Process list generation method and device, storage medium and computer program product

Through the automated process list generation method, material data and historical production data are used to solve the problem of low process list generation efficiency in the MPM system, and efficient and objective process list generation is achieved.

CN118941222AInactive Publication Date: 2024-11-12GOERTEK INC

Patent Information

Application Number
CN202411412763.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-11
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing MPM systems rely on the personal experience of process engineers in R&D process design, resulting in low efficiency in process list generation.

Method used

By obtaining the material data of the target product, generating the target prompt word, and entering it with the historical production data into the language model, generating a process list, and achieving automated generation.

Benefits of technology

It improves the efficiency and objectivity of process list generation, ensures the availability and quality of the generated list, and reduces the dependence on the personal abilities of process engineers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941222A_ABST
    Figure CN118941222A_ABST
Patent Text Reader

Abstract

The invention discloses a process list generation method and device, a storage medium and a computer program product, and relates to the technical field of production processes, the process list generation method is applied to a client, and the process list generation method comprises the steps of obtaining material data of a target product; sending the material data to a server, so that the server generates a target cue word according to the material data, matches corresponding historical production data from a predetermined historical database, inputs the target cue word and the historical production data into a predetermined language model, and generates a process list of the target product; and after the process list fed back by the server side is received, displaying the process list. The technical problem that the existing process list generation efficiency is low is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of production process technology, and in particular to a process list generation method, device, storage medium and computer program product. Background Art

[0002] With the rapid development and transformation and upgrading of the manufacturing industry, manufacturing companies are facing increasingly complex challenges such as product design, production process optimization and cost control. In this context, the importance of the MPM (Manufacturing Process Management) system as a key tool to improve corporate production efficiency and ensure product quality has become increasingly prominent.

[0003] However, in the current MPM system practice, although it has achieved remarkable results in production planning and scheduling, material management, quality control, etc., it still highly relies on the personal experience and professional judgment of process engineers in the core link of R&D process design. As a result, the process list manually designed by process engineers is greatly affected by the process engineers' knowledge background, work experience and subjective judgment, resulting in low efficiency in the generation of process lists.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a process list generation method, device, storage medium and computer program product, aiming to solve the technical problem of low efficiency in generating existing process lists.

[0006] To achieve the above purpose, the present application proposes a process list generation method, which is applied to a client. The process list generation method includes: Get the material data of the target product; Sending the material data to the server, so that the server generates a target prompt word according to the material data, matches the corresponding historical production data from a predetermined historical database, inputs the target prompt word and the historical production data into a predetermined language model, and generates a process list for the target product; After receiving the process list fed back by the server, the process list is displayed.

[0007] In addition, to achieve the above purpose, the present application also proposes a process list generation method, which is applied to the server, and the process list generation method includes: Receive material data of target products sent by the client; Generate target prompt words according to the material data, and match corresponding historical production data from a predetermined historical database; The target prompt words and historical production data are input into a predetermined language model to generate a process list for the target product.

[0008] In one embodiment, the step of generating a target prompt word according to the material data includes: Get preset craft tip templates; The material data and the preset process prompt template are input into a predetermined prompt engineering model to generate a target prompt word for the target product.

[0009] In one embodiment, the step of inputting the target prompt word and historical production data into a predetermined language model to generate a process list for the target product includes: Inputting the target prompt word and the historical production data into a predetermined language model, so that the predetermined language model retrieves associated data from the historical production data based on the target prompt word, and generates current level process content based on the associated data; Inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level, the execution steps are: inputting the target prompt words and historical production data into a predetermined language model; After the generated current-level process content is the lowest process level, each of the current-level process content is merged into a process list for the target product.

[0010] In one embodiment, the step of inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level includes: Obtaining a next-level process prompt template from the preset process prompt template; The process content of the current level and the process prompt template of the next level are input into a predetermined prompt engineering model to generate target prompt words of the next level.

