技术领域Technical field
本发明涉及工作流管理技术领域，尤其涉及一种工作流创建方法、装置、设备及存储介质。The present invention relates to the technical field of workflow management, and in particular to a workflow creation method, device, equipment and storage medium.
背景技术Background technique
对于工作流系统，无论是使用Activiti、Flowable或Camunda等开源引擎，创建流程和填写表单等业务流程通常都需要人工操作，并且当流程设计发生变更时，也需要依赖系统管理员进行人工处理，可能还需要管理员画流程图和配置表单等，导致流程设计效率低下，并且人工处理还可能出现错误填写等操作。For workflow systems, whether using open source engines such as Activiti, Flowable or Camunda, business processes such as creating processes and filling out forms usually require manual operations, and when the process design changes, it also needs to rely on the system administrator for manual processing, which may Administrators are also required to draw flow charts and configure forms, etc., resulting in inefficient process design, and manual processing may also lead to incorrect filling in and other operations.
同时，工作流系统中各类流程繁杂，大部分用户不清楚应该怎么选择流程，因此需要开发人员花费大量时间培训及编写操作手册指引用户提单，导致提单效率低下，运营成本大大增加。其中还存在用户在提单时不清楚字段含义，导致无法填写，因而需要花费大量时间沟通填写表单，期间答疑沟通成本高，虽然有FAQ等各类非结构化相关文档，但由于时间推移，人员更换，相关文档缺少迭代更新，用户查阅效果不佳，用户遇到问题还需找对应专业运维同事沟通，增加沟通成本。At the same time, various processes in the workflow system are complicated, and most users do not know how to choose the process. Therefore, developers need to spend a lot of time training and writing operation manuals to guide users to laminate, resulting in low bill of lading efficiency and greatly increasing operating costs. There are also cases where users are unclear about the meaning of fields when billing, resulting in the inability to fill them in. Therefore, it takes a lot of time to communicate and fill in the form. During the period, the cost of answering questions and communication is high. Although there are various unstructured related documents such as FAQ, due to the passage of time, personnel changes , the relevant documents lack iterative updates, and the user review effect is not good. When users encounter problems, they need to communicate with corresponding professional operation and maintenance colleagues, which increases communication costs.
发明内容Contents of the invention
基于此，有必要针对上述技术问题，提供一种工作流创建方法、装置、设备及存储介质，旨在实现工作流的自动化生成和智能填写等，从而显著提高工作效率和准确性，同时减少了人为错误，有效降低运营成本，降低用户操作负担，提升用户体验。Based on this, it is necessary to provide a workflow creation method, device, equipment and storage medium in response to the above technical problems, aiming to realize automatic generation and intelligent filling of workflows, thereby significantly improving work efficiency and accuracy, while reducing Eliminate human errors, effectively reduce operating costs, reduce user operating burden, and improve user experience.
一种工作流创建方法，所述工作流创建方法应用于语聊机器人，包括：A workflow creation method, the workflow creation method is applied to a voice chat robot, including:
获取目标用户对应的工作流创建信息；Obtain the workflow creation information corresponding to the target user;
基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型；Determine the first response information and workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph;
将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息；Input the first response information into the business process question and answer model to obtain the second response information output by the business process question and answer model;
将所述第二应答信息以及所述工作流类型发送至工作流创建引擎，以供所述工作流创建引擎创建与所述工作流创建信息对应的工作流。The second response information and the workflow type are sent to the workflow creation engine, so that the workflow creation engine can create a workflow corresponding to the workflow creation information.
根据本发明提供的一种工作流创建方法，所述基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型，包括：According to a workflow creation method provided by the present invention, determining the first response information and workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph includes:
对所述工作流创建信息进行文本分割，并将分割后的工作流创建信息向量化，得到工作流创建向量；Perform text segmentation on the workflow creation information, and vectorize the segmented workflow creation information to obtain a workflow creation vector;
将所述工作流创建向量与预设流程知识库进行查询匹配，得到所述工作流类型以及初始应答信息；Query and match the workflow creation vector with the preset process knowledge base to obtain the workflow type and initial response information;
对所述初始应答信息进行结构化处理，并将结构化后的初始应答信息与预设流程知识图谱进行匹配，以得到所述第一应答信息。The initial response information is structured, and the structured initial response information is matched with the preset process knowledge graph to obtain the first response information.
根据本发明提供的一种工作流创建方法，所述基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型之前，还包括：According to a workflow creation method provided by the present invention, before determining the first response information and the workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph, the method further includes:
获取业务流程知识；Acquire business process knowledge;
对所述业务流程知识进行信息抽取以及知识融合，得到工作流结构化知识，并对所述工作流结构化知识进行质量评估；Perform information extraction and knowledge fusion on the business process knowledge to obtain workflow structured knowledge, and perform quality assessment on the workflow structured knowledge;
若质量评估通过，则将所述工作流结构化知识存储至所述预设流程知识图谱。If the quality assessment passes, the workflow structured knowledge is stored in the preset process knowledge graph.
根据本发明提供的一种工作流创建方法，所述将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息之前，还包括：According to a workflow creation method provided by the present invention, before inputting the first response information into the business process question and answer model and obtaining the second response information output by the business process question and answer model, the method further includes:
获取若干组流程需求样本，并将各所述流程需求样本划分为模型训练集、模型验证集以及模型测试集；Obtain several sets of process requirement samples, and divide each of the process requirement samples into a model training set, a model verification set, and a model testing set;
基于所述模型训练集、所述模型验证集以及所述模型测试集，对初始业务流程问答模型进行迭代训练以及模型微调，得到所述业务流程问答模型。Based on the model training set, the model verification set and the model test set, iterative training and model fine-tuning are performed on the initial business process question and answer model to obtain the business process question and answer model.
根据本发明提供的一种工作流创建方法，所述获取目标用户对应的工作流创建信息，包括：According to a workflow creation method provided by the present invention, obtaining workflow creation information corresponding to a target user includes:
获取目标用户输入的工作流创建需求；Obtain the workflow creation requirements input by the target user;
基于所述工作流创建需求，判断是否匹配历史创建信息；Based on the workflow creation requirements, determine whether it matches historical creation information;
若是，则将匹配到的历史创建信息以及所述工作流创建需求进行关联组合，生成所述工作流创建信息；If so, associate and combine the matched historical creation information and the workflow creation requirements to generate the workflow creation information;
若否，则基于所述工作流创建需求，生成所述工作流创建信息。If not, the workflow creation information is generated based on the workflow creation requirement.
一种工作流创建方法，所述工作流创建方法应用于工作流创建引擎，包括：A workflow creation method, the workflow creation method is applied to a workflow creation engine, including:
接收语聊机器人发送的第二应答信息以及工作流类型；Receive the second response message and workflow type sent by the chatbot;
基于所述工作流类型，确定所述工作流对应的工作流创建模块；Based on the workflow type, determine the workflow creation module corresponding to the workflow;
对所述第二应答信息进行解析，得到工作流实体、实体属性以及实体关联情况；Parse the second response information to obtain workflow entities, entity attributes, and entity associations;
将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流。The workflow entity, the entity attributes and the entity association are input into the workflow creation module, so that the workflow creation module can create the workflow.
根据本发明提供的一种工作流创建方法，所述将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流之后，还包括：According to a workflow creation method provided by the present invention, the workflow entity, the entity attributes and the entity association are input into the workflow creation module, so that the workflow creation module can create the After the workflow, it also includes:
获取所述工作流的创建成功时间以及查看方式；Get the creation success time and viewing method of the workflow;
基于所述工作流类型、所述创建成功时间以及所述查看方式，生成创建成功信息；Generate creation success information based on the workflow type, the creation success time, and the viewing mode;
将所述创建成功信息推送至目标用户，以提醒所述目标用户进行查看。Push the creation success information to the target user to remind the target user to check.
一种工作流创建装置，包括：A workflow creation device including:
语聊机器人，用于获取用户输入的工作流创建信息；基于所述工作流创建信息与预设流程知识图谱，确定第一应答信息以及工作流类型；将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息；A chat robot used to obtain workflow creation information input by the user; determine the first response information and workflow type based on the workflow creation information and the preset process knowledge graph; input the first response information into the business process A question and answer model to obtain the second response information output by the business process question and answer model;
工作流创建引擎，用于接收语聊机器人发送的第二应答信息以及工作流类型；基于所述工作流类型，确定所述工作流对应的工作流创建模块；对所述第二应答信息进行解析，得到工作流实体、实体属性以及实体关联情况；将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流。A workflow creation engine, configured to receive the second response information and the workflow type sent by the chatbot; based on the workflow type, determine the workflow creation module corresponding to the workflow; and parse the second response information , obtain the workflow entity, entity attributes and entity association; input the workflow entity, the entity attribute and the entity association into the workflow creation module for the workflow creation module to create the work flow.
