Interaction processing method and apparatus in the field of intelligent manufacturing, computer device, storage medium, and computer program product

Abstract

The present application relates to an interaction processing method and apparatus in the field of intelligent manufacturing, a computer device, a storage medium, and a computer program product. The method comprises: in an interaction scenario in the field of intelligent manufacturing, in response to a query message input operation triggered on an interaction interface, obtaining a manufacturing process query message; on the basis of a historical query interaction message, performing intent recognition and entity extraction on the manufacturing process query message to obtain intent information and entity information; searching a data analysis platform in the field of intelligent manufacturing for a manufacturing index that conforms to the intent information and matches the entity information; and according to the intent information, performing manufacturing process characteristic analysis on manufacturing process data corresponding to the manufacturing index, and displaying, in the interaction interface, obtained visual display data as a response result of the manufacturing process query message. By using the method, the interaction process in the field of intelligent manufacturing is simplified, the time required for an interaction operation is shortened, and the interaction efficiency in the field of intelligent manufacturing is effectively improved.

Description

Interaction processing method and device in field of intelligent manufacturing, computer device, storage medium and computer program product

[0001] The present application claims priority to the Chinese patent application No. 202411304303.2, filed on September 19, 2024, entitled "Interaction processing method and device in field of intelligent manufacturing, computer device, storage medium and computer program product", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the technical field of computer, in particular to an interaction processing method and device in field of intelligent manufacturing, computer device, storage medium and computer program product. BACKGROUND

[0003] With the continuous development of various technical fields, the professionalism of the industry is becoming stronger and stronger. In a specific industry, there are usually various professional terms and industry-specific languages.

[0004] Taking the manufacturing industry as an example, a large amount of raw data is generated by the manufacturing production line, and these raw data need to be analyzed by professionals to understand the specific meaning. For data queries in specific fields such as manufacturing industry, a series of operation steps such as user login to a specific system, data query, data analysis, etc. are usually required to obtain the data results required by the user, thereby resulting in the problem of low interaction efficiency in the interactive scenario of data query in the field of intelligent manufacturing. SUMMARY

[0005] Therefore, it is necessary to provide an interaction processing method and device in field of intelligent manufacturing, computer device, computer readable storage medium and computer program product capable of improving the interaction efficiency.

[0006] In a first aspect, the present application provides an interaction processing method in field of intelligent manufacturing. The method comprises:

[0007] In the interactive scenario in the field of intelligent manufacturing, in response to an inquiry message input operation triggered in an interactive interface, obtaining an input manufacturing process inquiry message;

[0008] Based on a historical inquiry interactive message corresponding to the manufacturing process inquiry message, performing intent recognition and entity extraction on the manufacturing process inquiry message to obtain intent information and entity information;

[0009] From a data analysis platform in the field of intelligent manufacturing, finding a manufacturing index that conforms to the intent information and matches the entity information;

[0010] According to the intention information, manufacturing process characteristic analysis is performed on manufacturing process data corresponding to the manufacturing index, to obtain visualization display data representing manufacturing process characteristics;

[0011] The visualization display data is displayed in the interactive interface as a response result of the manufacturing process inquiry message.

[0012] In a second aspect, the present application further provides an interactive processing device in the field of intelligent manufacturing. The device comprises:

[0013] An input processing module is configured to, in an interactive scenario in the field of intelligent manufacturing, obtain an input manufacturing process inquiry message in response to an inquiry message input operation triggered in an interactive interface;

[0014] An intention recognition and entity extraction module is configured to perform intention recognition and entity extraction on the manufacturing process inquiry message based on historical inquiry interactive messages corresponding to the manufacturing process inquiry message, to obtain intention information and entity information;

[0015] An index searching module is configured to search, from a data analysis platform in the field of intelligent manufacturing, a manufacturing index that meets the intention information and matches the entity information;

[0016] A manufacturing process characteristic analysis module is configured to perform manufacturing process characteristic analysis on manufacturing process data corresponding to the manufacturing index according to the intention information, to obtain visualization display data representing manufacturing process characteristics;

[0017] A visualization display module is configured to display the visualization display data in the interactive interface as a response result of the manufacturing process inquiry message.

[0018] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0019] In an interactive scenario in the field of intelligent manufacturing, a manufacturing process inquiry message is obtained in response to an inquiry message input operation triggered in an interactive interface;

[0020] Intention recognition and entity extraction are performed on the manufacturing process inquiry message based on historical inquiry interactive messages corresponding to the manufacturing process inquiry message, to obtain intention information and entity information;

[0021] A manufacturing index that meets the intention information and matches the entity information is searched from a data analysis platform in the field of intelligent manufacturing;

[0022] According to the intention information, manufacturing process characteristic analysis is performed on the manufacturing process data corresponding to the manufacturing index, to obtain visualization display data representing manufacturing process characteristics;

[0023] The visualization display data is displayed in the interactive interface as a response result of the manufacturing process inquiry message.

[0024] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the following steps:

[0025] In an interactive scenario in the field of intelligent manufacturing, a manufacturing process inquiry message is obtained in response to an inquiry message input operation triggered in an interactive interface;

[0026] Based on historical inquiry interactive messages corresponding to the manufacturing process inquiry message, intention recognition and entity extraction are performed on the manufacturing process inquiry message, to obtain intention information and entity information;

[0027] From a data analysis platform in the field of intelligent manufacturing, a manufacturing index is found that matches the intention information and the entity information;

[0028] According to the intention information, manufacturing process characteristic analysis is performed on the manufacturing process data corresponding to the manufacturing index, to obtain visualization display data representing manufacturing process characteristics;

[0029] The visualization display data is displayed in the interactive interface as a response result of the manufacturing process inquiry message.

[0030] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program is executed by a processor to implement the following steps:

[0031] In an interactive scenario in the field of intelligent manufacturing, a manufacturing process inquiry message is obtained in response to an inquiry message input operation triggered in an interactive interface;

[0032] Based on historical inquiry interactive messages corresponding to the manufacturing process inquiry message, intention recognition and entity extraction are performed on the manufacturing process inquiry message, to obtain intention information and entity information;

[0033] From a data analysis platform in the field of intelligent manufacturing, a manufacturing index is found that matches the intention information and the entity information;

[0034] According to the intention information, manufacturing process characteristic analysis is performed on the manufacturing process data corresponding to the manufacturing index, and visual display data representing manufacturing process characteristics is obtained.

[0035] The visual display data is displayed in the interactive interface as a response result of the manufacturing process inquiry message.

