Work order content supplement identification method and system and electronic equipment thereof

Abstract

The embodiment of the invention provides a work order content supplementary recognition method, device and system. The method comprises the following steps: acquiring voice information data; performing recognition processing on the voice information data through a trained work order content supplement recognition model to obtain first text data; and on the basis of a preset verbal skill rule, performing supplementary processing on the first text data to obtain second text data. The method optimizes the grammar requirement of the work order generation text by using the trained work order content supplementary recognition model, performing accurate recognition on the voice information and combining the supplementary processing of the preset verbal skill rule, can flexibly cope with different scenes through intelligent recognition and supplementary, improves the user experience, reduces human errors and deviations, and improves the user experience. Therefore, the work order content identification and supplement efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent identification, and in particular to a method, device, system, electronic device and storage medium thereof for supplementary identification of work order content. Background Art

[0002] With the continuous development of artificial intelligence technology, speech recognition (ASR, Automatic Speech Recognition) technology has been widely used in various industries, especially in customer service, technical support, maintenance services and other fields. Speech recognition technology can convert user voice input into text, thereby simplifying the manual processing process and improving efficiency and accuracy.

[0003] However, traditional speech recognition technology faces multiple challenges, especially when processing work order data containing multiple information fields, long sentences and complex structures. Existing work order content recognition methods have problems when they need to process long, structured information, which not only includes the customer's specific requests, but also includes maintenance details, fault descriptions, contact information, etc. The recognition of long work order content may cause information missing, resulting in missing content in the recognized work order. Summary of the invention

[0004] An embodiment of the present invention provides a method for supplementing the identification of work order content to solve the problem that the existing work order content identification method has the problem of missing information when it needs to process long, structured information, which not only includes the customer's specific request, but also includes maintenance details, fault description, contact information, etc., and the identification of long information work order content may cause missing information, thereby causing the identified work order content to be missing.

[0005] In a first aspect, an embodiment of the present invention provides a method for supplementing identification of work order content, the method comprising the following steps: Acquire voice information data; The recognition model is supplemented by the trained work order content, and the voice information data is recognized and processed to obtain the first text data; Based on the preset speech rules, the first text data is supplemented and processed to obtain the second text data.

[0006] Optionally, the acquiring of voice information data includes: The surrounding environment data is collected through the audio sensor to obtain audio data; Performing voice recognition on the audio data to obtain voice audio data; The human voice audio data is preprocessed to obtain voice information data.

[0007] Optionally, before the trained work order content is used to supplement the recognition model and the voice information data is recognized and processed to obtain the first text data, the method further includes: Obtaining a work order content supplementary recognition model to be trained and a training work order recognition sample set, wherein the training work order recognition sample set includes voice information corresponding to the work order content, text recognition content of the voice information corresponding to the work order recognition content, and a text recognition content label of the voice information corresponding to the work order content; Based on the voice information corresponding to the work order content, the text recognition content of the voice information corresponding to the work order recognition content, and the text recognition content label of the voice information corresponding to the work order content, the work order content supplementary recognition model to be trained is iteratively trained, and a trained work order content supplementary recognition model is obtained after the iterative training is completed.

[0008] Optionally, the method of supplementing the recognition model with the trained work order content to perform recognition processing on the voice information data to obtain the first text data includes: When the voice information data is long voice information data, determining a corresponding voice interruption point; Based on the speech interruption point, determining the speech information content before and after the interruption point; Outputting text data of the voice information content before and after the interruption point respectively, and identifying the language connectivity before and after; Based on the language connectivity and the voice information content before and after the interruption point, first text data is obtained.

[0009] Optionally, the supplementary processing of the first text data based on a preset speech rule to obtain the second text data includes: Get the required and non-required data corresponding to the current work order type; Based on the preset speech rules and the required data, the first text data is supplemented to obtain the second text data.

[0010] Optionally, the first text data is supplemented based on the preset speech rules and the required data to obtain the second text data, including: Determine missing fields in the work order content based on the first text data; Determine the adjacent work order item content of the missing field; Determine the work order content of the missing field based on the adjacent work order item content; The work order content of the missing field is used as the second text data.