一种电子设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现上述工作流创建方法。An electronic device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the above-mentioned workflow creation method is implemented. .
一个或多个存储有计算机可读指令的可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如上述工作流创建方法。One or more readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to execute the above workflow creation method.
上述工作流创建方法、装置、设备及存储介质，通过获取目标用户对应的工作流创建信息，并基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型，进而将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息，进而将所述第二应答信息以及所述工作流类型发送至工作流创建引擎，以供所述工作流创建引擎创建与所述工作流创建信息对应的工作流，从而实现工作流的自动化生成和智能填写等，从而显著提高工作效率和准确性，同时减少了人为错误，有效降低运营成本，降低用户操作负担，提升用户体验。The above-mentioned workflow creation method, device, equipment and storage medium obtain the workflow creation information corresponding to the target user, and determine the first response information based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph. and the workflow type, and then input the first response information to the business process question and answer model to obtain the second response information output by the business process question and answer model, and then send the second response information and the workflow type to A workflow creation engine, for the workflow creation engine to create a workflow corresponding to the workflow creation information, thereby realizing automated generation and intelligent filling of workflows, thereby significantly improving work efficiency and accuracy, while reducing Eliminate human errors, effectively reduce operating costs, reduce user operating burden, and improve user experience.
附图说明Description of drawings
为了更清楚地说明本发明实施例的技术方案，下面将对本发明实施例的描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to explain the technical solutions of the embodiments of the present invention more clearly, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. , for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without exerting creative labor.
图1是本发明提供的工作流创建方法的流程示意图之一；Figure 1 is one of the flow diagrams of the workflow creation method provided by the present invention;
图2是本发明提供的工作流创建方法的流程示意图之二；Figure 2 is the second flow schematic diagram of the workflow creation method provided by the present invention;
图3是本发明提供的工作流创建装置的结构示意图；Figure 3 is a schematic structural diagram of a workflow creation device provided by the present invention;
图4是本发明提供的预设流程知识库的部分构建流程图；Figure 4 is a partial construction flow chart of the preset process knowledge base provided by the present invention;
图5是本发明提供的工作流创建系统的部分功能实现图；Figure 5 is a partial functional implementation diagram of the workflow creation system provided by the present invention;
图6是本发明提供的预设流程知识图谱的部分构建流程图；Figure 6 is a partial construction flow chart of the preset process knowledge graph provided by the present invention;
图7是本发明提供的信息结构化示例图；Figure 7 is an example diagram of information structure provided by the present invention;
图8是本发明提供的工单生成的功能实现示例图；Figure 8 is a functional implementation example diagram of work order generation provided by the present invention;
图9是本发明提供的表单填写的功能实现示例图；Figure 9 is an example diagram of the form filling function implementation provided by the present invention;
图10是本发明提供的流程设计更改的功能实现示例图；Figure 10 is a functional implementation example diagram of the process design change provided by the present invention;
图11是本发明提供的电子设备的结构示意图。Figure 11 is a schematic structural diagram of the electronic device provided by the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.
在本发明一个或多个实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本发明一个或多个实施例。在本发明一个或多个实施例中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本发明一个或多个实施例中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。The terminology used in one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to limit the one or more embodiments of the invention. As used in one or more embodiments of the invention, the singular forms "a," "the" and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and/or" as used in one or more embodiments of the present invention refers to and includes any and all possible combinations of one or more of the associated listed items.
应当理解，尽管在本发明一个或多个实施例中可能采用术语第一、第二等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本发明一个或多个实施例范围的情况下，第一也可以被称为第二，类似地，第二也可以被称为第一。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”。It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present invention, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present invention, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "when".
图1是本发明提供的工作流创建方法的流程示意图。如图1所示，该工作流创建方法应用于语聊机器人，包括：Figure 1 is a schematic flow chart of the workflow creation method provided by the present invention. As shown in Figure 1, this workflow creation method is applied to chatbots, including:
步骤S11，获取目标用户对应的工作流创建信息；Step S11, obtain the workflow creation information corresponding to the target user;
需要说明的是，所述目标用户是指需要创建工作流的用户，所述工作流创建信息是指所述目标用户在创建工作流的过程中具体的要求和期望所需要的创建信息，包括业务流程描述（如工作流的步骤、阶段、涉及的工作流实体、实体属性以及实体关联情况等）、用户交互需求（如表单要素以及用户权限管理等）、历史创建信息、自定义规则（如审批条件、流程分支以及自动化决策等）、流程监控和报告以及业务知识问答等结构化数据以及非结构化数据，在此不做限制。It should be noted that the target user refers to the user who needs to create a workflow, and the workflow creation information refers to the creation information required by the target user's specific requirements and expectations in the process of creating the workflow, including business Process description (such as workflow steps, stages, involved workflow entities, entity attributes, entity associations, etc.), user interaction requirements (such as form elements and user rights management, etc.), historical creation information, custom rules (such as approval Conditions, process branches and automated decision-making, etc.), process monitoring and reporting, business knowledge Q&A and other structured data and unstructured data are not limited here.
具体地，获取目标用户输入的工作流创建需求，进而基于所述工作流创建需求，判断是否匹配历史创建信息，从而若是，则将匹配到的历史创建信息以及所述工作流创建需求进行关联组合，生成所述工作流创建信息。Specifically, the workflow creation requirements input by the target user are obtained, and then based on the workflow creation requirements, it is determined whether the historical creation information matches, and if so, the matched historical creation information and the workflow creation requirements are associated and combined. , generate the workflow creation information.
步骤S12，基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型；Step S12, determine the first response information and workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph;
需要说明的是，所述预设流程知识库是由BPM（Business Process Management，业务流程管理）相关FAQ文档（Frequently Asked Questions，常见问题解答）、系统存量流程、用户信息以及历史创建信息等数据形成的，可通过SQL、Excel以及Word等多种方式实现数据接入，丰富数据源，可参考图4，图4是本发明提供的预设流程知识库的部分构建流程图，其中，可利用LangChain文档加载器进行文件加载等操作。此外，所述预设流程知识库可随着数据的接入进行持续性更新，以提高更精确的应答生成能力。It should be noted that the preset process knowledge base is formed by BPM (Business Process Management, Business Process Management) related FAQ documents (Frequently Asked Questions, Frequently Asked Questions), system inventory processes, user information, historical creation information and other data. Data access can be achieved through SQL, Excel, Word and other methods to enrich data sources. Please refer to Figure 4. Figure 4 is a partial construction flow chart of the preset process knowledge base provided by the present invention, in which LangChain can be used. The document loader performs operations such as file loading. In addition, the preset process knowledge base can be continuously updated as data is accessed to improve more accurate response generation capabilities.
进一步需要说明的是，所述预设流程知识图谱是指预先设置的存储有基本属性知识、关联知识、事件知识、时序知识以及资源类知识等各类结构化数据的知识图谱，其中，所述预设流程知识图谱是可以自动进行迭代更新的，以获取更为精确的知识，生成更准确细致的应答。It should be further noted that the preset process knowledge graph refers to a knowledge graph that is preset to store various types of structured data such as basic attribute knowledge, association knowledge, event knowledge, timing knowledge, and resource knowledge, where the The preset process knowledge graph can be automatically and iteratively updated to obtain more accurate knowledge and generate more accurate and detailed responses.
另外地，所述第一应答信息是由所述预设流程知识图谱以及所述工作流创建信息等生成的应答信息。所述工作流类型包括流程设计微调、工单生成以及表单填写等，在此不做限制。Additionally, the first response information is response information generated by the preset process knowledge graph and the workflow creation information. The workflow types include process design fine-tuning, work order generation, form filling, etc., and are not limited here.
具体地，对所述工作流创建信息进行文本分割，并将分割后的工作流创建信息向量化，得到工作流创建向量，进而将所述工作流创建向量与预设流程知识库进行查询匹配，得到所述工作流类型以及初始应答信息，从而对所述初始应答信息进行结构化处理，并将结构化后的初始应答信息与预设流程知识图谱进行匹配，以得到所述第一应答信息。Specifically, text segmentation is performed on the workflow creation information, and the segmented workflow creation information is vectorized to obtain a workflow creation vector, and then the workflow creation vector is queried and matched with a preset process knowledge base, The workflow type and initial response information are obtained, the initial response information is structured, and the structured initial response information is matched with the preset process knowledge graph to obtain the first response information.
