embodiments, before generating the technical protocol corresponding to the requirement information using the large model based on the first parameter information and the target technical protocol template, compliance verification can also be performed on the corresponding parameters in the first parameter information by referring to the corresponding standards in the device model database. To clearly understand this process, the following will be combined with... Figure 4 The process is described exemplarily.
[0096] Figure 4 This is a flowchart illustrating another method for generating a technical protocol according to an exemplary embodiment.
[0097] like Figure 4As shown, the method may include: Step 401: Obtain the reference standard for the fourth target parameter of the target device model from the preset device model database.
[0098] The aforementioned reference standard can be the reference value range of the fourth target parameter.
[0099] The fourth target parameter refers to the various parameters corresponding to the target device model in the device model database.
[0100] The fourth target parameter may include, but is not limited to, rated pressure, temperature range, explosion-proof rating, and electrical clearance.
[0101] Step 402: If the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard, a third mark is added to the parameter value of the fourth target parameter in the first parameter information. The third mark is used to indicate that the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard.
[0102] It can be understood that if the parameter value of the fourth target parameter in the first parameter information meets the reference standard, then the parameter value of the fourth target parameter in the first parameter information is determined to be compliant with the compliance verification.
[0103] In some embodiments, after determining that the parameter value of the fourth target parameter in the first parameter information meets the compliance verification, a fourth marker can be added to the parameter value of the fourth target parameter in the first parameter information. This fourth marker indicates that the parameter value of the fourth target parameter in the first parameter information conforms to the reference standard. Therefore, after obtaining the generated technical protocol, the user can determine that the parameter value of the fourth target parameter conforms to the reference standard through the fourth marker; that is, the parameter value of the fourth target parameter is compliant.
[0104] It should be noted that the first mark, second mark, third mark and fourth mark in this embodiment are different marks. In practical applications, the first mark, second mark, third mark and fourth mark can be set according to actual needs. This embodiment does not make specific limitations in this regard.
[0105] It is understood that if the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard, then the parameter value of the fourth target parameter in the first parameter information is determined to be non-compliant with the compliance check.
[0106] In this embodiment, by combining data from the device model database, compliance verification of the corresponding parameter values is achieved, effectively replacing the traditional method of relying on manual verification, reducing workload, and improving judgment efficiency and accuracy.
[0107] Based on any of the above embodiments, before generating the technical protocol corresponding to the technical protocol generation requirement information according to the first parameter information and the target technical protocol template through the large model, the overall credibility of the technical protocol that can be generated based on the first parameter information and the target technical protocol template can also be evaluated. If the overall credibility is greater than or equal to the preset credibility threshold, then the technical protocol corresponding to the technical protocol generation requirement information is generated according to the first parameter information and the target technical protocol template through the large model.
[0108] The preset credibility threshold is a credibility threshold that is set in advance according to actual needs. This embodiment does not specifically limit the value of the preset credibility threshold.
[0109] In other embodiments, if the overall credibility is less than a preset credibility threshold, a reminder message is output. The reminder message is used to prompt whether to continue generating the technical protocol, which can be generated based on the first parameter information and the target technical protocol template, since the overall credibility is less than the preset credibility threshold.
[0110] If an instruction to continue generating is received, the technical protocol corresponding to the generation requirement information is generated through the large model based on the first parameter information and the target technical protocol template.
[0111] In some embodiments, the parameter integrity of the parameters in the first parameter information can be determined according to the target technical protocol template, and the overall credibility of the generated technical protocol can be determined according to the degree of consistency between the multi-source parameters corresponding to the first parameter information, and the parameter integrity and the degree of consistency between the multi-source parameters.
[0112] The consistency of multi-source parameters is determined by merging the parameters obtained when combining the first parameter extraction result from the technical protocol generation requirement information, the second parameter extraction result from the parameter document, and the third parameter extraction result from the device identification information.
[0113] In other embodiments, the credibility of the target device model in the first parameter information can also be determined. Correspondingly, the overall credibility of the generateable technical protocol can be determined based on the integrity of the parameters and the degree of consistency between the multi-source parameters.
[0114] In some embodiments, the credibility, parameter integrity, and consistency among multi-source parameters can be weighted and summed to obtain the overall credibility of the generated technical protocol.
[0115] To facilitate a clear understanding of this disclosure, the following will be combined with... Figure 5The method of this embodiment is described by way of example.
