Wide-area cloud manufacturing industrial service system and method based on Internet of Things large model

Abstract

The invention provides a wide-area cloud manufacturing industrial service system and method based on an Internet of Things large model. The system comprises a service cloud platform and a user platform, wherein the service cloud platform is configured to obtain a constraint index; determining first service data from historical service data corresponding to the user based on the constraint index; responding to the condition that the first service data meets user requirements, and displaying the first service data to the user through a user platform; and in response to the condition that the first service data does not meet the user demand, taking one or more candidate service data of which the matching degree meets a preset matching condition as one or more second service data, and presenting the one or more second service data to the user through the user platform. Through the system, real demands of a manufacturing enterprise can be obtained, and accurately matched service data is provided for the manufacturing enterprise, so that high-quality operation of wide-area cloud manufacturing industrial services is supported.

Description

Technical Field

[0001] This specification relates to the field of manufacturing services, and in particular to wide-area cloud manufacturing industrial service systems and methods based on the Internet of Things (IoT) big data model. Background Technology

[0002] With the acceleration of industrial digitalization, manufacturing enterprises are generally migrating R&D, design, production, warehousing, and logistics to the cloud, forming a wide-area cloud manufacturing ecosystem that spans regions and organizations. Wide-area cloud manufacturing leverages the Industrial Internet of Things (IIoT) to abstract dispersed resources such as design, processing, testing, and logistics into tradable services, which can then be accessed on demand by enterprises of different regions and sizes through a cloud platform, achieving resource co-construction and capability sharing. However, because different manufacturing enterprises use different terminology and have varying process capabilities, existing wide-area cloud manufacturing services cannot achieve precise matching in a short time.

[0003] Therefore, there is an urgent need to provide a wide-area cloud manufacturing industrial service system and methodology based on the Internet of Things (IoT) big data model. By acquiring the real needs of manufacturing enterprises, this system can provide them with accurately matched service data to support the high-quality operation of wide-area cloud manufacturing industrial services. Summary of the Invention

[0004] The invention includes a wide-area cloud manufacturing industrial service system based on an Internet of Things (IoT) big data model. The system comprises a service cloud platform and a user platform. The service cloud platform is configured to: acquire constraint indicators through the user platform; determine first service data from the user's historical service data based on the constraint indicators; display the first service data to the user through the user platform if the first service data meets the user's needs; and, if the first service data does not meet the user's needs, determine a candidate service pool from a service database based on the constraint indicators and the user's needs, and generate matching degrees between multiple candidate service data in the candidate service pool and the user's needs; and use one or more candidate service data whose matching degrees meet preset matching conditions as one or more second service data, and present the one or more second service data to the user through the user platform.

[0005] The invention includes a wide-area cloud manufacturing industrial service method based on an Internet of Things (IoT) big data model. The method is executed by a service cloud platform within the wide-area cloud manufacturing industrial service system based on the IoT big data model. The method includes: acquiring constraint indicators through a user platform; determining first service data from the user's historical service data based on the constraint indicators; displaying the first service data to the user through the user platform in response to the first service data meeting the user's needs; and determining a candidate service pool from a service database based on the constraint indicators and the user's needs, and generating matching degrees between multiple candidate service data in the candidate service pool and the user's needs; and selecting one or more candidate service data whose matching degrees meet preset matching conditions as one or more second service data, and presenting the one or more second service data to the user through the user platform.

[0006] The beneficial effects of this manual include, but are not limited to: (1) Through the wide-area cloud manufacturing industrial service system based on the Internet of Things big model, the real needs of manufacturing enterprises can be obtained, and accurate matching service data can be provided to manufacturing enterprises to support the high-quality operation of the wide-area cloud manufacturing industrial service. (2) By obtaining user needs and constraint indicators, the service data required by users can be quickly filtered, avoiding complex searches in massive data and significantly improving the matching speed. After the service data obtained by the quick filtering does not meet the user's needs, service data with a higher degree of matching with the user can be further filtered to further improve the user experience. (3) By using the big language model, keywords can be quickly extracted from the information input by the user, and the field can be intelligently generated based on the keywords using the preset fragment library to generate instructions. The preset fields that can guide the user to conduct information interaction can be quickly obtained through the industry big model. This phased and model-based processing method avoids the computational burden of directly using a single model to process massive data, and ensures the accuracy of the final generated preset fields. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein: Figure 1 This is a platform schematic diagram of a wide-area cloud manufacturing industrial service system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification. Figure 2 This is an exemplary flowchart of a wide-area cloud manufacturing industrial service method based on an IoT big data model, as shown in some embodiments of this specification. Figure 3 This is an exemplary flowchart illustrating the acquisition of user requirements and constraint indicators according to some embodiments of this specification; Figure 4 This is an exemplary schematic diagram of a matching model shown according to some embodiments of this specification. Detailed Implementation

