Method and apparatus for generating a commissioning task sheet, computer program product and electronic device

Abstract

The present disclosure relates to the technical field of information processing, and relates to a method and device for generating a commissioned task sheet. The method comprises: in response to receiving detection requirement description information, determining a commissioned task creation requirement and a corresponding callable tool set according to a current user role and / or a current business context; extracting multi-dimensional requirement elements from the detection requirement description information; performing field mapping on the multi-dimensional requirement elements to obtain reference fields, generating a first reference draft according to the reference fields, calling a target detection knowledge base to perform matching verification on the first reference draft, and determining to-be-confirmed items in the first reference draft according to a verification result; in response to an operation instruction for the to-be-confirmed items, updating the first reference draft according to operation content, generating a second reference draft, verifying the second reference draft, determining target fields according to the second reference draft that passes the verification, filling a commissioned task template with the target fields, and obtaining a target detection commissioned task sheet.

Description

Technical Field

[0001] This disclosure relates to the field of information processing technology, and more specifically, to a method and apparatus for generating task orders, a computer program product, and an electronic device. Background Technology

[0002] In the testing service field, when submitting a testing request, clients need to rely on their experience to fill in the client, sample, testing items, and report requirements item by item, and finally generate a testing task order.

[0003] However, this approach has the following main problems: manual interpretation and data entry are inefficient and prone to misunderstandings and omissions; the filling process cannot ensure the accuracy of the requirements, and errors are often only discovered later, leading to issues such as miswriting business data, repeated communication and revisions, and extending the processing period.

[0004] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method and apparatus for generating task orders, a computer program product, and an electronic device, thereby overcoming, to at least a certain extent, the problems existing in the related technologies and improving the accuracy and efficiency of generating task orders.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a method for generating a task assignment form is provided, comprising: responding to received detection requirement description information, determining the task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context; extracting multi-dimensional requirement elements from the detection requirement description information, wherein the multi-dimensional requirement elements include at least client information, sample information, detection information, and report attribute information; performing field mapping processing on the multi-dimensional requirement elements based on the task creation requirement to obtain reference fields, generating a first reference draft based on the reference fields, and performing matching and verification of the first reference draft by calling a target detection knowledge base based on the callable toolset and the multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft based on the verification result; responding to an operation instruction for the items to be confirmed, updating the first reference draft according to the operation content corresponding to the operation instruction, and generating a second reference draft; verifying the second reference draft based on the task assignment form verification rules, and determining the target field based on the verified second reference draft, so as to use the target field to fill the task assignment template to obtain a target detection task assignment form.

[0008] In one exemplary embodiment of this disclosure, the response to receiving the detection requirement description information determines the entrusted task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context, including: if the task type is determined to be creating an entrustment order or modifying an entrustment order based on the current business context, then creating an entrusted task creation requirement; determining the type of the current user role, and filtering out the currently callable functional modules based on the type and the entrusted task creation requirement to obtain the callable toolset.

[0009] In one exemplary embodiment of this disclosure, based on the creation requirements of the entrusted task, the multidimensional requirement elements are processed by field mapping to obtain reference fields, and a first reference draft is generated based on the reference fields. The process includes: obtaining an entrusted task template based on the creation requirements of the entrusted task; processing the multidimensional requirement elements by field mapping based on the entrusted task template to normalize the multidimensional requirement requirements to the fields of the entrusted task template to obtain reference fields; and generating a first reference draft based on the reference fields.

[0010] In one exemplary embodiment of this disclosure, obtaining a task template based on task creation requirements includes: if it is determined that a historical template exists based on task creation requirements, providing functional options for the historical template; and in response to a selection operation for the functional options, determining the target historical template corresponding to the selection operation as the task template.

[0011] In one exemplary embodiment of this disclosure, the method further includes: determining the field source, missing field, and current draft version of each field in the first reference draft; and in response to at least one supplementation operation for a missing field, merging the supplementation field corresponding to the supplementation operation into the first reference draft.

[0012] In one exemplary embodiment of this disclosure, the process of calling a target detection knowledge base based on a callable toolset and multi-dimensional requirement elements to perform matching verification on a first reference draft, and determining the items to be confirmed in the first reference draft based on the verification results, includes: determining the target detection knowledge base based on the callable toolset; obtaining user master data from the target detection knowledge base based on client information; determining target detection items based on the detection methods in the detection information, and determining target detection standards based on the detection standard information in the detection information; performing matching verification on the first reference draft based on the user master data, target detection items, detection standard information, and target detection standards to obtain verification results; and determining the items to be confirmed in the first reference draft based on the verification results.

[0013] In one exemplary embodiment of this disclosure, a first reference draft is matched and verified based on user master data, target detection items, detection standard information, and target detection standards to determine items to be confirmed in the first reference draft according to the verification results. This includes: verifying whether the client information matches the user master data; querying available detection standards according to the target detection items and verifying whether the available detection standards match the target detection items; verifying whether the detection standards indicated in the detection standard information match the detection standards; if there are verification results with non-unique matching results and / or conflicting fields, at least one of candidate items, missing items, and risk warning information items is determined as items to be confirmed in the first reference draft based on the target detection knowledge base.

[0014] In one exemplary embodiment of this disclosure, responding to an operation instruction for an item to be confirmed, updating a first reference draft according to the operation content corresponding to the operation instruction, and generating a second reference draft, includes: responding to an operation instruction for an item to be confirmed, determining the operation content, and updating the first reference draft according to the operation content to obtain a second reference draft; calling a target detection knowledge base according to a callable toolset and multi-dimensional requirement elements, and performing matching verification on the updated first reference draft until the verification is passed to obtain the second reference draft.

[0015] In one exemplary embodiment of this disclosure, a second reference draft is validated based on the order verification rules, and a target field is determined based on the validated second reference draft. The target field is then used to fill in the task template to obtain a target detection task order. This includes: validating the main table required fields, sample required fields, field formats, and condition field contents in the second reference draft according to the order verification rules to obtain a first verification result; performing business consistency verification on the first reference draft to obtain a second verification result, whereby the business consistency verification includes detecting the consistency between the detection items, detection standards, and the detection items and detection standards; after the first and second verification results pass, the target field is determined based on the validated second reference draft and presented; in response to the determination and / or modification operations for the target field, the task template is invoked, and a target detection task is generated based on the target field after the determination and / or modification operations.