[0116] Figure 5 This is a flowchart illustrating another method for generating a technical protocol according to an exemplary embodiment. It should be noted that this embodiment uses technical protocol generation requirement information as an example to illustrate the method.
[0117] like Figure 5 As shown, it may include: Step 501: Obtain the input multimodal data, which includes: technical protocol generation requirement text, parameter document, and industrial equipment image.
[0118] Step 502: Perform intent recognition on the technical protocol generated requirement text to obtain intent recognition results.
[0119] Step 503: When the intent recognition result indicates an intent to generate a technical protocol, parameters are extracted from the technical protocol generation requirement text to obtain the first parameter extraction result.
[0120] For a detailed description of extracting parameters from the technical protocol generation requirement text to obtain the first parameter extraction result, please refer to the relevant descriptions in other embodiments, which will not be repeated here.
[0121] Step 504: Extract parameters from the parameter document to obtain the second parameter extraction result.
[0122] For a detailed description of step 504, please refer to the relevant descriptions in other embodiments, which will not be repeated here.
[0123] Step 505: Recognize the industrial equipment image to obtain the equipment identification information of the industrial equipment in the industrial equipment image.
[0124] Step 506: Extract parameters from the device identification information to obtain the third parameter extraction result.
[0125] Step 507: Merge the results of the first parameter extraction, the second parameter extraction, and the third parameter extraction to obtain the first parameter information.
[0126] The first parameter information includes: the parameter and its corresponding value, and may also include the source of the parameter.
[0127] The parameter source can be one of the following: technical protocol generation requirement text, industrial equipment image, or parameter document.
[0128] Step 508: Determine the corresponding target technology protocol template based on the first parameter information.
[0129] For a detailed description of step 508, please refer to the relevant descriptions in other embodiments, which will not be repeated here.
[0130] Step 509: Determine the parameter matching degree between the second parameter information and the first parameter information in the target technical protocol template.
[0131] Step 510: If the parameter matching degree is less than the matching degree threshold, determine the first target parameter missing in the first parameter information by comparing the second parameter information and the first parameter information.
[0132] Step 511: Add the first target parameter and its corresponding value to the first parameter information.
[0133] It should be noted that for a detailed description of steps 509 to 511, please refer to the relevant descriptions in other embodiments, which will not be repeated here.
[0134] Step 512: Using the large model, based on the first parameter information and the target technical protocol template, generate the technical protocol corresponding to the technical protocol generation requirement information.
[0135] Step 513: Verify the generated technical protocol.
[0136] Step 514: If the technical protocol passes the verification, output the technical protocol.
[0137] In some implementations, the generated technical protocol can be validated for compliance, and if the technical protocol passes the compliance validation, the technical protocol can be output.
[0138] It should be noted that if the generated technical protocol fails the verification, the technical protocol will be regenerated using a large model until the generated technical protocol passes the verification.
[0139] In this embodiment, the required technical protocol is automatically generated by generating requirement text, parameter document, and industrial equipment image based on the input technical protocol, which helps to improve the efficiency and reliability of obtaining the technical protocol.
[0140] Figure 6 This is a schematic diagram of a technology protocol generation apparatus according to an exemplary embodiment.
[0141] like Figure 6 As shown, the technical protocol generation device 600 includes: a first acquisition module 601, an identification module 602, a parameter extraction module 603, a first determination module 604, and a generation module 605, wherein: The first acquisition module 601 is used to acquire multimodal data, which includes: technical protocol generation requirement information, parameter documents, and industrial equipment images.
[0142] The recognition module 602 is used to recognize industrial equipment images to obtain equipment recognition information of industrial equipment in the industrial equipment images.
[0143] The parameter extraction module 603 is used to extract parameters from the technical protocol generation requirement information, parameter document and device identification information to obtain the first parameter information.
[0144] The first determining module 604 is used to determine the corresponding target technical protocol template based on the first parameter information.
[0145] The generation module 605 is used to generate the technical protocol corresponding to the generation requirement information based on the first parameter information and the target technical protocol template through the large model.
[0146] In one embodiment of this disclosure, the first determining module 604 may include: The first determining unit is used to determine the core parameter information required for selecting the technical protocol template from the first parameter information; The acquisition unit is used to acquire candidate technical protocol templates that match the core parameter information from a preset technical protocol template library; The second determining unit is used to determine the comprehensive matching score between the candidate technology protocol template and the first parameter information based on the rule matching result between the first parameter information and the candidate technology protocol template, and the semantic similarity between the first parameter information and the candidate technology protocol template. The third determining unit is used to select the candidate technical protocol template with the highest comprehensive matching score from the candidate technical protocol templates as the target technical protocol template.