[0008] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0009] Figure 1 This is a platform schematic diagram of a wide-area cloud manufacturing industrial service system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification.

[0010] In some embodiments, such as Figure 1 As shown, the wide-area cloud manufacturing industrial service system 100 based on the Internet of Things big model may include a user platform 110 and a service cloud platform 120.

[0011] In some embodiments, the user platform 110 is communicatively connected to the service cloud platform 120. The user platform 110 and the service cloud platform 120 can exchange information.

[0012] In some embodiments, the user platform 110 can communicate with user terminals of multiple users (e.g., user 1, user 2, ..., user n). The types of users include enterprises or individuals. The user platform 110 can receive information input from multiple users, such as basic sensory information.

[0013] In some embodiments, the user platform 110 may include a server and a user terminal. Users upload information to the server through user terminals (such as computers).

[0014] In some embodiments, the service cloud platform 120 may send the generated service data (such as first service data) to the user platform. The service cloud platform may include a public cloud, hybrid cloud, multi-layer cloud, or any combination thereof.

[0015] In some embodiments, the service cloud platform 120 includes a service business operation module 121, a service model library 122, a database 123, and a basic perception information acquisition interface 124, all connected by communication.

[0016] In some embodiments, the service cloud platform 120 is configured to obtain constraint indicators through a user platform, and determine first service data from the user's corresponding historical service data based on the constraint indicators. The service cloud platform 120 is also configured to display the first service data to the user through the user platform in response to the first service data meeting the user's needs. The service cloud platform 120 is further configured to, in response to the first service data not meeting the user's needs: determine a candidate service pool from a service database based on the constraint indicators and the user's needs, generate a matching degree between multiple candidate service data in the candidate service pool and the user's needs, and use one or more candidate service data whose matching degree meets preset matching conditions as one or more second service data, and present one or more second service data to the user through the user platform.

[0017] In some embodiments, the service business operation module 121 is configured to process or distribute data, information or instructions received by the service cloud platform 120.

[0018] In some embodiments, the service model library 122 is configured to manage user-related information. The service model library 122 may include a user service model 122-1 and a service data management model 122-2. The user service model 122-1 may be a model related to the user's industry, such as a large industry model. The service data management model 122-2 is configured to manage information related to service data (such as evaluation information).

[0019] In some embodiments, database 123 is configured to store data, information, or instructions received by the storage service cloud platform. Database 123 may include a user request database 123-1 and a service database 123-2. User request database 123-1 is configured to store user-related information, such as user requests and evaluation information. Service database 123-2 is configured to store storage service data, such as candidate service data and historical service data.

[0020] In some embodiments, the basic perception information acquisition interface 124 is configured to provide a data transmission channel between the user platform and the cloud platform. The basic perception information acquisition interface 124 may be a network communication interface, etc.

[0021] In some embodiments, the service cloud platform 120 may include a processor and memory. The service business computing module 121 is configured on the processor. The processor includes a central processing unit (CPU), an application-specific integrated circuit (ASIC), a controller, a microcontroller unit, a microprocessor, or any combination thereof.

[0022] In some embodiments, the service model library 122 and the database 123 may be configured within memory. In some embodiments, the memory may be integrated into a processor or located in the cloud, etc.

[0023] For further explanation of the above content, please see Figures 2-4 And its related descriptions.

[0024] In some embodiments of this specification, the wide-area cloud manufacturing industrial service system 100 based on the Internet of Things big data model can obtain the real needs of manufacturing enterprises and provide them with accurately matched service data to support the high-quality operation of the wide-area cloud manufacturing industrial service.