[0011] In one embodiment, after the step of inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level, the following steps are included: Extracting features of the process content at the current level to obtain current process features; Based on the current process characteristics, new historical production data is matched from the predetermined historical database, and the step of: inputting the target prompt word and the historical production data into a predetermined language model is performed.

[0012] In one embodiment, after the step of retrieving associated data from the historical production data based on the target prompt word by the predetermined language model and generating the current level process content based on the associated data, the method further includes: Receiving calibration process content for the current level process content; Based on the current level process content and the calibration process content, the predetermined language model is optimized to obtain a new predetermined language model.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a process list generation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the process list generation method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the process list generation method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the process list generation method described above are implemented.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application obtains the material data of the target product and sends the material data to the service end, so that the service end generates a target prompt word according to the material data, matches the corresponding historical production data from the predetermined historical database, inputs the target prompt word and the historical production data into a predetermined language model, and generates a process list for the target product. Thus, this application generates the target prompt word through the material data of the target product, thereby guiding the predetermined language model to retrieve data related to the material data from the historical production data, and sorting and generating the process list for the target product. Then, after receiving the process list fed back by the service end, the process list can be displayed. Therefore, on the one hand, this application can realize the generation of the process list without relying on the personal ability of the process engineer, effectively improving the generation efficiency of the process list and the objectivity of the process list. On the other hand, the process list of this application is generated based on real historical production data by guiding the predetermined language model, so the availability and quality of the generated process list are also guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of a process flow diagram provided for Example 1 of the process list generation method of this application; Figure 2 A schematic diagram of a process flow diagram provided for Embodiment 2 of the process list generation method of this application; Figure 3 A schematic diagram of a process flow diagram provided for Embodiment 3 of the process list generation method of this application; Figure 4 Generate a scene graph for the process list involved in the embodiment of the present application; Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the process list generation method in the embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: obtaining material data of the target product; sending the material data to the server, so that the server generates a target prompt word according to the material data, and matches the corresponding historical production data from a predetermined historical database, inputting the target prompt word and the historical production data into a predetermined language model, and generating a process list for the target product; after receiving the process list fed back by the server, displaying the process list.

[0024] In this embodiment, for ease of description, the following description is made with the process list generating device as the execution subject.

[0025] In the existing technology, in the current MPM system practice, although it has achieved remarkable results in production planning and scheduling, material management, quality control, etc., it still highly relies on the personal experience and professional judgment of process engineers in the core link of R&D process design. Therefore, the process list manually designed by the process engineer is greatly affected by the process engineer's knowledge background, work experience and subjective judgment, resulting in low efficiency in the generation of the process list.

[0026] The present application provides a solution, which generates target prompt words through the material data of the target product, thereby guiding the predetermined language model to retrieve data related to the material data from the historical production data, and organize and generate the process list of the target product. Therefore, on the one hand, the present application can realize the generation of the process list without relying on the personal ability of the process engineer, effectively improving the generation efficiency of the process list and the objectivity of the process list. On the other hand, the process list of the present application is generated based on real historical production data by guiding the predetermined language model, thus also ensuring the availability and quality of the generated process list.

[0027] Based on this, the present application embodiment provides a method for generating a process list, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the process list generation method of the present application.

[0028] In this embodiment, the process list generation method is applied to the client, including steps S10 to S30: Step S10, obtaining material data of the target product; It should be noted that the executor of this embodiment is a client, which may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc.

[0029] In addition, it should be noted that the target product is the product that is expected to be manufactured, such as watches, smart glasses and other objects, and the material data includes the lower-level materials used to make the target product, as well as the subordinate relationship between the lower-level materials and the target product, the unit dosage of the lower-level materials, material properties and other properties of the lower-level materials.

[0030] In this embodiment, after receiving the process list generation instruction, the client can read the material data of the target product corresponding to the process list generation instruction. For example, the client can display the list of materials to be selected to the user, and after receiving the process list generation instruction issued by the user, read the list of materials to be selected selected by the user as the material data of the target product.