[0016] According to one aspect of this disclosure, a task order generation device is provided, comprising: a requirement creation module, configured to respond to received detection requirement description information, determine the task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context; an information extraction module, configured to extract multi-dimensional requirement elements from the detection requirement description information, wherein the multi-dimensional requirement elements include at least client information, sample information, detection information, and report attribute information; a first verification module, configured to perform field mapping processing on the multi-dimensional requirement elements based on the task creation requirement to obtain reference fields, generate a first reference draft based on the reference fields, and call a target detection knowledge base to perform matching verification on the first reference draft based on the callable toolset and the multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft based on the verification result; a result confirmation module, configured to respond to an operation instruction for the items to be confirmed, update the first reference draft according to the operation content corresponding to the operation instruction, and generate a second reference draft; and a task generation module, configured to verify the second reference draft based on the task order verification rules, and determine the target field based on the verified second reference draft, so as to use the target field to fill the task template to obtain a target detection task order.

[0017] According to one aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the above methods.

[0018] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above methods by executing the executable instructions.

[0019] The task order generation method in the exemplary embodiments of this disclosure responds to receiving detection requirement description information, determines the task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context; extracts multi-dimensional requirement elements from the detection requirement description information, the multi-dimensional requirement elements including at least client information, sample information, detection information, and report attribute information; performs field mapping processing on the multi-dimensional requirement elements based on the task creation requirement to obtain reference fields, generates a first reference draft based on the reference fields, and calls the target detection knowledge base to match and verify the first reference draft based on the callable toolset and multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft based on the verification result; responds to the operation instruction for the items to be confirmed, updates the first reference draft according to the operation content corresponding to the operation instruction, and generates a second reference draft; verifies the second reference draft based on the task order verification rules, and determines the target field based on the verified second reference draft, so as to use the target field to fill the task template to obtain the target detection task order. The process of generating this task assignment form is automated through natural language interaction, significantly reducing the workload of manual interpretation and data entry, minimizing information omissions and errors, and improving the efficiency and accuracy of task assignment generation. Simultaneously, it can adaptively determine creation requirements and available toolsets based on the current user role and business context, thus providing differentiated processing capabilities for different business scenarios and improving operational flexibility. Furthermore, the introduction of an object detection knowledge base during the generation process for matching and validating drafts proactively identifies and locates items requiring confirmation, thereby advancing the discovery and correction of problems and avoiding repeated communication and modifications, effectively shortening the task processing cycle.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0021] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation.

[0022] Figure 1 An application environment according to an exemplary embodiment of this disclosure is shown.

[0023] Figure 2 A flowchart of a method for generating a task order according to an exemplary embodiment of the present disclosure is shown.

[0024] Figure 3 A flowchart illustrating an exemplary embodiment of the present disclosure for determining the requirements for creating a delegated task and the corresponding callable toolset is shown.

[0025] Figure 4 A flowchart illustrating an exemplary embodiment of the present disclosure for generating a first reference draft is shown.

[0026] Figure 5 A flowchart illustrating an implementation of verifying a first reference draft according to an exemplary embodiment of the present disclosure is shown.

[0027] Figure 6 A flowchart illustrating an example of determining an item to be confirmed in a first reference draft according to an exemplary embodiment of the present disclosure is shown.

[0028] Figure 7 A flowchart illustrating an example of obtaining a target detection task order according to an exemplary embodiment of the present disclosure is shown.

[0029] Figure 8 A schematic diagram illustrating a user providing a description of detection requirements via an interface, according to an exemplary embodiment of the present disclosure.

[0030] Figure 9 A schematic diagram of an interface showing a draft field displayed when a user clicks on a first reference draft, according to an exemplary embodiment of the present disclosure, is shown.

[0031] Figure 10 A schematic diagram of an interface for saving a request form after user confirmation, according to an exemplary embodiment of the present disclosure, is shown.

[0032] Figure 11 A schematic diagram of the composition of a task order generation apparatus according to an exemplary embodiment of the present disclosure is shown.

[0033] Figure 12 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0034] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0035] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0036] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details described, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0037] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0038] In practice, it has been found that non-destructive testing (NDT) orders or testing tasks require manual entry of each item in traditional forms, which presents the following problems: 1) Numerous fields, high entry costs, and high error rates; users need to fill in information such as the commissioning unit, contact person, contact number, unit address, sample name, specifications, sample material, quantity, testing items, testing standards, testing purpose, report type, required completion date, report delivery method, and sample processing method, which consumes significant time and labor costs. Furthermore, due to unfamiliarity with NDT business rules, key fields such as sample specifications, testing standards, and testing purpose may be overlooked, leading to repeated adjustments and communication modifications; 2) Incorrectly filled testing items render the task order invalid; mismatches between testing items and testing standards result in inconsistent project standards, making the task order unexecutable; 3) Existing automated task order generation may not reflect the user's actual testing needs or guarantee the authenticity of the task order content, posing a risk of incorrectly entered business data.

[0039] Based on one or more of the above-mentioned problems, an exemplary embodiment of this disclosure provides a method for generating task orders, which improves the accuracy and efficiency of generating task orders by extracting elements, verifying knowledge bases, filling templates, and generating task orders after user confirmation, based on the user's natural language description of the detection requirements.

[0040] It should be noted that the task order generation method of the exemplary embodiments of this disclosure can be applied to scenarios that require users to provide task orders, such as multi-business line acceptance, business personnel-assisted processing, customer self-service ordering, and laboratory information management systems, without specific limitations. The exemplary embodiments of this disclosure are illustrated using the generation of task orders in a non-destructive testing scenario as an example.

[0041] The task order generation method provided in the exemplary embodiments of this disclosure can be applied to, for example, Figure 1 The application environment shown is illustrated. Terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102, or it can be located in the cloud or on another network server.

[0042] In one exemplary embodiment, the provided task order generation method can be executed by server 102. Correspondingly, in this manner executed by server 102, server 102 can begin executing the steps in the technical solution of the exemplary embodiment of this disclosure in response to a triggering command, wherein the triggering command can be sent by terminal 101 or triggered locally by the server in response to some automated event.

[0043] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and big data and artificial intelligence platforms. Server 102 can execute background tasks.

[0044] Furthermore, in another exemplary embodiment, terminal 101 may also have similar functions to server 102, thereby executing the task order generation method provided by the exemplary embodiments of this disclosure. Terminal 101 may be a smartphone, tablet, laptop, desktop computer, IoT device, or portable wearable device. Terminal 101 may also be referred to as a mobile terminal, terminal device, mobile device, etc., and the exemplary embodiments of this disclosure do not limit the type of terminal 101.

[0045] Furthermore, the technical solutions of the exemplary embodiments of this disclosure can also be executed collaboratively by terminal 101 and server 102. In this collaborative execution method, some steps of the technical solutions provided by the exemplary embodiments of this disclosure are executed by terminal 101, while other steps are executed by server 102. It should be noted that in this collaborative execution method, the steps executed by terminal 101 and server 102 respectively can be dynamically adjusted according to actual circumstances, and no special restrictions are placed on this. Terminal 101 and server 102 can be directly or indirectly connected via wireless communication, and the exemplary embodiments of this disclosure do not impose any special restrictions here.