[0011] In a second aspect, an embodiment of the present invention further provides a work order content supplementary identification device, the work order content supplementary identification device comprising: A first acquisition module, used to acquire voice information data; A first processing module, used to supplement the recognition model with the trained work order content, perform recognition processing on the voice information data, and obtain first text data; The second processing module is used to perform supplementary processing on the first text data based on preset speech rules to obtain second text data.

[0012] In a third aspect, an embodiment of the present invention further provides a work order content supplementary identification system, the work order content supplementary identification system comprising: a work order content supplementary identification device, a server and a drilling device.

[0013] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the work order content supplementary identification method provided in the embodiment of the present invention are implemented.

[0014] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the work order content supplementary identification method provided in the embodiment of the invention are implemented.

[0015] In an embodiment of the present invention, voice information data is obtained; the voice information data is recognized and processed by a trained work order content supplement recognition model to obtain first text data; the first text data is supplemented and processed based on preset speech rules to obtain second text data. By using a trained work order content supplement recognition model to accurately recognize voice information, combined with the supplementary processing of preset speech rules, the grammatical requirements of the work order generated text are optimized. Through intelligent recognition and supplementation, it can flexibly respond to different scenarios, improve user experience, reduce human errors and deviations, and thus improve the efficiency of work order content recognition and supplementation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is an architecture diagram of a work order content supplementary identification system provided by an embodiment of the present invention; Figure 2 It is a flow chart of a method for supplementary identification of work order content provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of a work order content supplementary identification device provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0022] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0023] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0024] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0025] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0026] It should be noted that the work order content supplementary identification method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the work order content supplementary identification device is generally set in the server / terminal device.

[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0028] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for supplementary identification of work order content according to the present application. The method for supplementary identification of work order content comprises the following steps: Step S201, obtaining voice information data.

[0029] In this embodiment, the work order content supplementary identification method can be deployed in a work order content supplementary identification platform. The work order content supplementary identification platform can be constructed by a server or a server cluster. The server or server cluster can be any electronic device with voiceprint recognition, sound processing, data transmission, data storage and other functions. The work order content supplementary identification method runs on the electronic device (for example, Figure 1The server / terminal device shown in the figure can receive voice information data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0030] In this embodiment, the above-mentioned voice information data can be the natural language expression entered by the user in the work order system through a voice input device (such as a microphone or a mobile phone voice assistant), describing the work order content, problem details or request matters. This voice data may contain complete sentences, keywords or intermittent expressions, and may even contain pauses, repetitions or oral habitual words (such as "uh", "um", etc.). For example: "I need to apply for a new office software license, the department is the Finance Department, and my employee number is 5678."

[0031] Specifically, regarding the specific implementation process of the above-mentioned voice information data, this application will provide further detailed descriptions in subsequent specific embodiments, and will not be elaborated in detail here.

[0032] Step S202, supplementing the recognition model with the trained work order content, performing recognition processing on the voice information data to obtain the first text data.

[0033] In this embodiment, the work order content supplement recognition model can be a speech recognition and natural language processing (NLP) model based on deep learning technology. The model can be trained by a large number of work order content samples, and can accurately convert the user's voice input into text, and automatically complete the necessary fields or information according to the specific needs of the work order system.

[0034] In a possible embodiment, the above-mentioned work order content supplementary recognition model can be an ASR (automatic speech recognition) sub-model, which is used to convert speech into preliminary text data, and ensure the completeness and accuracy of the work order content through semantic understanding, completion of required fields, and elimination of invalid information.

[0035] In this embodiment, the above recognition processing can be to perform audio preprocessing (such as denoising, volume equalization, etc.) on the voice information data input by the user, and then perform voice recognition through the ASR model to convert the audio data into preliminary text data.

[0036] On this basis, semantic analysis and structured processing are performed through the NLP model to remove verbal pauses and repeated words, correct recognition errors, and supplement and improve according to preset rules to ensure that the output text data conforms to the standard format of the work order system.

