Production process abnormity identification method and abnormity identification device
By providing a production process abnormality recognition method and abnormality recognition device in the SPC system, non-numerical data can be processed and analyzed, which solves the problem that traditional SPC systems are difficult to control non-numerical data, and realizes more efficient abnormality detection and data visualization.
Patent Information
- Application Number
- CN202411766441.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-04
- Publication Date
- 2025-03-28
AI Technical Summary
Traditional statistical process control (SPC) systems are difficult to effectively process non-numerical data, such as crystal directions in semiconductor manufacturing and product appearance qualifications in consumer product manufacturing, and cannot effectively control SPC.
A production process abnormality recognition method and abnormality recognition device are provided. By receiving target requirements input by users, acquiring the characteristic data sets of preset types of products, identifying requirements for each characteristic data, determining its numerical conversion results, and constructing a characteristic statistical chart to realize the control of non-numerical data.
It realizes effective control of non-numerical data, optimizes user experience and interaction, improves the accuracy and efficiency of abnormal detection, and enhances data visualization and decision-making support.
Smart Images
Figure CN119719639A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of production process control, and in particular, to a production process anomaly identification method and an anomaly identification device. Background Art
[0002] At present, conventional statistical process control (SPC) systems mainly focus on the monitoring, analysis and visualization of numerical data. These systems are good at processing data that can be quantified and accurately measured, such as size, weight, temperature, etc., and use control charts (such as X-bar R charts, I-MR charts, etc.) to identify abnormal fluctuations in the process and ensure the stability of the production process and the consistency of product quality. However, in actual industrial production and quality management, many key characteristics are not numerical, but non-numerical data, which poses a challenge to traditional SPC systems.
[0003] For example, in the semiconductor manufacturing industry, the crystal orientation is a crucial quality parameter that directly affects the performance and reliability of the device. However, the crystal orientation is usually determined by technologies such as image recognition or X-ray diffraction. The results are often classified data (such as qualified / unqualified for a specific crystal orientation) rather than continuous numerical values. Similarly, in the field of consumer product manufacturing, the quality of product appearance (such as the presence of scratches, color uniformity, etc.) is also a non-numerical judgment based on visual inspection. However, traditional systems are unable to meet the SPC control requirements of such non-numerical data. Summary of the invention
[0004] In view of this, the purpose of the present application is to provide a production process anomaly identification method and an anomaly identification device to overcome at least one of the above-mentioned defects.
[0005] In a first aspect, an embodiment of the present application provides a method for identifying production process anomalies, the method comprising: receiving a target requirement input by a user on an operation interface, the target requirement representing a text requirement for a preset type of product under a preset detection item; obtaining a characteristic data set of the preset type of product, the characteristic data set comprising a plurality of characteristic data, each characteristic data indicating non-numerical data of a target product under a preset detection item collected at a detection point of an industrial equipment used to produce the preset type of product; for each characteristic data, performing a requirement identification on the characteristic data to determine a numerical conversion result of the characteristic data; and constructing a characteristic statistical graph based on the numerical conversion result, the characteristic statistical graph comprising a plurality of data points, each data point representing a numerical conversion result of a target product under a preset detection item.
[0006] In an optional embodiment of the present application, a query instruction for viewing a target data point is received, the query instruction carries a data point identifier, and the data point identifier is used to indicate a target data point; in response to the query instruction, non-numerical data of a target product corresponding to the target data point under a preset detection item is displayed in an associated area of the target data point.
[0007] In an optional embodiment of the present application, for each characteristic data, the characteristic data is identified with requirements to determine a numerical conversion result of the characteristic data, including: for each characteristic data, the characteristic data and the target detection requirements are identified to determine an identification result of the characteristic data, wherein the identification result is non-numerical; for each characteristic data, data conversion is performed on the identification result corresponding to the characteristic data to obtain a numerical conversion result of the characteristic data.
[0008] In an optional embodiment of the present application, the recognition result is normal characteristic data or abnormal characteristic data, wherein the recognition result of each characteristic data is determined in the following manner: for each characteristic data, determine whether the characteristic data is consistent with the target detection requirement; for each characteristic data, if the characteristic data is consistent with the target detection requirement, determine the recognition result of the characteristic data as normal characteristic data; for each characteristic data, if the characteristic data is inconsistent with the target detection requirement, determine the recognition result of the characteristic data as abnormal characteristic data.
