Work order automatic filling method, device and system and electronic equipment thereof

Abstract

The embodiment of the invention provides a work order automatic filling method, device and system. The method comprises the following steps: acquiring voice information data; and through a trained work order content identification model, identifying the voice information data to obtain corresponding text data, and filling the text data into corresponding work order items which are necessary items in the work order. Through the trained work order content recognition model, the obtained user voice information data can be recognized, the filling content in the work order item is extracted from the user voice information data, the learning cost and the application cost of work order issuing and management are reduced, and the work order accuracy 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 for automatically filling out a work order. Background Art

[0002] With the rapid development of information technology, more and more companies are beginning to rely on digital work order management systems to improve work efficiency and reduce human errors. These systems usually require users to fill in a lot of work order content, especially for the mandatory items in the work order, it is necessary to ensure the accuracy and completeness of the information.

[0003] Since the existing work order filling methods mostly use manual filling of work order items, there is a problem that when processing a large amount of text information, it is not only time-consuming and labor-intensive, but also easy to cause data errors due to improper operation or typos, affecting subsequent processing and decision-making. Summary of the invention

[0004] An embodiment of the present invention provides a method for automatically filling out work orders to solve the problem that existing work order filling methods mostly use manual filling of work order items. Therefore, when processing a large amount of text information, it is not only time-consuming and labor-intensive, but also easy to cause data errors due to improper operation or typos, affecting subsequent processing and decision-making.

[0005] In a first aspect, an embodiment of the present invention provides a method for automatically filling out a work order, the method comprising the following steps: Acquire voice information data; The voice information data is recognized through the trained work order content recognition model to obtain corresponding text data, and the text data is filled in the corresponding work order item, which is a required item in the work order.

[0006] Optionally, the acquiring of voice information data includes: The user's voice data is recognized through the audio sensor to obtain the voice information data to be processed; The voice information data to be processed is preprocessed to obtain voice information data.

[0007] Optionally, before the voice information data is recognized by the trained work order content recognition model to obtain corresponding text data, the method further includes: Obtain a work order content recognition model to be trained and a training work order sample set, wherein the training work order sample set includes work order content, mandatory items corresponding to the work order content, and content labels corresponding to the mandatory items; Based on the work order content, the required items corresponding to the work order content, and the filled-in content labels corresponding to the required items, the work order content recognition model to be trained is iteratively trained, and a trained work order content recognition model is obtained after the iterative training is completed.

[0008] Optionally, the voice information data is recognized by using a trained work order content recognition model to obtain corresponding text data, including: Performing vector processing on the voice information data to obtain feature vector data corresponding to at least one voice information data; Based on the feature vector data, corresponding text data is determined.

[0009] Optionally, the voice information data is recognized by using a trained work order content recognition model to obtain corresponding text data, and the method further includes: Processing the voice information data according to user needs and user language characteristics to obtain target voice information data; Based on the target voice information data, corresponding text data is determined.

[0010] Optionally, the step of filling the text data into the corresponding work order item by using the trained work order content recognition model includes: Determine the type of work order to be filled; Based on the work order category, determining the work order item; The text data is matched with the work order item based on the trained work order content recognition model, and the text data is filled into the corresponding work order item after the match is successful.

[0011] In a second aspect, an embodiment of the present invention further provides a work order automatic filling device, the work order automatic filling device comprising: A first acquisition module, used to acquire voice information data; The recognition module is used to recognize the voice information data through the trained work order content recognition model, obtain the corresponding text data, and fill the text data into the corresponding work order item, which is a required item in the work order.

[0012] In a third aspect, an embodiment of the present invention further provides a work order automatic filling system, the work order automatic filling system comprising: a work order automatic filling 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 method for automatically filling out work orders provided in an 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 in the method for automatically filling out a work order provided in an 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 by a trained work order content recognition model to obtain corresponding text data, and the text data is filled in the corresponding work order item, which is a required item in the work order. The trained work order content recognition model can recognize the acquired user voice information data, extract the filled-in content in the work order item, reduce the learning cost and application cost of work order release and management, and improve the accuracy of the work order. 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 automatic filling system provided by an embodiment of the present invention; Figure 2 is a flow chart of a method for automatically filling out a work order provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of another work order automatic filling device provided in 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] like Figure 1 As shown, Figure 1It is an architecture diagram of a work order automatic filling system 100 provided by an embodiment of the present invention, and the work order automatic filling system includes: a work order automatic filling device 300, a server 101 and an intelligent terminal 102. Among them, the above-mentioned work order automatic filling device 300 also includes a first acquisition module, which can be used to obtain voice information data; a recognition module, which can be used to recognize the voice information data through a trained work order content recognition model, obtain corresponding text data, and fill the text data into the corresponding work order item, which is a required item in the work order.