[0025] Figure 2 This is an exemplary flowchart of a wide-area cloud manufacturing industrial service method based on an IoT big data model, as shown in some embodiments of this specification. In some embodiments, the wide-area cloud manufacturing industrial service method process 200 based on an IoT big data model can be executed by a service cloud platform. Figure 2 As shown, the wide-area cloud manufacturing industrial service method 200 based on the Internet of Things big model includes the following steps.

[0026] Step 210: Obtain constraint indicators through the user platform.

[0027] For more information about users and the user platform, please see [link / reference]. Figure 1 And related descriptions.

[0028] Constraint metrics refer to the limiting factors that users specify for service data. For example, constraint metrics may include limitations on the type, industry, and / or category of service data. For instance, if a user inputs "articular robotic arm," then "articular" becomes a constraint metric for the robotic arm.

[0029] Service data refers to information or data provided to users. For example, if a user inquires about the specifications of a machine tool, the service data may include the machine tool's maximum turning diameter, maximum machining length, and spindle bore diameter, etc.

[0030] In some embodiments, the service cloud platform can extract information uploaded by users through the user platform using methods such as speech recognition, text recognition, or image recognition, and identify one or more constraint indicators from the information.

[0031] In some embodiments, the service cloud platform can also guide users to complete information interaction according to preset fields, thereby obtaining constraint indicators. (See also: [link to relevant content]) Figure 3 And its related descriptions.

[0032] Step 220: Based on the constraint indicators, determine the first service data from the user's corresponding historical service data.

[0033] Historical service data refers to the service data provided by the service cloud platform to the current user at a historical time.

[0034] In some embodiments, historical service data may include first service data and second service data displayed to users by the service cloud platform through the user platform at historical times. For further explanation of the second service data, see step 240 and its related description.

[0035] In some embodiments, the service cloud platform can extract historical service data corresponding to a user from the service database based on the user's identity characteristics (e.g., name or registration information). For descriptions of the service database and other libraries of the service cloud platform, see [link to relevant documentation]. Figure 1 And its related descriptions.

[0036] The first service data refers to service data that includes constraint indicators.

[0037] In some embodiments, the service cloud platform can filter historical service data containing constraint indicators from the user's corresponding historical service data based on constraint indicators, and use the obtained historical service data as the first service data. For example, if a user queries information related to "articular robotic arm" and the constraint indicator is "articular", the processor determines historical service data containing "articular" and related to robotic arms as the first service data.

[0038] In some embodiments, the first service data may include two scenarios: meeting user needs and not meeting user needs.

[0039] Step 230: In response to the fact that the first service data meets the user's needs, the first service data is displayed to the user through the user platform.

[0040] In some embodiments, the correspondence between the first service data and user needs includes the first service data meeting the user needs and the first service data not meeting the user needs.

[0041] User requirements refer to information related to the service data that a user expects to obtain. In some embodiments, user requirements may include the type, domain, and / or level of detail of the service data that the user expects to receive from the service cloud platform.

[0042] In some embodiments, the service cloud platform may obtain user requirements from historical time periods as current user requirements from a user requirements database.

[0043] In some embodiments, the service cloud platform can also guide users to complete information interaction according to preset fields, thereby obtaining user needs. (See also: [link to relevant content]) Figure 3 And its related descriptions.

[0044] In some embodiments, the first service data meeting user needs can be defined as follows: the similarity between the types of service data in the first service data and the types of service data in the user's needs is not less than a first similarity threshold, and the user's evaluation information of the first service data is not less than an evaluation threshold. The first similarity threshold and the evaluation threshold can be preset based on historical experience. For an explanation of the evaluation information, please refer to the following text and its related description.

[0045] In some embodiments, the first similarity threshold may be positively correlated with the average historical access count of a preset field. See [link to documentation] for an explanation of the preset field. Figure 3 And its related description. The higher the average historical access count of the preset field, the higher the confidence level of the preset field. Increasing the first similarity threshold based on the average historical access count can increase the likelihood that the filtered first service data meets the user's needs.

[0046] The similarity of service data types can be represented by the ratio of the number of identical service data types to the total number of service data types in the user's requirements. Identical service data types can be those in the first set of service data that are the same as those in the user's requirements. For example, if the service data types in the user's requirements are A, B, and C, and the service data types in the first set of service data are A, B, and D, then the similarity of the service data types is 66%, where A, B, C, and D represent different service data types.