[0046] refer to Figure 2 The diagram shown is a flowchart of a method for generating a task order, an exemplary embodiment of this disclosure.Figure 2 As shown, the method for generating the task order includes steps S210 to S250: Step S210: Upon receiving the detection requirement description information, determine the task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context.

[0047] Step S220: Extract multi-dimensional requirement elements from the testing requirement description information. The multi-dimensional requirement elements include at least client information, sample information, testing information, and report attribute information.

[0048] Step S230: Create requirements based on the delegated task, perform field mapping processing on the multi-dimensional requirement elements to obtain reference fields, generate a first reference draft based on the reference fields, and call the target detection knowledge base to match and verify the first reference draft based on the callable toolset and multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft based on the verification results.

[0049] Step S240: In response to the operation instruction for the item to be confirmed, update the first reference draft according to the operation content corresponding to the operation instruction, and generate the second reference draft.

[0050] Step S250: Validate the second reference draft based on the authorization form validation rules, and determine the target fields based on the validated second reference draft. Use the target fields to fill the authorization task template to obtain the target detection authorization task form.

[0051] The task order generation method in the exemplary embodiments of this disclosure automates the generation of task orders, significantly reducing the workload of manual item-by-item interpretation and data entry, minimizing information omissions and entry errors, and improving the efficiency and accuracy of task order generation. Simultaneously, it can adaptively determine creation requirements and available toolsets based on the current user role and business context, thus providing differentiated processing capabilities for different business scenarios and improving operational flexibility. Furthermore, the introduction of a target detection knowledge base during the generation process for matching and verifying drafts proactively identifies and locates items requiring confirmation, thereby advancing the discovery and correction of problems, avoiding repeated communication and modifications, and effectively shortening the task processing cycle.

[0052] The steps are explained in more detail below.

[0053] In step S210, the response receives the detection requirement description information and determines the entrusted task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context.

[0054] In the exemplary embodiments of this disclosure, the testing requirement description information is the original input that triggers the entire process, and can be unstructured or semi-structured information. For example, it could be the requirement text described by the current user in natural language in a web form, a sent email, an instant messaging message, or text converted from speech. The testing requirement description information can include client information, sample name, testing items, report requirements, etc. For example, a natural language requirement entered by the current user: "Help me create a request form. The client is Company B in location A. One aluminum alloy sensor needs to be tested using CT (Computed Tomography), according to national standards xxxx1 and xxxx2. A standard report is required; the report can be picked up in person, and the sample needs to be returned." The current user role refers to the identity type of the current user, such as customer, customer service specialist, sales manager, laboratory technical expert, auditor, etc. Differentiated testing permissions, items, interfaces, and functions can be pre-configured for different roles. The current business context is the business environment in which the current operation takes place. It can be explicit, such as the testing category selected by the user, the request form, etc.; or it can be implicit, determined based on the user's department affiliation, historical communication records, or the attributes of the current project. For example, based on the short-term memory of a large model, historically generated order forms or order information for the current user role can be retrieved as the current business context. The request for creating an order form determines whether it belongs to order creation, task query, or report query. If it is not order creation, only read-only tools are allowed; if it is order creation, the creation function can be accessed. This avoids directly calling arbitrary task interfaces, which could lead to subsequent constraints from business capabilities. The callable toolset refers to the set of functions required to handle the order creation request in the current state. This set is dynamically changing and aims to provide the most relevant operational functions, preventing users from performing unauthorized or non-compliant operations.

[0055] In one exemplary embodiment, such as Figure 3 Upon receiving the detection requirement description information, the system determines the task creation requirements and corresponding callable toolsets based on the current user role and / or current business context, including: Step S310: If the task type is determined to be either creating a commission order or modifying a commission order based on the current business context, then create a commission task creation requirement.

[0056] The task type refers to the form of the current operation, determined by the current business context, and can include creating a task order and modifying a task order. This disclosure can understand the current business context through a large model (such as a pre-trained agent), determine the task type, and then, based on the task type, determine whether the current task is creating or modifying a task order, thus generating the task order.

[0057] Step S320: Determine the type of the current user role, and filter out the currently callable functional modules based on the type and the requirements for creating delegated tasks, to obtain the callable toolset.

[0058] As mentioned above, the current user role type is a fine-grained classification of user identity, such as a customer submitting samples for testing or a customer service representative. Each type is granted different access permissions to functional modules within the system. Functional modules can refer to independently callable program units with specific auxiliary functions, such as importing customer information, recommending testing standards, and modifying tracking records. The system can use all functional module permissions available to a given user type as a basis, and the rules in the task creation requirements as a filter to select functional modules that meet both the role's permissions and the current task scenario requirements. These modules are then aggregated and activated to determine the set of callable tools. Of course, callable tools are not limited to visible buttons or menus; they can also be background verification scripts, such as order verification rules.

[0059] This disclosure employs a dual screening process, combining role permissions with generated task requirements. This not only ensures that users can only use the tools they are authorized to use, but also guarantees that these tools are truly needed for the current scenario, providing accurate processing capabilities for the subsequent generation of task orders.

[0060] In step S220, multi-dimensional requirement elements are extracted from the testing requirement description information. The multi-dimensional requirement elements include at least client information, sample information, testing information, and report attribute information.

[0061] In the exemplary embodiments of this disclosure, the multidimensional requirement elements are structured information units parsed and extracted from the testing requirement description information. These elements include: client information (such as client organization, address, contact person, and telephone number); sample information (such as sample name, sample number, specifications, material, and quantity); testing information (such as testing items, testing standards, acceptance standards, testing purpose, testing location, and sample processing method, e.g., return or self-processing); and report attribute information (such as report type, report delivery method, and required completion date). Of course, the multidimensional requirement elements may also include other elements, which can be flexibly set according to the actual testing scenario.

[0062] This involves performing operations such as word segmentation, named entity recognition, and dependency parsing on the description of testing requirements to identify details in the text, such as names of people, companies, and phone numbers (client information); sample names, models, and specifications (sample information); testing project names, standard codes, and methods (testing information); and report types, qualification requirements, and language (report attribute information). For example, an information extraction model can be used to process these details and obtain multi-dimensional requirement elements. Exemplarily, the information extraction model can be built using lightweight neural networks, such as CNNs (Convolutional Neural Networks), RNNs (Recurrent Neural Networks), and DNNs (Deep Neural Networks). In contrast to lightweight neural networks, more complex information extraction models can also be used, such as heavyweight neural networks, such as BERT (Bidirectional Encoder Representation from Transformers), Transformer (a language processing model), and any heavyweight neural network suitable for information extraction. Furthermore, the information extraction model can also be a large model with hundreds of millions of records. LLM (Large Language Model) refers to a deep learning model trained on a large amount of data, which can generate natural language text or understand the meaning of language text. This disclosure uses a large language model as an example for illustration.