[0020] Specifically, the above-mentioned voice information data may include but is not limited to the audio signal or voice stream provided by the user through voice input, which may also include the user's voice content, and may contain voice waveforms, spectrum data or other digitized audio information in the voice. The above-mentioned voice information data can also be captured by an audio sensor (such as a microphone) and transmitted to a subsequent processing module for analysis.

[0021] The work order content recognition model can be any trained artificial intelligence model and can be used to process the work content of work order content recognition. Specifically, the work order content recognition model can convert voice information data into structured text data, and can also understand and recognize the intention of the user's voice by learning a large amount of work order content, tags related to the work order content, and required items, and then convert the voice into corresponding text content.

[0022] The above-mentioned text data may include but is not limited to text information extracted from voice information data through a work order content recognition model. Generally speaking, the above-mentioned text data is usually in text form of the content required to be filled in the work order, representing a text description of specific items in the work order (such as customer information, event description, etc.).

[0023] The above-mentioned work order items may be specific content or fields that need to be filled in the work order. Specifically, each work order is usually composed of multiple work order items, and these items correspond to specific information categories, such as "customer name", "event type", "priority", etc. More specifically, in this embodiment, the above-mentioned work order items may specifically refer to the content that must be filled in the work order, that is, the required items.

[0024] The above-mentioned work order automatic filling system recognizes the above-mentioned voice information data through a trained work order content recognition model, converts it into corresponding text data, and fills the text data into the corresponding work order item according to the work order content.

[0025] Through voice recognition and automatic data filling, work orders can be completed quickly, shortening the work cycle and improving overall work efficiency. At the same time, it also reduces the risk of human omissions, ensures the integrity and consistency of the work order content, and improves customer service quality and response speed.

[0026] like Figure 2 As shown, Figure 2 : is a flow chart of a method for automatically filling in a work order provided by an embodiment of the present invention, and the method for automatically filling in a work order comprises the steps of: 201. Acquire voice information data.

[0027] In an embodiment of the present invention, the above-mentioned work order automatic filling method can be applied to the above-mentioned work order automatic filling system. The above-mentioned work order automatic filling system has functions such as work order data processing, work order data sending and receiving, and work order data memory storage, and can be constructed based on a server or a server cluster. The above-mentioned server or server cluster can be an electronic device with work order data processing capabilities.

[0028] The above-mentioned voice information data may include but is not limited to the audio signal or voice stream provided by the user through voice input, which may also include the user's voice content, and may contain voice waveforms, spectrum data or other digitized audio information in the voice. The above-mentioned voice information data can also be captured by an audio sensor (such as a microphone) and transmitted to a subsequent processing module for analysis.

[0029] 202. The voice information data is recognized through the trained work order content recognition model to obtain the corresponding text data, and the text data is filled in the corresponding work order item, which is a required item in the work order.

[0030] In an embodiment of the present invention, the work order content recognition model can be any trained artificial intelligence model, and can be used to process the work content of work order content recognition. Specifically, the work order content recognition model can convert voice information data into structured text data, and can also understand and recognize the intention of the user's voice by learning a large amount of work order content, tags related to the work order content, and required items, and then convert the voice into corresponding text content.

[0031] The above-mentioned text data may include but is not limited to text information extracted from voice information data through a work order content recognition model. Generally speaking, the above-mentioned text data is usually in text form of the content required to be filled in the work order, representing a text description of specific items in the work order (such as customer information, event description, etc.).

[0032] The above-mentioned work order items may be specific content or fields that need to be filled in the work order. Specifically, each work order is usually composed of multiple work order items, and these items correspond to specific information categories, such as "customer name", "event type", "priority", etc. More specifically, in this embodiment, the above-mentioned work order items may specifically refer to the content that must be filled in the work order, that is, the required items.

[0033] The above recognition process may be a process in which the above trained work order content recognition model starts to recognize the voice information data and converts the voice into text data according to the user's intention. For example, the user may say "the equipment is faulty and needs to be repaired", and the system parses this sentence through the voice recognition model, recognizes the two key points "equipment failure" and "repair", and generates corresponding text data.