[0047] Evaluation information can be the user's level of satisfaction with the first service data or the second service data.

[0048] In some embodiments, the evaluation information may include ratings corresponding to data items contained in the service data. The ratings may indicate the user's level of satisfaction with the data items; a higher rating indicates greater satisfaction. For example, the first service data includes the machine tool's maximum turning diameter and maximum machining length, and the evaluation information may include the user's ratings for the maximum turning diameter and the maximum machining length. The data items contained in the service data may be data from different service data categories.

[0049] Since the first service data is historical service data, the service cloud platform can obtain the historical evaluation information corresponding to the first service data through the service data management model.

[0050] For instructions on obtaining evaluation information, please refer to [link / reference]. Figure 4 And its related descriptions.

[0051] In some embodiments, in response to the first service data meeting the user's needs, the service cloud platform can send the first service data to the user platform and display it to the user through the user platform.

[0052] Step 240: In response to the fact that the first service data does not meet the user's needs, a candidate service pool is determined from the service database based on the constraint indicators and the user's needs, and the matching degree between multiple candidate service data in the candidate service pool and the user's needs is generated.

[0053] In some embodiments, the first service data may fail to meet user needs if the similarity between the service data type in the first service data and the service data type in the user's needs is lower than a first similarity threshold, and the user's evaluation information of the first service data is lower than an evaluation threshold.

[0054] A candidate service pool is a dataset containing multiple candidate service data entries. Candidate service data refers to the service data to be determined and displayed to the user.

[0055] In some embodiments, the service cloud platform can construct query feature vectors based on constraint indicators and user needs, query one or more candidate service data corresponding to reference feature vectors in the service database whose similarity to the query feature vectors meets the similarity conditions, and add one or more candidate service data to the candidate service pool. The similarity between vectors is negatively correlated with the vector distance, which includes Euclidean distance.

[0056] In some embodiments, the service database includes multiple reference feature vectors and candidate service data corresponding to each reference feature vector. The processor can construct reference feature vectors based on historical constraint indicators and historical user needs in historical data, and use historical service data displayed to users in the historical data as candidate service data corresponding to the reference feature vectors.

[0057] Similarity criteria can include a similarity between vectors that is greater than a second similarity threshold. The second similarity threshold can be preset based on historical experience.

[0058] In some embodiments, the service cloud platform can also determine similarity conditions based on the number of constraint indicators, the current system load, and the historical number of users of the constraint indicators. Based on the constraint indicators and user needs, it can filter out candidate service data that meet the similarity conditions from the service database and include them in the candidate service pool.

[0059] The current system load refers to the current resource load of the service cloud platform. In some embodiments, the current system load may include CPU computing load, memory load, disk read load, and data transfer load. The service cloud platform can obtain the current system load from its own devices (such as CPU and disk).

[0060] Historical usage of constraint metrics refers to the number of users who used constraint metrics within a preset historical time period. The preset historical time period can be pre-set based on historical experience, such as 5 minutes or 10 minutes prior to the current moment.

[0061] In some embodiments, the service cloud platform can query the corresponding second similarity threshold in a first preset table based on the number of constraint indicators, the current system load, and the historical number of users of the constraint indicators to obtain similarity conditions.

[0062] In some embodiments, the first preset table can be set by staff based on experience, including the correspondence between the number of multiple sets of constraint indicators, the current system load, the historical number of times the constraint indicators have been used, and the second similarity threshold. For example, the higher the current system load, the lower the second similarity threshold. Or, for example, the more constraint indicators there are, and the more historical number of times the constraint indicators have been used, the lower the second similarity threshold.

[0063] In some embodiments, the service cloud platform can select candidate service data that meets similarity criteria from the service database and add them to the candidate service pool based on constraint indicators and user needs. See the relevant description above for details.

[0064] In some embodiments of this specification, in order to avoid excessive computational burden caused by screening, the system load can be effectively reduced and the data processing efficiency improved by dynamically adjusting the similarity conditions.

[0065] Matching degree refers to the data that characterizes the degree of matching between candidate service data and user needs.

[0066] In some embodiments, the matching degree can be determined in multiple ways. For example, for a single candidate service data, the service cloud platform can calculate the similarity between the service data types in the candidate service data and the service data types in the user's requirements, and use the similarity as the matching degree corresponding to the candidate service data. For an explanation of calculating the similarity of service data types, see step 230 and its related description.