[0031] Step S20, sending the material data to the server, so that the server generates a target prompt word according to the material data, matches the corresponding historical production data from a predetermined historical database, inputs the target prompt word and the historical production data into a predetermined language model, and generates a process list for the target product; It should be noted that the server is a device that provides target prompt word generation service and predetermined language model service, such as a local server, a cloud server, etc.

[0032] In addition, it should be noted that the predetermined historical database at least includes historical production data corresponding to the target product, and the historical production data may include relevant data of the historical production process.

[0033] In addition, it should be noted that the predetermined language model can be a Transformer model, BERT (Bidirectional Encoder Representations from Transformers, a deep learning model based on the Transformer architecture), a convolutional neural network, a recurrent neural network, or other models trained for natural language processing.

[0034] As an example, in this embodiment, the material data may be sent to the server, and the server generates a target prompt word according to the material data and a preset process prompt template, and matches the corresponding historical production data from a predetermined historical database according to the material data. Then, the target prompt word and the historical production data may be input into a predetermined language model, so that the predetermined language model retrieves associated data from the historical production data based on the target prompt word, and generates a process list for the target product based on the associated data.

[0035] As another example, in order to improve the accuracy of the process list, this embodiment can send the material data to the server, and the server generates a target prompt word according to the process prompt template of the highest level (such as the process level) in the preset process prompt template based on the material data, and matches the corresponding historical production data from the preset historical database according to the material data. Then the server can input the target prompt word and the historical production data into a predetermined language model, so that the predetermined language model retrieves the associated data from the historical production data based on the target prompt word, and generates the current level process content based on the associated data. Then the server generates a new target prompt word based on the current level process content and the next level prompt template in the preset process prompt template, and executes the steps of: inputting the target prompt word and the historical production data into the predetermined language model until it is iterated to the generated current level process content is the lowest level (such as the process unit level), and then merging the current level process content into the process list of the target product.

[0036] Step S30: after receiving the process list fed back by the server, display the process list.

[0037] It should be noted that the process list may include the basic steps / operations, personnel, equipment, tooling, tools, working hours, process parameters and other control requirements for each process level such as process, workstation, workstation, process unit, etc. in the production process of the target product.

[0038] After receiving the process list of the target product fed back by the server, this embodiment can display the process list in at least one form such as text, image, and voice. Furthermore, after displaying the process list, this embodiment can also obtain a calibrated process list for the process list, and optimize the predetermined language model based on the process list and the calibrated process list to obtain a new predetermined language model. In this way, the predetermined language model can be optimized and iterated with each process of generating the process list, so that the predetermined language model is more suitable for the generation of the process list, and the generated process list is more accurate.

[0039] The first embodiment of the present application provides a method for generating a process list, by obtaining the material data of the target product and sending the material data to the server, so that the server generates a target prompt word according to the material data, matches the corresponding historical production data from the predetermined historical database, inputs the target prompt word and the historical production data into a predetermined language model, and generates a process list for the target product. Thus, the target prompt word generated by the material data of the target product in this embodiment guides the predetermined language model to retrieve data related to the material data from the historical production data, sorts and generates a process list for the target product. Then, after receiving the process list fed back by the server, the process list is displayed. Therefore, on the one hand, this embodiment can realize the generation of the process list without relying on the personal ability of the process engineer, effectively improving the generation efficiency of the process list and the objectivity of the process list. On the other hand, the process list of the present application is generated based on real historical production data by guiding the predetermined language model, so the availability and quality of the generated process list are also guaranteed.

[0040] Based on this, the present application also provides a method for generating a process list, referring to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the process list generation method of the present application.

[0041] In this embodiment, the process list generation method is applied to the server, including steps S40 to S60: Step S40, receiving material data of the target product sent by the client; Step S50, generating a target prompt word according to the material data, and matching the corresponding historical production data from a predetermined historical database; Step S60: input the target prompt words and historical production data into a predetermined language model to generate a process list for the target product.