[0034] The above filling process can be a process in which the above work order automatic filling system judges according to the type and attributes of the filled work order, and fills the corresponding text data into the corresponding work order item. For example, if the user's voice information data mentions "equipment failure", the system will fill "equipment failure" into the "fault description" item; if it mentions "maintenance", it will fill "maintenance" into the "handling method" item. This process is realized through the recognition module and the preset matching rules.

[0035] In the embodiment of the present invention, voice information data is obtained; the voice information data is recognized by a trained work order content recognition model to obtain corresponding text data, and the text data is filled in the corresponding work order item, which is a required item in the work order. Through the trained work order content recognition model, the obtained user voice information data can be recognized, and the filled-in content in the work order item can be extracted from it, thereby reducing the learning cost and application cost of work order release and management, and improving the accuracy of the work order.

[0036] Optionally, in the step of acquiring voice information data, the user's voice data may be recognized by an audio sensor to obtain voice information data to be processed; and the voice information to be processed may be pre-processed to obtain voice information data.

[0037] In the embodiment of the present invention, the audio sensor may be any sensor module that can capture voice signals in the environment and convert them into digital audio data.

[0038] The above-mentioned voice information data to be processed can be the original voice data received from the audio sensor, in the state before the preliminary preprocessing step, specifically, the content input by the user through voice, but it may also contain noise, fuzzy or other irregular parts, which require further processing and cleaning before it can be used for subsequent voice recognition or analysis.

[0039] The above-mentioned preprocessing may refer to a series of processing operations on the original voice data during the voice recognition process to ensure that the data is more accurate and clear in the subsequent recognition steps. Specifically, it can improve the accuracy of recognition by removing interference information, enhancing voice quality, and extracting useful features. The specific steps may include the following schemes for preprocessing: Noise removal: Voice data is often accompanied by background noise (such as environmental noise, wind noise, traffic noise, etc.), which will interfere with the normal operation of the voice recognition system. Noise removal technology aims to remove these irrelevant sounds and retain only the effective part of the user's voice. Common noise removal methods include spectrum subtraction and time domain filtering. Echo cancellation: In some cases, especially when recording with a microphone, echoes may occur, which can affect the clarity and quality of speech. Echo cancellation technology improves the quality of speech signals by analyzing the original signal and subtracting the echo component from it. Speech enhancement, the purpose of speech enhancement is to improve the clarity of speech and make it easier for the recognition system to understand. This can be done through methods such as volume adjustment and frequency smoothing. For example, the high-frequency components in the speech signal can be enhanced to make it clearer and easier to recognize. Speech segmentation: Speech data is usually a continuous audio stream containing multiple language units (such as words, syllables, etc.). Speech segmentation technology divides the continuous speech signal into short time frames or phonemes for subsequent analysis. This helps the system to more accurately identify each unit in the speech; Feature extraction is a key step in preprocessing. It converts the original speech signal into digital features that can be processed by computers. Common feature extraction methods include Mel-frequency cepstral coefficients (MFCC), filter banks, linear predictive coding (LPC), etc. These features can effectively express the audio characteristics of speech. Silence removal: The silence before and after the user speaks will be removed to reduce the amount of useless data, improve recognition efficiency, and avoid the system processing irrelevant information.

[0040] In a possible embodiment, the above-mentioned work order automatic filling system receives the user's voice input through an audio sensor, converts it into digital voice data, and obtains voice information data with corresponding characteristics after preprocessing the voice data.

[0041] After preprocessing, the above-mentioned automatic work order filling system obtains high-quality "voice information data", which will be passed as input to the speech recognition model. The recognition model accurately converts voice information into text data through the trained algorithm. This process improves the accuracy and efficiency of automatic work order filling, reduces the need for manual intervention, thereby optimizing the user experience and improving work efficiency.

[0042] Optionally, before the trained work order content recognition model is used to recognize the voice information data and obtain the corresponding text data, the step also includes obtaining the work order content recognition model to be trained and a training work order sample set; based on the work order content, the required items corresponding to the work order content, and the content labels corresponding to the required items, the work order content recognition model to be trained is iteratively trained, and the trained work order content recognition model is obtained after the iterative training is completed.