步骤S13，将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息；Step S13: Input the first response information into the business process question and answer model to obtain the second response information output by the business process question and answer model;
需要说明的是，所述业务流程问答模型是由模型训练集、模型验证集以及模型测试集等流程需求样本迭代训练得到。另外地，所述第二应答信息是指由所述业务流程问答模型针对第一应答信息生成的应答信息，当所述目标用户通过所述语聊机器人进行业务询问时，可将所述第二应答信息返回至所述目标用户，以实现用户交互，增强系统应答能力。It should be noted that the business process question and answer model is obtained by iterative training of process requirement samples such as a model training set, a model verification set, and a model testing set. In addition, the second response information refers to the response information generated by the business process question and answer model for the first response information. When the target user makes a business inquiry through the voice chat robot, the second response information can be The response information is returned to the target user to realize user interaction and enhance the system's response capability.
步骤S14，将所述第二应答信息以及所述工作流类型发送至工作流创建引擎，以供所述工作流创建引擎创建与所述工作流创建信息对应的工作流。Step S14: Send the second response information and the workflow type to the workflow creation engine, so that the workflow creation engine can create a workflow corresponding to the workflow creation information.
需要说明的是，所述工作流创建引擎是指根据工作流创建信息中如工作流实体、实体属性以及实体关联情况等不同决定信息来传递路由、内容等级等逻辑解决引擎，其可以为Activiti流程引擎等，在此不做限制。例如，生成员工请假条的工作流程，当部门主管批准请假时，所述工作流创建引擎按照业务逻辑生成将请假条下发至公司上层领导的工作流，以供其进行确认批准。其中，所述工作流创建引擎包括各种工作流类型模块，如工单生成模块、表单填写模块以及流程设计微调模块等，在此不做限制。It should be noted that the workflow creation engine refers to a logical solution engine that delivers routing, content levels, etc. based on different decision information in the workflow creation information such as workflow entities, entity attributes, and entity associations. It can be an Activiti process. Engines, etc. are not limited here. For example, take the workflow of generating an employee's leave request. When the department head approves the leave, the workflow creation engine generates a workflow that sends the leave request to the company's upper-level leaders for confirmation and approval according to business logic. The workflow creation engine includes various workflow type modules, such as a work order generation module, a form filling module, a process design fine-tuning module, etc., which are not limited here.
进一步需要说明的是，所述工作流（Workflow）是一种系统化、有序的业务流程，用于组织、管理和执行特定的工作任务或业务活动，所述工作流可以涵盖各种组织内的业务流程，从简单的日常任务到复杂的业务流程都可以使用工作流进行规划和管理，可根据实际情况进行设置，在此不做详述。It should be further noted that the workflow (Workflow) is a systematic and orderly business process used to organize, manage and execute specific work tasks or business activities. The workflow can cover various tasks within an organization. Business processes, from simple daily tasks to complex business processes, can be planned and managed using workflows. They can be set according to the actual situation and will not be described in detail here.
具体地，将所述第二应答信息以及所述工作流类型等信息发送至所述工作流创建引擎，以供所述工作流创建引擎接收到所述第二应答信息以及所述工作流类型等信息后，创建与所述工作流创建信息对应的工作流，可参考图5，图5是本发明提供的工作流创建系统的部分功能实现图。Specifically, the second response information and the workflow type and other information are sent to the workflow creation engine, so that the workflow creation engine receives the second response information and the workflow type and so on. After receiving the information, create a workflow corresponding to the workflow creation information. Refer to Figure 5. Figure 5 is a partial functional implementation diagram of the workflow creation system provided by the present invention.
本发明实施例通过获取目标用户对应的工作流创建信息，并基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型，进而将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息，进而将所述第二应答信息以及所述工作流类型发送至工作流创建引擎，以供所述工作流创建引擎创建与所述工作流创建信息对应的工作流，从而实现工作流的自动化生成和智能填写等，从而显著提高工作效率和准确性，同时减少了人为错误，有效降低运营成本，降低用户操作负担，提升用户体验。The embodiment of the present invention obtains the workflow creation information corresponding to the target user, and determines the first response information and workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph, and then uses the workflow creation information to determine the first response information and the workflow type. The first response information is input to the business process question and answer model to obtain the second response information output by the business process question and answer model, and then the second response information and the workflow type are sent to the workflow creation engine for the The workflow creation engine creates a workflow corresponding to the workflow creation information, thereby realizing automated generation and intelligent filling of workflows, etc., thereby significantly improving work efficiency and accuracy, while reducing human errors, effectively reducing operating costs, and reducing User operation burden improves user experience.
在本发明的一个实施例中，所述基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型，包括：In one embodiment of the present invention, determining the first response information and workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph includes:
对所述工作流创建信息进行文本分割，并将分割后的工作流创建信息向量化，得到工作流创建向量；将所述工作流创建向量与预设流程知识库进行查询匹配，得到所述工作流类型以及初始应答信息；对所述初始应答信息进行结构化处理，并将结构化后的初始应答信息与预设流程知识图谱进行匹配，以得到所述第一应答信息。Carry out text segmentation on the workflow creation information, and vectorize the segmented workflow creation information to obtain a workflow creation vector; query and match the workflow creation vector with the preset process knowledge base to obtain the work flow creation vector. Stream type and initial response information; perform structured processing on the initial response information, and match the structured initial response information with the preset process knowledge graph to obtain the first response information.
需要说明的是，所述工作流创建向量是指将工作流创建信息转换为数学向量过程中得到的向量值，以允许计算机系统等更好地理解和处理文本等数据。另外地，所述初始应答信息是指根据所述预设流程知识库生成的应答信息。It should be noted that the workflow creation vector refers to the vector value obtained in the process of converting workflow creation information into a mathematical vector, so as to allow computer systems and the like to better understand and process text and other data. Additionally, the initial response information refers to response information generated according to the preset process knowledge base.
具体地，对所述工作流创建信息进行文本分割，如将文本分割成单词或词汇单元以及去除停用词等操作，其中，所述停用词为在文本中频繁出现但通常不携带特定信息的词语，如“and”、“the”等。进而将分割后的工作流创建信息向量化，得到工作流创建向量，可采用词袋模型（Bag of Words，BoW）、TF-IDF（Term Frequency-Inverse DocumentFrequency）以及使用词嵌入模型（如Word2Vec、GloVe、FastText）等方式进行向量化，在此不做限制。Specifically, perform text segmentation on the workflow creation information, such as segmenting the text into words or vocabulary units and removing stop words, where the stop words appear frequently in the text but usually do not carry specific information. words, such as "and", "the", etc. Then, the divided workflow creation information is vectorized to obtain the workflow creation vector. Bag of Words (BoW), TF-IDF (Term Frequency-Inverse DocumentFrequency), and word embedding models (such as Word2Vec, GloVe, FastText) and other methods are used for vectorization, and there are no restrictions here.
进一步地，将所述工作流创建向量与预设流程知识库进行查询匹配，其中，可以采用faiss（Facebook AI Similarity Search）搜索方法，根据匹配结果确定所述工作流类型以及所述初始应答信息，进而对所述初始应答信息进行结构化处理，即，将所述初始应答信息转换为结构化信息，可参考图7，图7是本发明提供的信息结构化示例图，并将结构化后的初始应答信息与预设流程知识图谱进行匹配，即，匹配到与所述初始应答信息对应的相关实体节点，从而将结构化后的初始应答信息填充至所述相关实体节点，以得到所述第一应答信息。Further, query and match the workflow creation vector with a preset process knowledge base, where the faiss (Facebook AI Similarity Search) search method can be used to determine the workflow type and the initial response information according to the matching results, Then, the initial response information is structured, that is, the initial response information is converted into structured information. Refer to Figure 7. Figure 7 is an example diagram of information structuring provided by the present invention, and the structured information is The initial response information is matched with the preset process knowledge graph, that is, the relevant entity node corresponding to the initial response information is matched, thereby filling the structured initial response information into the relevant entity node to obtain the third A response message.