[0042] It should be noted that the executor of this embodiment is the server, which may be a computing service device with data processing, network communication and program running functions, such as a server, a cloud device, etc.

[0043] As an example, after receiving the material data of the target product sent by the client, the server in this embodiment generates a target prompt word according to the material data and a preset process prompt template, and matches the corresponding historical production data from a predetermined historical database according to the material data. Then, the target prompt word and the historical production data can be input into a predetermined language model, so that the predetermined language model retrieves the associated data from the historical production data based on the target prompt word, and generates the process list of the target product based on the associated data. The preset process prompt template is a template pre-set to guide the predetermined language model to generate the prompt word of the process list.

[0044] As another example, in order to improve the accuracy of the process list, the preset process prompt template may include multiple process prompt templates divided according to the process level, such as a process prompt template at the process level, a process prompt template at the workstation level, a process prompt template at the workstation level, and a process prompt template at the process unit level. It is understandable that the process level can be set according to actual needs, and can be more or less than the process level in the above example. In this embodiment, the server can generate a target prompt word according to the material data and the process prompt template at the highest level (such as the process level) in the preset process prompt template, and match the corresponding historical production data from the predetermined historical database according to the material data. Then, the target prompt word and the historical production data can be input into a predetermined language model, so that the predetermined language model retrieves the associated data from the historical production data based on the target prompt word, and generates the current level process content based on the associated data. Then, a new target prompt word is generated based on the current level process content and the next level prompt template in the preset process prompt template, and the steps are executed: the target prompt word and historical production data are input into a predetermined language model, until the current level process content generated by iteration is the lowest process level (such as the process unit level), and then the current level process contents are merged into the process list of the target product.

[0045] In a feasible embodiment, the step of generating a target prompt word according to the material data in step S50 includes steps S51-S52: Step S51, obtaining a preset process prompt template; Step S52, inputting the material data and the preset process prompt template into a predetermined prompt engineering model to generate a target prompt word for the target product.

[0046] It should be noted that the predetermined prompt engineering model is a model pre-set for generating prompt words, such as GPT (Generative Pre-trained Transformer), BERT (Bidirectional Encoder Representations from Transformers), T5 (Text-to-Text Transfer Transformer), BART (Bidirectional and Auto-Regressive Transformers) and other models.

[0047] It should also be noted that the preset process prompt template is a template that is pre-set to guide a predetermined language model to generate prompt words for a process list. The preset process prompt template can be a single prompt template or a plurality of process prompt templates divided according to process levels, such as a process prompt template at the process level, a process prompt template at the workstation level, a process prompt template at the workstation level, and a process prompt template at the process unit level.

[0048] Taking the preset process prompt template as a separate prompt template as an example, in this embodiment, the server can obtain the preset process prompt template, input the material data and the preset process prompt template into the preset prompt engineering model, and generate the target prompt words of the target product. The generated target prompt words can output a complete process list after inputting the preset language model.

[0049] Taking the example that the preset process prompt template is a plurality of process prompt templates divided according to the process level, the server in this embodiment can obtain the preset process prompt template, input the material data and the process prompt template of the highest process level in the preset process prompt template into the predetermined prompt engineering model, and generate the target prompt word of the target product. The target prompt word generated at this time can output the current level process content of the target product belonging to the highest process level after inputting the predetermined language model. Then the server obtains the process prompt template of the next level in the preset process prompt template, inputs the current level process content and the process prompt template of the next level into the predetermined prompt engineering model, generates the target prompt word of the next level, and then executes the step of inputting the target prompt word and the historical production data into the predetermined language model. After the generation of the current level process content of all process levels is completed, it is merged into a process list.

[0050] In this embodiment, by setting a prompt word template for process bill generation in advance (i.e., a preset process prompt template), the material data and the preset process prompt template can be input into a predetermined prompt engineering model to generate a target prompt word for the target product, thereby making the target prompt word more in line with the user's needs for process bill generation.