[0043] In an embodiment of the present invention, the above-mentioned training work order sample set may include, but is not limited to, work order filled-in content, mandatory items corresponding to the work order filled-in content, and filled-in content labels corresponding to the mandatory items.

[0044] The above-mentioned work order content can be specific information or data that the user or system needs to fill in on the work order. Specifically, these contents usually include descriptions, detailed information or instructions for specific work order tasks. For example, in an equipment maintenance work order, the work order content may include fault description, maintenance method, repair time and other information.

[0045] The above-mentioned mandatory items corresponding to the work order content may refer to the content items that must be filled in when processing the work order. Specifically, each mandatory item corresponds to one or more specific information in the work order content. For example, the work order may have mandatory items such as "fault description", "maintenance time", and "processing results". Therefore, the above-mentioned work order automatic filling system must ensure that these mandatory items are filled in completely in the work order, otherwise the work order will not be submitted or processed. That is, the mandatory items are the most important part of the work order, ensuring the integrity and validity of the work order.

[0046] The above-mentioned content labels corresponding to the required items can be specific text labels or categories corresponding to the required items in the work order, which are used to identify the relationship between the user's voice or other input and the work order content. Specifically, during the training process, the labels help the model recognize and understand which work order item each voice input should be filled in. For example, the required item "fault description" may have a label "fault information", while the required item "handling method" may have a label "maintenance method".

[0047] In a possible embodiment, the above-mentioned work order automatic filling system obtains the work order content recognition model to be trained and its corresponding training work order sample set, and uses the above-mentioned training work order sample set for training according to the corresponding labels. When the data output by the model reaches a certain similarity interval with the label data, the training is completed.

[0048] Through iterative training, the work order content recognition model is continuously optimized, enabling it to better understand and process various voice information, thereby improving the accuracy and robustness of voice recognition. Each iterative optimization makes the model more stable in practical applications, especially when processing different voice inputs (such as user accents, speaking speed or environmental noise interference). It can provide high-precision recognition results, thereby effectively realizing automated work order filling.

[0049] Optionally, in the step of identifying voice information data through a trained work order content recognition model to obtain corresponding text data, it also includes vector processing of the voice information to obtain feature vector data corresponding to at least one voice information data; based on the feature vector data, the corresponding text data is determined.

[0050] In the embodiment of the present invention, the above-mentioned vector processing process may refer to converting speech information into a numerical form (i.e., a feature vector) that can be processed by a computer, so as to facilitate subsequent operations such as speech recognition, intent understanding, and content matching. Specifically, it may be performed in the following manner: Speech-to-text conversion, which is converted into text through an ASR system, converting audio signals into characters or words, but the text itself is still in a plain text form, and the computer does not understand the meaning; TF-IDF (Term Frequency-Inverse Document Frequency): Evaluates the importance of a word in a document and generates a weighted vector; Extraction of feature vectors,In the process of vector processing, feature extraction is performed on the text, that is, useful information is extracted from the text to help the recognition system perform better matching and classification, for example, word frequency (TF): the frequency of a word appearing in the text, sentiment analysis: judging the sentiment tendency of the sentence (positive, negative, neutral), entity recognition: identifying key entities in the text (such as "equipment failure", "replace battery", etc.).

[0051] Vector matching and classification,Once the text is converted into a feature vector, it can be matched with the corresponding required items in the work order through vector matching or classification algorithms.,For example, similarity calculation (such as cosine similarity) is used to determine whether a vector matches the work order item "fault description", so that its content can be automatically filled in the work order.

[0052] Through vector processing, the system can more accurately understand and process complex voice information, reduce errors in voice recognition, and improve the automation and accuracy of work order filling. In addition, the vectorized representation method also enables the system to handle a large number of different voice inputs, with greater adaptability and flexibility.

[0053] Optionally, in the step of identifying the voice information data through the trained work order content recognition model to obtain the corresponding text data, it also includes processing the voice information data according to user needs and user language characteristics to obtain target voice information data; based on the target voice information data, determining the corresponding text data.

[0054] In an embodiment of the present invention, the above-mentioned user needs may refer to the expectations or requirements expressed by the user through voice in a specific situation, such as functional needs, information needs, and contextual needs. For example, if the user says "device failure, cannot be turned on", the system needs to identify "device failure" as the fault description, and further identify "cannot be turned on" as the problem details. This is the user's demand in voice input, and the system needs to automatically fill in the work order items based on this information.

