System for constructing a standardized process based on an AIGC model

Abstract

The present invention belongs to the field of artificial intelligence technology. It provides a system for constructing a standardized process based on an AIGC model, including: a reference data acquisition module determines the object attribute information of the target object for which a standardized process needs to be constructed, and accordingly obtains the handling operation information of other identical or similar objects; a standardized process construction module generates prompt information based on the object attribute information, and calls the AIGC model to automatically generate preliminary second standardized process information for the prompt information and the handling operation information; a standardized process modification module corrects the generated second standardized process information based on the modification opinions of the management personnel to obtain third standardized process information, outputs it to the management personnel, and stores it in a specified storage area based on the confirmation operation of the management personnel. The present invention utilizes the AIGC model to achieve the efficient and automatic construction of the standardized process, and its rationality is higher, which is beneficial to improving the accuracy of handling abnormal situations.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and more particularly, to a system for constructing a standardized process based on an AIGC model. Background Art

[0002] In the process of enterprise production management, constructing in advance a standardized process for handling various abnormal situations and promptly handling the emerging abnormal situations according to this standardized process can significantly improve the handling efficiency of abnormal situations and reduce production losses. However, the existing standardized processes are basically formulated based on the production experience of a small number of experienced production personnel, which may not necessarily be the optimal ones, and such standardized processes formulated entirely relying on production experience are also obviously not applicable to those new devices and new products.

[0003] Therefore, how to further optimize and adjust the standardized process for enterprise production management is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0004] In view of this, the present invention provides a system for constructing a standardized process based on an AIGC model, an electronic device, a computer storage medium, and a computer program product to solve the above technical problems.

[0005] The present invention discloses a system for constructing a standardized process based on an AIGC model, the system comprising a reference data acquisition module, a standardized process construction module, and a standardized process modification module; wherein, the reference data acquisition module is configured to determine the object attribute information of a target object for which a standardized process is to be constructed, and acquire the handling operation information of the same or similar other objects according to the object attribute information; wherein, the handling operation information includes handling operation record information and first standardized process information; the standardized process construction module is configured to generate a prompt message based on the object attribute information, call the AIGC model to automatically generate preliminary second standardized process information from the prompt message and the handling operation information, and output the second standardized process information to the management personnel; the standardized process modification module is configured to perform partial correction on the generated second standardized process information based on the modification opinions of the management personnel to obtain third standardized process information, output the third standardized process information to the management personnel, and store it in a specified storage area based on the confirmation operation of the management personnel.

[0006] In some embodiments, obtaining the handling operation information of other same or similar objects according to the object attribute information includes: determining several other same or similar objects according to the object attribute information, obtaining the first standardized process information of other objects belonging to the same type, and obtaining the handling operation record information of other objects belonging to similar types; wherein, obtaining the handling operation record information of other objects belonging to similar types includes: according to the similarity degree between the target object and other objects belonging to similar types, determining the number of data acquisition items and the time distribution length of the acquired data according to the similarity degree, and obtaining the handling operation record information of other objects belonging to similar types according to the number of data acquisition items and the time distribution length.

[0007] In some embodiments, generating the prompt information based on the object attribute information includes: separating the expert information of the standardized process from the object attribute information, where the expert information includes the number of experts and the level evaluation information of each expert, and evaluating the expert ability level information according to the number of experts and each level evaluation information; determining the refined level corresponding to the second standardized process information according to the expert ability level information and the preset relationship, and generating the prompt information according to the refined level.

[0008] In some embodiments, evaluating the expert ability level information according to the number of experts and each level evaluation information includes: inputting the number of experts and each level evaluation information into a convolutional evaluation model, and the convolutional evaluation model outputs the evaluated expert ability level information; wherein, the expert ability level information is a level value, and the higher the level value, the higher the expert ability, and vice versa.

[0009] In some embodiments, the convolutional evaluation model is trained by a distributed training method based on a consortium blockchain.

[0010] In some embodiments, locally correcting the generated second standardized process information based on the modification opinions of the management personnel to obtain the third standardized process information includes: performing semantic analysis on each modification opinion to determine its corresponding position in the second standardized process information, and locally modifying or replacing the standardized process information at the position according to the modification opinion; repeating the above steps to obtain the third standardized process information.

[0011] In some embodiments, outputting the third standardized process information to the management personnel and storing it in the designated storage area based on the confirmation operation of the management personnel includes: sending the third standardized process information to another group of experts for verification and confirmation. If the confirmation from another group of experts is received, then: outputting the third standardized process information to the management personnel and storing it in the designated storage area based on the confirmation operation of the management personnel.