[0037] In this embodiment, the first text data may be preliminary text data converted from the user's voice content without supplementation or optimization, and may include repetitions, idiomatic expressions, pause words, and even recognition errors in the user's expression process.

[0038] Specifically, regarding the specific implementation process of supplementing the recognition model with the trained work order content, recognizing and processing the voice information data, and obtaining the first text data, this application will provide further detailed descriptions of this in subsequent specific embodiments, and will not be elaborated in detail here.

[0039] Step S203, based on the preset speech rules, the first text data is supplemented and processed to obtain the second text data.

[0040] In this embodiment, the preset speech rules can be a set of standardized rules designed based on the needs of the work order management system, which is used to ensure that the recognized text data meets the mandatory requirements and logical relevance of the work order. For example, when the user's voice mentions "printer", the system will automatically require the model field to be supplemented and provide standard speech templates based on common scenarios to ensure data integrity and standardization.

[0041] In this embodiment, supplementary processing can be a process of optimizing and improving the first text data based on preset speech rules, including identifying missing fields, cleaning redundant information, completing necessary content, and intelligently filling in according to context or field relevance to ensure that the final generated data complies with the logic and format requirements of the work order system.

[0042] In this embodiment, the second text data can be complete work order text data after supplementary processing, including all required fields and logically related items, with clear semantics and standardized format, and can be directly parsed and stored by the work order system for subsequent work order circulation, management and execution.

[0043] Specifically, regarding the specific implementation process of supplementing the first text data based on the preset speech rules to obtain the second text data, this application will provide further detailed descriptions of this in subsequent specific embodiments and will not be elaborated on here.

[0044] This application obtains voice information data; uses a trained work order content supplement recognition model to identify and process the voice information data to obtain first text data; and based on preset speech rules, supplements the first text data to obtain second text data. By using a trained work order content supplement recognition model to accurately identify voice information, combined with supplementary processing based on preset speech rules, the grammatical requirements of the work order generated text are optimized. Through intelligent recognition and supplementation, it can flexibly respond to different scenarios, improve user experience, reduce human errors and deviations, and thus improve the efficiency of work order content recognition and supplementation.

[0045] In some optional implementations, step S201 includes the following steps: The surrounding environment data is collected through the audio sensor to obtain audio data; Performing voice recognition on the audio data to obtain voice audio data; Preprocess the human voice audio data to obtain voice information data.

[0046] In this embodiment, the surrounding environment data may be a set of audio signals including human voice, background noise, and environmental sound (such as keyboard tapping and machine operation sound) collected by an audio sensor, which is used for subsequent human voice extraction and noise reduction processing.

[0047] In this embodiment, the audio data may be original audio information obtained after preliminary sampling and digital processing of surrounding environment data, including all environmental sound details, and human voice separation and noise reduction processing have not yet been performed.

[0048] In this embodiment, the human voice audio data can be a pure human voice signal extracted from the audio data, obtained after noise reduction and background sound stripping, which mainly contains the user's voice expression content and serves as the core input data for the subsequent speech recognition model to perform text conversion.

[0049] In a possible embodiment, the surrounding environment data is collected through an audio sensor to collect audio signals including human voice, background noise and ambient sound, and the audio signals are digitized to generate raw audio data; then, the audio data is processed using a human voice recognition algorithm, and the pure human voice signal is extracted through separation technology, and the ambient noise and irrelevant audio parts are removed to generate human voice audio data; finally, the human voice audio data is preprocessed, and the audio quality is optimized by using noise filtering, volume normalization and phoneme alignment, while invalid information such as pauses and catchphrases are eliminated, and finally structured voice information data is generated to provide standardized input for subsequent voice recognition and content supplementation.

[0050] In this embodiment, by collecting surrounding environment data, extracting human voice audio data, and preprocessing voice information data, it is possible to efficiently extract clear and accurate human voice content from a complex audio environment, effectively reducing the interference of background noise and invalid information. This method not only improves the accuracy of speech recognition, but also provides high-quality input data for subsequent work order content supplementation and processing, thereby lowering the threshold for using the work order system, improving the efficiency and accuracy of work order information entry, and significantly improving user experience and system performance.