本发明实施例通过对所述工作流创建信息进行文本分割，并将分割后的工作流创建信息向量化，得到工作流创建向量，进而将所述工作流创建向量与预设流程知识库进行查询匹配，得到所述工作流类型以及初始应答信息，从而对所述初始应答信息进行结构化处理，并将结构化后的初始应答信息与预设流程知识图谱进行匹配，以得到所述第一应答信息，进而通过预设流程知识库以及预设流程知识图谱，实现高效精准地识别用户意图，并根据其意图生成精确且实际的应答信息，从而有效提高语聊机器人的应答能力，提升用户体验及工作效率，进而降低运营成本，减轻用户操作负担。The embodiment of the present invention performs text segmentation on the workflow creation information and vectorizes the segmented workflow creation information to obtain a workflow creation vector, and then queries the workflow creation vector with the preset process knowledge base. Match to obtain the workflow type and initial response information, thereby structuring the initial response information, and matching the structured initial response information with the preset process knowledge graph to obtain the first response Information, and then through the preset process knowledge base and preset process knowledge graph, it is possible to efficiently and accurately identify user intentions, and generate accurate and practical response information based on their intentions, thereby effectively improving the response capabilities of the chatbot, improving user experience and Work efficiency, thereby reducing operating costs and reducing user operational burdens.
在本发明的一个实施例中，所述基于所述工作流创建信息、预设流程知识库以及预设流程知识图谱，确定第一应答信息以及工作流类型之前，还包括：In one embodiment of the present invention, before determining the first response information and the workflow type based on the workflow creation information, the preset process knowledge base and the preset process knowledge graph, the method further includes:
获取业务流程知识；对所述业务流程知识进行信息抽取以及知识融合，得到工作流结构化知识，并对所述工作流结构化知识进行质量评估；若质量评估通过，则将所述工作流结构化知识存储至所述预设流程知识图谱。Obtain business process knowledge; perform information extraction and knowledge fusion on the business process knowledge to obtain workflow structured knowledge, and perform a quality assessment on the workflow structured knowledge; if the quality assessment passes, the workflow structure The knowledge is stored in the preset process knowledge graph.
需要说明的是，传统的基于向量搜索的过程为：加载文件-读取文本-文本分割-文本向量化-问句向量化-在文本向量中匹配出与问句向量最相似的top k个-匹配出的文本作为上下文和问题一起添加到prompt（应答）中-提交给LLM（Large Language Model，大语言模型）生成回答。当向量搜索可以产生相关的文本块时，这种方法非常有效。然而，当LLM需要来自多个文档甚至多个块的信息来生成答案时，简单的向量相似性搜索可能是不够精确的。而且，这种方法还很容易遗漏互相关联的文档块，从而导致信息检索不完整。同时，因此，为了减少基于嵌入的语义搜索所导致的不准确性，需要构建基于BPM业务流程领域的预设流程知识图谱。It should be noted that the traditional vector-based search process is: load the file - read the text - text segmentation - text vectorization - question vectorization - match the top k most similar to the question vector in the text vector - The matched text is added to the prompt (response) as context and question - submitted to LLM (Large Language Model) to generate an answer. This method works well when a vector search can produce relevant chunks of text. However, when LLM requires information from multiple documents or even multiple chunks to generate an answer, a simple vector similarity search may not be accurate enough. Furthermore, this approach can easily miss interrelated document chunks, resulting in incomplete information retrieval. At the same time, therefore, in order to reduce the inaccuracy caused by embedding-based semantic search, it is necessary to build a preset process knowledge graph based on the BPM business process domain.
进一步需要说明的是，所述业务流程知识是指与BPM相关的各类知识，包括基本属性知识、关联知识、事件知识、时序知识以及资源类知识等。所述工作流结构化知识是由对业务流程知识进行信息抽取以及知识融合等构建操作后得到的。It should be further noted that the business process knowledge refers to various types of knowledge related to BPM, including basic attribute knowledge, association knowledge, event knowledge, timing knowledge, resource knowledge, etc. The workflow structured knowledge is obtained by performing information extraction, knowledge fusion and other construction operations on business process knowledge.
具体地，获取业务流程知识，进而对所述业务流程知识进行信息抽取以及知识融合，得到工作流结构化知识，其中，信息抽取是指从所述业务流程知识提取出工作流实体、实体属性以及实体关联情况等，比如请假流程中部门主管与公司上层领导两个实体，以及两者之间的逻辑关系等，在此基础上形成本体化的知识表达，例如，只有在部门主管批准请假之后，才将请假条的流程转移到公司上层领导处；知识融合是指对所述业务流程知识进行整合，以消除矛盾和歧义，比如某些实体可能有多种表达，某个特定称谓也能对应多个不同的实体以及近义词之间的关联等。Specifically, business process knowledge is obtained, and then information extraction and knowledge fusion are performed on the business process knowledge to obtain workflow structured knowledge, where information extraction refers to extracting workflow entities, entity attributes, and Entity associations, etc., such as the two entities of the department head and the company's upper-level leaders in the leave process, as well as the logical relationship between the two, etc., based on this, form an ontological knowledge expression. For example, only after the department head approves the leave, Only then did the leave request process be transferred to the company's upper-level leaders; knowledge fusion refers to the integration of the business process knowledge to eliminate contradictions and ambiguities. For example, some entities may have multiple expressions, and a specific title can also correspond to multiple Associations between different entities and synonyms, etc.
进一步地，对所述工作流结构化知识进行质量评估，其中，可以通过系统进行质量评估，也可以通过人工甄别进行质量评估，进而若质量评估通过，则将所述工作流结构化知识存储至所述预设流程知识图谱，可参考图6，图6是本发明提供的预设流程知识图谱的部分构建流程图。另外地，为了更新知识图谱以及追求更精准的应答生成能力，构建预设流程知识图谱是一个迭代更新的过程，每一轮迭代包含：信息抽取、知识融合、知识计算（质量评估）、知识储存四个阶段。Further, a quality assessment is performed on the workflow structured knowledge. The quality assessment can be carried out through the system or through manual screening. If the quality assessment passes, the workflow structured knowledge is stored in For the preset process knowledge graph, reference can be made to Figure 6, which is a partial construction flow chart of the preset process knowledge graph provided by the present invention. In addition, in order to update the knowledge graph and pursue more accurate response generation capabilities, building the preset process knowledge graph is an iterative update process. Each iteration includes: information extraction, knowledge fusion, knowledge calculation (quality assessment), knowledge storage four stages.
另外地，所述预设流程知识图谱还可以实现知识建模，即，针对所述目标用户所有的工作流创建信息等建立一个以目标用户为中心的知识图谱，以实现生成更高效以及更个性化的精准应答信息，提高目标用户的工作效率。In addition, the preset process knowledge graph can also implement knowledge modeling, that is, a knowledge graph centered on the target user is established for all the workflow creation information of the target user, so as to achieve more efficient and personalized generation. Provide personalized and accurate response information to improve the work efficiency of target users.
本发明实施例通过获取业务流程知识，进而对所述业务流程知识进行信息抽取以及知识融合，得到工作流结构化知识，并对所述工作流结构化知识进行质量评估，从而若质量评估通过，则将所述工作流结构化知识存储至所述预设流程知识图谱，进而实现减少基于嵌入的语义搜索所导致的不准确性，提高应答的准确性，为用户提高更优质的服务质量。The embodiment of the present invention obtains business process knowledge, then performs information extraction and knowledge fusion on the business process knowledge to obtain workflow structured knowledge, and performs quality assessment on the workflow structured knowledge, so that if the quality assessment passes, Then, the workflow structured knowledge is stored in the preset process knowledge graph, thereby reducing inaccuracies caused by embedding-based semantic search, improving the accuracy of responses, and improving better service quality for users.
在本发明的一个实施例中，所述将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息之前，还包括：In one embodiment of the present invention, before inputting the first response information into the business process question and answer model and obtaining the second response information output by the business process question and answer model, the method further includes:
获取若干组流程需求样本，并将各所述流程需求样本划分为模型训练集、模型验证集以及模型测试集；基于所述模型训练集、所述模型验证集以及所述模型测试集，对初始业务流程问答模型进行迭代训练以及模型微调，得到所述业务流程问答模型。Obtain several groups of process requirement samples, and divide each process requirement sample into a model training set, a model verification set, and a model test set; based on the model training set, the model verification set, and the model test set, perform an initial The business process question and answer model undergoes iterative training and model fine-tuning to obtain the business process question and answer model.
需要说明的是，如果直接采用ChatGLM6B模型等语言模型的大模型语料库，因其并未针对BPM工作流有对应的训练集，所以ChatGLM6B模型等生成的应答结果无法达到目标精确度，因此需要重新训练以得到所述业务流程问答模型，其中，可以采用P-Tuning v2方法进行模型微调，以更好的为目标用户服务，给用户带来更优质的服务体验。It should be noted that if you directly use the large model corpus of language models such as the ChatGLM6B model, there is no corresponding training set for the BPM workflow, so the response results generated by the ChatGLM6B model cannot reach the target accuracy, so it needs to be retrained. In order to obtain the business process question and answer model, the P-Tuning v2 method can be used to fine-tune the model to better serve the target users and bring a better service experience to the users.