[0009] In an optional embodiment of the present application, each data point in the characteristic statistical graph is a normal data point or an abnormal data point, the abnormal data point indicates that the numerical conversion result corresponding to the data point is abnormal characteristic data, and the normal data point indicates that the numerical conversion result corresponding to the data point is normal characteristic data.
[0010] In an optional embodiment of the present application, the method further includes: in response to the requirement identification operation, converting the target requirement into a string form to determine the target detection requirement; matching the target detection requirement with each characteristic data to perform requirement identification and determine the numerical conversion result of each characteristic data.
[0011] In the second aspect, an embodiment of the present application also provides an abnormality identification device, which includes: a target demand receiving module, used to receive a target demand input by a user on an operation interface, wherein the target demand represents a text demand for a preset type of product under a preset detection item; a characteristic data set acquisition module, used to acquire a characteristic data set of the preset type of product, wherein the characteristic data set includes multiple characteristic data, each characteristic data indicates non-numeric data of a target product under a preset detection item collected at a detection point of an industrial equipment used to produce the preset type of product; a numerical conversion result determination module, used to perform demand identification on the characteristic data for each characteristic data to determine a numerical conversion result of the characteristic data; a characteristic statistical graph construction module, used to construct a characteristic statistical graph based on the numerical conversion result, wherein the characteristic statistical graph includes multiple data points, each data point representing a numerical conversion result of a target product under a preset detection item.
[0012] In an optional embodiment of the present application, the numerical conversion result determination module is also used to perform the following processing: for each characteristic data, the characteristic data and the target detection requirements are identified to determine the identification result of the characteristic data, and the identification result is non-numerical; for each characteristic data, the identification result corresponding to the characteristic data is converted to obtain a numerical conversion result of the characteristic data.
[0013] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method described above are performed.
[0014] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described above are executed.
[0015] The production process anomaly identification method and anomaly identification device provided by the embodiment of the present application receive the target demand input by the user on the operation interface, the target demand represents the text demand for the preset type of product under the preset detection item; obtain the characteristic data set of the preset type of product, the characteristic data set includes multiple characteristic data, each characteristic data indicates the non-numerical data of a target product under the preset detection item collected at the detection point of the industrial equipment used to produce the preset type of product; for each characteristic data, the characteristic data is identified to determine the numerical conversion result of the characteristic data; according to the numerical conversion result, a characteristic statistical graph is constructed, the characteristic statistical graph includes multiple data points, each data point represents the numerical conversion result of a target product under the preset detection item. Through this application, the control demand for non-numerical data is realized.
[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0018] Figure 1 A flowchart of a method for identifying production process anomalies provided in an embodiment of the present application;
[0019] Figure 2 A schematic diagram of the structure of an abnormality identification device provided in an embodiment of the present application;
[0020] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0021] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.
[0022] First, the application scenarios to which this application is applicable are introduced. This application can be applied in the field of production process control.
[0023] Research has found that the limitations of conventional SPC systems are: they can only process numerical data, and cannot perform effective SPC control on non-numerical data (such as crystal orientation, product appearance, etc.). Some customers need to perform SPC control on non-numerical data at work, but conventional systems cannot meet this demand. Traditional systems are unable to meet the SPC control needs of such non-numerical data because they lack the ability to directly process classified data, text data or image data.
[0024] Based on this, the embodiment of the present application provides a production process anomaly identification method and an anomaly identification device, wherein the method includes: receiving a target requirement input by a user on an operation interface, the target requirement represents a text requirement for a preset type of product under a preset detection item; obtaining a characteristic data set of a preset type of product, the characteristic data set includes multiple characteristic data, each characteristic data indicates a non-numerical data of a target product under a preset detection item collected at a detection point of an industrial equipment used to produce a preset type of product; for each characteristic data, the characteristic data is identified to determine a numerical conversion result of the characteristic data; based on the numerical conversion result, a characteristic statistical graph is constructed, the characteristic statistical graph includes multiple data points, each data point represents a numerical conversion result of a target product under a preset detection item. Through this application, the control requirements for non-numerical data are realized.