[0147] In one embodiment of this disclosure, the second determining unit is specifically used for: determining the rule matching result between the first parameter information and the candidate technical protocol template; determining the semantic similarity between the first parameter information and the candidate technical protocol template; and performing a weighted summation of the rule matching result and the semantic similarity to obtain a comprehensive matching score between the candidate technical protocol template and the first parameter information.
[0148] In one embodiment of this disclosure, the device may further include: The second determining module is used to determine the parameter matching degree between the second parameter information and the first parameter information in the target technical protocol template; The third determining module is used to determine the first target parameter missing in the first parameter information by comparing the second parameter information and the first parameter information when the parameter matching degree is less than the matching degree threshold. The fourth determination module is used to add the first target parameter and its corresponding parameter value to the first parameter information.
[0149] In one embodiment of this disclosure, the parameter value of the first target parameter is obtained as follows: When it is determined that there is a constraint relationship between the second target parameter and the first target parameter in the first parameter information, the parameter value of the first target parameter is estimated according to the constraint relationship and the parameter value of the second target parameter to obtain the parameter value of the first target parameter, and the parameter value of the first target parameter is marked with a first mark, wherein the first mark is used to indicate that the parameter value of the first target parameter is an estimated value; When it is determined that the parameter value of the first target parameter is calculated from the third target parameter in the first parameter information through a preset functional relationship, the parameter value of the first target parameter is calculated based on the preset functional relationship and the parameter value of the third target parameter. If it is determined that there is no constraint relationship between each parameter in the first parameter information and the first target parameter, and there is no functional relationship between each parameter in the first parameter information and the first target parameter, the parameter value of the first target parameter is set as a preset placeholder, and the parameter value of the first target parameter is marked with a second mark, wherein the second mark is used to indicate that the parameter value of the first target parameter needs to be manually confirmed.
[0150] In one embodiment of this disclosure, the first parameter information includes: the target device model; the device may further include: The second acquisition module is used to obtain the reference standard for the fourth target parameter of the target device model from the preset device model database; The marking module is used to add a third mark to the parameter value of the fourth target parameter in the first parameter information when the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard. The third mark is used to indicate that the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard.
[0151] It should be noted that the foregoing description of the technical protocol generation method embodiment also applies to the technical protocol generation apparatus of this embodiment, and will not be repeated here.
[0152] The technical protocol generation apparatus provided in this embodiment, after acquiring technical protocol generation requirement information, parameter documents, and industrial equipment images, identifies the industrial equipment images to obtain equipment identification information of the industrial equipment in the images. It then extracts parameters from the technical protocol generation requirement information, parameter documents, and equipment identification information to obtain first parameter information. Based on the first parameter information, it determines the corresponding target technical protocol template and generates the technical protocol corresponding to the technical protocol generation requirement information using a large model, based on the first parameter information and the target technical protocol template. Thus, by combining the parameter documents and industrial equipment images, it automatically generates technical protocols that meet the technical protocol generation requirement information, helping to improve the efficiency and reliability of obtaining technical protocols.
[0153] It should be noted that the acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of national laws and regulations.
[0154] According to embodiments of this disclosure, an electronic device is also provided, including: a processor and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the technical protocol generation method disclosed in embodiments of this disclosure.
[0155] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the technical protocol generation method disclosed in this disclosure.
[0156] To implement the above embodiments, this disclosure also provides a computer program product.
[0157] The computer program product includes a computer program that, when executed by a processor, implements the technical protocol generation method disclosed in this embodiment.
[0158] Figure 7 This is a structural block diagram of an electronic device according to an exemplary embodiment. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.
[0159] like Figure 7As shown, the electronic device 1000 includes a processor 111, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 112 or a program loaded from memory 116 into random access memory (RAM) 113. The RAM 113 also stores various programs and data required for the operation of the electronic device 1000. The processor 111, ROM 112, and RAM 113 are interconnected via a bus 114. An input / output (I / O) interface 115 is also connected to the bus 114.
[0160] The following components are connected to I / O interface 115: memory 116 including hard disks, etc.; and communication section 117 including network interface cards such as local area network (LAN) cards, modems, etc., communication section 117 performs communication processing via a network such as the Internet; and driver 118 is also connected to I / O interface 115 as needed.
[0161] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 117. When the computer program is executed by processor 111, it performs the functions defined in the methods of this disclosure.