进一步需要说明的是，所述流程需求样本是指在系统运维过程中目标用户产生的相关问答数据，比如“什么是配置类？”等用户问答，并且所述每个流程需求样本都携带有对应的样本标签，如“什么是配置类？”对应的样本标签为“通常提的需求不涉及开发，比如导数据、权限申请等非开发类需求，目前支撑的配置类需求有：导业务数据、权限配置、流程节点调整等”。另外地，所述模型训练集用于模型训练过程，所述模型验证集用于在每个训练迭代后，对验证集的性能进行评估，以根据评估结果进行模型微调；所述模型测试集用于评估模型的性能及准确率。It should be further noted that the process requirement samples refer to relevant question and answer data generated by target users during the system operation and maintenance process, such as "What is a configuration class?" and other user questions and answers, and each of the process requirement samples carries a The corresponding sample tag, such as "What is a configuration class?" The corresponding sample tag is "Usually the requirements do not involve development, such as non-development requirements such as data import and permission application. Currently supported configuration class requirements include: import business data , permission configuration, process node adjustment, etc." Additionally, the model training set is used in the model training process, and the model verification set is used to evaluate the performance of the verification set after each training iteration to fine-tune the model based on the evaluation results; the model test set is used To evaluate the performance and accuracy of the model.
具体地，在一实施例中，获取若干组流程需求样本，并将各所述流程需求样本划分为模型训练集、模型验证集以及模型测试集，进而对所述模型训练集、所述模型验证集以及所述模型测试集进行数据预处理，如对输入文本进行分词、去除停用词以及转换为模型所需的输入格式等。Specifically, in one embodiment, several groups of process requirement samples are obtained, and each of the process requirement samples is divided into a model training set, a model verification set and a model test set, and then the model training set, the model verification set are Data preprocessing is performed on the set and the model test set, such as segmenting the input text, removing stop words, and converting it into the input format required by the model.
进一步地，加载预训练的初始业务流程问答模型，包括其词汇表和权重参数等，其中，所述初始业务流程问答模型可为ChatGLM6B模型等，在初始业务流程问答模型的输入层添加额外的可训练参数，用于表示Prompt参数，以构建基于P-Tuning v2方法的初始业务流程问答模型。Further, load the pre-trained initial business process question and answer model, including its vocabulary and weight parameters, etc., wherein the initial business process question and answer model can be a ChatGLM6B model, etc., and add additional optional parameters to the input layer of the initial business process question and answer model. Training parameters, used to represent Prompt parameters to build an initial business process question and answer model based on the P-Tuning v2 method.
更进一步地，将所述模型训练集输入至所述初始业务流程问答模型，得到所述初始业务流程问答模型输出的预测值，进而基于所述预测值和所述流程需求样本对应的样本标签，利用熵损失函数计算得到模型损失值，在本实施例中，损失函数可以根据实际需求进行设置，此处不做具体限定。在计算获得模型损失值之后，本次训练过程结束，再利用误差反向传播算法及SGD优化器等更新初始业务流程问答模型中的模型参数，之后再进行下一次训练。在每个训练迭代后，评估所述模型验证集的性能，并根据需要进行模型调整。Furthermore, the model training set is input to the initial business process question and answer model to obtain the predicted value output by the initial business process question and answer model, and then based on the predicted value and the sample label corresponding to the process demand sample, The model loss value is calculated using the entropy loss function. In this embodiment, the loss function can be set according to actual needs, and is not specifically limited here. After the model loss value is calculated and obtained, the training process ends, and the error back propagation algorithm and SGD optimizer are used to update the model parameters in the initial business process question and answer model, and then the next training is performed. After each training iteration, the performance of the model validation set is evaluated and model adjustments are made as needed.
进一步地，在模型调整过程中，根据模型测试集判断更新后的初始业务流程问答模型是否满足预设训练结束条件，若满足，则将更新后的初始业务流程问答模型作为业务流程问答模型，若不满足，则继续训练模型，其中，预设训练结束条件包括损失收敛和达到最大迭代次数阈值等。Further, during the model adjustment process, it is judged based on the model test set whether the updated initial business process question and answer model meets the preset training end conditions. If it meets, the updated initial business process question and answer model will be used as the business process question and answer model. If If not, continue training the model, where the preset training end conditions include loss convergence and reaching the maximum iteration threshold.
更进一步地，在模型训练完成后，使用所述训练测试集评估所述业务流程问答模型的性能及准确率。Furthermore, after the model training is completed, the training test set is used to evaluate the performance and accuracy of the business process question and answer model.
本发明实施例通过获取若干组流程需求样本，并将各所述流程需求样本划分为模型训练集、模型验证集以及模型测试集，进而基于所述模型训练集、所述模型验证集以及所述模型测试集，对初始业务流程问答模型进行迭代训练，得到所述业务流程问答模型，从而增加模型的鲁棒性，生成更精确更专业的专业领域应答，进而为用户提高优质服务，提高用户体验。The embodiment of the present invention obtains several groups of process requirement samples and divides each process requirement sample into a model training set, a model verification set and a model test set, and then based on the model training set, the model verification set and the Model test set, iteratively train the initial business process question and answer model to obtain the business process question and answer model, thereby increasing the robustness of the model and generating more accurate and professional responses in professional fields, thereby improving quality services for users and improving user experience. .
在本发明的一个实施例中，所述获取目标用户对应的工作流创建信息，包括：In one embodiment of the present invention, obtaining the workflow creation information corresponding to the target user includes:
获取目标用户输入的工作流创建需求；基于所述工作流创建需求，判断是否匹配历史创建信息；若是，则将匹配到的历史创建信息以及所述工作流创建需求进行关联组合，生成所述工作流创建信息；若否，则基于所述工作流创建需求，生成所述工作流创建信息。Obtain the workflow creation requirements input by the target user; based on the workflow creation requirements, determine whether the historical creation information matches; if so, associate and combine the matched historical creation information and the workflow creation requirements to generate the work flow creation information; if not, generate the workflow creation information based on the workflow creation requirement.
需要说明的是，所述工作流创建需求是指目标用户创建工作流的需求信息，可以通过语聊机器人与所述目标用户进行多轮对话来获得，例如，当所述目标用户想要生成工单时，语聊机器人便需要与所述目标用户通过多轮对话确定是否根据历史创建记录生成工单以及是否按照表单填写默认值提单等，以便从所述目标用户处获取生成工单所需要的信息，而当所述目标用户仅需生成一个全体通知时，还可直接通过一轮对话便让所述语聊机器人明白所述目标用户的意图，因此所述工作流创建需求的获取方式取决于所述目标用户的需求，在此不做限制，可根据实际情况进行设置。It should be noted that the workflow creation requirements refer to the requirement information for the target user to create a workflow, which can be obtained through multiple rounds of conversations between the chatbot and the target user. For example, when the target user wants to generate a workflow At this time, the chat robot needs to determine through multiple rounds of dialogue with the target user whether to generate a work order based on historical creation records and whether to fill in the default value bill of lading according to the form, etc., in order to obtain the information required to generate the work order from the target user. information, and when the target user only needs to generate a general notification, the chatbot can also directly let the chatbot understand the intention of the target user through a round of dialogue. Therefore, the method of obtaining the workflow creation requirements depends on The needs of the target users are not limited here and can be set according to the actual situation.
进一步需要说明的是，为了进一步提升工作流的创建效率，语聊机器人可以通过提取目标用户的历史创建信息来明确目标用户的真实需求，其中，历史创建信息是指目标用户之前创建工作流的记录信息，例如表单生成历史信息、工单提取历史信息以及流程设计修改历史信息等，还包括表单数据以及流程设计节点等结构化及非结构化数据，可根据目标用户的实际需求进行设置，在此不做限制。It should be further explained that in order to further improve the efficiency of workflow creation, the chatbot can clarify the real needs of the target user by extracting the historical creation information of the target user. Among them, the historical creation information refers to the record of the workflow created by the target user before. Information, such as form generation history information, work order extraction history information, and process design modification history information, etc. It also includes structured and unstructured data such as form data and process design nodes, which can be set according to the actual needs of the target users. Here No restrictions.