[0036] The above-mentioned interactive processing method and device in the field of intelligent manufacturing, computer equipment, storage medium and computer program product can, in the interactive scenario in the field of intelligent manufacturing, obtain an input manufacturing process inquiry message in response to an inquiry message input operation triggered in an interactive interface, perform intention recognition and entity extraction on the manufacturing process inquiry message based on historical inquiry interactive messages corresponding to the manufacturing process inquiry message, accurately understand the specific intention information and interactive related entity information of the user's current interactive operation, facilitate accurate acquisition of matched manufacturing process data for data analysis, accurately find manufacturing process data in the data acquisition process by searching for manufacturing indexes that match the intention information and the entity information from a data analysis platform in the field of intelligent manufacturing, perform manufacturing process characteristic analysis on manufacturing process data corresponding to the manufacturing indexes according to the intention information, obtain visual display data representing manufacturing process characteristics, and finally display the visual display data in the interactive interface as a response result of the manufacturing process inquiry message. Only simple interactive operations are required to obtain the data interaction result in the field of intelligent manufacturing in a visual manner. Not only can the manufacturing process data be obtained for manufacturing process characteristic analysis to obtain intuitively displayed data results through intention recognition and information extraction, but also the interactive process is simplified and the time required for the interactive operation is shortened, thereby effectively improving the interactive efficiency in the field of intelligent manufacturing. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0038] FIG. 1 is an application environment diagram of an interactive processing method in the field of intelligent manufacturing in one embodiment;

[0039] FIG. 2 is a flowchart of an interactive processing method in the field of intelligent manufacturing in one embodiment;

[0040] FIG. 3 is a flowchart of an interactive processing method in the field of intelligent manufacturing in another embodiment;

[0041] FIG. 4 is a schematic diagram of a text transcription process of a voice message in an embodiment;

[0042] FIG. 5 is a schematic diagram of a flow of an intent recognition and entity extraction process in an embodiment;

[0043] FIG. 6 is a schematic diagram of an interaction between a computer device and a data analysis platform in an embodiment;

[0044] FIG. 7 is a structural block diagram of an interaction processing apparatus in the field of intelligent manufacturing in an embodiment;

[0045] FIG. 8 is an internal structural diagram of a computer device in an embodiment;

[0046] FIG. 9 is an internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0048] The terms “first”, “second”, “third”, and “fourth” and the like in the specification of the present application and the claims and the drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a list of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed, or can optionally include other steps or units inherent to such processes, methods, products, or devices.

[0049] In this document, the term “embodiment” means that a particular feature, result, or characteristic described in connection with an embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it mutually exclusive or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0050] The interaction processing method in the field of intelligent manufacturing provided by the embodiments of the present application can be applied in an application environment as shown in FIG. 1. Among them, the terminal 102, the server 104, the data analysis platform 106 communicate through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other servers. The server 104 responds to the inquiry message input operation triggered by the user on the interactive interface of the terminal 102 in the interactive scenario in the field of intelligent manufacturing, determines the input manufacturing process inquiry message; based on the historical inquiry interaction message corresponding to the manufacturing process inquiry message, the intent recognition and entity extraction of the manufacturing process inquiry message are performed to obtain the intent information and entity information; from the data analysis platform 106 in the field of intelligent manufacturing, find the manufacturing index that matches the intent information and matches the entity information; according to the intent information, the manufacturing process data corresponding to the manufacturing index is analyzed to obtain the visual display data representing the manufacturing process characteristics; the visual display data is taken as the response result of the manufacturing process inquiry message, and the visual display data is displayed on the interactive interface of the terminal 102.

[0051] Among them, the terminal 102 can be, but is not limited to, various desktop computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0052] In one embodiment, as shown in FIG. 2, an interaction processing method in the field of intelligent manufacturing is provided. Taking the computer device as an example, the computer device can be a server with interactive function, which can complete the interaction and data analysis process based on the server. The computer device can also be a system composed of a terminal and a server, the terminal provides the function of interacting with the user, and reports the signal corresponding to the interaction operation to the server, and the server performs background data analysis and processing, and feeds back the final result obtained by analysis to the terminal to display to the user triggering the interaction operation. In addition, the computer device can also be a terminal with strong computing power, which can not only respond to the user's interaction operation in the terminal, but also obtain the final result directly in the terminal through data analysis. Specifically, the computer device implements the interaction processing method in the field of intelligent manufacturing, specifically including the following steps:

[0053] Step 202, in the interactive scenario in the field of intelligent manufacturing, the input manufacturing process inquiry message is obtained in response to the inquiry message input operation triggered on the interactive interface.

[0054] The intelligent manufacturing field is a new production mode with the characteristics of self-perception, self-decision, self-execution, self-adaptation, and self-learning, based on the deep integration of new-generation information technology and advanced manufacturing technology, and involving all or part of the processes in the design, production, management, and service of manufacturing activities.

[0055] The interactive scenario in the intelligent manufacturing field refers to a scenario that can provide an interactive interface to realize human-computer interaction in a specific industry environment. For example, in the manufacturing industry, a computer device can provide an interactive interface for a manufacturing scenario, a user can trigger an interactive operation for the interactive interface, and the computer device can analyze the characteristics of the corresponding manufacturing process by responding to the interactive operation and feed back the interactive result to the user, thereby realizing human-computer interaction.

[0056] The interactive interface is a display page that provides a human-computer interaction interface to the user. Specifically, the interactive interface can display specific operation modes for human-computer interaction, facilitating the user in the intelligent manufacturing field or the non-intelligent manufacturing field to understand the specific human-computer interaction mode and trigger the interactive operation. In addition, the interactive interface can also be used to display the results obtained by analyzing the data after responding to the interactive operation, so that the user can trigger the interactive operation and view the response result of the interactive operation in the same interactive interface.

[0057] The inquiry message input operation is a specific implementation mode of human-computer interaction. The inquiry message input operation can specifically include a text input operation and a voice input operation. The computer device can provide input interfaces of various inquiry message input modes, and the input interfaces can be integrated into an input control. The user can input the manufacturing process inquiry message by selecting the corresponding input control.

[0058] The manufacturing process inquiry message is an input message that can be used to inquire about manufacturing process data to directly obtain a visual display result, input by the user through the interactive interface. The message type of the manufacturing process inquiry message can specifically include a voice message and a text message. For example, the interactive interface can display a text input control and a voice input control, facilitating the user to select the desired interactive mode to input the manufacturing process inquiry message. In one embodiment, after the user clicks the text input control, a text message can be input through an input device such as a physical keyboard or a virtual keyboard. In another embodiment, after the user clicks the voice input control, the computer device can activate a voice collection device such as a microphone to collect the user's voice and obtain a voice message.

[0059] In a specific embodiment, in an interactive scenario in the field of intelligent manufacturing, in an interactive interface, a text input control and a voice input control can be displayed for a user to select an interaction mode. If the user selects the text input control in the interactive interface to invoke an input panel, the computer device can obtain a manufacturing process inquiry message with a message category of text in response to a text input operation triggered in the input panel. If the user selects the voice input control in the interactive interface and triggers a voice input operation, the computer device can obtain a manufacturing process inquiry message with a message category of voice in response to the voice input operation.

[0060] In step 204, intent recognition and entity extraction are performed on the manufacturing process inquiry message based on a historical inquiry interactive message corresponding to the manufacturing process inquiry message, to obtain intent information and entity information.

[0061] The historical inquiry interactive message is a historical message corresponding to an interaction that occurred before the input of the manufacturing process inquiry message. The computer device can obtain the historical inquiry interactive message corresponding to the manufacturing process inquiry message through historical data searching. Specifically, the historical inquiry interactive message of the manufacturing process inquiry message can be a historical message corresponding to an interaction that occurred once or N times before by the same logged-in user, or a historical message corresponding to an interaction that occurred within a preset historical time period. The message type of the historical inquiry interactive message can be the same as or different from that of the manufacturing process inquiry message. For example, the manufacturing process inquiry message is a text message, and the historical inquiry interactive message can be a text message or a voice message. Specifically, the acquisition strategy of the historical inquiry interactive message of the manufacturing process inquiry message can be set according to the needs of specific application scenarios, which is not limited herein.