[0055] The above user language characteristics may refer to the individual characteristics and habits displayed by the user when using language. Each person has a different language style. These language characteristics may include accent, speaking speed, word usage habits, grammatical structure, etc. For example, accent, pronunciation, speaking speed, intonation, vocabulary habits, etc.; In a possible embodiment, the above-mentioned work order automatic filling system performs analysis based on the specific needs of the user. For example, if the user is filling out a work order for equipment failure, the above-mentioned work order automatic filling system will automatically identify the content related to the equipment problem and maintenance requirements in the voice, and adjust the voice processing algorithm by recognizing the user's language characteristics, such as the user's accent, speaking speed, grammatical habits, etc., to ensure that the above-mentioned work order automatic filling system can understand the user's actual needs. For example, some users may prefer to use "repair" instead of "maintenance", and the system needs to understand and adapt to this language difference.

[0056] By optimizing the implementation steps of this embodiment, clear target voice information data that meets user needs can be obtained, which not only improves the accuracy of voice recognition, but also ensures that the content filled in the work order is highly consistent with the user's actual needs, ultimately greatly improving work efficiency and the accuracy of work order processing.

[0057] Optionally, the step of filling the text data into the corresponding work order item through the trained work order content recognition model also includes determining the work order category to be filled in; determining the work order item based on the work order category; matching the text data with the work order item based on the trained work order content recognition model, and filling the text data into the corresponding work order item after a successful match.

[0058] In an embodiment of the present invention, the above-mentioned work order automatic filling system determines the work order category, such as equipment maintenance work order, installation service work order, etc., and further determines the work order items that need to be filled in according to the work order category, such as "fault description", "maintenance plan" or "processing result", and then matches the text data converted from the user's voice with the preset work order items. For example, if the user's voice mentions "the device cannot start", the system will match the text data with the work order item "fault description", and after the match is successful, the recognized text data will be filled in the corresponding work order item.

[0059] Through this process, the information entered by the user can be filled into the work order efficiently and accurately, which improves the level of automation of work order filling. Compared with traditional manual filling, this automatic matching and filling method not only saves time, but also effectively avoids human errors and improves the accuracy and work efficiency of work order processing.

[0060] like Figure 3 As shown, the embodiment of the present invention further provides a work order automatic filling device 300, which includes: The first acquisition module 301 is used to acquire voice information data; The recognition module 302 is used to recognize the voice information data through the trained work order content recognition model, obtain corresponding text data, and fill the text data into the corresponding work order item, which is a required item in the work order.

[0061] Optionally, the first acquisition module 301 includes: The first acquisition submodule is used to recognize the user's voice data through an audio sensor to obtain voice information data to be processed; The second acquisition submodule is used to pre-process the voice information data to be processed to obtain voice information data.

[0062] Optionally, the above device further comprises: A second acquisition module is used to acquire a work order content recognition model to be trained and a training work order sample set, wherein the training work order sample set includes work order content, mandatory items corresponding to the work order content, and content labels corresponding to the mandatory items; The training module is used to iteratively train the work order content recognition model to be trained based on the work order content, the required items corresponding to the work order content, and the filled-in content labels corresponding to the required items, and obtain the trained work order content recognition model after the iterative training is completed.

[0063] Optionally, the identification module 302 includes: A first processing submodule, configured to perform vector processing on the voice information data to obtain feature vector data corresponding to at least one voice information data; The first determination submodule is used to determine corresponding text data based on the feature vector data.

[0064] Optionally, the above device further comprises: The second processing submodule is used to process the voice information data according to user needs and user language characteristics to obtain target voice information data; The second determination submodule is used to determine corresponding text data based on the target voice information data.

[0065] Optionally, the identification module 302 includes: The third determination submodule is used to determine the type of work order filled in; A fourth determination submodule, configured to determine the work order item based on the work order category; The filling submodule is used to match the text data with the work order item based on the trained work order content recognition model, and fill the text data into the corresponding work order item after the match is successful.

[0066] 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 of the above-mentioned work order automatic filling methods.

[0067] Specifically, it includes a processor 401 and a memory 402, and a computer program for executing the method for automatically filling in a work order, which is stored in the memory 402 and can be run on the processor 401, wherein: The processor 401 runs the computer program of the work order automatic filling method stored in the memory 402, and performs the following steps: Acquire voice information data; The voice information data is recognized through the trained work order content recognition model to obtain corresponding text data, and the text data is filled in the corresponding work order item, which is a required item in the work order.