[0051] The second embodiment of the present application provides a method for generating a process list, by receiving the material data of the target product sent by the client; generating a target prompt word according to the material data, and matching the corresponding historical production data from a predetermined historical database; inputting the target prompt word and the historical production data into a predetermined language model to generate a process list for the target product. Thus, the target prompt word generated by the material data of the target product in this embodiment guides the predetermined language model to retrieve data related to the material data from the historical production data, and sorts and generates a process list for the target product. Then, after receiving the process list fed back by the service end, the process list can be displayed. Therefore, on the one hand, this embodiment can realize the generation of the process list without relying on the personal ability of the process engineer, effectively improving the generation efficiency of the process list and the objectivity of the process list. On the other hand, the process list of the present application is generated based on real historical production data by guiding the predetermined language model, so the availability and quality of the generated process list are also guaranteed.

[0052] Based on the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned second embodiment can refer to the above introduction, and will not be repeated in the following. Figure 3 , step S50 includes steps S53 to S55: Step S53, inputting the target prompt word and the historical production data into a predetermined language model, so that the predetermined language model retrieves associated data from the historical production data based on the target prompt word, and generates the current level process content based on the associated data; Step S54, inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level, executing the steps: inputting the target prompt words and historical production data into a predetermined language model; Step S55, after the generated current level process content is the lowest process level, each of the current level process contents is merged into a process list of the target product.

[0053] In this embodiment, the server inputs the target prompt word and the historical production data into a predetermined language model, so that the predetermined language model retrieves the associated data from the historical production data based on the target prompt word, and generates the current level process content based on the associated data. Then the current level process content is input into the predetermined prompt engineering model to generate the target prompt word of the next level, and the step of inputting the target prompt word and the historical production data into the predetermined language model is performed. Thus, this embodiment generates the target prompt word of the next level based on the current level process content output by the predetermined language model, which is used for the input of the predetermined language model, thereby realizing the gradual refinement of the process list of the target product from the highest process level (process level) to the lowest process level (station unit level). After the generated current level process content is the lowest process level, each current level process content is merged into the process list of the target product. Therefore, compared with the one-time generation method, the process list generated by this embodiment has higher accuracy and practicality.

[0054] In an optional embodiment, the step of inputting the process content of the current level into a predetermined prompt engineering model to generate a target prompt word of the next level in step S54 includes steps A10 to A20: Step A10, obtaining a next-level process prompt template in the preset process prompt template; Step A20, inputting the process content of the current level and the process prompt template of the next level into a predetermined prompt engineering model to generate target prompt words of the next level.

[0055] This embodiment can obtain the next level of process prompt templates from the preset process prompt templates; input the current level process content and the next level process prompt template into the predetermined prompt engineering model to generate the next level of target prompt words. Therefore, this embodiment generates target prompt words for each process level on the one hand, and generates target prompt words based on the current level process content on the other hand, so that the target prompt words can be more targeted to each process level, and the output current level process content is more accurate.

[0056] In an optional embodiment, after the step of inputting the process content of the current level into a predetermined prompt engineering model to generate the target prompt words of the next level in step S54, steps B10 to B20 are included: Step B10, extracting features from the current level process content to obtain current process features; Step B20, based on the current process characteristics, new historical production data is matched from the predetermined historical database, and the step of: inputting the target prompt word and the historical production data into a predetermined language model is executed.

[0057] In order to further improve the accuracy of each current level process content, in this embodiment, the feature extraction of the current level process content is performed to obtain the current process feature. Then, based on the current process feature, the historical data in the predetermined historical database are matched, and the historical data with a matching rate higher than the predetermined matching threshold is used as the current process feature to match the new historical production data, and the step of inputting the target prompt word and the historical production data into a predetermined language model is performed. In this embodiment, after the current level process content of each process level is generated, the historical production data can be updated, so that the subsequent predetermined language model retrieves the associated data based on the target prompt word of the next level and generates the current level process content of the next level. The historical production data used has a better correlation with the next process level, which helps to improve the accuracy and comprehensiveness of the current level process content of the next level.