[0062] Intent recognition is a process for determining the intent or purpose expressed in a user's input sentence. The result obtained through intent recognition is the intent information. Simply put, intent recognition is a semantic understanding of a user's speech in order to better answer the user's questions or provide related services. In continuous multiple dialogues, according to the user's usual language expression habit, the manufacturing process inquiry message that can be input is not a complete sentence. Therefore, intent recognition needs to be performed on the manufacturing process inquiry message based on the historical inquiry interactive message corresponding to the manufacturing process inquiry message, so as to accurately understand the real intent of the manufacturing process inquiry message input by the user this time. Entity recognition is a process for recognizing entity words with specific meanings in the manufacturing process inquiry message. The result obtained through entity recognition is the entity information.

[0063] In some specific embodiments, taking the manufacturing process inquiry message as a text message for example, after obtaining the historical inquiry interaction message corresponding to the text message, the computer device can directly take the text in the text message as the processing object, perform intent recognition on the text corresponding to the historical inquiry interaction message to obtain intent information, and perform entity recognition processing on the text to obtain entity information.

[0064] In other specific embodiments, taking the manufacturing process inquiry message as a voice message for example, after obtaining the historical inquiry interaction message corresponding to the text message, the computer device can first transcribe the voice message into text, and based on the transcribed text, perform intent recognition on the text corresponding to the historical inquiry interaction message to obtain intent information, and perform entity recognition processing on the text to obtain entity information.

[0065] Step 206, find a manufacturing indicator that matches the intent information and matches the entity information from the data analysis platform in the field of intelligent manufacturing.

[0066] Among them, the data analysis platform is a manufacturing process characteristic analysis platform specially used for managing and analyzing data in the field of intelligent manufacturing. Taking manufacturing industry as an example, the data analysis platform of manufacturing industry can be built based on manufacturing execution system (MES) or other industrial systems, so as to collect and analyze data related to production line. Enterprises can use the data analysis platform of manufacturing industry to help monitor the performance of production line, optimize production process, and improve overall efficiency. The computer device is connected with the data analysis platform through network, and can realize data interaction with the data analysis platform, such as data query and data acquisition.

[0067] Data indicator is a measurement standard used to match different dimensional data in the field of intelligent manufacturing. Different intent information corresponds to different data indicators, and different entity information may also correspond to different data indicators. The manufacturing indicator can be a set of two or more manufacturing data indicators. In some embodiments, the manufacturing indicator at least contains a data indicator corresponding to the intent information and a data indicator corresponding to the entity information. The data analysis platform can find manufacturing process data that matches the intent information and matches the entity information based on the manufacturing indicator, and feed back the manufacturing process data to the computer device.

[0068] In some embodiments, after the computer device performs the intent recognition and entity extraction on the manufacturing process inquiry message to obtain the intent information and the entity information, the computer device can send the intent information and the entity information to the data analysis platform, and the data analysis platform can find the manufacturing index that matches the intent information and the entity information, and then the computer device can find the manufacturing process data corresponding to the manufacturing index according to the manufacturing index. In the case that the computer device itself stores various data indexes of the data analysis platform, the computer device can also obtain the manufacturing index that matches the intent information and the entity information through data index matching processing, and send the manufacturing index to the data analysis platform, find the manufacturing index from the data analysis platform, and then obtain the manufacturing process data corresponding to the manufacturing index.

[0069] In step 208, the manufacturing process data corresponding to the manufacturing index is analyzed according to the intent information to obtain visual display data representing the manufacturing process characteristics.

[0070] The manufacturing process data refers to various data generated in the manufacturing production process. The manufacturing process data covers various aspects from design to production execution, including but not limited to production tasks, personnel, equipment, materials, process quality, and safety and environmental protection information. For example, the manufacturing process data can include at least one of various data such as production task data, workshop personnel data, production equipment data, production material data, process quality data, and production safety and environmental data.

[0071] The production task data includes production plan and execution data, work order information (such as production start time, intermediate pause time, production end time), work time consumption information, and completion quantity of production plan, etc. These data support statistical analysis of key production management indexes such as beat, production output, plan delivery completion accuracy, and order delivery cycle. The workshop personnel data includes information such as who produces which product model at which workstation, starting time, and completion time record. This kind of data helps to locate the cause when quality problems occur, and also can statistically analyze the work efficiency of personnel. The production equipment data involves the state and tooling data of equipment, the on-off state of equipment, alarm data, real-time data such as running pressure, speed, and temperature. These data support statistical analysis of equipment downtime, calculation of equipment utilization efficiency, and analysis and optimization of equipment parameter setting according to alarm data. The production material data includes the name, quantity, batch of materials, and the time when the materials are accepted and used by the workstation. This kind of data supports accurate control of material demand and inventory level, and ensures quality traceability. The process quality data covers the whole process quality management and control data from raw material inspection to product delivery, such as quality accidents and customer complaint handling. The production safety and environmental data focuses on safety and environmental data in the production process to ensure the compliance of production activities.

[0072] The manufacturing process characteristic analysis is a data processing manner for analyzing and evaluating key characteristics of a manufacturing system to optimize production processes and product quality. The specific processing manner of the manufacturing process characteristic analysis can be determined based on the intention information, such as performing statistics on the production quantity of a day, or calculating the product failure rate of a certain process procedure. The computer device can first obtain manufacturing process data corresponding to a manufacturing index, and then perform manufacturing process characteristic analysis on the manufacturing process data by using the manufacturing process characteristic analysis manner indicated by the intention data to obtain a manufacturing process characteristic analysis result.

[0073] The visual display data refers to a data composition of a presentation form capable of visually displaying the trend and key information of an index. For different categories of manufacturing process characteristic analysis results, a corresponding visual display manner can be pre-configured in the computer device, and a data chart matched with different categories of data samples can be displayed or the manufacturing process characteristic analysis result can be directly displayed. Specifically, the visual display manner can specifically include a bar chart, a line chart, a pie chart, a scatter chart, or a direct numerical display and text description.

[0074] In some embodiments, a series of general data presentation components developed in advance can be configured in the computer device. Each data presentation component can receive data input of different indexes, automatically select a suitable presentation manner according to the structure and configuration of the data, and automatically generate a corresponding chart or text description. The general component has the characteristics of flexible design and high maintainability, so as to adapt to different data structures and presentation requirements. Through the above processing manner, the processing efficiency of converting the manufacturing process characteristic analysis result into visual display data can be further improved. Further, in order to ensure that the user can easily understand and use the data presentation component, the computer device can provide clear legends, tool tips, and operation guides for the data presentation component, and ensure that the chart can be well displayed on different devices and screen sizes by pre-configuring a display adaptation strategy.

[0075] In step 210, the visual display data is displayed in the interactive interface as a response result of the manufacturing process inquiry message.

[0076] The response result of the manufacturing process inquiry message is interactive data used as an answer to the manufacturing process inquiry message. For example, after the user inputs the manufacturing process inquiry message through the interactive interface, the visual display result obtained through data analysis processing will be displayed in the interactive interface as the response result of the manufacturing process inquiry message, so that the user can obtain the data display result by inputting a simple message.

[0077] In some embodiments, in the interactive interface of the computer device, the manufacturing process inquiry message and the visualized display data can be displayed in the form of a dialogue, for example, the user input manufacturing process inquiry message is displayed in a message bubble pointing to a first direction, and the visualized display data obtained through data analysis is displayed in a message bubble pointing to a second direction. The first direction and the second direction are different directions, for example, the first direction is a direction pointing to the right side of the interactive interface, and the second direction is a direction pointing to the left side of the interactive interface, so as to match the interaction habits of general interaction scenarios.

[0078] In other embodiments, in the interactive interface of the computer device, the manufacturing process inquiry message and the visualized display data can be displayed in a time sequence, for example, when the user inputs the manufacturing process inquiry message, a target display is displayed, and after obtaining the visualized display data through manufacturing process characteristic analysis based on the manufacturing process inquiry message, the manufacturing process inquiry message is removed and the visualized display data is displayed, so that there is sufficient space in the display page to display the visualized display data.