[0012] The present invention also discloses an electronic device, which is applied to a standardized process construction system based on an AIGC model as described in any one of the preceding items, and includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0013] The present invention also discloses a computer storage medium, which is applied to a standardized process construction system based on an AIGC model as described in any one of the preceding items, and the computer-readable storage medium stores a computer program.

[0014] The present invention also discloses a computer program product, which is applied to a standardized process construction system based on an AIGC model as described in any one of the preceding items; the computer program product includes executable computer program code.

[0015] The beneficial effects of the present invention are as follows: The solution of the present invention can utilize the AIGC model to realize the automatic construction of the standardized process, and the construction efficiency of the standardized process is very high; on the other hand, the standardized process constructed by the present invention refers to the disposal operation information of more other objects that are the same or similar, and its rationality is higher, which is beneficial to improving the accuracy of disposing abnormal situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0017] Figure 1 is a schematic structural diagram of a standardized process construction system based on an AIGC model disclosed in an embodiment of the present invention.

[0018] Figure 2 is a schematic diagram of data processing of a standardized process construction system based on an AIGC model disclosed in an embodiment of the present invention.

[0019] Figure 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. Detailed implementation manners

[0020] The following specific embodiments illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0021] In addition, the technical features involved in different implementation manners of the present application described below can be combined with each other as long as they do not conflict with each other.

[0022] As Figure 1 、 Figure 2 shown, an embodiment of the present invention discloses a standardized process construction system based on an AIGC model. The system includes a reference data acquisition module, a standardized process construction module, and a standardized process modification module. Among them, the reference data acquisition module is used to determine the object attribute information of the target object for which the standardized process needs to be constructed, and obtain the handling operation information of the same or similar other objects according to the object attribute information. Among them, the handling operation information includes handling operation record information and first standardized process information. The standardized process construction module is used to generate prompt information based on the object attribute information, call the AIGC model to automatically generate preliminary second standardized process information for the prompt information and the handling operation information, and output the second standardized process information to the management personnel. The standardized process modification module is used to locally correct the generated second standardized process information based on the modification opinions of the management personnel to obtain third standardized process information, output the third standardized process information to the management personnel, and store it in a specified storage area based on the confirmation operation of the management personnel.

[0023] In the above technical solution, the standardized process construction system of the present invention utilizes an AIGC model to achieve the automatic construction of a standardized process. Specifically: First, the reference data acquisition module first determines the target object for which a standardized process needs to be formulated this time, and obtains object attribute information including equipment type, equipment use, equipment model, etc., and obtains the handling operation information of the same or similar other objects in multiple acquisition channels according to the object attribute information, including handling operation record information and the first standardized process information. Next, the standardized process construction module first generates a prompt message based on the object attribute information, and then calls the AIGC model. Under the constraint of the prompt message, the AIGC model processes the handling operation information to automatically generate preliminary second standardized process information and outputs the second standardized process information to the management personnel for verification. If there are any unreasonable places, the management personnel will input relevant opinion information on the interaction interface. Finally, the standardized process modification module locally corrects the generated second standardized process information based on the modification opinions of the management personnel to obtain the final third standardized process information. The third standardized process information is output to the management personnel on the one hand, and can be automatically stored in the specified storage area after the management personnel confirm it for subsequent use.

[0024] The solution of the present invention can utilize the AIGC model to achieve the automatic construction of a standardized process, and the construction efficiency of the standardized process is very high; on the other hand, the standardized process constructed by the present invention refers to more handling operation information of the same or similar other objects, and its rationality is higher, which is beneficial to improving the accuracy of handling abnormal situations.

[0025] AIGC is the abbreviation of the English phrase "Artificial Intelligence Generated Content", which means "Artificial Intelligence Generated Content" in Chinese. This is a relatively new concept, referring to the use of artificial intelligence technology to create or generate various types of digital content, such as text, images, audio, videos, etc. The advantage of AIGC lies in its high efficiency and innovation. Compared with the traditional manual creation method, AIGC can greatly shorten the content creation time and improve production efficiency. At the same time, due to the powerful data processing and analysis capabilities of artificial intelligence, it can generate more personalized and diverse content to meet the needs of different users. The present invention utilizes AIGC to automatically generate preliminary standardized process information.