[0067] In some embodiments, the service cloud platform can also obtain historical evaluation information of users on multiple candidate service data and generate a matching score based on the historical evaluation information. The service cloud platform obtains historical evaluation information of users on multiple candidate service data through a service data management model.

[0068] In some embodiments, the service cloud platform can generate a matching score based on historical evaluation information of multiple candidate service data. For example, the service cloud platform can calculate the average value of historical evaluation information based on the historical evaluation information of multiple candidate service data and use the average value as the matching score.

[0069] In some embodiments, the processor may take the average or weighted average of the scores of multiple data items in a single historical evaluation information as the score corresponding to the single historical evaluation information, and take the average of the scores corresponding to multiple historical evaluation information as the average of the historical evaluation information.

[0070] In some embodiments, the weights of multiple data items in a single historical evaluation information may be different, and the weight of each data item can be set according to user preferences.

[0071] In some embodiments, the service cloud platform may determine the matching degree based on satisfaction. See also: [link to relevant content] Figure 4 And related descriptions.

[0072] In some embodiments of this specification, determining the matching degree through historical evaluation information can make the matching degree more consistent with the user's true intentions, thereby improving the accuracy of subsequent second service data.

[0073] Step 250: Select one or more candidate service data that meet the preset matching conditions as one or more second service data, and present one or more second service data to the user through the user platform.

[0074] Secondary service data refers to the service data further determined and displayed to the user after the primary service data fails to meet the user's needs. The content of secondary service data is similar to that of primary service data, and will not be repeated here.

[0075] In some embodiments, preset matching criteria may include a matching degree higher than a matching degree threshold. The matching degree threshold is preset based on historical experience.

[0076] In some embodiments, the service cloud platform may determine preset matching conditions based on the user's industry, the number of failed matching records, and the number of multiple candidate service data.

[0077] In some embodiments, the service cloud platform can obtain the user's industry from the user demand database, such as the machinery industry or the power industry.

[0078] Matching failure records can be records where the user determines that the first or second service data displayed by the user platform is unnecessary (i.e., matching failed). In some embodiments, matching failure records include the number of matching failures within a first preset time period. The first preset time period can be preset based on historical experience.

[0079] In some embodiments, the service cloud platform can query the corresponding matching threshold in a second preset table based on the user's industry, the number of failed matching records, and the number of multiple candidate service data, and use the obtained matching threshold as the matching threshold in the preset matching conditions.

[0080] In some embodiments, the second preset table may be set based on historical experience, including the correspondence between multiple groups of industries, the number of matching failures, the number of candidate service data, and the matching degree threshold.

[0081] In some embodiments of this specification, the matching threshold is intelligently adjusted by comprehensively considering the user's industry, the number of failed matches, and the number of candidate service data, thus balancing the breadth and accuracy of matching. For industries where matching is prone to failure, the matching threshold is lowered to increase the success rate of matching, while when there is a large amount of selectable service data, the threshold is raised to recommend higher-quality and more accurate service data.

[0082] In some embodiments, the service cloud platform may send one or more second service data to the user platform, and the user platform may present one or more second service data to the user.

[0083] In some embodiments described herein, by acquiring user needs and constraint indicators, the service data required by the user can be quickly filtered, avoiding complex searches in massive amounts of data and significantly improving the matching speed. Furthermore, if the service data obtained from the rapid filtering does not meet the user's needs, further filtering of service data with a higher degree of matching with the user can be performed, further improving the user experience.

[0084] Figure 3 This is an exemplary flowchart illustrating the process of obtaining user requirements and constraint metrics according to some embodiments of this specification. In some embodiments, the process 300 for obtaining user requirements and constraint metrics may be executed by a service cloud platform. Figure 3 As shown, the process 300 for obtaining user needs and constraint metrics includes the following steps.

[0085] Step 310: Receive basic perception information input by the user through the user platform.

[0086] For more information about the user platform and users, please see [link / details]. Figure 1 And its related descriptions.

[0087] Basic sensing information refers to information directly input by the user. In some embodiments, basic sensing information may include enterprise information and product information. Enterprise information may include enterprise type, production scale, products, capacity, production method, and production material configuration, while product information may include equipment type, equipment name, process type, and material type.