[0079] In addition, for the visualized display data displayed in the display page, the user can interact with the visualized display data through operations such as clicking, filtering, or inputting data, and the computer device can respond to the operation to update the chart in real time to reflect the latest data state.

[0080] The above-mentioned interactive processing method in the field of intelligent manufacturing, in the interactive scenario in the field of intelligent manufacturing, through responding to the inquiry message input operation triggered in the interactive interface, obtaining the input manufacturing process inquiry message, then based on the historical inquiry interaction message corresponding to the manufacturing process inquiry message, performing intent recognition and entity extraction on the manufacturing process inquiry message, so as to accurately understand the specific intent information and the entity information related to the interaction of the user's this time interaction operation, facilitate accurate acquisition of matched manufacturing process data for data analysis, in the data acquisition process, by searching for manufacturing indicators that match the intent information and the entity information from the data analysis platform in the field of intelligent manufacturing, the precise search for manufacturing process data can be realized, and then according to the intent information, the manufacturing process data corresponding to the manufacturing indicators is analyzed to obtain visualized display data representing the manufacturing process characteristics, and finally the visualized display data is displayed as the response result of the manufacturing process inquiry message, and the visualized display data is displayed in the interactive interface. Through simple interaction operation, the data interaction result in the field of intelligent manufacturing can be obtained through visualized display, not only the manufacturing process data can be obtained through intent recognition and information extraction for analysis to obtain intuitive display data results, but also the interaction process is simplified and the time required for interaction operation is shortened, thereby effectively improving the interaction efficiency in the field of intelligent manufacturing.

[0081] In some embodiments, as shown in FIG. 3, in the case of a manufacturing process inquiry message being a voice message, the interactive processing method in the field of intelligent manufacturing further includes steps 302 to 308:

[0082] Step 302, based on a non-autoregressive end-to-end speech recognition model, feature extraction is performed on the voice message to obtain a voice feature vector; the non-autoregressive end-to-end speech recognition model is trained based on a sample voice message, and the sample voice message contains professional terms in the field of intelligent manufacturing.

[0083] Step 304, through the self-attention mechanism of the non-autoregressive end-to-end speech recognition model, the voice feature vector is sequentially subjected to feature encoding and context modeling to obtain encoded features.

[0084] Step 306, based on the encoded features, feature integration is performed to obtain integrated features.

[0085] Step 308, text transcription is performed on the integrated features to obtain a message text representing the voice message.

[0086] Further, based on the historical inquiry interactive messages corresponding to the manufacturing process inquiry message, intent recognition and entity extraction are performed on the manufacturing process inquiry message to obtain intent information and entity information, i.e., step 204 includes step 310:

[0087] Step 310, based on the historical inquiry interactive messages corresponding to the manufacturing process inquiry message, intent recognition and entity extraction are performed on the message text to obtain intent information and entity information.

[0088] Among them, the non-autoregressive end-to-end speech recognition model can be a Paraformer model. For ease of description, the Paraformer model is used in the following embodiments. The Paraformer model adopts a non-autoregressive structure and can output all target characters in a single decoding, thereby significantly improving the computational efficiency. Compared with traditional autoregressive models, Paraformer has obvious advantages in decoding speed because it avoids the process of generating target characters one by one and reduces the computational complexity.

[0089] Specifically, in terms of structure, the Paraformer adopts a deep model structure, including multiple encoder and decoder layers, and a specific attention mechanism, which helps to improve the expression ability of the model. Through the non-autoregressive structure design, the Paraformer can generate all target characters in a single decoding, greatly improving the decoding speed.

[0090] In the training process, taking the manufacturing industry in the field of intelligent manufacturing as an example, in order to optimize the unique data set in the manufacturing process, the Paraformer model is specially adjusted and trained. Specifically, it includes: using a large number of manufacturing field recordings to fine-tune the Paraformer model to improve the Paraformer model's ability to recognize specific industry terminology, technical language, and production environment noise. And by introducing manufacturing-related speech data during training, the Paraformer model can better adapt to the unique speech patterns and contexts of this field. Considering the various noise interference that may exist in the production site, the Paraformer model is subjected to model reinforcement training to improve its recognition accuracy in noisy environments.

[0091] In a specific embodiment, for speech messages, it is necessary to transcribe the speech message into message text, and then facilitate subsequent intent recognition and entity extraction processing. Specifically, taking the speech transcription processing by the Paraformer model as an example, as shown in FIG. 4, the processing process of the Paraformer model specifically includes speech input 402, feature extraction 404, feature encoding 406, context modeling 408, feature integration 410, text transcription 412, and text output 414.

[0092] Specifically, the Paraformer performs in-depth feature extraction on the input speech data to obtain a speech feature vector, which converts the sound wave data in the original speech data into a feature vector that can represent the essence of the speech. These feature vectors capture the frequency spectrum, pitch, energy, and other potential acoustic features of the speech. The extracted feature vectors are fed into the Paraformer model for encoding to obtain original encoded features. The Paraformer model utilizes the self-attention mechanism in the Transformer model, which can effectively capture the dependencies between different time steps in the sequence, facilitating the understanding of the context of the speech. Through the self-attention mechanism, the Paraformer can perform in-depth context modeling on the original encoded features to obtain updated encoded features, enabling the Paraformer model to understand long-distance dependencies in the speech and more accurately transcribe continuous speech streams. The original encoded features are further integrated in the Paraformer model to form a comprehensive feature representation, i.e., integrated features. Through feature integration, complex acoustic features can be converted into a unified internal representation. Finally, the Paraformer model passes the integrated feature representation to the output layer for text transcription, generating the message text corresponding to the speech message and outputting it.

[0093] In the embodiment, a non-autoregressive end-to-end speech recognition model is used to optimize the model by taking the unique speech data set generated in the field of intelligent manufacturing as the training sample, and the non-autoregressive end-to-end speech recognition model is used to realize the transcription of the speech message to the message text, which greatly improves the applicability and accuracy of the text transcription result, ensures that the model can understand and process the terms and concepts specific to the field of intelligent manufacturing, and facilitates subsequent accurate intent recognition and entity extraction, and then obtains the manufacturing process data for data analysis.

[0094] In some embodiments, the manufacturing process inquiry message is subjected to intent recognition and entity extraction based on the historical inquiry interactive message corresponding to the manufacturing process inquiry message, to obtain intent information and entity information, including:

[0095] The message text of the manufacturing process inquiry message is subjected to intent recognition and entity extraction based on a natural language understanding model, to obtain original intent information and original entity words;

[0096] The historical state information corresponding to the historical inquiry interactive message corresponding to the manufacturing process inquiry message is obtained, and the current state information is constructed based on the original intent information and the original entity words;

[0097] The intent information matched with the manufacturing process inquiry message is obtained through intent prediction based on the historical state information and the current state information;

[0098] The original entity words are subjected to standardization processing to obtain the entity information matched with the manufacturing process inquiry message.

[0099] The natural language understanding model is a model that extracts information from text, understands the meaning of the text, and can perform corresponding operations or generate responses according to the understanding through a specific algorithm. Through the natural language understanding model, the message text of the manufacturing process inquiry message can be subjected to intent recognition and entity extraction, and the original intent information and the original entity words can be directly obtained. In the process of intent recognition, the natural language understanding model can use the original intent information directly obtained to construct the current state information from the historical state information corresponding to the historical inquiry interactive message corresponding to the manufacturing process inquiry message, to realize the combination of the historical state and the current state, and then perform intent prediction through the combination of the historical state information and the current state information to obtain the intent information, so that the user's intent can be determined in the case that the message text of the manufacturing process inquiry message lacks words directly representing the intent.