[0063] Optionally, for extracted requirement elements with low confidence, they can be marked and a question to be confirmed can be generated. For example, when the text contains an ambiguous description such as "do it according to the previous standard", the requirement element "detection standard" can be highlighted to be confirmed, a prompt can be generated, and a feature completion operation can be performed to obtain the complete multi-dimensional requirement element, so as to realize human-computer collaborative feature completion.

[0064] This disclosure, through semantic understanding, can accurately capture user intent and list information points as multi-dimensional demand elements, effectively avoiding information omissions or misalignments caused by human interpretation, thus improving the accuracy of element extraction. At the same time, the structured multi-dimensional demand elements provide an accurate prerequisite for subsequent operations such as field mapping and knowledge base verification.

[0065] In step S230, requirements are created based on the entrusted task, and the multi-dimensional requirement elements are processed by field mapping to obtain reference fields. A first reference draft is generated based on the reference fields, and the target detection knowledge base is called according to the callable toolset and multi-dimensional requirement elements to perform matching and verification on the first reference draft, so as to determine the items to be confirmed in the first reference draft based on the verification results.

[0066] In the exemplary embodiments of this disclosure, field mapping processing is a transformation process that establishes a correspondence between high-level business semantic units of multi-dimensional demand elements and specific, low-level database fields in the entrusted task template. For example, the user's spoken phrase "self-pickup report" is mapped to a report delivery method, "sample needs to be returned" is mapped to a sample processing field, and "CT scan" is mapped to a test item candidate. This mapping relationship can be implemented based on a predefined mapping table or a machine learning model, which is a conventional mapping method, and this disclosure does not impose any special restrictions on the specific mapping method.

[0067] The first reference draft is composed of mapped reference fields and has a complete form structure, but it has not yet been verified for technical compliance and may have issues such as incorrect standard references or mismatch between the project and the sample.

[0068] In one exemplary embodiment, such as Figure 4 Based on the requirements created by the delegated task, the multi-dimensional requirement elements are mapped to obtain reference fields. A first reference draft is then generated based on these reference fields, including: Step S410: Obtain the task template according to the task creation requirements.

[0069] A task assignment template is a predefined, structured form framework that can contain all the fields and their default attributes required for a specific business scenario. For example, an electronic and electrical appliance testing task assignment template may include fields such as a bill of materials and exemption clauses. This template determines the skeleton and data container of the final form. The task assignment creation requirements can be read first, specifying the version of the task assignment template to be used in the current scenario. Then, the complete field structure of the template can be loaded, including metadata information such as field identifiers, field types, default values, and required attributes.

[0070] Optionally, a task template can be obtained based on the task creation requirements. This may include: if a historical template is determined to exist based on the task creation requirements, providing functional options for the historical template; and then responding to the selection operation for the functional options, determining the target historical template corresponding to the selection operation as the task template.

[0071] The historical templates are instances of task templates that the current user has used in past operations and which have been recorded and saved. These differ from the system's default blank templates; they are snapshots containing historical data such as specific clients, sample types, and combinations of testing items. For example, a complete template used by a user last month when submitting a sample. If a historical template for the current user exists based on the task creation requirements, an interactive selection entry can be provided on the user interface, allowing the user to reuse templates (i.e., task orders) from past business scenarios in an optional manner. This function option may include operation buttons such as select, preview, compare, and confirm. Furthermore, the user can instruct on the provided function options through clicking, dragging, or voice commands to designate the target historical template as the task order.

[0072] Optionally, when it is determined that a historical template exists based on the requirements for creating the entrusted task, the matching criteria may include the current user role, the current business context, the current client information, and similar sample names. If one or more historical template instances that meet the criteria are retrieved, the historical template reuse mechanism can be triggered, that is, providing functional options for historical templates.

[0073] This disclosure allows for the reuse of historical templates, enabling quick application or modification of existing templates. It effectively avoids errors in filling out basic information due to typos or misunderstandings, and simplifies the form-filling process into an intuitive selection process. For customers unfamiliar with the complete form-filling process or new employees, it reduces operational difficulty and learning costs.

[0074] Step S420: Based on the delegated task template, perform field mapping processing on the multidimensional requirement elements to normalize the multidimensional requirement requirements to the fields of the delegated task template and obtain reference fields.

[0075] After obtaining the task template, the multi-dimensional requirements elements can be mapped to fields. This process establishes an assignment relationship between each specific element in the multi-dimensional requirements and its corresponding field in the task template, and performs necessary format conversions, value range standardization, and logical combination. In the field mapping process, the diverse expressions of the original extraction results can be uniformly converted into standard expressions conforming to the preset format or value range of the template fields, thereby normalizing the element expressions and obtaining standard field keys that can be directly filled into the task template, i.e., reference fields.

[0076] In practice, for each element, its target field in the task template can be determined, and the following normalization operations can be performed: conversion from natural language to standard values, format unification (e.g., date format unification to YYYY-MM-DD), and value range matching (e.g., matching the detection project name with the internal detection project code library). For required fields that exist in the task template but for which multidimensional requirement elements have not provided values, they can be pre-filled based on the template default values ​​or left blank for subsequent marking.

[0077] Step S430: Generate a first reference draft based on the reference fields.

[0078] After obtaining the reference fields, the task template can be populated with all reference fields to generate the first reference draft. At this point, the form is filled in, but it has not yet undergone subsequent professional validation by the knowledge base.

[0079] This disclosure obtains corresponding task templates based on the generated task creation requirements, ensuring that template selection matches the business scenario and avoiding field redundancy or missing fields caused by using a single general template. Furthermore, by mapping and normalizing multi-dimensional requirement elements to standard fields in the template, it ensures consistent and standardized data formats, improving the accuracy of information processing and workflow efficiency.

[0080] In one exemplary embodiment, when generating the first reference draft, a method for updating the draft through multi-turn dialogue is also provided. Specifically, the field source, missing fields, and current draft version of each field in the first reference draft can be determined; in response to at least one supplementation operation for a missing field, the supplementary field corresponding to the supplementation operation is merged into the first reference draft.

[0081] Specifically, the field source is the data origin identifier for each populated field in the first reference draft, recording the source of the field's value, such as reused historical templates, system default values, or user-added values. Alternatively, the field source can identify the field's position in the original detection requirement description information. Missing fields are fields determined to be mandatory based on the task's creation requirements but lacking valid values ​​in the current first reference draft. The current draft version is the version identifier obtained each time the first reference draft undergoes content changes, used to track the draft's modification history and support version comparison and rollback operations.