[0025] See also Figure 1 , Figure 1 This is a flow chart of the production process anomaly identification method provided in the embodiment of the present application. Figure 1 As shown in , the method for identifying production process anomalies provided by the embodiment of the present application includes:
[0026] S101: receiving target requirements input by a user on an operation interface.
[0027] The target requirements represent the textual requirements for the preset types of products under the preset test items.
[0028] In an optional embodiment, taking the crystal direction as east, south, west and north as an example, the user may determine in the operation interface that the target requirement is that the crystal direction is east. Here, the preset product type is crystal, the preset inspection item is the crystal direction, and the text requirement is to check whether the crystal direction is east. Or, taking the product appearance qualification as an example, the text requirement may be to check whether there are any scratches on the product appearance.
[0029] S102: Obtain a characteristic data set of a preset category of products.
[0030] The characteristic data set includes a plurality of characteristic data, each characteristic data indicating non-numeric data of a target product under a preset detection item collected at a detection point of an industrial equipment for producing a preset type of product.
[0031] For example, there are multiple production lines, and the production lines are used to produce industrial equipment for preset types of products. Multiple detection points are set on each production line, and each detection point is used to detect non-numerical data under preset detection items of the target product.
[0032] Here, numerical data is data that can be subjected to mathematical operations and is usually expressed in digital form, such as length, weight, temperature, etc.
[0033] In an optional embodiment, in the SPC system, conventional measurement data such as product size and weight are all numerical data, and process control can be performed by calculating statistics such as mean value and standard deviation.
[0034] Non-numeric data is data that cannot be directly subjected to mathematical operations and is usually expressed in the form of text, symbols or codes, such as crystal orientation, whether the product appearance is qualified, etc.
[0035] In another optional embodiment: In the work of some customers, it is necessary to perform SPC control on whether the crystal orientation or appearance of the product is qualified, and these data are non-numerical data.
[0036] Crystal orientation refers to the directionality of crystal. The properties of crystal are different along different directions of the lattice. In the crystal, a straight line connecting any two lattice points in the lattice is called a crystal column, and the orientation of the crystal column is called the crystal direction, which represents a specific direction in the crystal. The crystal direction index is usually used to determine the position of the crystal direction in the crystal. The crystal direction index is a set of integers, which is determined by determining the projection of the vector from the origin to a specific point in the crystal on the coordinate axis.
[0037] S103 . For each characteristic data, identify the demand of the characteristic data to determine the numerical conversion result of the characteristic data.
[0038] Specifically, for each characteristic data, the characteristic data and the target detection requirement are identified to determine the identification result of the characteristic data.
[0039] The recognition result is a non-numeric result, and the recognition result is normal characteristic data or abnormal characteristic data.
[0040] The recognition result of each characteristic data is determined in the following manner:
[0041] For each characteristic data, determine whether the characteristic data is consistent with the target detection requirements;
[0042] Here, the target detection requirement is obtained by converting according to the target requirement.
[0043] In response to the requirement identification operation, the target requirement is converted into a string form to determine the target detection requirement;
[0044] First, identify and clarify the target needs that need to be detected or addressed.
[0045] For example, the target demand may be "detect whether the direction of the crystal is east", "detect whether there are scratches on the product appearance", etc.
[0046] Secondly, describe these text requirements in natural language and convert them into string form. The requirements in string form should be clear, accurate, and easy for the system to understand and process.
[0047] Match the target detection requirements with each characteristic data to identify the requirements and determine the numerical conversion results of each characteristic data.
[0048] Here, the converted string needs to be parsed to clarify the specific detection or processing tasks.
[0049] For example, from “detecting whether the direction of the crystal is east”, we can deduce that the task is to detect the direction and the object is the crystal.
[0050] The target detection requirement is matched with each characteristic data to determine whether the characteristic data is consistent with the target detection requirement.
[0051] For each characteristic data, if the characteristic data is consistent with the target detection requirement, the recognition result of the characteristic data is determined as normal characteristic data; for each characteristic data, if the characteristic data is inconsistent with the target detection requirement, the recognition result of the characteristic data is determined as abnormal characteristic data.
[0052] For example, if the target detection requirement is to detect that the direction of the crystal is east, if the non-numeric data corresponding to the characteristic data is that the direction of the crystal is east, then the recognition result corresponding to the characteristic data is considered to be normal characteristic data; if the non-numeric data corresponding to the characteristic data is that the direction of the crystal is any direction other than east, then the recognition result corresponding to the characteristic data is considered to be abnormal characteristic data.