[0100] In some embodiments, the original entity words are subjected to standardization processing to obtain the entity information matched with the manufacturing process inquiry message, including: obtaining the entity standardization expression mode in the field of intelligent manufacturing; and performing entity mapping on the original entity words according to the entity standardization expression mode to obtain the standardized entity information.

[0101] Since there may be abbreviations or aliases in the message text of the manufacturing process inquiry message, for the extracted original entity word, the original entity word can be standardized to obtain entity information matched with the manufacturing process inquiry message. Different intelligent manufacturing fields may correspond to different entity standardization expressions. In the computer device, the entity standardization expression matched with the intelligent manufacturing field can be pre-configured, so that in the process of entity extraction, the entity standardization expression of the intelligent manufacturing field can be used to obtain entity information that can accurately express the meaning of the entity.

[0102] Among them, the standardization processing can be obtained by industry standard word entity mapping processing, for example, for the original entity word, in the defined synonym mapping table, whether the original entity word has a corresponding synonym is found, if the synonym is found, the original entity word is replaced with the synonym, so as to realize the standardization processing of the original entity word, and obtain the entity information.

[0103] In a specific application, taking Rasa as an example of natural speech understanding model, the process of Rasa performing intent recognition and entity extraction on the message text of the manufacturing process inquiry message is shown in FIG. 5. Rasa can specifically include a semantic understanding component Interpreter (502), an entity mapping component EntitySynonymMapper (504), a state tracker component Tracker (506), a dialogue policy component Policy (508), and an intent analysis component Action (510).

[0104] Specifically, the specific process of implementing intent recognition and entity extraction by the Rasa model includes:

[0105] The message text of the manufacturing process inquiry message is first transmitted to the Interpreter component of Rasa. The Interpreter component is usually composed of an NLU (Natural Language Understanding) model and is responsible for understanding the user's message. The Interpreter component uses a pre-trained model to analyze the text, identifies the user's intent (intent) and extracts the entity (entity) in the message. Among them, the intent is the basic operation that the user wants to complete, and the entity is the specific data in the message.

[0106] In order to improve the accuracy of the processing result, it is necessary to standardize the abbreviations or aliases in the message text. Specifically, if the message text contains abbreviations or aliases, the entity mapping component EntitySynonymMapper will convert the abbreviations or aliases into the standardized full name format, and the specific steps are as follows: First, the entity extraction component is used to identify the entity words in the message text and give the original value. Secondly, the entity mapping component will look up the defined synonym mapping table to see if there is a corresponding synonym for the original value of the entity word. If a synonym is found, the original value is replaced with the synonym. The entity value after synonym replacement is filled into the corresponding entity category to be used as input for subsequent dialogue processing, which can improve the accuracy and consistency of the dialogue system, so that the system can better understand the user's intention, and reasonable use of entity mapping can effectively handle the user's diverse expressions and improve user experience.

[0107] Further, the extracted intent and entity information are then passed to the dialogue state tracker Tracker. The Tracker is responsible for maintaining the current state of the dialogue, which includes the user's intent, entity value obtained from the current message text, and the history of the current message text. Correspondingly, each history message also has a corresponding history state, including the user's intent corresponding to the history message, entity value and history message before the history message. The Tracker passes the current state and history state to the dialogue policy component Policy.

[0108] The Policy component is essentially a machine learning model that can determine what action should be taken next based on the current state and history of the dialogue. The Policy component predicts the next most appropriate intent by analyzing the current state and history state, and sends it to the Action component. The Action component can be a message to the user, an operation or a request for more information. Further, after the predicted intent is executed, the Action component can obtain the execution result and return it to the Tracker component, so that the execution result is added to the history state of the dialogue for future decision-making.

[0109] In this embodiment, the natural language understanding model can perform intent recognition and entity extraction on the message text of the manufacturing process inquiry message. The natural language understanding model can be used to analyze the intent based on the history message to obtain more accurate intent information. At the same time, by standardizing the entity words, more accurate entity information can be obtained to improve the accuracy of the subsequent data search process.

[0110] In some embodiments, the computer device can send the intent information and the entity information to the data analysis platform to find the manufacturing indicators that match the intent information and the entity information. Before sending, the computer device can format the intent information and the entity information according to the data format requirements of the data analysis platform, so that the data analysis platform can directly find the data indicators according to the intent information and the entity information to obtain the manufacturing indicators.

[0111] In some specific applications, the intent information extracted by Rasa includes intent and corresponding intent-value, and the entity information includes entity and corresponding entity-value. Taking the format requirement of the manufacturing process characteristic analysis platform as an example, the format is JSON, the computer device sets the intent and the entity as the key in the JSON format, and sets the corresponding value as the value, and the conversion result is {“key1”:“value1”,“key2”:“value2”…}, wherein the type of the value can be customized according to actual conditions, and supports string, array, Boolean and the like.

[0112] In this embodiment, through the conversion of the data format, the error caused by the incompatibility of the data format between the computer device and the data analysis platform can be avoided, the effective interaction between the computer device and the data analysis platform can be ensured, and the smooth execution of data searching can be ensured.

[0113] In some embodiments, the manufacturing indicators are a combination of manufacturing process intent indicators and manufacturing process entity indicators. From the data analysis platform in the field of intelligent manufacturing, the manufacturing indicators that match the intent information and the entity information are found, and specifically include:

[0114] From the data analysis platform in the field of intelligent manufacturing, the manufacturing process intent indicators that match the intent information and the manufacturing process entity indicators that match the entity information are found.

[0115] The manufacturing process intent indicators and the manufacturing process entity indicators are combined to obtain the manufacturing indicators.

[0116] In the data analysis platform, there are many different categories of data indicators, each of which is used to refer to a different data composition structure. Specifically, the data analysis platform can include data indicators that match the intent information and data indicators that match the entity information. After the computer device sends the intent information and the entity information to the data analysis platform, the data analysis platform can find the manufacturing process intent indicators that match the intent information and the manufacturing process entity indicators that match the entity information through information matching, wherein the number of the manufacturing process intent indicators that match the intent information is generally one, and the number of the manufacturing process entity indicators that match the entity information can be one or more.

[0117] Specifically, the data analysis platform can feed the found manufacturing process intent indicators and manufacturing process entity indicators directly to the computer device, and the computer device can combine the manufacturing process intent indicators and the manufacturing process entity indicators to obtain the manufacturing indicators. The data analysis platform can also combine the found manufacturing process intent indicators and manufacturing process entity indicators to obtain the manufacturing indicators and then send them to the computer device.

[0118] In some embodiments, the data analysis platform is provided with a query interface, a data analysis interface, and a visualization interface. Further, according to the intent information, the manufacturing process data corresponding to the manufacturing indicators is analyzed for manufacturing process characteristics to obtain visualization display data representing the manufacturing process characteristics, including:

[0119] The query interface matching the manufacturing indicators is called to query the manufacturing process data corresponding to the manufacturing indicators.

[0120] The data analysis interface matching the intent information is called to analyze the manufacturing process data for manufacturing process characteristics to obtain manufacturing process characteristic analysis results.

[0121] The visualization interface matching the data analysis interface is called to convert the manufacturing process characteristic analysis results to obtain the visualization display data.