[0058] In an optional embodiment, step S53 includes steps C10 to C20: Step C10, receiving calibration process content for the current level process content; Step C20: optimizing the predetermined language model based on the current level process content and the calibration process content to obtain a new predetermined language model.

[0059] It should be noted that the calibration process content may be calibration information for the current level process content, or may be the calibrated current level process content.

[0060] It is understandable that since the predetermined language model may not be constructed specifically for the generation of a process list, there may be deviations in description and logic. In this embodiment, after the current level process content is generated, if the calibration process content for the current level process content is received, a corresponding loss function can be constructed based on the difference between the current level process content and the calibration process content, and then the model parameters of the predetermined language model can be updated based on the loss function to optimize the predetermined language model and obtain a new predetermined language model. Therefore, this embodiment can make the output accuracy of the predetermined language model higher through this optimization process.

[0061] The third embodiment of the present application provides a method for generating a process list, which generates a target prompt word of the next level based on the current level process content output by a predetermined language model, and is used for the input of the predetermined language model, thereby realizing the gradual refinement of the process list of the target product from the highest process level (process level) to the lowest process level (station unit level). After the generated current level process content is the lowest process level, each current level process content is merged into the process list of the target product. Therefore, the process list generated by this embodiment has higher accuracy and practicality than the one-time generation method.

[0062] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the process list generation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0063] Please refer to Figure 4 , Figure 4 A scene graph is generated for the process list involved in the embodiment of the present application. In this embodiment, the server may include a data layer and an application layer, and the data layer includes a predetermined historical database and a predetermined prompt engineering model. The user end may be equipped with an MPM system, and the MPM system obtains the material data of the target product and sends it to the application layer of the server end, and the application layer matches the material data with the historical data in the predetermined historical database to obtain the historical production data of the target product. And the material data is input into the predetermined prompt engineering model to obtain the target prompt word. Then the target prompt word and the historical production data are input into the predetermined language model to obtain the current level process content and store it. Then the current level process content is matched with the historical data in the predetermined historical database to obtain new historical production data, and the current level process content is input into the predetermined prompt engineering model to obtain the target prompt word of the next level, and then the step of inputting the target prompt word and the historical production data into the predetermined language model to obtain the current level process content, until the current level process content of each process level is generated, the current level process content of each process level is integrated to obtain the process list of the target product, and the process list is fed back to the client for display.

[0064] The present application provides a process list generation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the process list generation method in the above-mentioned embodiment one.

[0065] Reference below Figure 5, which shows a schematic diagram of the structure of a process list generation device suitable for implementing the embodiment of the present application. The process list generation device in the embodiment of the present application can be a client or a server, and the process list generation device includes but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted hosts), and fixed terminals such as desktop computers and servers. Figure 5 The process list generating device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0066] like Figure 5 As shown, the process list generation device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the process list generation device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the process list generation device to communicate with other devices wirelessly or wired to exchange data. Although the process list generation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0067] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0068] The process list generation device provided by the present application adopts the process list generation method in the above embodiment, which can solve the technical problem of low generation efficiency of the existing process list. Compared with the prior art, the beneficial effects of the process list generation device provided by the present application are the same as the beneficial effects of the process list generation method provided by the above embodiment, and the other technical features in the process list generation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0069] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0070] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0071] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the process list generating method in the above-mentioned embodiment.

[0072] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0073] The computer-readable storage medium may be included in the process bill generating device; or may exist independently without being assembled into the process bill generating device.

[0074] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a process list generating device, the process list generating device: obtains material data of a target product; sends the material data to a server, so that the server generates a target prompt word based on the material data, matches the corresponding historical production data from a predetermined historical database, inputs the target prompt word and the historical production data into a predetermined language model, and generates a process list for the target product; and after receiving the process list fed back by the server, displays the process list.