[0088] In some embodiments, basic sensing information may also include drawings or documents. The service cloud platform can extract key parameters from drawings or documents through industry large models and cross-validate them with other basic sensing information.

[0089] Key parameters refer to data contained in drawings or documents. In some embodiments, key parameters may include tolerances, materials, and dimensions of the product in the drawings or documents.

[0090] In some embodiments, the service cloud platform can extract key parameters from drawings or documents using industry-wide large models.

[0091] Industry-specific large models can be large models designed for different industries. In some embodiments, industry-specific large models may include natural language processing (NLP) models and computer vision (CV) models.

[0092] In some embodiments, the service cloud platform can obtain a large industry model corresponding to the user's industry from a service model library. The service model library includes multiple large industry models corresponding to different industries. These large industry models can be pre-set based on industry experience. For an explanation of the service model library, see [link to documentation]. Figure 1 And its related descriptions.

[0093] Cross-validation refers to verifying whether other basic sensing information matches key parameters. In some embodiments, matching may include identical fields and consistent values.

[0094] For example, if the service cloud platform extracts the key parameter "the size of the five-axis machining center is A1" from the industry big data model for the drawing input by the user, and "the size of the five-axis machining center is A2" exists in other basic perception information input by the user, then the service cloud platform determines that the basic perception information does not match the key parameter.

[0095] In some embodiments, in response to a match between other basic perception information and key parameters, the service cloud platform can add the key parameters to the constraint indicators. In response to a mismatch between other basic perception information and key parameters, the service cloud platform can further issue a reminder to the user through the user platform (such as "The drawing does not match the entered information, please confirm").

[0096] In some embodiments of this specification, by cross-validating key parameters in drawings or files with other basic sensing information, conflicting data can be detected and alerted in a timely manner, ensuring the accuracy of constraint indicators.

[0097] Step 320: Extract keywords from basic sensory information.

[0098] Keywords are words or phrases related to the user's industry and needs. For example, keywords can include industry, location, materials, and processes.

[0099] In some embodiments, the service cloud platform can embed basic perceptual information input by the user into a preset formatted extraction instruction, and input the extraction instruction into a semantic analysis model (such as a Large Language Model (LLM)). The natural language processing capabilities of the semantic analysis model are then used to extract keywords. The extraction instruction may include the type of keywords to be extracted, such as industry, location, material, and process.

[0100] Step 330: Generate field generation instructions based on keywords.

[0101] Field generation instructions are instructions used to generate preset fields.

[0102] In some embodiments, the service cloud platform can retrieve instruction fragments corresponding to keywords from a preset fragment library, concatenate the instruction fragments corresponding to the keywords, and generate field generation instructions.

[0103] In some embodiments, the preset fragment library can be pre-set based on historical experience, including multiple instruction fragments and multiple fragment correspondences (i.e., the correspondence between keywords and instruction fragments).

[0104] For example, the keyword is "injection molding", and the instruction fragment corresponding to "injection molding" in the preset fragment library is "For 'injection molding', generate fields such as number of cavities, mold steel, gate type and demolding method".

[0105] In some embodiments, the service cloud platform can sequentially concatenate multiple instruction fragments to obtain field generation instructions.

[0106] Step 340: Input the field generation command into the industry big model to obtain the preset fields corresponding to the keywords.

[0107] Preset fields are fields used to remind users of the types of service data they need to enter. For example, preset fields could be "number of cavities, mold steel, gate type, and demolding method," etc.

[0108] In some embodiments, the service cloud platform can input field generation instructions into an industry big model corresponding to the user's industry, and use the natural language processing capabilities of the industry big model to obtain preset fields corresponding to keywords.

[0109] Step 350: Display preset fields through the user platform to guide users to complete information interaction according to the preset fields, thereby obtaining user needs and constraint indicators.

[0110] In some embodiments, the service cloud platform can send preset fields to the user platform, and display the preset fields on the user platform to guide the user to complete information interaction (such as inputting information) according to the preset fields, thereby obtaining user needs and constraint indicators.

[0111] In some embodiments, the service cloud platform can extract user needs and constraint indicators from information entered by the user according to preset fields through methods such as natural language processing.