[0122] The data analysis platform can pre-configure the query interface, the data analysis interface, and the visualization interface to meet the user's demand for querying data corresponding to specific data indicators in the field of intelligent manufacturing. The query interface can receive a dialogue state composed of intent information, entity information, and historical messages. The query interface allows the user to query specific data according to specific data indicators. Each data indicator has a corresponding query interface, so that the data analysis platform can provide accurate data according to the user's selection. The data analysis interface is used to process the query conditions provided by the user and call the corresponding manufacturing process characteristic analysis and analysis logic according to the query conditions. The visualization interface is used to visually display the analysis results to the user in the form of graphs or tables, so that the user can easily understand complex data.

[0123] In a specific implementation, the computer device calls a query interface matching the manufacturing index to enable the digital analysis platform to query the manufacturing process data corresponding to the manufacturing index and feed back to the computer device, realize the acquisition of the manufacturing process data, then call a data analysis interface matching the intent information to enable the digital analysis platform to analyze the manufacturing process characteristics of the manufacturing process data, obtain the manufacturing process characteristic analysis result and feed back to the computer device, finally call a visualization interface matching the data analysis interface to enable the digital analysis platform to convert the manufacturing process characteristic analysis result, obtain the visual display data and feed back to the computer device, and realize the effective interaction between the computer device and the digital analysis platform.

[0124] In a specific embodiment, taking the field of intelligent manufacturing as an example, the computer device inputs the formatted data (602) to the data analysis platform (604), and the data analysis platform is a key tool for data management and analysis in manufacturing industry, which can help enterprises monitor the performance of production lines, optimize production processes, and improve overall efficiency. The data analysis platform can be built based on manufacturing execution system (MES) or other industrial systems to collect and analyze data related to production lines.

[0125] The implementation process of the specific interaction process between the data analysis platform and the computer device is as follows:

[0126] In order to call the interface of the digital analysis platform, the following data needs to be collected in the intelligent question and answer process: intent information, including the specific index that the user wants to query, such as capacity, YU, FTY, etc. Entity information, including specific objects related to the query, such as specific production lines, product models, time ranges, etc. The data composition of the dialogue state includes not only the intent information and the entity information, but also the user's previous query history, so that the system can provide coherent context-related information.

[0127] The formatted data obtained by the computer device from Rasa needs to be integrated into the digital analysis platform. It usually involves passing the output data of Rasa to the underlying service interface of the platform. The output data of Rasa may include intent information, entity information, or dialogue state containing intent information and entity information, etc. These output data are important indicators for analyzing the status of the production line.

[0128] In order to meet the user's demand for querying data corresponding to specific data indicators in the field of intelligent manufacturing, the digital analysis platform can be pre-configured with query interfaces, data analysis interfaces, and visualization interfaces.

[0129] The query interface can receive the intent information, entity information, and historical message to form a dialogue state. The query interface allows the user to query specific data according to specific data indicators such as capacity, YU, FTY, etc. Each data indicator has a corresponding query interface, so that the digital analysis platform can determine which data analysis interface of the indicator to call according to the intent information and entity information, so as to provide accurate data according to the user's selection. The data analysis interface is used to process the query conditions provided by the user, and according to the query conditions, the corresponding manufacturing process characteristic analysis and analysis logic are called, which can be specifically according to the data provided by the query interface, combined with the dialogue state, to perform necessary manufacturing process characteristic analysis and analysis, such as calculating the average value, trend analysis, etc. Once the data is passed in, the digital analysis platform will process these data according to the pre-defined indicator algorithm. The indicator algorithm is designed according to the best practices of the manufacturing industry and the specific needs of the enterprise to ensure that the performance of the production line can be accurately reflected. The visualization interface is used to receive the results of the data analysis interface and convert them into charts or tables so that the user interface can display these information and visually display the analysis results to the user in the form of graphs or tables, so that the user can easily understand complex data.

[0130] As shown in FIG. 6, the computer device inputs the formatted data (602) into the data analysis platform (604). When the data analysis platform interface service is called, the system checks whether the response is successful (606). If successful, the digital analysis platform will return the analyzed data information (608), which can include key performance indicators (KPIs) such as production efficiency, failure rate, capacity, etc. If the interface service call fails, the system can retry calling the interface service or guide the user to input more effective information if necessary to ensure the integrity and accuracy of the data. For example, in some cases, if the digital analysis platform needs more context information to accurately interpret certain indicators, the computer device can prompt the user to input additional data or clarify certain information.

[0131] A series of general data presentation components can be pre-developed and configured in the digital analysis platform or the computer device. Each data presentation component can receive data input of different indicators, automatically select the appropriate presentation method according to the structure and configuration of the data, and automatically generate the corresponding chart or text description. The general component has the characteristics of flexible design and high maintainability, so as to adapt to different data structures and presentation needs. Through the above processing method, the processing efficiency of converting the manufacturing process characteristic analysis results into visual display data can be further improved. Further, in order to ensure that the user can easily understand and use the data presentation component, the computer device can provide clear legends, tool tips, operation guides for the data presentation component, and through pre-configuration of display adaptation strategies, ensure that the chart can be well displayed on different devices and screen sizes.

[0132] In the embodiment, the powerful data management and data analysis processing capability of the data analysis platform can be utilized, the effective interaction between the data analysis platform and the computer device is realized by calling various interfaces configured in the data analysis platform, the manufacturing process inquiry message input by the user is analyzed by the computer device to obtain the intention information and the entity information, the intention information and the entity information are provided to the data analysis platform through the interface calling, the analysis processing result of the data analysis platform is obtained, and finally the user is shown in the form of visual display data, realizing efficient interactive response.

[0133] The application further provides an application scenario of the interactive processing method in the field of intelligent manufacturing. Specifically, the interactive processing method in the field of intelligent manufacturing is applied in the application scenario as follows:

[0134] The existing question and answer systems in the market mostly utilize information retrieval, knowledge reasoning and other technologies to help users more conveniently obtain required knowledge. However, such question and answer systems still have certain limitations in accurately understanding problems and providing effective feedback in specific fields. Therefore, the application proposes an interactive processing in the field of intelligent manufacturing, specifically including the following contents:

[0135] The computer device is provided with an interactive interface for querying characteristic data of a manufacturing process, in the interactive interface, a text input control and a voice input control are displayed to allow a user to select an interaction mode, if the user selects the voice input control in the interactive interface and triggers a voice input operation, the computer device will respond to the voice input operation to obtain input voice data, that is, a manufacturing process inquiry message.

[0136] The computer device transmits the input speech data to the Paraformer model, which performs in-depth feature extraction on the input speech data to obtain speech feature vectors. The Paraformer model converts the sound wave data in the original speech data into feature vectors that can represent the essence of the speech. These feature vectors capture the frequency spectrum, pitch, energy, and other potential acoustic features of the speech. The extracted feature vectors are fed into the Paraformer model for encoding to obtain original encoded features. The Paraformer model utilizes the self-attention mechanism in the Transformer model, which can effectively capture the dependencies between different time steps in the sequence and facilitate understanding of the context of the speech. Through the self-attention mechanism, the Paraformer can perform in-depth context modeling on the original encoded features to obtain updated encoded features, enabling the Paraformer model to understand long-distance dependencies in the speech and more accurately transcribe continuous speech streams. The original encoded features are further integrated in the Paraformer model to form a comprehensive feature representation, i.e., integrated features. Feature integration can convert complex acoustic features into a unified internal representation. Finally, the Paraformer model passes the integrated feature representation to the output layer for text transcription, generating the message text corresponding to the speech message.