[0026] In some embodiments, obtaining the handling operation information of other objects that are the same or similar according to the object attribute information includes: determining several other objects that are the same or similar according to the object attribute information, obtaining the first standardized process information of other objects belonging to the same type, and obtaining the handling operation record information of other objects belonging to similar types; wherein, obtaining the handling operation record information of other objects belonging to similar types includes: according to the similarity degree between the target object and other objects belonging to similar types, determining the number of data to be obtained and the time distribution length of the obtained data according to the similarity degree, and obtaining the handling operation record information of other objects belonging to similar types according to the number of data to be obtained and the time distribution length.

[0027] In the embodiments of the present invention, the AIGC model of the present invention generates preliminary standardized process information by referring to the handling operation information of other objects that are the same or similar. In specific implementation, if an other object is the same as the target object, such as a certain device of the same brand and the same model, the ready-made first standardized process information of this other object is directly obtained; and if an other object is similar to the target object, such as the same brand but different models, or different brands but the same use and function of a certain device, the handling operation record information of these devices is obtained, and the handling operation record information refers to the historical record of the actual handling methods taken by the staff when various types of abnormal situations occur in similar other objects.

[0028] In addition, for the first standardized process information of other objects of the same type (similarity degree 100%), only one piece can be obtained, or several pieces can of course be obtained to cope with the fine-tuning of the first standardized process information. For the handling operation record information of other objects of similar types, an appropriate number of data to be obtained needs to be determined, which can ensure that the AIGC model extracts accurate and effective information from it. Specifically: first calculate the similarity degree between the target object and this other object (such as 75%, 80%), determine the number of data to be obtained and the time distribution length of the obtained data according to the similarity degree, where the number of data to be obtained is, for example, 100 pieces, 200 pieces, and the time distribution length of the data refers to the time duration between the earliest data and the latest data in the obtained data, such as 6 months, 12 months. Such settings can ensure that the amount of data obtained is within a reasonable range, and the time distribution of the obtained data is also within a reasonable range, because the standardized process information will change slowly due to actual production. For example, for a certain abnormal situation, the original handling method of device A was to stop device A, and later it was found that by reducing the load of device B, this abnormal situation of device A could be solved, and at this time the standardized process information would be modified. All in all, the higher the similarity degree, the more the corresponding number of data to be obtained and the longer the time distribution length.

[0029] Thus, by obtaining the disposal operation record information of similar devices within a reasonable range, the AIGC model can perform semantic analysis on more diverse data, thereby obtaining more appropriate standardized process information. For example, the above-mentioned changes in the abnormal disposal of Device A can guide the AIGC model to also tend to find a milder disposal process when determining the standard disposal process for other abnormal situations.

[0030] It should be noted that the similarity degree between the target object and other objects can be evaluated and calculated based on preset rules. The preset rules at least include the evaluation methods and evaluation result weights corresponding to the brand, model, function, usage, and specific parameters (power, size, etc.), which will not be elaborated here.

[0031] In some embodiments, generating the prompt information based on the object attribute information includes: separating the expert information of the standardized process from the object attribute information. The expert information includes the number of experts and the level evaluation information of each expert, and the expert ability level information is evaluated based on the number of experts and each level evaluation information; according to the expert ability level information and the preset relationship, the fine level corresponding to the second standardized process information is determined, and the prompt information is generated according to the fine level.

[0032] In the embodiment of the present invention, before the AIGC model processes the disposal operation information to generate the second standardized process information, it is also necessary to determine the prompt information for guiding the generation of the standardized process by the AIGC model. This prompt information mainly includes the fine level corresponding to the generated second standardized process information. The higher the fine level, the more detailed the disposal processes involved in the generated second standardized process information for each abnormal situation; the lower the fine level, the more rough the disposal processes involved in the generated second standardized process information for each abnormal situation. For example, for a high fine level, the generated second standardized process information is "reduce the operating power of Device A and shut down several devices including B, C, D, and E"; for a low fine level, the generated second standardized process information is "reduce the operating power of Device A and shut down multiple downstream devices related to Device A".

[0033] The reason for such a setting in the present invention is as follows: When it is evaluated that the higher the expert ability level of the manufacturer where the target device is located, the more concise the preliminary second standardized process information generated by the AIGC model is, and more detailed information can be supplemented by experts; while when it is evaluated that the lower the expert ability level of the manufacturer where the target device is located, the insufficient ability of experts to supplement, at this time, the preliminary second standardized process information generated by the AIGC model is more detailed, and experts only need to identify the error situations in the detailed standardized process, which can reduce the requirement degree for experts to supplement details. Obviously, in the preset relationship, the expert ability level information and the refinement level of the second standardized process information are negatively correlated.