[0112] In some embodiments of this specification, by using a large language model, keywords can be quickly extracted from the user's original input information. Based on the keywords, fields are intelligently generated using a preset fragment library to generate instructions. Furthermore, preset fields that can guide the user's information interaction are quickly obtained through an industry-wide large model. This phased and model-based processing method avoids the computational burden of directly using a single model to process massive amounts of data, while ensuring the accuracy of the final generated preset fields.

[0113] Figure 4 This is an exemplary schematic diagram of a matching model shown according to some embodiments of this specification.

[0114] In some embodiments, such as Figure 4 As shown, the service cloud platform is configured to predict user satisfaction with multiple candidate service data 430 based on multiple candidate service data 411, historical evaluation information of other users on multiple candidate service data 412, historical service data 413, basic perception information 414, and constraint indicators 415, through a matching model 420. The service cloud platform can determine the matching degree 440 based on the satisfaction 430.

[0115] For more information on matching degree, candidate service data, historical evaluation information, historical service data, basic perception information, and constraint indicators, please refer to [link to relevant documentation]. Figure 2 and Figure 3 And related descriptions.

[0116] Other users can be users other than the current user.

[0117] The historical service data 413 input to the matching model can be the historical service data corresponding to the current user.

[0118] In some embodiments, the matching model can be a machine learning model. For example, the matching model can be any one or a combination of a deep neural network (DNN) model or other custom model structures.

[0119] In some embodiments, the matching model can be obtained by the service cloud platform through model training. For example, the service cloud platform can train the matching model using multiple labeled training samples.

[0120] In some embodiments, training samples may include sample service data of sample users, historical evaluation information of samples, historical service data of samples, basic perception information of samples, and sample constraint indicators. Labels may include sample users' satisfaction with the sample service data. Historical evaluation information of samples may be historical evaluation information of the sample service data by users other than the sample users. Historical service data of samples may be the historical service data corresponding to the sample users.

[0121] In some embodiments, training samples can be generated based on historical data. For example, the service cloud platform can use candidate service data, sample basic perception information, and sample constraint indicators determined in a first historical time from historical data as sample service data, sample basic perception information, and sample constraint indicators, and use the historical users corresponding to the sample constraint indicators as sample users. The service cloud platform uses the historical service data of sample users in a second historical time and the historical evaluation information of other historical users (excluding the sample users) on the sample service data as sample historical service data and sample historical evaluation information. The first historical time is later than the second historical time.

[0122] In some embodiments, the labels may be determined by the service cloud platform and / or manually. For example, the service cloud platform may use the ratio of the sample user's rating of the sample service data to the number of times the sample user asks a question again within a second preset time period after the sample service data is displayed as the first label. The second preset time period may be preset based on historical experience.

[0123] In some embodiments, the service cloud platform can input training samples into an initial matching model, construct a loss function based on the satisfaction level output by the initial matching model and the labels, update the parameters of the initial matching model based on the loss function, and complete the training of the initial matching model when preset conditions are met, thus obtaining a trained matching model. Preset conditions may include loss function convergence or the number of iterations reaching a preset threshold, etc.

[0124] In some embodiments, the service cloud platform may determine the satisfaction level corresponding to the candidate service data as the matching degree corresponding to the candidate service data.

[0125] In some embodiments, in response to a user selecting at least one of one or more second service data or ending the service interaction, the service cloud platform can send evaluation guidance information to the user through the user platform, guiding the user to evaluate one or more second service data to collect evaluation information. The service cloud platform can use one or more second service data and evaluation information as training samples to train and / or update the matching model.

[0126] Ending service interaction can occur when a user does not select a second service and chooses to end the service.

[0127] Evaluation guidance information refers to prompts used to guide users to enter evaluation information. For example, evaluation guidance information could be "Please rate the service data".

[0128] In some embodiments, the service cloud platform may obtain user-inputted evaluation information through the user platform.

[0129] In some embodiments, the service cloud platform may use one or more second service data as sample service data in the training samples, and use the evaluation information as the sample historical evaluation information corresponding to users other than the sample users in other training samples, to train and / or update the matching model.

[0130] In some embodiments of this specification, by using the second service count and real-time user evaluation information as new training samples, the machine learning model can be incrementally trained and updated, thereby improving the model's predictive ability and accuracy.

[0131] In some embodiments of this specification, by comprehensively analyzing multi-dimensional information through machine learning models, a deeper level of intelligent prediction can be made on the matching degree between users and candidate service data, thereby recommending service data that is more likely to satisfy users and improving the accuracy and personalization of services.