具体地，获取目标用户输入的工作流创建需求，进而基于所述工作流创建需求，判断是否匹配历史创建信息，如，对所述工作流创建需求进行语义分析等，以及通过直接对目标用户发起询问（如：是否根据2024年1月8号的历史提单记录进行提单？）等方式判断是否匹配历史创建信息。进一步地，若是，则将匹配到的历史创建信息以及所述工作流创建需求等信息进行关联组合，生成所述工作流创建信息。Specifically, obtain the workflow creation requirements input by the target user, and then determine whether the historical creation information matches the workflow creation requirements based on the workflow creation requirements, such as performing semantic analysis on the workflow creation requirements, etc., and directly initiating the workflow creation requirements to the target user. Inquire (for example: Do you want to make a bill of lading based on the historical bill of lading record on January 8, 2024?) to determine whether it matches the historical creation information. Further, if so, the matched historical creation information and the workflow creation requirements and other information are associated and combined to generate the workflow creation information.
另外地，若不需要匹配历史创建信息，则可直接根据所述工作流创建需求，生成所述工作流创建信息，例如，可直接通过语聊机器人与目标用户之间的多轮对话获取到提取表单所需的数据信息等，进而对该数据信息进行分析整合，生成所述工作流创建信息，可根据实际情况进行设置，在此不做限制。In addition, if there is no need to match historical creation information, the workflow creation information can be generated directly according to the workflow creation requirements. For example, the extraction can be obtained directly through multiple rounds of conversations between the chatbot and the target user. The data information required by the form, etc. are then analyzed and integrated to generate the workflow creation information, which can be set according to the actual situation and is not limited here.
本发明实施例通过获取目标用户输入的工作流创建需求，进而基于所述工作流创建需求，判断是否匹配历史创建信息，从而若是，则将匹配到的历史创建信息以及所述工作流创建需求进行关联组合，生成所述工作流创建信息，另外地，若否，则基于所述工作流创建需求，生成所述工作流创建信息，进而通过语聊机器人与目标用户进行对话，明确目标用户的真实需求，从而有效提升工作流创建效率，为用户提供高效便携服务，进而有效降低运营成本，减轻用户操作负担。The embodiment of the present invention obtains the workflow creation requirements input by the target user, and then determines whether the historical creation information matches based on the workflow creation requirements. If so, the matched historical creation information and the workflow creation requirements are processed. The associated combination is used to generate the workflow creation information. In addition, if not, the workflow creation information is generated based on the workflow creation requirements, and then the chat robot is used to communicate with the target user to clarify the true identity of the target user. needs, thereby effectively improving the efficiency of workflow creation, providing users with efficient and portable services, thereby effectively reducing operating costs and reducing user operational burdens.
图2是本发明提供的工作流创建方法的流程示意图。如图2所示，该工作流创建方法应用于工作流创建引擎，包括：Figure 2 is a schematic flow chart of the workflow creation method provided by the present invention. As shown in Figure 2, this workflow creation method is applied to the workflow creation engine, including:
步骤S21，接收语聊机器人发送的第二应答信息以及工作流类型；Step S21: Receive the second response information and workflow type sent by the chat robot;
需要说明的是，所述语聊机器人为AI语聊机器人，可针对目标用户的问题生成对应的应答信息，并返回至所述目标用户，以实现用户交互及明确用户意图等。It should be noted that the chat robot is an AI chat robot that can generate corresponding response information for the target user's questions and return it to the target user to achieve user interaction and clarify user intentions.
步骤S22，基于所述工作流类型，确定所述工作流对应的工作流创建模块；Step S22: Based on the workflow type, determine the workflow creation module corresponding to the workflow;
需要说明的是，工作流创建模块是指与工作流类型对应的创建模块，包括工单生成模块、表单填写模块以及流程设计微调模块等，在此不做限制。It should be noted that the workflow creation module refers to the creation module corresponding to the workflow type, including a work order generation module, a form filling module, a process design fine-tuning module, etc., which are not limited here.
具体地，将所述工作流类型与预设工作流创建模块库进行对比匹配，确定所述工作流对应的工作流创建模块。Specifically, the workflow type is compared and matched with a preset workflow creation module library to determine the workflow creation module corresponding to the workflow.
步骤S23，对所述第二应答信息进行解析，得到工作流实体、实体属性以及实体关联情况；Step S23, parse the second response information to obtain the workflow entity, entity attributes and entity association information;
需要说明的是，所述工作流实体包括工作流的名称、执行者、填写数据等，所述实体属性包括执行者身份等，所述实体关联情况包括执行顺序等，可参考图7。It should be noted that the workflow entity includes the name of the workflow, the executor, the filled-in data, etc., the entity attributes include the identity of the executor, etc., and the entity association includes the execution order, etc. See Figure 7 .
具体地，可根据第二应答信息中对应的相关实体节点（即，知识图谱）进行解析，还可以通过语义分割等方式进行解析，得到工作流实体、实体属性以及实体关联情况等信息，在此不做限制。Specifically, it can be parsed according to the corresponding relevant entity nodes (i.e., knowledge graph) in the second response information, or it can also be parsed through semantic segmentation and other methods to obtain information such as workflow entities, entity attributes, and entity associations. Here, No restrictions.
步骤S24，将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流。Step S24: Input the workflow entity, the entity attributes and the entity association information into the workflow creation module, so that the workflow creation module can create the workflow.
需要说明的是，所述工作流创建模块的创建方式取决于工作流类型，并不一致，每一个模块有相应的创建方法，可参考图8、图9以及图10，在此对创建方式不做限制，可根据实际情况进行设置。同时，设立单独的创建模块有利于提高工作效率，可同时进行多个工作流的创建。It should be noted that the creation method of the workflow creation module depends on the workflow type and is not consistent. Each module has a corresponding creation method. Please refer to Figure 8, Figure 9 and Figure 10. The creation method will not be discussed here. Limits can be set according to actual conditions. At the same time, setting up a separate creation module is helpful to improve work efficiency, and multiple workflows can be created at the same time.
本发明实施例通过接收语聊机器人发送的第二应答信息以及工作流类型，并基于所述工作流类型，确定所述工作流对应的工作流创建模块，进而对所述第二应答信息进行解析，得到工作流实体、实体属性以及实体关联情况，从而将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流，进而通过工作流创建引擎实现工作流的自动化生成和智能填写等，从而显著提高工作效率和准确性，同时减少了人为错误，进而有效降低运营成本，减轻用户操作负担，提升用户体验。The embodiment of the present invention receives the second response information and the workflow type sent by the chat robot, and determines the workflow creation module corresponding to the workflow based on the workflow type, and then analyzes the second response information. , obtain the workflow entity, entity attributes and entity association, thereby inputting the workflow entity, the entity attribute and the entity association into the workflow creation module for the workflow creation module to create the Workflow, and then realize the automated generation and intelligent filling of workflows through the workflow creation engine, thereby significantly improving work efficiency and accuracy, while reducing human errors, thereby effectively reducing operating costs, reducing user operation burdens, and improving user experience.
在本发明的一个实施例中，所述所述将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流之后，还包括：In one embodiment of the present invention, the workflow entity, the entity attributes and the entity association are input into the workflow creation module, so that the workflow creation module can create the work After streaming, it also includes:
获取所述工作流的创建成功时间以及查看方式；基于所述工作流类型、所述创建成功时间以及所述查看方式，生成创建成功信息；将所述创建成功信息推送至目标用户，以提醒所述目标用户进行查看。Obtain the creation success time and viewing mode of the workflow; generate creation success information based on the workflow type, the creation success time and the viewing mode; push the creation success information to the target user to remind all View the target users.
需要说明的是，创建成功信息是指当工作流创建成功时生成的提醒信息，包括工作流类型、创建成功时间、工作流截图以及查看方式等，在此不做限制。It should be noted that the creation success information refers to the reminder information generated when the workflow is successfully created, including the workflow type, creation success time, workflow screenshots, viewing methods, etc., which are not limited here.
具体地，获取所述工作流的创建成功时间以及查看方式，进而将所述工作流类型、所述创建成功时间以及所述查看方式等信息进行关联组合，生成创建成功信息，从而将所述创建成功信息推送至目标用户，以提醒所述目标用户进行查看，其中，可以通过短信、APP通知、小程序提醒以及电子邮箱等方式进行推送，在此不做限制，可根据实际情况进行设置。Specifically, the creation success time and viewing mode of the workflow are obtained, and then the workflow type, the creation success time, the viewing mode and other information are associated and combined to generate creation success information, thereby creating the creation success time. The successful information is pushed to the target user to remind the target user to view the information. The information can be pushed through SMS, APP notification, mini program reminder, email, etc. There is no restriction here and can be set according to the actual situation.