[0034] Among them, the expert ability level information is comprehensively evaluated based on the number of experts and the level evaluation information of each expert. The level evaluation information of experts can be comprehensively evaluated based on the expert's abnormal handling experience, professional title level, other technical titles, etc. This comprehensive evaluation can be automatically evaluated by a model or pre-evaluated by reviewers based on a scoring form. The present invention does not make specific limitations.

[0035] In some embodiments, evaluating the expert ability level information according to the number of experts and each level evaluation information includes: inputting the number of experts and each level evaluation information into a convolutional evaluation model, and the convolutional evaluation model outputs the expert ability level information evaluated by it; wherein, the expert ability level information is a level value, and the higher the level value, the higher the expert ability, and vice versa.

[0036] In the embodiments of the present invention, the present invention further pre-constructs a convolutional evaluation model, such as based on AlexNet, MobileNet, ResNet, etc. This convolutional evaluation model can classify the input number of experts and each level evaluation information, so as to obtain the high and low situation of the overall ability of the expert team of this manufacturer. The expert ability level information is a level value, and the higher the level value, the higher the expert ability, and vice versa.

[0037] In some embodiments, the convolutional evaluation model is trained by a distributed training method based on a consortium blockchain.

[0038] In the embodiments of the present invention, in order to ensure the evaluation and classification ability of the convolutional evaluation model, the present invention adopts a distributed training method to perform pre-training on the convolutional evaluation model before use. Specifically, the convolutional evaluation model is published on a consortium blockchain, which is a distributed network system based on blockchain technology and smart contracts and jointly maintained by multiple organizations. The present invention uses each organizational node in the consortium blockchain to train the convolutional evaluation model separately, and then feeds back the key model parameters in the trained convolutional evaluation model to the local organizational node. The local organizational node performs a fusion process on the key model parameters, that is, preliminary key model parameters are obtained, and a preliminary convolutional evaluation model is constructed from the preliminary key model parameters. Finally, the local organizational node uses the training data to perform local training on the preliminary convolutional evaluation model until the training reaches the standard.

[0039] In some embodiments, the locally correcting the generated second standardized process information based on the modification opinions of the management personnel to obtain third standardized process information includes: performing semantic analysis on each of the modification opinions to determine its corresponding position in the second standardized process information, and locally modifying or replacing the standardized process information at the position according to the modification opinion; repeating the above steps to obtain the third standardized process information.

[0040] In the embodiments of the present invention, after receiving multiple modification opinions from the management personnel, since the modification opinions may not be directly marked at the corresponding positions in the second standardized process information, for example, they are centrally filled in a modification opinion document. Therefore, the present invention first uses a semantic analysis model to perform semantic analysis on each modification opinion to determine which standardized process information in the second standardized process information the modification opinion is directed to, that is, to determine the corresponding position of the modification opinion. Then, based on the above position correspondence relationship, the standardized process information at each position in the second standardized process information is automatically locally corrected, and the local correction includes modification or replacement.

[0041] In some embodiments, the outputting the third standardized process information to the management personnel and storing it in a specified storage area based on the confirmation operation of the management personnel includes: sending the third standardized process information to another group of experts for verification and confirmation. If the confirmation from another group of experts is received, then: outputting the third standardized process information to the management personnel and storing it in a specified storage area based on the confirmation operation of the management personnel.

[0042] In an embodiment of the present invention, the experts are divided into two groups. One group is used to put forward modification opinions for the standardized process modification module to locally correct the initially generated second standardized process information; while the other group of experts is responsible for re-verifying and confirming the third standardized process information after local correction. If there are no defects or errors, the third standardized process information is output to the manager of the standardized process and stored in a specified storage area based on the confirmation operation of the manager. The formulated standardized process can be executed in subsequent production management, that is, in the event of an abnormal situation, relevant response methods and response sequences are sought from the standardized process to ensure the normal operation of production or reduce losses.

[0043] Moreover, by generating the final standardized process through two groups of experts, the probability of a situation where local errors occur in the standardized process due to incorrect opinions of certain experts (such as experts with insufficient experience) can be reduced.

[0044] As Figure 3 shown, an embodiment of the present invention also discloses an electronic device, which is applied to a standardized process construction system based on an AIGC model as described in any one of the preceding items, and includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0045] An embodiment of the present invention also discloses a computer storage medium, which is applied to a standardized process construction system based on an AIGC model as described in any one of the preceding items, and the computer-readable storage medium stores a computer program.