[0082] In practice, when filling in the task template based on reference fields to generate the first reference draft, three metadata records need to be executed in parallel. This involves tagging each filled field with a source label, comparing the required fields defined in the template with the currently filled fields to identify all required fields with no value or empty values, marking them as missing fields, and assigning a version number to the current draft, such as V1.0. Furthermore, missing fields can be highlighted on the user interface to guide users in completing them, for example, with a red border, an asterisk, or a separate panel. Users can perform one or more completion operations by clicking, typing, or selecting. Each time a user completes filling in one or more missing fields and triggers a save or confirmation action, the completed fields are merged with the current first reference draft, and the following updates are performed: tagging the newly added fields with source labels, re-identifying missing fields, and incrementing the current draft version number, such as V1.0 → V1.1.

[0083] It should be noted that this process of supplementing, merging, and updating the draft can continue until all required missing fields are filled, or the user chooses to force submission to proceed to the subsequent validation stage. In other words, through multiple rounds of dialogue, the new fields added by the user are merged into the existing draft without overwriting already confirmed valid fields. Finally, the first reference draft and its corresponding draft version can be output.

[0084] Optionally, missing fields can be categorized and assigned to different roles for completion. For example, the client's address can be completed by customer service, while standard types can be completed by the customer through a self-service terminal. Furthermore, it can support multiple people collaboratively editing the same draft and record the executor and time of each completion operation, further improving traceability information and increasing efficiency.

[0085] This disclosure ensures the traceability of every piece of information on the final order by recording the source of fields, enabling rapid identification of the root cause in case of disputes or errors. Explicitly specifying missing fields ensures that no required information is omitted, avoiding the repeated communication required for forms to be rejected due to oversights in traditional manual form filling, thus improving efficiency. Furthermore, version control of drafts provides support for operational documentation and compliance auditing.

[0086] In one exemplary embodiment, an implementation method for verifying a first reference draft is also provided. For example... Figure 5 The first reference draft is matched and validated using the available toolset and multi-dimensional requirement elements by invoking the target detection knowledge base. Based on the validation results, the items to be confirmed in the first reference draft are determined, including: Step S510: Determine the object detection knowledge base based on the available toolset.

[0087] The target detection knowledge base can be located based on the verification tools included in the available toolset.

[0088] Step S520: Based on the client information, obtain user master data from the object detection knowledge base.

[0089] User master data is the client's business profile data stored in the target detection knowledge base. It includes basic information such as registered account, name, and address, and may also include the client's historical inspection records, special requirements, testing items, and standard preferences.

[0090] Step S530: Determine the target testing item based on the testing method in the testing information, and determine the target testing standard based on the testing standard information in the testing information.

[0091] The system can match and confirm target testing items in the knowledge base based on the testing method or testing item name in the testing information. The target testing item can include attributes such as item code, item name, field of study, required sample quantity, and standard processing time. Correspondingly, based on the testing standard information (such as standard code) in the testing information, the system can match target testing standards in the knowledge base, which can include standard name, current valid version, and scope of application. For example, testing items can be matched based on testing methods such as CT scans; testing standards can be matched based on the standard number or standard name entered by the user.

[0092] Step S540: Based on the user master data, target detection items, detection standard information and target detection standards, perform matching verification on the first reference draft to obtain the verification result, and determine the items to be confirmed in the first reference draft according to the verification result.

[0093] After obtaining the user master data, target testing items, and target testing standards, multi-dimensional cross-validation can be performed. This includes: verifying whether the target testing standard is currently valid; verifying whether the target testing item falls within the contract framework or authorization scope recorded in the user master data; verifying the applicability relationship between the target testing item and the target testing standard (whether the item can reference the standard); and verifying whether the combination complies with the laboratory's current qualifications and capabilities. The validation results can record whether each item passed and the specific reasons.

[0094] In one exemplary embodiment, such as Figure 6 Based on user master data, target detection items, detection standard information, and target detection standards, the first reference draft is matched and validated to determine the items to be confirmed in the first reference draft, including: Step S610: Verify whether the client information matches the user master data.

[0095] By comparing the client information in the first draft with the user master data obtained from the knowledge base, it can be verified whether the name matches the registered name, whether there are multiple client entities with similar names, and whether the client's status is normal. If they do not match, they are identified as conflicting fields, and a pending confirmation item is generated.

[0096] Step S620: Query available detection standards based on the target detection item, and verify whether the available detection standards match the target detection item.

[0097] Based on the target detection project, the system queries the knowledge base for all available detection standard sets corresponding to that project. It then verifies whether the set is empty (i.e., whether any standards are available for the project) and whether the applicability relationship between the target detection project and these available standards holds. If the set is empty, it is considered a missing item; if multiple available standards exist but the user has not specified a specific standard, the matching result is considered not unique, and a candidate list, i.e., items to be confirmed, is generated.

[0098] Step S630: Verify whether the test standard indicated in the test standard information matches the available test standards.

[0099] The extracted testing standard information is matched against one or more available testing standards identified from the knowledge base. This verifies whether the standard code exists, whether the standard version is currently valid, and whether the standard truly belongs to the set of available testing standards. If the specified standard is obsolete, it is considered a conflicting field; if the standard code can correspond to multiple versions, the matching result is not unique, thus identifying an item to be confirmed.

[0100] Step S640: If there are non-unique matching results and / or conflicting field verification results, then based on the object detection knowledge base, determine at least one of the candidate items, missing items, and risk warning information items as items to be confirmed in the first reference draft.

[0101] Based on the above verification results, if any step results in a non-unique match or conflicting fields, a pending confirmation item will be generated. Candidate items (presenting alternative solutions for the user to select), missing items (prompting the user to supplement), and risk warning information items (indicating potential risks) can be determined based on the specific verification process (i.e., the three verification methods mentioned above).

[0102] In addition, if the matching fails, that is, no matching item is found, the field matching failure is confirmed. The original text of the user (i.e. the detection requirement description information) can be retained, and a manual confirmation or supplement is prompted.

[0103] This disclosure breaks down complex business compliance verification into three dimensions: customer, project, and standard. The verification objectives of each step are clear, which facilitates implementation and maintenance. It also ensures that the generated items to be confirmed correspond to specific issues, reducing the user's understanding cost. At the same time, by identifying the items to be confirmed and having the user confirm them, it can prevent the model from fabricating specific information such as customer, project, standard, or business identifiers, thus ensuring the accuracy of the order.

[0104] In step S240, in response to the operation instruction for the item to be confirmed, the first reference draft is updated according to the operation content corresponding to the operation instruction, and a second reference draft is generated.