本发明实施例通过获取所述工作流的创建成功时间以及查看方式，并基于所述工作流类型、所述创建成功时间以及所述查看方式，生成创建成功信息，进而将所述创建成功信息推送至目标用户，以提醒所述目标用户进行查看，从而提高工作效率，使目标用户能够及时高效地查看创建成功的工作流，提高用户体验。The embodiment of the present invention obtains the creation success time and viewing mode of the workflow, generates creation success information based on the workflow type, the creation success time and the viewing mode, and then pushes the creation success information to the target user to remind the target user to view, thereby improving work efficiency, enabling the target user to view the successfully created workflow in a timely and efficient manner, and improving user experience.
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。It should be understood that the sequence number of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
在一实施例中，提供一种工作流创建装置，该工作流创建装置与上述实施例中工作流创建方法一一对应。如图3所示，该工作流创建装置包括语聊机器人31和工作流创建引擎32。各功能模块详细说明如下：In one embodiment, a workflow creation device is provided, which corresponds one-to-one to the workflow creation method in the above embodiment. As shown in FIG. 3 , the workflow creation device includes a chat robot 31 and a workflow creation engine 32 . The detailed description of each functional module is as follows:
语聊机器人31，用于获取用户输入的工作流创建信息；基于所述工作流创建信息与预设流程知识图谱，确定第一应答信息以及工作流类型；将所述第一应答信息输入至业务流程问答模型，得到所述业务流程问答模型输出的第二应答信息；The chat robot 31 is used to obtain the workflow creation information input by the user; determine the first response information and the workflow type based on the workflow creation information and the preset process knowledge map; input the first response information to the business The process question and answer model obtains the second response information output by the business process question and answer model;
工作流创建引擎32，用于接收语聊机器人发送的第二应答信息以及工作流类型；基于所述工作流类型，确定所述工作流对应的工作流创建模块；对所述第二应答信息进行解析，得到工作流实体、实体属性以及实体关联情况；将所述工作流实体、所述实体属性以及所述实体关联情况输入所述工作流创建模块，以供所述工作流创建模块创建所述工作流。The workflow creation engine 32 is used to receive the second response information and the workflow type sent by the chatbot; based on the workflow type, determine the workflow creation module corresponding to the workflow; and perform the second response information on the second response information. Parse to obtain the workflow entity, entity attributes and entity association; input the workflow entity, the entity attributes and the entity association into the workflow creation module for the workflow creation module to create the Workflow.
工作流创建装置还用于：Workflow creation devices are also used to:
对所述工作流创建信息进行文本分割，并将分割后的工作流创建信息向量化，得到工作流创建向量；Perform text segmentation on the workflow creation information, and vectorize the segmented workflow creation information to obtain a workflow creation vector;
将所述工作流创建向量与预设流程知识库进行查询匹配，得到所述工作流类型以及初始应答信息；Query and match the workflow creation vector with the preset process knowledge base to obtain the workflow type and initial response information;
对所述初始应答信息进行结构化处理，并将结构化后的初始应答信息与预设流程知识图谱进行匹配，以得到所述第一应答信息。The initial response information is structured, and the structured initial response information is matched with the preset process knowledge graph to obtain the first response information.
工作流创建装置还用于：Workflow creation devices are also used to:
获取业务流程知识；Acquire business process knowledge;
对所述业务流程知识进行信息抽取以及知识融合，得到工作流结构化知识，并对所述工作流结构化知识进行质量评估；Perform information extraction and knowledge fusion on the business process knowledge to obtain workflow structured knowledge, and perform quality assessment on the workflow structured knowledge;
若质量评估通过，则将所述工作流结构化知识存储至所述预设流程知识图谱。If the quality assessment passes, the workflow structured knowledge is stored in the preset process knowledge graph.
工作流创建装置还用于：Workflow creation devices are also used to:
获取若干组流程需求样本，并将各所述流程需求样本划分为模型训练集、模型验证集以及模型测试集；Obtain several sets of process requirement samples, and divide each of the process requirement samples into a model training set, a model verification set, and a model testing set;
基于所述模型训练集、所述模型验证集以及所述模型测试集，对初始业务流程问答模型进行迭代训练以及模型微调，得到所述业务流程问答模型。Based on the model training set, the model verification set and the model test set, iterative training and model fine-tuning are performed on the initial business process question and answer model to obtain the business process question and answer model.
工作流创建装置还用于：Workflow creation devices are also used to:
获取目标用户输入的工作流创建需求；Obtain the workflow creation requirements input by the target user;
基于所述工作流创建需求，判断是否匹配历史创建信息；Based on the workflow creation requirements, determine whether it matches historical creation information;
若是，则将匹配到的历史创建信息以及所述工作流创建需求进行关联组合，生成所述工作流创建信息；If so, associate and combine the matched historical creation information and the workflow creation requirements to generate the workflow creation information;
若否，则基于所述工作流创建需求，生成所述工作流创建信息。If not, the workflow creation information is generated based on the workflow creation requirement.
工作流创建装置还用于：Workflow creation devices are also used to:
获取所述工作流的创建成功时间以及查看方式；Get the creation success time and viewing method of the workflow;
基于所述工作流类型、所述创建成功时间以及所述查看方式，生成创建成功信息；Generate creation success information based on the workflow type, the creation success time, and the viewing mode;
将所述创建成功信息推送至目标用户，以提醒所述目标用户进行查看。Push the creation success information to the target user to remind the target user to check.
关于工作流创建装置的具体限定可以参见上文中对于工作流创建方法的限定，在此不再赘述。上述工作流创建装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于电子设备中的处理器中，也可以以软件形式存储于电子设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。For specific limitations on the workflow creation device, please refer to the limitations on the workflow creation method mentioned above, which will not be described again here. Each module in the above-mentioned workflow creation device can be implemented in whole or in part by software, hardware and combinations thereof. Each of the above modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
在一个实施例中，提供了一种电子设备，该电子设备可以是服务器。该电子设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该电子设备的处理器用于提供计算和控制能力。该电子设备的存储器包括可读存储介质、内存储器。该可读存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为可读存储介质中的操作系统和计算机可读指令的运行提供环境。该电子设备的数据库用于存储工作流创建方法所涉及的数据。该电子设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种工作流创建方法。本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质。In one embodiment, an electronic device is provided, which may be a server. The electronic device includes a processor, memory, network interface and database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes readable storage media and internal memory. The readable storage medium stores an operating system, computer readable instructions and a database. The internal memory provides an environment for the execution of an operating system and computer-readable instructions in a readable storage medium. The database of the electronic device is used to store data involved in the workflow creation method. The network interface of the electronic device is used to communicate with an external terminal through a network connection. The computer readable instructions when executed by the processor implement a workflow creation method. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media.
在一个实施例中，提供了一种电子设备，该电子设备可以是终端设备，其内部结构图可以如图11所示。该电子设备包括通过系统总线连接的处理器、存储器、网络接口。其中，该电子设备的处理器用于提供计算和控制能力。该电子设备的存储器包括可读存储介质。该可读存储介质存储有计算机可读指令。该电子设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种工作流创建方法。本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质。In one embodiment, an electronic device is provided. The electronic device may be a terminal device, and its internal structure diagram may be as shown in Figure 11. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a readable storage medium. The readable storage medium stores computer readable instructions. The network interface of the electronic device is used to communicate with an external terminal through a network connection. The computer readable instructions when executed by the processor implement a workflow creation method. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media.
在一实施例中，提供了一种电子设备，包括存储器、处理器以及存储在存储器中并可在处理器上运行的计算机可读指令，处理器执行计算机可读指令时实现如上述工作流创建方法的步骤。In one embodiment, an electronic device is provided, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor. When the processor executes the computer readable instructions, the above workflow creation is implemented. Method steps.
在一实施例中，提供了一种可读存储介质，可读存储介质存储有计算机可读指令，计算机可读指令被处理器执行时实现如上述工作流创建方法步骤。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，该计算机可读指令可存储于一非易失性可读取存储介质或易失性可读存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器（ROM）、可编程ROM（PROM）、电可编程ROM（EPROM）、电可擦除可编程ROM（EEPROM）或闪存。易失性存储器可包括随机存取存储器（RAM）或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM（SRAM）、动态RAM（DRAM）、同步DRAM（SDRAM）、双数据率SDRAM（DDRSDRAM）、增强型SDRAM（ESDRAM）、同步链路（Synchlink） DRAM（SLDRAM）、存储器总线（Rambus）直接RAM（RDRAM）、直接存储器总线动态RAM（DRDRAM）、以及存储器总线动态RAM（RDRAM）等。In one embodiment, a readable storage medium is provided. The readable storage medium stores computer readable instructions. When the computer readable instructions are executed by a processor, the steps of the above workflow creation method are implemented. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer readable instructions. The computer readable instructions can be stored in a non-volatile readable memory. In a storage medium or a volatile readable storage medium, when executed, the computer readable instructions may include the processes of the embodiments of the above methods. Any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs. Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.