[0046] An embodiment of the present invention also discloses a computer program product, which is applied to a standardized process construction system based on an AIGC model as described in any one of the preceding items; the computer program product includes executable computer program code.

[0047] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0048] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0050] As described above, only the preferred embodiments of the present invention are given, and they are not intended to limit the protection scope of the present invention.

Claims

1. A standardized process construction system based on the AIGC model, characterized by: The system includes a reference data acquisition module, a standardized process construction module, and a standardized process modification module; wherein, The reference data acquisition module is used to determine the object attribute information of the target object for which the standardized process construction is required, and to acquire the disposal operation information of other identical or similar objects according to the object attribute information; wherein the disposal operation information includes the disposal operation record information and the first standardized process information; The standardized process construction module is used to generate prompt information based on the object attribute information, call the AIGC model to automatically generate preliminary second standardized process information for the prompt information and the disposal operation information, and output the second standardized process information to the management personnel; The standardized process modification module is used to partially modify the generated second standardized process information based on the modification opinions of the management personnel, obtain the third standardized process information, output the third standardized process information to the management personnel, and store it in the designated storage area based on the confirmation operation of the management personnel; The acquiring, according to the object attribute information, the disposal operation information of other identical or similar objects includes: Determine a number of other identical or similar objects according to the object attribute information, obtain the first standardized process information of other objects of the same type, where the same type refers to the same brand and the same model; and obtain the disposal operation record information of other objects of a similar type, where the similar type refers to the same brand and different models, or different brands and the same purpose and function; Wherein, the obtaining of the disposal operation record information of other objects of similar type includes: calculating the similarity between the target object and other objects of similar type, determining the number of data acquisitions and the time distribution length of the acquired data according to the similarity, and obtaining the disposal operation record information of other objects of similar type according to the number of data acquisitions and the time distribution length; wherein, the higher the similarity, the more corresponding data acquisitions and the longer the time distribution length; The generating prompt information based on the object attribute information includes: Separating and deriving expert information of the standardized process from the object attribute information, the expert information including the number of experts and the level evaluation information of each expert, and deriving expert capability level information according to the number of experts and the level evaluation information; Determine a refinement level corresponding to the second standardized process information according to the expert capability level information and a preset relationship, and generate the prompt information according to the refinement level; Among them, when the expert capability level of the manufacturer of the target object is assessed to be higher, the preliminary second standardization process information generated by the AIGC model is set to be more concise, and more detailed information is supplemented by the experts; when the expert capability level of the manufacturer of the target object is assessed to be lower, the expert's ability to supplement is insufficient. At this time, the preliminary second standardization process information generated by the AIGC model is set to be more detailed, and the experts only need to identify errors in the detailed standardization process to reduce the requirement for the experts to supplement the details.

2. A standardized process construction system based on the AIGC model according to claim 1, characterized in that: The expert capability level information obtained by evaluating the number of experts and each level evaluation information includes: The number of experts and the level assessment information are input into a convolutional assessment model, and the convolutional assessment model outputs the expert ability level information obtained through its assessment; wherein the expert ability level information is a level value, and a higher level value represents a higher expert ability, and vice versa.

3. A standardized process construction system based on the AIGC model according to claim 2, characterized in that: The convolutional evaluation model is trained using a distributed training method based on a consortium chain.

4. A standardized process construction system based on the AIGC model according to claim 3, characterized in that: The partially modifying the generated second standardized process information based on the modification opinions of the management personnel to obtain the third standardized process information includes: Performing semantic analysis on each of the modification opinions to determine its corresponding position in the second standardized process information, and partially modifying or replacing the standardized process information at the position according to the modification opinion; Repeat the above steps to obtain the third standardized process information.

5. A standardized process construction system based on the AIGC model according to claim 4, characterized in that: The step of outputting the third standardized process information to the manager and storing the third standardized process information in a designated storage area based on the manager's confirmation operation includes: The third standardized process information is sent to another group of experts for verification and confirmation. If confirmation is received from the other group of experts, the third standardized process information is output to the management personnel and stored in a designated storage area based on the confirmation operation of the management personnel.

6. An electronic device, characterized in that: A standardized process construction system based on an AIGC model as described in any one of claims 1 to 5 comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

7. A computer storage medium, characterized in that: Applied to a standardized process construction system based on an AIGC model as described in any one of claims 1 to 5, the computer storage medium stores a computer program.

8. A computer program product, characterized in that: Applied to a standardized process construction system based on the AIGC model as described in any one of claims 1 to 5; the computer program product includes executable computer program code.

Images