[0053] For each characteristic data, the recognition result corresponding to the characteristic data is converted into data to obtain a numerical conversion result of the characteristic data.
[0054] Here, the recognition result is converted into normal characteristic data, and the numerical conversion result is determined to be a normal value. The recognition result is converted into abnormal characteristic data, and the numerical conversion result is determined to be an abnormal value. For example, the normal value can be represented by 1 and the abnormal value can be represented by 0.
[0055] S104. Construct a characteristic statistical graph according to the numerical conversion result.
[0056] The characteristic statistical graph includes multiple data points, each of which represents a numerical conversion result of a target product under a preset test item.
[0057] In an optional embodiment, the characteristic statistical graph can be a Chart (statistical chart), which is a form of displaying data through graphic symbols (such as circles, rectangles, lines, etc.). These graphic symbols can clearly indicate key information such as the quantity, proportion, trend, etc. of the data, making the data easier to understand and analyze.
[0058] There are many types of charts, each with its own specific application scenarios and advantages. Here are some common chart types:
[0059] Bar Chart: Use the height or length of a bar to represent the size of data. It is very suitable for comparing data differences between different categories. A bar chart can be placed horizontally or vertically. When placed vertically, it is also called a bar chart.
[0060] Pie Chart: It is mainly used to show the proportion of several large sectors in the whole, rather than to compare different sectors. Pie chart can clearly show the distribution of data, which is very suitable for displaying market share, budget allocation and other scenarios.
[0061] Line Chart: Use lines to represent the trend of data, usually used to show the change of data over time or other continuous variables. Line charts can clearly show the fluctuations and trends of data, and are very suitable for displaying scenes such as stock prices and temperature changes.
[0062] Radar Chart: Also known as spider chart, it is mainly used to show the comparison of multiple variables. Radar chart displays the data of multiple variables in a radial form on a graph, which can clearly show the relative size and relationship between each variable.
[0063] Other types: In addition to the common chart types mentioned above, there are also many other types such as scatter chart, polar area chart, doughnut chart, etc., each of which has different application scenarios and advantages.
[0064] Preferably, the characteristic statistical graph in the present application can be a line graph in a Chart graph, and each data point in the line graph represents a numerical conversion result of a target product under a preset detection item. Each data point in the characteristic statistical graph is a normal data point or an abnormal data point. The abnormal data point indicates that the numerical conversion result corresponding to the data point is abnormal characteristic data, and the normal data point indicates that the numerical conversion result corresponding to the data point is normal characteristic data.
[0065] Taking the direction of the crystal as an example, the normal data point corresponds to the normal value 1, which means that the numerical conversion result of the target product under the crystal direction detection item is that the direction of the crystal is normal. The abnormal data point corresponds to the abnormal value 0, which means that the numerical conversion result of the target product under the crystal direction detection item is that the direction of the crystal is abnormal.
[0066] Specifically, a query instruction for viewing a target data point is received.
[0067] The query instruction carries a data point identifier, and the data point identifier is used to indicate a target data point;
[0068] In response to the query instruction, non-numerical data of the target product corresponding to the target data point under the preset detection item is displayed in the associated area of the target data point.
[0069] Among them, after generating the characteristic statistical graph, that is, generating the Chart graph, receiving the query instruction triggered by the user clicking a certain target data point in the operation interface.
[0070] First, verification and parsing instructions can be performed. First, the legality and integrity of the query instruction are verified, including checking the validity of the data point identifier, parsing the query instruction, extracting the data point identifier and other parameters that may be included, such as the query range, sorting method, etc., which are not specifically limited here.
[0071] Secondly, based on the data point identifier, the target data point is located in the database or data warehouse. The target data point may be one or more, depending on the scope and conditions of the query instruction. In this application, the target data point can be one.
[0072] Then, based on the location and context information of the target data point, its associated area is determined. The associated area may be a specific page, view, chart or data table, etc., which is used to display the non-numeric data of the target data point and improve the efficiency and accuracy of data query.