[0137] Next, the message text of the manufacturing process inquiry message is passed to the Interpreter component of Rasa, which uses a pre-trained model to analyze the text, identify the user's intent, and extract entities from the message text. If the message text contains abbreviations or aliases, the Entity Synonym Mapper component converts the abbreviations or aliases to standardized full name formats. Further, the extracted intent information and standardized entity information are then passed to the Tracker component. The Tracker is responsible for maintaining the current state of the conversation based on the user's intent, entity values obtained from the current message text, and the history of the current message text. Subsequently, the Tracker passes the current state and the history state to the Policy component. The Policy component analyzes the current state and the history state to predict the most appropriate intent for the next step and sends it to the Action component, which can be a message to the user, an operation to be performed, or a request for more information. Further, after the predicted intent is executed, the Action component can obtain the execution result and return it to the Tracker component.

[0138] Thus, Rasa extracts intent information and entity information. The intent information includes intent and corresponding intent-value, and the entity information includes entity and corresponding entity-value. Taking the format requirement of the manufacturing process characteristic analysis platform as an example, the computer device sets the intent and entity as the key in the JSON format, and sets the corresponding value as the value, and the conversion result is {“key1”:“value1”,“key2”:“value2”…}, wherein the type of the value can be customized according to the actual situation, and supports string, array, Boolean and the like, so that the data analysis platform can directly match the intent information and entity information according to the format, find the data indicators, obtain the manufacturing indicators, and perform data analysis and the like based on the manufacturing process data corresponding to the manufacturing indicators, to obtain the visual display data finally used for display to the user.

[0139] The output data of Rasa can include intent information, entity information, or conversation state information containing intent information and entity information, which are important indicators for analyzing the production line status. The formatted data obtained by the computer device from Rasa needs to be integrated into the digital analysis platform, which specifically involves transferring the output data of Rasa to the underlying service interface of the platform.

[0140] In order to meet the user's demand for querying data corresponding to specific data indicators in the field of intelligent manufacturing, the digital analysis platform can be pre-configured with a query interface, a data analysis interface and a visualization interface. The query interface can receive the conversation state composed of intent information, entity information and historical messages. The query interface allows the user to query specific data according to specific data indicators such as production capacity, YU and FTY. Each data indicator has a corresponding query interface, so that the digital analysis platform can determine which data analysis interface of the indicator to call according to the intent information and entity information, so as to provide accurate data according to the user's selection. The data analysis interface is used to process the query conditions provided by the user, and to call the corresponding data processing and analysis logic according to the query conditions. Specifically, it can be to perform necessary data processing and analysis according to the data provided by the query interface, in combination with the conversation state, such as calculating the average value, trend analysis and the like. Once the data is transmitted, the digital analysis platform will process these data according to the predefined indicator algorithm. The indicator algorithm is designed according to the best practices of the manufacturing industry and the specific needs of the enterprise, to ensure that the performance of the production line can be accurately reflected. The visualization interface is used to receive the results of the data analysis interface, and convert them into charts or tables, so that the user interface can display these information, and the analysis results are intuitively displayed to the user in the form of graphs or tables, so that the user can easily understand the complex data.

[0141] When the interface service is called, the system checks whether the response is successful. If successful, the digital analytics platform returns the analyzed data information, which can include key performance indicators such as production efficiency, failure rate, capacity, etc. If the interface service call fails, the system can retry calling the interface service or, if necessary, guide the user to input more effective information to ensure the integrity and accuracy of the data. For example, in some cases, if the data analytics platform needs more contextual information to accurately interpret certain indicators, the computer device can prompt the user to input additional data or clarify certain information.

[0142] Through the above processing mode, the Paraforme model is adopted, the unique voice data set generated by the manufacturing industry is used as the training sample for model optimization, and the Paraforme model is used to realize the transcription of the voice message to the message text, which greatly improves the applicability and accuracy of the text transcription result, ensures that the model can understand and process terms and concepts specific to the field of intelligent manufacturing, facilitates subsequent accurate intent recognition and entity extraction, and then obtains manufacturing process data for data analysis. And by integrating Rasa technology and combining training based on the Paraformer model, it can efficiently extract deep features and accurately match entities from user input text. The bidirectional training mechanism and understanding ability of the context relationship of the Paraformer model make it perform well in the complex environment of the manufacturing industry, and it can better capture user intent and key information. In addition, this scheme tightly integrates natural language processing, speech recognition, and underlying interface services, making full use of the efficiency and functionality of the underlying interface services. Not only does it improve the overall performance of the system, but it also ensures the smoothness and accuracy of data processing. Finally, by providing highly customized visual presentation to meet the specific functional requirements of the manufacturing industry for data display, production data and management indicators can be presented in an intuitive and easy-to-understand manner, helping management and operators make more appropriate decisions.

[0143] It should be understood that, although each step in the flowchart involved in the above embodiments is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least some of the other steps or steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiments of the present application also provide an intelligent manufacturing field interaction processing apparatus for implementing the above-mentioned interaction processing method in the field of intelligent manufacturing. The solution provided by the apparatus is similar to the solution described in the above-mentioned method, and therefore the specific limitations in one or more embodiments of the intelligent manufacturing field interaction processing apparatus provided below can refer to the limitations of the intelligent manufacturing field interaction processing method described above, which will not be repeated here.

[0145] In one embodiment, as shown in FIG. 7, an intelligent manufacturing field interaction processing apparatus is provided, comprising: an input processing module 702, an intent recognition and entity extraction module 704, an index searching module 706, a manufacturing process characteristic analysis module 708, and a visualization display module 710, wherein:

[0146] The input processing module 702 is configured to, in an intelligent manufacturing field interaction scenario, obtain an input manufacturing process inquiry message in response to an inquiry message input operation triggered in an interaction interface;

[0147] The intent recognition and entity extraction module 704 is configured to perform intent recognition and entity extraction on the manufacturing process inquiry message based on historical inquiry interaction messages corresponding to the manufacturing process inquiry message, to obtain intent information and entity information;

[0148] The index searching module 706 is configured to search for manufacturing indexes that match the intent information and are matched with the entity information from a data analysis platform in the field of intelligent manufacturing;

[0149] The manufacturing process characteristic analysis module 708 is configured to perform manufacturing process characteristic analysis on manufacturing process data corresponding to the manufacturing indexes according to the intent information, to obtain visualization display data representing manufacturing process characteristics;

[0150] The visualization display module 710 is configured to display the visualization display data as a response result of the manufacturing process inquiry message in the interaction interface.

[0151] In some embodiments, the interactive processing apparatus in the field of intelligent manufacturing includes a text transcription module configured to perform feature extraction on the voice message based on a non-autoregressive end-to-end speech recognition model to obtain a voice feature vector, wherein the non-autoregressive end-to-end speech recognition model is trained based on sample voice messages containing professional terms in the field of intelligent manufacturing, and the voice feature vector is sequentially subjected to feature coding and context modeling through a self-attention mechanism of the non-autoregressive end-to-end speech recognition model to obtain encoded features, and the encoded features are integrated to obtain integrated features, and the integrated features are subjected to text transcription to obtain a message text representing the voice message.

[0152] The intent recognition and entity extraction module 704 is specifically configured to perform intent recognition and entity extraction on the message text based on historical inquiry interaction messages corresponding to the manufacturing process inquiry message to obtain intent information and entity information.