[0051] In some optional implementations, before step S202, the following steps are included: Obtain the work order content supplementary recognition model to be trained and the training work order recognition sample set, Based on the voice information corresponding to the work order content, the text recognition content of the voice information corresponding to the work order recognition content, and the text recognition content label of the voice information corresponding to the work order content, the work order content supplementary recognition model to be trained is iteratively trained, and a trained work order content supplementary recognition model is obtained after the iterative training is completed.

[0052] In this embodiment, the training work order recognition sample set includes voice information corresponding to the work order content, text recognition content of the voice information corresponding to the work order recognition content, and text recognition content labels of the voice information corresponding to the work order content; In this embodiment, firstly, a work order content supplementary recognition model to be trained and a training work order recognition sample set are obtained, the sample set including voice data corresponding to the work order content, text content of these voice data after preliminary text recognition, and correct label data corresponding to these texts; then, the input and output pairs of the model are constructed by preprocessing the voice, text and label data in the sample set (such as cleaning, standardization and feature extraction); then, the sample data is input into the model to be trained, and the model is iteratively trained using a supervised learning method. During the training process, the model parameters are continuously adjusted to minimize the loss function, and the model performance is evaluated through a validation set; when the training is completed, an optimized model that can accurately recognize voice data and supplement the work order content is obtained, and the model has high recognition accuracy and supplement completeness, and can be used for practical applications of the work order system.

[0053] In this embodiment, by iteratively training the work order content supplementary recognition model and using a rich and diverse training sample set (including voice data, recognized text content and labels), the recognition accuracy and generalization ability of the model in different scenarios are significantly improved. The model can efficiently convert complex and diverse voice information into structured work order data, reduce recognition errors and field omissions, and ensure the integrity and accuracy of the work order content. This process not only reduces the manual intervention cost of work order information entry, but also improves the automation and stability of the system, thereby bringing higher efficiency and better user experience to the work order management process.

[0054] In some optional implementations, step S202 includes the following steps: When the voice information data is long voice information data, determining a corresponding voice interruption point; Based on the speech interruption point, determining the speech information content before and after the interruption point; Output the speech information before and after the interruption point as text data, and identify the language connectivity before and after; Based on the language connectivity and the voice information content before and after the interruption point, the first text data is obtained.

[0055] In this embodiment, the long voice information can be a voice input with a long duration and rich content, such as a detailed description of a work order problem or a long conversation by a user. Due to its length, direct processing may result in reduced recognition accuracy.

[0056] In this embodiment, the speech interruption points can be natural pauses or sentence gaps detected in long speech, which usually represent semantic separation points. By identifying these interruption points, the long speech can be divided into shorter segments that are easier to handle, thereby improving recognition efficiency and accuracy.

[0057] In this embodiment, language connectivity can be used to evaluate the semantic and grammatical association between the speech segments before and after the interruption point. When processing long speech, ensuring the coherence of the segments before and after helps to accurately reassemble the segmented text data to form a complete and coherent first text data. In this embodiment, when the voice information data is long voice information data, firstly, the natural pauses, volume changes or intonation breakpoints in the voice stream are detected by the voice processing algorithm, the voice breakpoints are determined, and the long voice is divided into multiple shorter segments. Then, based on these breakpoints, the voice information content before and after the breakpoints is extracted respectively, and each segment is input into the voice recognition model for independent text data output. At the same time, through language connectivity analysis, the relevance of the semantic and grammatical structures of the segments before and after the breakpoint is detected, and the potential semantic breakage or dislocation problems are corrected to ensure the consistency of the logic and context of the previous and next texts. Finally, based on the language connectivity and the voice information content of each segment, it is spliced ​​into a complete first text data to ensure the integrity, accuracy and coherence of the text. The common problems of interruption, omission and semantic dislocation in long voice recognition are effectively solved. Through voice breakpoint detection and language connectivity analysis, the recognition accuracy and coherence of long voice information can be significantly improved, and information loss or recognition errors caused by single processing of long audio can be avoided, thereby improving the integrity and availability of work order content supplementation and reducing the workload of manual proofreading and correction.