[0073] Finally, in response to the query instruction, the system extracts the non-numeric data of the target product corresponding to the target data point under the preset detection item from the database, and displays these non-numeric data in the associated area in an appropriate manner (such as text box, picture box, audio player, etc.). For example, taking the target requirement that the direction of the crystal is east as an example, the non-numeric data displayed in the associated area corresponding to the abnormal data point may be that the direction of the crystal is south.
[0074] Specifically, there are additional functions and user experience optimization, providing data screening and filtering functions, allowing users to further filter target data points according to specific conditions (such as time range, product type, detection items, etc.), and updating the display content in the associated area in real time to reflect the user's screening and filtering operations, thereby enhancing the scalability and compatibility of the system.
[0075] Preferably, the user is allowed to view and compare non-numeric data between different data points through interactive operations such as clicking and dragging, and a data export function is provided to allow the user to export the target data point and its associated non-numeric data as a file (such as CSV, Excel, PDF, etc.).
[0076] In an optional embodiment, the present application may also support a data sharing function, allowing users to share query results and display content with others through social media, email, etc., collect user feedback during use, which is used to improve the system's functions and user experience, provide error handling and exception capture mechanisms, ensure that the system can give clear prompt information when encountering problems, and guide users to perform correct operations.
[0077] The production process anomaly identification method and anomaly identification device provided by the embodiment of the present application receive the target demand input by the user on the operation interface, the target demand represents the text demand for the preset type of product under the preset detection item; obtain the characteristic data set of the preset type of product, the characteristic data set includes multiple characteristic data, each characteristic data indicates the non-numerical data of a target product under the preset detection item collected at the detection point of the industrial equipment used to produce the preset type of product; for each characteristic data, the characteristic data is identified to determine the numerical conversion result of the characteristic data; according to the numerical conversion result, a characteristic statistical graph is constructed, the characteristic statistical graph includes multiple data points, each data point represents the numerical conversion result of a target product under the preset detection item. Through this application, the control requirements for non-numerical data are realized, the user experience and interaction are optimized, the accuracy and efficiency of anomaly detection are improved, and data visualization and decision support are enhanced.
[0078] This application meets the customer's demand for text data, that is, non-numerical data collection, and expands the application and control scope of SPC. By viewing the chart, it can be determined whether the production process needs to be improved, and corresponding measures can be taken as soon as possible to improve it.
[0079] This application can achieve refined control of the production process through the numerical conversion of non-numeric data and the analysis of characteristic statistical graphs. Once an abnormal data point is found, each link in the production process can be traced back to find out the problem and take targeted improvement measures. By controlling and analyzing the non-numeric data of the target product under the preset test items, product quality problems can be discovered in time and corresponding measures can be taken to improve them, thereby improving product quality and customer satisfaction.
[0080] As the production process continues, characteristic data sets will continue to accumulate and improve. By analyzing these data, new abnormal patterns and potential problems can be continuously discovered, providing data support for the continuous improvement of the production process. Based on characteristic statistical charts and abnormality identification results, intelligent algorithms and models can be further developed to achieve automated monitoring of the production process and abnormality warnings, reduce labor costs, and improve production efficiency.
[0081] Based on the same inventive concept, an abnormality identification device corresponding to the production process abnormality identification method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned production process abnormality identification method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.
[0082] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of the abnormality identification device provided in the embodiment of the present application. Figure 2As shown in , the abnormality identification device 200 includes:
[0083] The target requirement receiving module 201 is used to receive the target requirement input by the user on the operation interface, wherein the target requirement represents the text requirement for the preset type of product under the preset test item;
[0084] The characteristic data set acquisition module 202 is used to acquire a characteristic data set of the preset type of product, wherein the characteristic data set includes a plurality of characteristic data, each characteristic data indicating non-numerical data of a target product under a preset detection item collected at a detection point of an industrial equipment used to produce the preset type of product;
[0085] A numerical conversion result determination module 203 is used to identify the requirements of each characteristic data to determine the numerical conversion result of the characteristic data;
[0086] The characteristic statistical graph construction module 204 is used to construct a characteristic statistical graph according to the numerical conversion result, wherein the characteristic statistical graph includes a plurality of data points, each data point representing a numerical conversion result of a target product under a preset detection item.
[0087] Specifically, the numerical conversion result determination module is also used to perform the following processing:
[0088] For each characteristic data, the characteristic data and the target detection requirement are identified, and an identification result of the characteristic data is determined, wherein the identification result is a non-numerical type;
[0089] For each characteristic data, the recognition result corresponding to the characteristic data is converted into data to obtain a numerical conversion result of the characteristic data.