[0105] In an exemplary embodiment of this disclosure, a confirmation item can be displayed to the user, thereby responding to an operation instruction for the item to be confirmed, and updating the first reference draft according to the operation content corresponding to the operation instruction. The operation instruction can take forms including, but is not limited to, mouse click selection, keyboard input, voice confirmation, and touch gestures. The type of operation instruction is determined by the type of the item to be confirmed, such as selection confirmation, modification fill, or ignore / skip.

[0106] In an exemplary embodiment, responding to an operation instruction for an item to be confirmed, updating a first reference draft according to the operation content corresponding to the operation instruction, and generating a second reference draft, includes: responding to an operation instruction for an item to be confirmed, determining the operation content, and updating the first reference draft according to the operation content to obtain a second reference draft; calling a target detection knowledge base according to a callable toolset and multi-dimensional requirement elements, and performing matching verification on the updated first reference draft until the verification is passed to obtain the second reference draft.

[0107] The updated first reference draft is an intermediate state of the draft after the user's operation. Before passing the final verification, it is still within the lifecycle of the "first reference draft," but the content has undergone incremental changes. In this disclosure, the verification does not end after one operation. Instead, whenever the draft content changes due to user operation, a new round of matching verification is triggered, forming a closed loop of operation, verification, and re-operation until the termination condition is met, that is, passing the above verification. For example, all fields in the draft meet the rule requirements in the object detection knowledge base, and no new, mandatory confirmation items are generated.

[0108] In addition, to prevent infinite loops, a maximum number of iterations can be set, or the loop can be terminated and a second reference draft generated when the user explicitly chooses to force a submission.

[0109] In this disclosure, user modifications may cause conflicts with other related fields. The cyclic verification mechanism can correct these conflicts in a timely manner, ensuring that the final draft is internally consistent and compliant in all dimensions. This process minimizes secondary errors that may be introduced by human modifications and improves the quality of the draft generation.

[0110] Optionally, users can update the first reference draft through multiple operation commands. During updates, it is crucial to ensure that the draft version is the one that has saved the corresponding operation content for each command, thus accurately preserving the operation content and preventing content loss or fabrication. After the operation, all pending confirmation items in the second reference draft are updated to confirmed values ​​or explicitly marked as ignored. At this point, the draft reaches a complete state ready for the final verification stage.

[0111] In step S250, the second reference draft is validated based on the order validation rules, and the target field is determined based on the validated second reference draft. The target field is then used to fill the task template to obtain the target detection task order.

[0112] In the exemplary embodiments of this disclosure, the order verification rules are predefined and independent of the set of business compliance check rules in the testing knowledge base. These rules are used to verify the completeness, consistency, and standardization of the order itself as a business document, not just the correctness of the testing technology. For example, the procedure may include whether all required fields are filled, whether numerical fields are within a reasonable range, whether date fields are logically correct, whether fee information is complete, and whether the business logic between fields is consistent. For example, the main table may verify required fields such as the client, contact person, contact number, report type, and completion date; the sample may verify required fields such as sample name, specifications, material, quantity, testing items, and testing standards; the format may verify fields such as contact number, date, and quantity; and the conditional fields may verify that mailed reports require an address, electronic reports require an email address, and testing at a specified location requires location information.

[0113] In one exemplary embodiment, such as Figure 7 The second reference draft is validated based on the order validation rules, and the target fields are determined based on the validated second reference draft. These target fields are then used to populate the task template, resulting in a target detection task order, including: Step S710: Verify the required fields in the main table, the required fields in the sample table, the field formats, and the content of the condition fields in the second reference draft according to the verification rules of the entrustment form, and obtain the first verification result.

[0114] In this step, a comprehensive basic check is performed on the second reference draft according to the order verification rules. This includes scanning each required field in the main table and the sample table to confirm there are no missing or empty values; verifying the data format compliance of each field, such as whether the date is a valid date and the phone number has the correct number of digits; and parsing the dependency logic of the condition fields to check whether the corresponding target fields of the condition trigger fields are correctly filled. Any violations are recorded as failures in the first verification result.

[0115] Step S720: Perform business consistency verification on the first reference draft to obtain the second verification result. Business consistency verification includes verifying the consistency of the test items, test standards, and the consistency between the test items and test standards.

[0116] If the first verification passes or is executed in parallel, a deeper level of business consistency verification can be performed. This verification process may include: whether the test item itself belongs to the set of permissible items; whether the testing standard itself is currently valid and the organization is qualified; whether the matching relationship between the test item and the testing standard is correct, that is, whether the standard is indeed applicable to the test item, and whether the test conditions of the item are within the scope specified by the standard. This ensures that there are no contradictions between technical elements. Any violation is recorded as a failure in the second verification result.

[0117] Step S730: After the first and second verification results pass, the target field is determined based on the second reference draft that has passed the verification, and the target field is presented.

[0118] Once both the first and second validation results are passed, all fields in the draft are organized into the target field set and presented to the user. At this point, a final manual review can be conducted to confirm or modify the data.

[0119] Step S740: In response to the determination and / or modification operations for the target field, call the delegated task template and generate a target detection delegated task based on the target field after the determination and / or modification operations.

[0120] It can respond to user confirmation or modification requests, first updating the target fields with the changes, then calling the official task template to fill the target fields into their corresponding positions, completing the final rendering, generating a target detection task order, and archiving it. Existing task order services can be reused for saving the task order.

[0121] In addition, after user confirmation, it can be determined whether the current draft version is accurate, ensuring that the content of the final generated order is accurate and complete.

[0122] This disclosure combines a first verification (basic verification) and a second verification (consistency verification), with clear division of labor between the two, to ensure that the final document is both complete and logically consistent, thereby improving the accuracy of the generated order. Furthermore, after completing all automated verifications, a target field preview and confirmation step is added, returning the final decision-making power to the user. The user can make final confirmations and fine-tuning based on ad-hoc communication, providing flexibility and further ensuring the accuracy of the order.

[0123] like Figure 8The image shown is a schematic diagram illustrating how a user provides a description of their testing needs through an interface. Figure 9 The image shown is a schematic diagram of the interface when a user clicks on the first reference draft to display the draft fields. Figure 10 The image shown is a schematic diagram of the interface for saving the order form after user confirmation.

[0124] The task order generation method in the exemplary embodiments of this disclosure automates the generation of task orders, significantly reducing the workload of manual item-by-item interpretation and data entry, minimizing information omissions and entry errors, and improving the efficiency and accuracy of task order generation. Simultaneously, it can adaptively determine creation requirements and available toolsets based on the current user role and business context, thus providing differentiated processing capabilities for different business scenarios and improving operational flexibility. Furthermore, the introduction of a target detection knowledge base during the generation process for matching and verifying drafts proactively identifies and locates items requiring confirmation, thereby advancing the discovery and correction of problems, avoiding repeated communication and modifications, and effectively shortening the task processing cycle.