[0058] In some optional implementations, step S203 includes the following steps: Get the required and non-required data corresponding to the current work order type; Based on the preset speech rules and required data, the first text data is supplemented to obtain the second text data.

[0059] In this embodiment, the mandatory data may be core fields set for the current work order type. These fields are the information necessary to complete the work order processing. The lack of any one of them may cause the work order to fail to be submitted or the processing to fail. For example, in an equipment maintenance work order, the mandatory items may include fields such as equipment type, equipment model, fault description, and person in charge. Non-mandatory data may be information fields that are auxiliary but not mandatory for work order processing. Even if these fields are empty, they will not affect the normal flow and processing of the work order. For example, in an equipment maintenance work order, non-mandatory items may include fields such as remarks information, attachment upload, and estimated completion time.

[0060] In this embodiment, first, according to the current work order type, the corresponding mandatory data and non-mandatory data are obtained from the configuration database of the work order system. The mandatory data includes the core fields required by the work order type (such as equipment type, fault description, person in charge, etc.), while the non-mandatory data includes auxiliary fields (such as remarks information, attachment upload, etc.). Then, based on the preset speech rules, the first text data is parsed, the filled fields therein are identified, and the missing mandatory items are supplemented. The supplementation process includes: automatically detecting missing fields, matching context and adjacent field content, using the identified information to deduce or prompt the user to supplement, and finally generating structured and complete second text data to ensure that the work order data meets the logical rules for submission and processing.

[0061] In this embodiment, by automatically identifying and supplementing the required fields, the manual operation and omission risks of users in the work order filling process are significantly reduced, and the integrity and accuracy of the work order data are improved. At the same time, on the basis of ensuring the integrity of the required items, the system reasonably supplements the non-mandatory items, further enhancing the richness and readability of the work order data, reducing the user's learning cost, and improving the overall user experience and operating efficiency of the work order system.

[0062] In some optional implementations, the step of “supplementing the first text data based on the preset speech rules and the required data to obtain the second text data” includes the following steps: Determine missing fields in the work order content based on the first text data; Determine the adjacent work order item content for the missing field; Determine the work order content of the missing fields based on the content of adjacent work order items; The work order content of the missing fields is used as the second text data.

[0063] In this embodiment, the first text data is firstly structured and parsed to identify the missing fields in the work order content, which are usually required items of the work order but are not filled in the current data. Then, by analyzing the adjacent work order items of the missing field, including the context semantics, the logical relationship between the fields, and the associated information of the filled fields, the potential content of the missing field is derived. Subsequently, the natural language processing (NLP) algorithm is used to perform semantic matching and reasoning on the adjacent fields, determine the work order content of the missing field, and fill it into the corresponding position, and finally form the second text data, ensuring that all required fields are effectively supplemented and meet the logic and rule requirements of the work order, effectively solving the processing interruption and rework problems caused by the missing work order information, and reducing the cognitive burden of users when filling in the work order. Through intelligent deduction and supplementation, the system can automatically improve the work order content to a large extent, reduce the risk of human omissions, improve the completeness and accuracy of the work order content, and ultimately speed up the circulation efficiency of the work order, and improve the automation level and user experience of the system.

[0064] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a work order content supplementary identification device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0065] like Figure 3 As shown, the work order content supplementary identification device 300 described in this embodiment includes: a first acquisition module 301, a first processing module 302 and a second processing module 303. Among them: The first acquisition module 301 is used for the first acquisition module to acquire voice information data; The first processing module 302 is used to supplement the recognition model with the trained work order content, perform recognition processing on the voice information data, and obtain the first text data; The second processing module 303 is used to perform supplementary processing on the first text data based on preset speech rules to obtain second text data.

[0066] The acquisition module 301 includes: The acquisition submodule is used to collect surrounding environment data through an audio sensor to obtain audio data; A human voice recognition submodule, used to perform human voice recognition on the audio data to obtain human voice audio data; The preprocessing submodule is used to preprocess the human voice audio data to obtain voice information data.