[0090] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 3 As shown in , the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .
[0091] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 1 The specific implementation of the steps of the production process anomaly identification method in the method embodiment shown can be found in the method embodiment, and will not be repeated here.
[0092] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The specific implementation of the steps of the production process anomaly identification method in the method embodiment shown can be found in the method embodiment, and will not be repeated here.
[0093] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0094] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0095] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0096] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0097] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0098] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for identifying production process anomalies, characterized in that: include: Receiving a target requirement input by a user on an operation interface, wherein the target requirement represents a text requirement for a preset type of product under a preset test item; Acquire a characteristic data set of the preset type of product, the characteristic data set comprising a plurality of characteristic data, each characteristic data indicating non-numerical data of a target product under a preset detection item collected at a detection point of an industrial equipment for producing the preset type of product; For each characteristic data, the characteristic data is identified according to the requirements to determine the numerical conversion result of the characteristic data; According to the numerical conversion result, a characteristic statistical graph is constructed, wherein the characteristic statistical graph includes a plurality of data points, each data point representing a numerical conversion result of a target product under a preset detection item.
2. The method according to claim 1, characterized in that The method further comprises: Receiving a query instruction for viewing a target data point, the query instruction carries a data point identifier, and the data point identifier is used to indicate a target data point; In response to the query instruction, non-numerical data of the target product corresponding to the target data point under the preset detection item is displayed in the associated area of the target data point.
3. The method according to claim 2, characterized in that The step of identifying the requirement of each characteristic data to determine the numerical conversion result of the characteristic data includes: For each characteristic data, the characteristic data and the target detection requirement are identified, and an identification result of the characteristic data is determined, wherein the identification result is a non-numerical type; For each characteristic data, the recognition result corresponding to the characteristic data is converted into data to obtain a numerical conversion result of the characteristic data.
4. The method according to claim 3, characterized in that The recognition result is normal characteristic data or abnormal characteristic data, The recognition result of each characteristic data is determined in the following manner: For each characteristic data, determining whether the characteristic data is consistent with the target detection requirement; For each characteristic data, if the characteristic data is consistent with the target detection requirement, determining the recognition result of the characteristic data as normal characteristic data; For each characteristic data, if the characteristic data is inconsistent with the target detection requirement, the recognition result of the characteristic data is determined as abnormal characteristic data.
5. The method according to claim 4, characterized in that Each data point in the characteristic statistical graph is a normal data point or an abnormal data point. The abnormal data point indicates that the numerical conversion result corresponding to the data point is abnormal characteristic data, and the normal data point indicates that the numerical conversion result corresponding to the data point is normal characteristic data.
6. The method according to claim 3, characterized in that The method further comprises: In response to the requirement identification operation, converting the target requirement into a string form to determine the target detection requirement; The target detection requirement is matched with each characteristic data to perform requirement identification and determine the numerical conversion result of each characteristic data.
7. An abnormality identification device, characterized in that: include: A target requirement receiving module, used to receive a target requirement input by a user on an operation interface, wherein the target requirement represents a text requirement for a preset type of product under a preset test item; A characteristic data set acquisition module, used to acquire a characteristic data set of the preset type of product, the characteristic data set including a plurality of characteristic data, each characteristic data indicating non-numerical data of a target product under a preset detection item collected at a detection point of an industrial equipment used to produce the preset type of product; A numerical conversion result determination module is used to identify the requirements of each characteristic data to determine the numerical conversion result of the characteristic data; The characteristic statistical graph construction module is used to construct a characteristic statistical graph according to the numerical conversion result, wherein the characteristic statistical graph includes a plurality of data points, each data point representing a numerical conversion result of a target product under a preset detection item.
8. The device according to claim 7, characterized in that The numerical conversion result determination module is also used to perform the following processing: For each characteristic data, the characteristic data and the target detection requirement are identified, and an identification result of the characteristic data is determined, wherein the identification result is a non-numerical type; For each characteristic data, the recognition result corresponding to the characteristic data is converted into data to obtain a numerical conversion result of the characteristic data.
9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of any method as claimed in claims 1 to 6.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are executed.