[0153] In some embodiments, the intent recognition and entity extraction module 704 is specifically configured to perform intent recognition and entity extraction on the message text of the manufacturing process inquiry message based on a natural language understanding model to obtain original intent information and original entity words, to obtain historical state information corresponding to the historical inquiry interaction messages corresponding to the manufacturing process inquiry message, and to construct current state information based on the original intent information and the original entity words, to perform intent prediction based on the historical state information and the current state information to obtain intent information matched with the manufacturing process inquiry message, and to perform standardization processing on the original entity words to obtain entity information matched with the manufacturing process inquiry message.

[0154] In some embodiments, the intent recognition and entity extraction module 704 is specifically configured to obtain an entity standardization expression manner in the field of intelligent manufacturing, and to perform entity mapping on the original entity words according to the entity standardization expression manner to obtain standardized entity information.

[0155] In some embodiments, the manufacturing indicator is a combination of manufacturing process intent indicators and manufacturing process entity indicators, and the indicator searching module 706 is specifically configured to search for manufacturing process intent indicators conforming to the intent information and manufacturing process entity indicators matched with the entity information from a data analysis platform in the field of intelligent manufacturing, and to combine the manufacturing process intent indicators and the manufacturing process entity indicators to obtain a manufacturing indicator.

[0156] In some embodiments, the data analysis platform provides a query interface, a data analysis interface, and a visualization interface; the manufacturing process characteristic analysis module 708 is configured to call the query interface matching the manufacturing index, query the manufacturing process data corresponding to the manufacturing index; call the data analysis interface matching the intent information, perform manufacturing process characteristic analysis on the manufacturing process data, and obtain manufacturing process characteristic analysis results; call the visualization interface matching the data analysis interface, perform data conversion on the manufacturing process characteristic analysis results, and obtain visualization display data.

[0157] The above-mentioned interactive processing device in the field of intelligent manufacturing can accurately understand the specific intent information and the entity information related to the interaction of the user in this interaction operation under the interactive scene in the field of intelligent manufacturing by responding to the input operation of the inquiry message triggered in the interactive interface, obtaining the input manufacturing process inquiry message, and performing intent recognition and entity extraction on the manufacturing process inquiry message based on the historical inquiry interactive message corresponding to the manufacturing process inquiry message. This facilitates accurate acquisition of matched manufacturing process data for data analysis. In the data acquisition process, the manufacturing index matching the intent information and the entity information is found from the data analysis platform in the field of intelligent manufacturing, which can realize accurate search of the manufacturing process data. Then, the manufacturing process data corresponding to the manufacturing index is analyzed according to the intent information to obtain visualization display data representing the manufacturing process characteristics. Finally, the visualization display data is taken as the response result of the manufacturing process inquiry message, and the visualization display data is displayed in the interactive interface. Only simple interaction operation is required to obtain the data interaction result in the field of intelligent manufacturing in a visual manner. Not only can the manufacturing process data be obtained for analysis to obtain intuitively displayed data results through intent recognition and information extraction, but also the interaction process is simplified and the time required for interaction operation is shortened, thereby effectively improving the interaction efficiency in the field of intelligent manufacturing.

[0158] Each module in the above-mentioned interactive processing device in the field of intelligent manufacturing can be realized by software, hardware, and a combination thereof in whole or in part. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0159] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in FIG. 8. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement an interactive processing method in the field of intelligent manufacturing.

[0160] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram thereof can be as shown in FIG. 9. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, mobile cellular network, NFC (near field communication), or other technologies. The computer program is executed by the processor to implement an interactive processing method in the field of intelligent manufacturing. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, trackball, or touchpad arranged on the shell of the computer device, or can be an external keyboard, touchpad, or mouse, etc.

[0161] Those skilled in the art can understand that the structure shown in FIG. 8 or FIG. 9 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] In an embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0163] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0164] In an embodiment, a computer program product is provided, including a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0166] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a logic device based on quantum computing, etc., without being limited thereto.

[0167] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0168] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An interaction processing method in the field of intelligent manufacturing, characterized by, The method comprises: In the interactive scene of the intelligent manufacturing field, in response to the input operation of the inquiry message triggered in the interactive interface, the input manufacturing process inquiry message is obtained; Based on the historical inquiry interaction message corresponding to the manufacturing process inquiry message, the manufacturing process inquiry message is subjected to intent recognition and entity extraction to obtain intent information and entity information; From the data analysis platform of the intelligent manufacturing field, manufacturing indicators that match the intent information and match the entity information are searched; According to the intent information, the manufacturing process data corresponding to the manufacturing indicators is subjected to manufacturing process characteristic analysis to obtain visual display data representing the manufacturing process characteristics; The visual display data is displayed as the response result of the manufacturing process inquiry message in the interactive interface.

2. The method of claim 1, wherein, In the case where the manufacturing process inquiry message is a voice message, the method further comprises: Based on a non-autoregressive end-to-end speech recognition model, the voice message is subjected to feature extraction to obtain a voice feature vector; the non-autoregressive end-to-end speech recognition model is trained based on a sample voice message containing professional terms in the intelligent manufacturing field; Through the self-attention mechanism of the non-autoregressive end-to-end speech recognition model, the voice feature vector is subjected to feature encoding and context modeling in sequence to obtain encoded features; Based on the encoded features, integrated features are obtained; The integrated features are subjected to text transcription to obtain a message text representing the voice message; The method further comprises: Based on the historical inquiry interaction message corresponding to the manufacturing process inquiry message, the message text is subjected to intent recognition and entity extraction to obtain intent information and entity information.

3. The method of claim 1, wherein, The method further comprises: Based on a natural language understanding model, the message text of the manufacturing process inquiry message is subjected to intent recognition and entity extraction respectively to obtain original intent information and original entity words; The historical state information corresponding to the historical inquiry interaction message corresponding to the manufacturing process inquiry message is obtained, and based on the original intent information and the original entity words, current state information is constructed; Based on the historical state information and the current state information, intent prediction is performed to obtain intent information matching the manufacturing process inquiry message; The original entity words are subjected to standardization processing to obtain entity information matching the manufacturing process inquiry message.

4. The method of claim 3, wherein, The method further comprises: An entity standardization expression manner of the intelligent manufacturing field is obtained; According to the entity standardization expression manner, the original entity words are subjected to entity mapping to obtain standardized entity information.

5. The method according to any one of claims 1 to 4, characterized in that, The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator; The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator; The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator; The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator.

6. The method according to any one of claims 1 to 4, characterized in that, The data analysis platform is provided with a query interface, a data analysis interface, and a visualization interface; The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator. The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator. The manufacturing indicators are a manufacturing indicator combination including a manufacturing process intention indicator and a manufacturing process entity indicator. The device comprises: 7.An interaction processing apparatus in the field of smart manufacturing, characterized by An input processing module configured to, in an interactive scenario in the field of intelligent manufacturing, obtain an input manufacturing process inquiry message in response to an inquiry message input operation triggered in an interactive interface; An intention recognition and entity extraction module configured to perform intention recognition and entity extraction on the manufacturing process inquiry message based on historical inquiry interactive messages corresponding to the manufacturing process inquiry message, to obtain intention information and entity information; An indicator searching module configured to search for manufacturing indicators that match the intention information and the entity information from a data analysis platform in the field of intelligent manufacturing; A manufacturing process characteristic analysis module configured to perform manufacturing process characteristic analysis on manufacturing process data corresponding to the manufacturing indicators according to the intention information, to obtain visualization display data; A visualization display module configured to display the visualization display data as a response result of the manufacturing process inquiry message in the interactive interface. The processor executes the computer program to realize the steps of the method of any one of claims 1 to 6.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, ​

Images