[0067] Before the first processing module 302, the following steps are included: A second acquisition module is used to acquire a work order content supplementary recognition model to be trained and a training work order recognition sample set, wherein the training work order recognition sample set includes voice information corresponding to the work order content, text recognition content of the voice information corresponding to the work order recognition content, and a text recognition content label of the voice information corresponding to the work order content; The recognition module is used to iteratively train the work order content supplementary recognition model to be trained based on the voice information corresponding to the work order content, the text recognition content of the voice information corresponding to the work order recognition content, and the text recognition content label of the voice information corresponding to the work order content, and obtain the trained work order content supplementary recognition model after the iterative training is completed.

[0068] The first processing module 302 includes: A first determination submodule, used for determining a corresponding voice interruption point when the voice information data is long voice information data; A second determination submodule, configured to determine the voice information content before and after the voice interruption point based on the voice interruption point; The recognition submodule is used to output text data of the voice information content before and after the interruption point, and recognize the language connectivity before and after; The third determination submodule is used to obtain the first text data based on the language connectivity and the voice information content before and after the interruption point.

[0069] The second processing module 303 includes: The acquisition submodule is used to obtain the required and non-required data corresponding to the current work order type; The supplementing submodule is used to supplement the first text data based on preset speech rules and the required data to obtain second text data.

[0070] Among them, the supplementary submodules include: A first determining unit, configured to determine a missing field in the work order content based on the first text data; A second determining unit, used to determine the adjacent work order item content of the missing field; A third determining unit, configured to determine the work order content of the missing field based on the adjacent work order item content; The fourth determining unit is used to use the work order content of the missing field as the second text data.

[0071] In this embodiment, voice information data is obtained; the voice information data is recognized and processed by a trained work order content supplement recognition model to obtain first text data; the first text data is supplemented and processed based on preset speech rules to obtain second text data. By using a trained work order content supplement recognition model to accurately recognize voice information, combined with the supplementary processing of preset speech rules, the grammatical requirements of the work order generated text are optimized. Through intelligent recognition and supplementation, it can flexibly respond to different scenarios, improve user experience, reduce human errors and deviations, and thus improve the efficiency of work order content recognition and supplementation.

[0072] In this embodiment, the operations performed by the above-mentioned units or modules respectively correspond one-to-one to the steps of the work order content supplementary identification method in the above-mentioned implementation mode, and will not be repeated here.

[0073] like Figure 4 As shown, an embodiment of the present invention further provides an electronic device 400, including a processor, and the processor can execute any one of the above-mentioned work order content supplementary identification methods.

[0074] Specifically, it includes a processor 401 and a memory 402, and a computer program for executing a work order content supplementary identification method stored in the memory 402 and capable of running on the processor 401, wherein: The processor 401 runs the computer program of the work order content supplementary identification method stored in the memory 402, and performs the following steps: Acquire voice information data; The recognition model is supplemented by the trained work order content, and the voice information data is recognized and processed to obtain the first text data; Based on the preset speech rules, the first text data is supplemented and processed to obtain the second text data.

[0075] Optionally, the processor 401 executes the acquiring of voice information data, including: The surrounding environment data is collected through the audio sensor to obtain audio data; Performing voice recognition on the audio data to obtain voice audio data; The human voice audio data is preprocessed to obtain voice information data.

[0076] Optionally, before the processor 401 executes the trained work order content supplementary recognition model to perform recognition processing on the voice information data to obtain the first text data, the method further includes: Obtaining a work order content supplementary recognition model to be trained and a training work order recognition sample set, wherein the training work order recognition sample set includes voice information corresponding to the work order content, text recognition content of the voice information corresponding to the work order recognition content, and a text recognition content label of the voice information corresponding to the work order content; Based on the voice information corresponding to the work order content, the text recognition content of the voice information corresponding to the work order recognition content, and the text recognition content label of the voice information corresponding to the work order content, the work order content supplementary recognition model to be trained is iteratively trained, and a trained work order content supplementary recognition model is obtained after the iterative training is completed.