[0162] In an exemplary embodiment, a storage medium including instructions is also provided, such as a memory including instructions, which can be executed by the processor 111 of the electronic device 1000 to perform the above-described method. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.
[0163] In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.
[0164] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0165] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for generating a technical protocol, characterized in that, The method includes: Acquire multimodal data, wherein the multimodal data includes: technical protocol generation requirement information, parameter documents, and industrial equipment images; The industrial equipment image is identified to obtain the equipment identification information of the industrial equipment in the industrial equipment image; The technical protocol generation requirement information, the parameter document, and the device identification information are processed to extract parameters and obtain the first parameter information; Based on the first parameter information, determine the corresponding target technology protocol template; Using a large model, based on the first parameter information and the target technical protocol template, a technical protocol corresponding to the technical protocol generation requirement information is generated.
2. The method as described in claim 1, characterized in that, The step of determining the corresponding target technology protocol template based on the first parameter information includes: From the first parameter information, determine the core parameter information required for selecting the technical protocol template; From the preset technical protocol template library, obtain candidate technical protocol templates that match the core parameter information; Based on the rule matching results between the first parameter information and the candidate technology protocol template, and the semantic similarity between the first parameter information and the candidate technology protocol template, a comprehensive matching score between the candidate technology protocol template and the first parameter information is determined. The candidate technology protocol template with the highest comprehensive matching score among the candidate technology protocol templates is selected as the target technology protocol template.
3. The method as described in claim 2, characterized in that, The step of determining the comprehensive matching score between the candidate technology protocol template and the first parameter information based on the rule matching result between the first parameter information and the candidate technology protocol template, and the semantic similarity between the first parameter information and the candidate technology protocol template, includes: Determine the rule matching result between the first parameter information and the candidate technology protocol template; Determine the semantic similarity between the first parameter information and the candidate technology protocol template; The rule matching result and the semantic similarity are weighted and summed to obtain the comprehensive matching score between the candidate technology protocol template and the first parameter information.
4. The method as described in claim 2, characterized in that, The method further includes: Determine the parameter matching degree between the second parameter information and the first parameter information in the target technology protocol template; If the parameter matching degree is less than the matching degree threshold, the first target parameter missing in the first parameter information is determined by comparing the second parameter information and the first parameter information. Add the first target parameter and its corresponding value to the first parameter information.
5. The method as described in claim 4, characterized in that, The method for obtaining the value of the first target parameter is as follows: When it is determined that there is a constraint relationship between the second target parameter in the first parameter information and the first target parameter, the parameter value of the first target parameter is estimated according to the constraint relationship and the parameter value of the second target parameter to obtain the parameter value of the first target parameter, and the parameter value of the first target parameter is marked with a first mark, wherein the first mark is used to indicate that the parameter value of the first target parameter is an estimated value; If it is determined that the parameter value of the first target parameter is calculated from the third target parameter in the first parameter information through a preset function relationship, the parameter value of the first target parameter is calculated according to the preset function relationship and the parameter value of the third target parameter. If it is determined that there is no constraint relationship between each parameter in the first parameter information and the first target parameter, and there is no functional relationship between each parameter in the first parameter information and the first target parameter, the parameter value of the first target parameter is set as a preset placeholder, and the parameter value of the first target parameter is marked with a second mark, wherein the second mark is used to indicate that the parameter value of the first target parameter needs to be manually confirmed.
6. The method as described in claim 1, characterized in that, The first parameter information includes: the target device model, and the method further includes: Obtain the reference standard for the fourth target parameter of the target device model from the preset device model database; If the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard, a third mark is added to the parameter value of the fourth target parameter in the first parameter information, wherein the third mark is used to indicate that the parameter value of the fourth target parameter in the first parameter information does not conform to the reference standard.
7. A technical protocol generation device, characterized in that, The device includes: The first acquisition module is used to acquire multimodal data, wherein the multimodal data includes: technical protocol generation requirement information, parameter documents, and industrial equipment images; The recognition module is used to recognize the industrial equipment image to obtain the equipment recognition information of the industrial equipment in the industrial equipment image; The parameter extraction module is used to extract parameters from the technical protocol generation requirement information, the parameter document, and the device identification information to obtain the first parameter information; The first determining module is used to determine the corresponding target technology protocol template based on the first parameter information; The generation module is used to generate the technical protocol corresponding to the technical protocol generation requirement information based on the first parameter information and the target technical protocol template using a large model.
8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.