[0125] In an exemplary embodiment of this disclosure, a task order generation apparatus is also provided. (See reference...) Figure 11 As shown, the task order generation device 1100 may include a requirement creation module 1110, an information extraction module 1120, a first verification module 1130, a result confirmation module 1140, and a task generation module 1150. Specifically: The requirement creation module 1110 is used to respond to received detection requirement description information, determine the commission task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context; the information extraction module 1120 is used to extract multi-dimensional requirement elements from the detection requirement description information, the multi-dimensional requirement elements including at least client information, sample information, detection information and report attribute information; the first verification module 1130 is used to perform field mapping processing on the multi-dimensional requirement elements based on the commission task creation requirement to obtain reference fields, generate a first reference draft based on the reference fields, and call the target detection knowledge base to match and verify the first reference draft based on the callable toolset and multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft based on the verification result; the result confirmation module 1140 is used to respond to the operation instructions for the items to be confirmed, update the first reference draft according to the operation content corresponding to the operation instructions, and generate a second reference draft; the commission task generation module 1150 is used to verify the second reference draft based on the commission form verification rules, and determine the target fields based on the verified second reference draft, so as to use the target fields to fill the commission task template to obtain the target detection commission task form.

[0126] In one exemplary embodiment of this disclosure, the response to receiving the detection requirement description information determines the entrusted task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context, including: if the task type is determined to be creating an entrustment order or modifying an entrustment order based on the current business context, then creating an entrusted task creation requirement; determining the type of the current user role, and filtering out the currently callable functional modules based on the type and the entrusted task creation requirement to obtain the callable toolset.

[0127] In one exemplary embodiment of this disclosure, based on the creation requirements of the entrusted task, the multidimensional requirement elements are processed by field mapping to obtain reference fields, and a first reference draft is generated based on the reference fields. The process includes: obtaining an entrusted task template based on the creation requirements of the entrusted task; processing the multidimensional requirement elements by field mapping based on the entrusted task template to normalize the multidimensional requirement requirements to the fields of the entrusted task template to obtain reference fields; and generating a first reference draft based on the reference fields.

[0128] In one exemplary embodiment of this disclosure, obtaining a task template based on task creation requirements includes: if it is determined that a historical template exists based on task creation requirements, providing functional options for the historical template; and in response to a selection operation for the functional options, determining the target historical template corresponding to the selection operation as the task template.

[0129] In one exemplary embodiment of this disclosure, the method further includes: determining the field source, missing field, and current draft version of each field in the first reference draft; and in response to at least one supplementation operation for a missing field, merging the supplementation field corresponding to the supplementation operation into the first reference draft.

[0130] In one exemplary embodiment of this disclosure, the process of calling a target detection knowledge base based on a callable toolset and multi-dimensional requirement elements to perform matching verification on a first reference draft, and determining the items to be confirmed in the first reference draft based on the verification results, includes: determining the target detection knowledge base based on the callable toolset; obtaining user master data from the target detection knowledge base based on client information; determining target detection items based on the detection methods in the detection information, and determining target detection standards based on the detection standard information in the detection information; performing matching verification on the first reference draft based on the user master data, target detection items, detection standard information, and target detection standards to obtain verification results; and determining the items to be confirmed in the first reference draft based on the verification results.

[0131] In one exemplary embodiment of this disclosure, a first reference draft is matched and verified based on user master data, target detection items, detection standard information, and target detection standards to determine items to be confirmed in the first reference draft according to the verification results. This includes: verifying whether the client information matches the user master data; querying available detection standards according to the target detection items and verifying whether the available detection standards match the target detection items; verifying whether the detection standards indicated in the detection standard information match the detection standards; if there are verification results with non-unique matching results and / or conflicting fields, at least one of candidate items, missing items, and risk warning information items is determined as items to be confirmed in the first reference draft based on the target detection knowledge base.

[0132] In one exemplary embodiment of this disclosure, responding to an operation instruction for an item to be confirmed, updating a first reference draft according to the operation content corresponding to the operation instruction, and generating a second reference draft, includes: responding to an operation instruction for an item to be confirmed, determining the operation content, and updating the first reference draft according to the operation content to obtain a second reference draft; calling a target detection knowledge base according to a callable toolset and multi-dimensional requirement elements, and performing matching verification on the updated first reference draft until the verification is passed to obtain the second reference draft.

[0133] In one exemplary embodiment of this disclosure, a second reference draft is validated based on the order verification rules, and a target field is determined based on the validated second reference draft. The target field is then used to fill in the task template to obtain a target detection task order. This includes: validating the main table required fields, sample required fields, field formats, and condition field contents in the second reference draft according to the order verification rules to obtain a first verification result; performing business consistency verification on the first reference draft to obtain a second verification result, whereby the business consistency verification includes detecting the consistency between the detection items, detection standards, and the detection items and detection standards; after the first and second verification results pass, the target field is determined based on the validated second reference draft and presented; in response to the determination and / or modification operations for the target field, the task template is invoked, and a target detection task is generated based on the target field after the determination and / or modification operations.

[0134] Since the details of each functional module of the task order generation apparatus of the exemplary embodiments of this disclosure have been described in the exemplary embodiments of the task order generation method described above, they will not be repeated here.

[0135] It should be noted that although several modules or units of the task order generation device have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, two or more modules and functions described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0136] Exemplary embodiments of this disclosure also provide a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the above-described task order generation method.

[0137] In one implementation, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing a computer program, such as read-only memory, NAND flash memory, etc.

[0138] In one implementation, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0139] Computer program code can be written in one or more programming languages. Examples of programming languages ​​include C, Java, and C++. Program code can execute entirely on the user's computing device, partially on the user's computing device, or as a standalone software package. It can also execute partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via an internet connection provided by a mobile network operator).

[0140] Computer programs can be carried or transmitted via signals such as electricity, magnetism, light, electromagnetic radiation, and infrared radiation. Electronic devices can convert the signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, to execute) the method steps of various exemplary embodiments of this disclosure, such as the task order generation method described above.

[0141] Furthermore, in exemplary embodiments of this disclosure, an electronic device capable of implementing the above-described methods is also provided. Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be specifically implemented as: entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as "circuit," "module," or "system."

[0142] The following reference Figure 12 To describe an electronic device 1200 according to such an embodiment of the present disclosure. Figure 12 The electronic device 1200 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein. The electronic device 1200 includes a processor and a memory for storing executable instructions of the processor. The processor is configured to perform any of the above methods by executing executable instructions.