[0068] Optionally, the processor 401 executes the acquiring of voice information data, including: The user's voice data is recognized through the audio sensor to obtain the voice information data to be processed; The voice information data to be processed is preprocessed to obtain voice information data.

[0069] Optionally, before the processor 401 executes the trained work order content recognition model to recognize the voice information data and obtain corresponding text data, the method further includes: Obtain a work order content recognition model to be trained and a training work order sample set, wherein the training work order sample set includes work order content, mandatory items corresponding to the work order content, and content labels corresponding to the mandatory items; Based on the work order content, the required items corresponding to the work order content, and the filled-in content labels corresponding to the required items, the work order content recognition model to be trained is iteratively trained, and a trained work order content recognition model is obtained after the iterative training is completed.

[0070] Optionally, the processor 401 executes the trained work order content recognition model to recognize the voice information data to obtain corresponding text data, including: Performing vector processing on the voice information data to obtain feature vector data corresponding to at least one voice information data; Based on the feature vector data, corresponding text data is determined.

[0071] Optionally, the processor 401 executes the trained work order content recognition model to recognize the voice information data to obtain corresponding text data, and the method further includes: Processing the voice information data according to user needs and user language characteristics to obtain target voice information data; Based on the target voice information data, corresponding text data is determined.

[0072] Optionally, the processor 401 further executes the trained work order content recognition model to fill the text data into the corresponding work order item, including: Determine the type of work order to be filled; Based on the work order category, determining the work order item; The text data is matched with the work order item based on the trained work order content recognition model, and the text data is filled into the corresponding work order item after the match is successful.

[0073] 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 automatic filling method or the application-side work order automatic filling 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.

[0074] 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).

[0075] 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 automatically filling out a work order, characterized in that: include: Acquire voice information data; The voice information data is recognized through a trained work order content recognition model to obtain corresponding text data, and the text data is filled in the corresponding work order item, which is a required item in the work order.

2. The work order automatic filling method according to claim 1, characterized in that: The acquiring of voice information data comprises: The user's voice data is recognized through the audio sensor to obtain the voice information data to be processed; The voice information data to be processed is preprocessed to obtain voice information data.

3. The work order automatic filling method according to claim 1, characterized in that: Before the voice information data is recognized by the trained work order content recognition model to obtain corresponding text data, the method further includes: Obtaining a work order content recognition model to be trained and a training work order sample set, wherein the training work order sample set includes work order content, mandatory items corresponding to the work order content, and content labels corresponding to the mandatory items; Based on the work order content, the required items corresponding to the work order content, and the filled-in content labels corresponding to the required items, the work order content recognition model to be trained is iteratively trained, and a trained work order content recognition model is obtained after the iterative training is completed.

4. The work order automatic filling method according to claim 1, characterized in that: The voice information data is recognized by the trained work order content recognition model to obtain corresponding text data, including: Performing vector processing on the voice information data to obtain feature vector data corresponding to at least one voice information data; Based on the feature vector data, corresponding text data is determined.

5. The method for automatically filling out a work order as claimed in claim 4, characterized in that: The method further comprises: recognizing the voice information data by using the trained work order content recognition model to obtain corresponding text data; Processing the voice information data according to user needs and user language characteristics to obtain target voice information data; Based on the target voice information data, corresponding text data is determined.

6. The method for automatically filling out a work order as claimed in claim 1, characterized in that: The step of filling the text data into the corresponding work order item through the trained work order content recognition model includes: Determine the type of work order to be filled; Based on the work order category, determining the work order item; The text data is matched with the work order item based on the trained work order content recognition model, and the text data is filled into the corresponding work order item after the match is successful.

7. A work order automatic filling device, characterized in that: include: A first acquisition module, used to acquire voice information data; The recognition module is used to recognize the voice information data through the trained work order content recognition model, obtain the corresponding text data, and fill the text data into the corresponding work order item, which is a required item in the work order.

8. A work order automatic filling system, characterized in that: The work order automatic filling system comprises: a work order automatic filling device; The work order automatic filling device is determined by a work order automatic filling 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 in the method for automatically filling in a work order 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 method for automatically filling in a work order as described in any one of claims 1 to 6 are implemented.

Images