[0075] Alternatively, receiving material data of a target product sent by a client; generating a target prompt word based on the material data, and matching corresponding historical production data from a predetermined historical database; inputting the target prompt word and historical production data into a predetermined language model to generate a process list for the target product.

[0076] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0077] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0079] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned process list generation method, and can solve the technical problem of low efficiency in generating the existing process list. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the process list generation method provided in the above-mentioned embodiment, and will not be described in detail here.

[0080] The present application also provides a computer program product, including a computer program, which implements the steps of the process list generation method as described above when executed by a processor.

[0081] The computer program product provided by this application can solve the technical problem of low efficiency in generating the existing process list. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as those of the process list generating method provided by the above embodiment, which will not be described in detail here.

[0082] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A process list generation method, It is characterized in that Applied to the client, the process list generation method includes: Get the material data of the target product; Sending the material data to the server, so that the server generates a target prompt word according to the material data, matches the corresponding historical production data from a predetermined historical database, inputs the target prompt word and the historical production data into a predetermined language model, and generates a process list for the target product; After receiving the process list fed back by the server, the process list is displayed.

2. A process list generation method, It is characterized in that Applied to the server, the process list generation method includes: Receive material data of target products sent by the client; Generate target prompt words according to the material data, and match corresponding historical production data from a predetermined historical database; The target prompt words and historical production data are input into a predetermined language model to generate a process list for the target product.

3. The process list generation method according to claim 2, It is characterized in that The step of generating a target prompt word according to the material data comprises: Get preset craft tip templates; The material data and the preset process prompt template are input into a predetermined prompt engineering model to generate a target prompt word for the target product.

4. The process list generation method according to claim 3, It is characterized in that The step of inputting the target prompt word and historical production data into a predetermined language model to generate a process list for the target product includes: Inputting the target prompt word and the historical production data into a predetermined language model, so that the predetermined language model retrieves associated data from the historical production data based on the target prompt word, and generates current level process content based on the associated data; Inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level, the execution steps are: inputting the target prompt words and historical production data into a predetermined language model; After the generated current-level process content is the lowest process level, each of the current-level process contents is merged into a process list for the target product.

5. The process list generation method according to claim 4, It is characterized in that The step of inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level includes: Obtaining a next-level process prompt template from the preset process prompt template; The process content of the current level and the process prompt template of the next level are input into a predetermined prompt engineering model to generate target prompt words of the next level.

6. The process list generation method according to claim 4, It is characterized in that After the step of inputting the process content of the current level into a predetermined prompt engineering model to generate target prompt words of the next level, the method includes: Extracting features of the current level process content to obtain current process features; Based on the current process characteristics, new historical production data is matched from the predetermined historical database, and the step of: inputting the target prompt word and the historical production data into a predetermined language model is performed.

7. The process list generation method according to claim 4, It is characterized in that After the step of retrieving associated data from the historical production data based on the target prompt word by the predetermined language model and generating the current level process content based on the associated data, the method includes: Receiving calibration process content for the current level process content; Based on the current level process content and the calibration process content, the predetermined language model is optimized to obtain a new predetermined language model.

8. A process list generation device, It is characterized in that The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the process bill generating method according to any one of claims 1 to 7.

9. A storage medium, It is characterized in that The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the process list generation method according to any one of claims 1 to 7 are implemented.

10. A computer program product, It is characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the process list generating method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Intelligent process generation method and system based on data driving

    CN118297275A

  • Production manufacturing instruction generation method and device, equipment and storage medium

    CN118396250A

  • Laser trajectory feeder with cooling device

    KR1020240074551A

  • Knowledge-based assembly process planning method, apparatus and system

    WO2022252061A1

Cited By

  • Information processing method, information processing device, and information processing program

    WO2026105549A1