[0132] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0133] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A wide-area cloud manufacturing industrial service system based on an Internet of Things (IoT) big data model, characterized in that: This includes a service cloud platform and a user platform, wherein the service cloud platform is configured as follows: Obtain constraint indicators through the user platform; Based on the aforementioned constraint indicators, the first service data is determined from the user's corresponding historical service data; In response to the first service data meeting the user's needs, the first service data is displayed to the user through the user platform; In response to the first service data not meeting the user's needs: Based on the constraint indicators and the user requirements, a candidate service pool is determined from the service database, and the matching degree between multiple candidate service data in the candidate service pool and the user requirements is generated. One or more candidate service data that meet the preset matching conditions are used as one or more second service data, and the one or more second service data are presented to the user through the user platform.

2. The system as described in claim 1, characterized in that, The service cloud platform is further configured as follows: Based on the number of constraint indicators, the current system load, and the historical number of users of the constraint indicators, similarity conditions are determined. Based on the constraint indicators and the user requirements, candidate service data that meet the similarity conditions are selected from the service database and included in the candidate service pool.

3. The system as described in claim 1, characterized in that, The service cloud platform is further configured as follows: The user platform receives basic perception information input by the user, which includes fields. Extract keywords from the basic perception information; Based on the keywords, generate field generation instructions; Input the field generation command into the industry big model to obtain the preset fields corresponding to the keywords; The user platform displays the preset fields to guide the user to complete information interaction according to the preset fields, thereby obtaining the user's needs and the constraint indicators.

4. The system as described in claim 1, characterized in that, The service cloud platform is further configured as follows: Obtain the user's historical evaluation information on the multiple candidate service data; The matching degree is generated based on the historical evaluation information.

5. The system as described in claim 4, characterized in that, The service cloud platform is further configured as follows: In response to the user selecting at least one of the one or more second service data or ending the service interaction, the system sends evaluation guidance information to the user through the user platform to guide the user to evaluate the one or more second service data in order to collect evaluation information. The matching model is trained and / or updated using the one or more second service data and the evaluation information as training samples.

6. A wide-area cloud manufacturing industrial service method based on an IoT big data model, characterized in that: The method is executed by a service cloud platform within a wide-area cloud manufacturing industrial service system based on an IoT big data model, and includes: Obtain constraint indicators through the user platform; Based on the aforementioned constraint indicators, the first service data is determined from the user's corresponding historical service data; In response to the first service data meeting the user's needs, the first service data is displayed to the user through the user platform; In response to the first service data not meeting the user's needs: Based on the constraint indicators and the user requirements, a candidate service pool is determined from the service database, and the matching degree between multiple candidate service data in the candidate service pool and the user requirements is generated. One or more candidate service data that meet the preset matching conditions are used as one or more second service data, and the one or more second service data are presented to the user through the user platform.

7. The method as described in claim 6, characterized in that, The step of determining the candidate service pool from the service database based on the constraint indicators and the user requirements includes: Based on the number of constraint indicators, the current system load, and the historical number of users of the constraint indicators, similarity conditions are determined. Based on the constraint indicators and the user requirements, candidate service data that meet the similarity conditions are selected from the service database and included in the candidate service pool.

8. The method as described in claim 6, characterized in that, The method further includes: The user platform receives basic perception information input by the user, which includes fields. Extract keywords from the basic perception information; Based on the keywords, generate field generation instructions; Input the field generation command into the industry big model to obtain the preset fields corresponding to the keywords; The user platform displays the preset fields to guide the user to complete information interaction according to the preset fields, thereby obtaining the user's needs and the constraint indicators.

9. The method as described in claim 6, characterized in that, The matching degree between the multiple candidate service data in the candidate service pool and the user's needs includes: Obtain the user's historical evaluation information on the multiple candidate service data; The matching degree is generated based on the historical evaluation information.

10. The method as described in claim 9, characterized in that, The method further includes: In response to the user selecting at least one of the one or more second service data or ending the service interaction, the system sends evaluation guidance information to the user through the user platform to guide the user to evaluate the one or more second service data in order to collect evaluation information. The matching model is trained and / or updated using the one or more second service data and the evaluation information as training samples.

Images