[0143] like Figure 12 As shown, the electronic device 1200 is presented in the form of a general-purpose computing device. The components of the electronic device 1200 may include, but are not limited to: at least one processing unit 1210, at least one storage unit 1220, a bus 1230 connecting different system components (including storage unit 1220 and processing unit 1210), and a display unit 1240.

[0144] The storage unit stores program code that can be executed by the processing unit 1210, causing the processing unit 1210 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0145] Storage unit 1220 may include readable media in the form of volatile storage units, such as random access memory (RAM) 1221 and / or cache memory 1222, and may further include read-only memory (ROM) 1223.

[0146] Storage unit 1220 may also include a program / utility 1224 having a set (at least one) program module 1225, such program module 1225 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0147] Bus 1230 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0148] Electronic device 1200 can also communicate with one or more external devices 1300 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 1200, and / or any device that enables electronic device 1200 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1250. Furthermore, electronic device 1200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 12100. As shown, network adapter 12100 communicates with other modules of electronic device 1200 via bus 1230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0149] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0150] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0151] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for generating a task assignment sheet, characterized in that, include: Upon receiving the detection requirement description information, the system determines the task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context. Extract multi-dimensional requirement elements from the testing requirement description information. The multi-dimensional requirement elements include at least client information, sample information, testing information, and report attribute information. Based on the creation requirements of the entrusted task, the multi-dimensional requirement elements are processed by field mapping to obtain reference fields. A first reference draft is generated according to the reference fields. The first reference draft is matched and verified by calling the target detection knowledge base according to the callable toolset and multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft according to the verification results. In response to the operation instruction for the item to be confirmed, the first reference draft is updated according to the operation content corresponding to the operation instruction, and a second reference draft is generated. The second reference draft is validated based on the order validation rules, and the target fields are determined based on the validated second reference draft. The target fields are then used to fill the task template to obtain the target detection task order.

2. The method according to claim 1, characterized in that, The response receives the detection requirement description information and determines the delegated task creation requirement and the corresponding callable toolset based on the current user role and / or the current business context, including: If the task type is determined to be either creating a commission order or modifying a commission order based on the current business context, then the commission task creation requirement is created. Determine the type of the current user role, and filter out the currently callable functional modules based on the type and the requirements for creating the delegated task, to obtain the callable toolset.

3. The method according to claim 1, characterized in that, The process of creating requirements based on the delegated task involves mapping the multi-dimensional requirement elements to obtain reference fields, and generating a first reference draft based on the reference fields, including: Based on the aforementioned task creation requirements, obtain the task template. Based on the entrusted task template, the multidimensional requirement elements are processed by field mapping to normalize the multidimensional requirement requirements to the fields of the entrusted task template, thereby obtaining the reference fields; The first reference draft is generated based on the reference fields.

4. The method according to claim 3, characterized in that, The step of obtaining the task template based on the task creation requirements includes: If a historical template is determined to exist based on the task creation requirements, then functional options for that historical template are provided. In response to a selection operation for a function option, the target historical template corresponding to the selection operation is determined as the delegated task template.

5. The method according to claim 3, characterized in that, The method further includes: Determine the field source, missing fields, and current draft version for each field in the first reference draft; In response to at least one supplementation operation for the missing field, the supplementation field corresponding to the supplementation operation is merged into the first reference draft.

6. The method according to claim 1, characterized in that, The step of calling the target detection knowledge base to perform matching verification on the first reference draft based on the callable toolset and multi-dimensional requirement elements, and determining the items to be confirmed in the first reference draft based on the verification results, includes: The target detection knowledge base is determined based on the callable toolset; Based on the client information, user master data is obtained from the target detection knowledge base; The target testing items are determined based on the testing methods in the testing information, and the target testing standards are determined based on the testing standard information in the testing information. Based on the user master data, the target detection items, the detection standard information, and the target detection standard, the first reference draft is matched and verified to obtain the verification result, so as to determine the items to be confirmed in the first reference draft according to the verification result.

7. The method according to claim 6, characterized in that, The step of performing a matching verification on the first reference draft based on the user master data, the target detection items, the detection standard information, and the target detection standard, and determining the items to be confirmed in the first reference draft based on the verification results, includes: Verify whether the client information matches the user master data; Based on the target detection item, query available detection standards and verify whether the available detection standards match the target detection item; Verify whether the detection standard indicated in the detection standard information matches the available detection standards; If there are non-unique matching results and / or conflicting field verification results, then at least one of the candidate items, missing items, and risk warning information items is determined as the items to be confirmed in the first reference draft based on the target detection knowledge base.

8. The method according to claim 1, characterized in that, The response to the operation instruction for the item to be confirmed, updating the first reference draft according to the operation content corresponding to the operation instruction, and generating a second reference draft includes: In response to the operation instruction for the item to be confirmed, the operation content is determined, and the first reference draft is updated according to the operation content to obtain the second reference draft; The target detection knowledge base is invoked based on the callable toolset and multi-dimensional requirement elements to perform matching and verification on the updated first reference draft until the verification is passed, thus obtaining the second reference draft.

9. The method according to claim 1, characterized in that, The process of validating the second reference draft based on the order verification rules, and determining the target fields based on the valid second reference draft, and then using the target fields to populate the task template to obtain a target detection task order, includes: According to the order verification rules, the required fields in the main table, the required fields in the sample, the field formats, and the content of the condition fields in the second reference draft are verified to obtain the first verification result. The first reference draft is checked for business consistency to obtain a second check result. The business consistency check includes checking the consistency of the test items, test standards, and the consistency between the test items and test standards. Once the first and second verification results pass, the target field is determined based on the second reference draft that has passed verification, and the target field is presented. In response to the determination and / or modification operations on the target field, the delegated task template is invoked to generate the target detection delegated task based on the target field after the determination and / or modification operations.

10. A task order generation device, characterized in that, The device includes: The requirement creation module is used to respond to the received detection requirement description information, and determine the requirement for creating the delegated task and the corresponding callable toolset based on the current user role and / or the current business context. The information extraction module is used to extract multi-dimensional demand elements from the testing demand description information. The multi-dimensional demand elements include at least client information, sample information, testing information, and report attribute information. The first verification module is used to create requirements based on the entrusted task, perform field mapping processing on the multi-dimensional requirement elements to obtain reference fields, generate a first reference draft based on the reference fields, and call the target detection knowledge base to perform matching verification on the first reference draft based on the callable toolset and multi-dimensional requirement elements, so as to determine the items to be confirmed in the first reference draft based on the verification results. The result confirmation module is used to respond to the operation instructions for the item to be confirmed, update the first reference draft according to the operation content corresponding to the operation instructions, and generate the second reference draft. The task generation module is used to verify the second reference draft based on the task form verification rules, and determine the target fields based on the verified second reference draft, so as to fill the task template with the target fields to obtain the target detection task form.

Images