[0077] Optionally, the processor 401 executes the trained work order content supplementary recognition model to perform recognition processing on the voice information data to obtain first text data, including: When the voice information data is long voice information data, determining a corresponding voice interruption point; Based on the speech interruption point, determining the speech information content before and after the interruption point; Outputting text data of the voice information content before and after the interruption point respectively, and identifying the language connectivity before and after; Based on the language connectivity and the voice information content before and after the interruption point, first text data is obtained.

[0078] Optionally, the processor 401 performs the supplementary processing on the first text data based on the preset speech rules to obtain the second text data, including: Get the required and non-required data corresponding to the current work order type; Based on the preset speech rules and the required data, the first text data is supplemented to obtain the second text data.

[0079] Optionally, the processor 401 further performs supplementary processing on the first text data based on the preset speech rules and the required data to obtain second text data, including: Determine missing fields in the work order content based on the first text data; Determine the adjacent work order item content of the missing field; Determine the work order content of the missing field based on the adjacent work order item content; The work order content of the missing field is used as the second text data.

[0080] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the work order content supplement identification method or the application-side work order content supplement identification method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0081] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0082] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for supplementing identification of work order content, characterized in that: include: Acquire voice information data; The recognition model is supplemented by the trained work order content, and the voice information data is recognized and processed to obtain the first text data; Based on the preset speech rules, the first text data is supplemented and processed to obtain the second text data.

2. The work order content supplementary identification method according to claim 1, characterized in that: The acquiring of voice information data comprises: The surrounding environment data is collected through the audio sensor to obtain audio data; Performing voice recognition on the audio data to obtain voice audio data; The human voice audio data is preprocessed to obtain voice information data.

3. The work order content supplementary identification method according to claim 1, characterized in that: Before the recognition model is supplemented by the trained work order content and the voice information data is recognized and processed to obtain the first text data, the method further includes: Obtaining a work order content supplementary recognition model to be trained and a training work order recognition sample set, wherein the training work order recognition sample set includes voice information corresponding to the work order content, text recognition content of the voice information corresponding to the work order recognition content, and a text recognition content label of the voice information corresponding to the work order content; Based on the voice information corresponding to the work order content, the text recognition content of the voice information corresponding to the work order recognition content, and the text recognition content label of the voice information corresponding to the work order content, the work order content supplementary recognition model to be trained is iteratively trained, and a trained work order content supplementary recognition model is obtained after the iterative training is completed.

4. The work order content supplementary identification method according to claim 1, characterized in that: The method of supplementing the recognition model with the trained work order content and performing recognition processing on the voice information data to obtain the first text data includes: When the voice information data is long voice information data, determining a corresponding voice interruption point; Based on the speech interruption point, determining the speech information content before and after the interruption point; Outputting text data of the voice information content before and after the interruption point respectively, and identifying the language connectivity before and after; Based on the language connectivity and the voice information content before and after the interruption point, first text data is obtained.

5. The work order content supplementary identification method according to claim 1, characterized in that: The method of supplementing the first text data based on the preset speech rules to obtain the second text data includes: Get the required and non-required data corresponding to the current work order type; Based on the preset speech rules and the required data, the first text data is supplemented to obtain the second text data.

6. The method for supplementing identification of work order content as claimed in claim 5, characterized in that: The first text data is supplemented based on the preset speech rules and the required data to obtain the second text data, including: Determine missing fields in the work order content based on the first text data; Determine the adjacent work order item content of the missing field; Determine the work order content of the missing field based on the adjacent work order item content; The work order content of the missing field is used as the second text data.

7. A work order content supplementary identification device, characterized in that: include: A first acquisition module, used to acquire voice information data; A first processing module, used to supplement the recognition model with the trained work order content, perform recognition processing on the voice information data, and obtain first text data; The second processing module is used to perform supplementary processing on the first text data based on preset speech rules to obtain second text data.

8. A work order content supplementary identification system, characterized in that: The work order content supplementary identification system comprises: a work order content supplementary identification device; The work order content supplementary identification device is determined by a work order content supplementary identification method shown in claims 1-6.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the work order content supplementary identification method as described in any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the work order content supplementary identification method according to any one of claims 1 to 6 are implemented.

Images