以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围，均应包含在本发明的保护范围之内。The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the foregoing embodiments. Modifications are made to the recorded technical solutions, or equivalent substitutions are made to some of the technical features; however, these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should all be included in the present invention. within the scope of protection.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410102089.6ACN117634865B (en) | 2024-01-25 | 2024-01-25 | Workflow creation method, device, equipment and storage medium |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410102089.6ACN117634865B (en) | 2024-01-25 | 2024-01-25 | Workflow creation method, device, equipment and storage medium |
| Publication Number | Publication Date |
|---|---|
| CN117634865Atrue CN117634865A (en) | 2024-03-01 |
| CN117634865B CN117634865B (en) | 2024-12-06 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410102089.6AActiveCN117634865B (en) | 2024-01-25 | 2024-01-25 | Workflow creation method, device, equipment and storage medium |
| Country | Link |
|---|---|
| CN (1) | CN117634865B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118941251A (en)* | 2024-10-14 | 2024-11-12 | 深圳市智慧城市科技发展集团有限公司 | Business process modeling method, device and storage medium |
| CN120634484A (en)* | 2025-08-08 | 2025-09-12 | 北京飞书科技有限公司 | Model-based workflow creation method, device, equipment, medium and product |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942220A (en)* | 2013-01-23 | 2014-07-23 | 成都勤智数码科技股份有限公司 | Method used for intelligently linking work orders with knowledge of knowledge base and suitable for IT operation and maintenance system |
| US10474745B1 (en)* | 2016-04-27 | 2019-11-12 | Google Llc | Systems and methods for a knowledge-based form creation platform |
| CN111753075A (en)* | 2020-08-12 | 2020-10-09 | 腾讯科技（深圳）有限公司 | Method and device for creating question and answer data of customer service robot and computer equipment |
| CN111966787A (en)* | 2020-08-18 | 2020-11-20 | 上海海洋大学 | Intelligent fishery question-answering robot construction method based on knowledge graph |
| CN112036736A (en)* | 2020-08-28 | 2020-12-04 | 杭州指令集智能科技有限公司 | Workflow creating method and device |
| CN112507092A (en)* | 2020-12-03 | 2021-03-16 | 北京智齿博创科技有限公司 | Implementation method for completing work order intelligent filling function based on AI text robot |
| CN114417010A (en)* | 2021-12-31 | 2022-04-29 | 第四范式（北京）技术有限公司 | Knowledge graph construction method and device for real-time workflow and storage medium |
| CN115292022A (en)* | 2022-09-29 | 2022-11-04 | 泰豪软件股份有限公司 | Workflow engine system, implementation method, storage medium and computer equipment |
| CN115481229A (en)* | 2022-09-22 | 2022-12-16 | 上海浦东发展银行股份有限公司 | Method and device for pushing answer call, electronic equipment and storage medium |
| WO2023004805A1 (en)* | 2021-07-30 | 2023-02-02 | 西门子股份公司 | Workflow modeling implementation system and method, and storage medium |
| CN116521653A (en)* | 2022-01-20 | 2023-08-01 | 合肥美的电冰箱有限公司 | Food material question-answering method and system based on knowledge graph |
| CN116992092A (en)* | 2023-07-31 | 2023-11-03 | 远光软件股份有限公司 | Method and device for establishing flow model, storage medium and terminal equipment |
| CN117235228A (en)* | 2023-09-25 | 2023-12-15 | 上海东普信息科技有限公司 | Customer service question-answer interaction method, device, equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942220A (en)* | 2013-01-23 | 2014-07-23 | 成都勤智数码科技股份有限公司 | Method used for intelligently linking work orders with knowledge of knowledge base and suitable for IT operation and maintenance system |
| US10474745B1 (en)* | 2016-04-27 | 2019-11-12 | Google Llc | Systems and methods for a knowledge-based form creation platform |
| CN111753075A (en)* | 2020-08-12 | 2020-10-09 | 腾讯科技（深圳）有限公司 | Method and device for creating question and answer data of customer service robot and computer equipment |
| CN111966787A (en)* | 2020-08-18 | 2020-11-20 | 上海海洋大学 | Intelligent fishery question-answering robot construction method based on knowledge graph |
| CN112036736A (en)* | 2020-08-28 | 2020-12-04 | 杭州指令集智能科技有限公司 | Workflow creating method and device |
| CN112507092A (en)* | 2020-12-03 | 2021-03-16 | 北京智齿博创科技有限公司 | Implementation method for completing work order intelligent filling function based on AI text robot |
| WO2023004805A1 (en)* | 2021-07-30 | 2023-02-02 | 西门子股份公司 | Workflow modeling implementation system and method, and storage medium |
| CN114417010A (en)* | 2021-12-31 | 2022-04-29 | 第四范式（北京）技术有限公司 | Knowledge graph construction method and device for real-time workflow and storage medium |
| CN116521653A (en)* | 2022-01-20 | 2023-08-01 | 合肥美的电冰箱有限公司 | Food material question-answering method and system based on knowledge graph |
| CN115481229A (en)* | 2022-09-22 | 2022-12-16 | 上海浦东发展银行股份有限公司 | Method and device for pushing answer call, electronic equipment and storage medium |
| CN115292022A (en)* | 2022-09-29 | 2022-11-04 | 泰豪软件股份有限公司 | Workflow engine system, implementation method, storage medium and computer equipment |
| CN116992092A (en)* | 2023-07-31 | 2023-11-03 | 远光软件股份有限公司 | Method and device for establishing flow model, storage medium and terminal equipment |
| CN117235228A (en)* | 2023-09-25 | 2023-12-15 | 上海东普信息科技有限公司 | Customer service question-answer interaction method, device, equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118941251A (en)* | 2024-10-14 | 2024-11-12 | 深圳市智慧城市科技发展集团有限公司 | Business process modeling method, device and storage medium |
| CN120634484A (en)* | 2025-08-08 | 2025-09-12 | 北京飞书科技有限公司 | Model-based workflow creation method, device, equipment, medium and product |
| Publication number | Publication date |
|---|---|
| CN117634865B (en) | 2024-12-06 |
| Publication | Publication Date | Title |
|---|---|---|
| US11663409B2 (en) | Systems and methods for training machine learning models using active learning | |
| US11677861B2 (en) | System and method for interoperable communication between entities with different structures | |
| US20190180196A1 (en) | Systems and methods for generating and updating machine hybrid deep learning models | |
| US9043285B2 (en) | Phrase-based data classification system | |
| CN112036842B (en) | Intelligent matching device for scientific and technological service | |
| US20190197185A1 (en) | Intelligent natural language query processor | |
| US12181844B2 (en) | Building management system with natural language model-based data structure generation | |
| CN114647741B (en) | Automatic process decision and reasoning method and device, computer equipment and storage medium | |
| CN117634865A (en) | Workflow creation method, device, equipment and storage medium | |
| WO2021128679A1 (en) | Data decision-making-based test data generation method and apparatus, and computer device | |
| CN113988071A (en) | An intelligent dialogue method and device based on financial knowledge graph, and electronic equipment | |
| WO2019113122A1 (en) | Systems and methods for improved machine learning for conversations | |
| US10896034B2 (en) | Methods and systems for automated screen display generation and configuration | |
| US11249751B2 (en) | Methods and systems for automatically updating software functionality based on natural language input | |
| CN117725895A (en) | Document generation methods, devices, equipment and media | |
| US20190228297A1 (en) | Artificial Intelligence Modelling Engine | |
| US12164875B2 (en) | Social network adapted response | |
| CN118227599A (en) | Data standard treatment method, system, equipment and medium based on automatic flow | |
| KR20240053911A (en) | Method and system for AI collaboration service based on source code automatic generation system | |
| US11314488B2 (en) | Methods and systems for automated screen display generation and configuration | |
| CN114218362A (en) | Method, system, terminal device and medium for inquiring clinical test data | |
| CN119003063A (en) | RPA application generation method, device, equipment, medium and product | |
| US12282501B2 (en) | Method and apparatus for an AI-assisted virtual consultant | |
| US11829735B2 (en) | Artificial intelligence (AI) framework to identify object-relational mapping issues in real-time | |
| US12327092B2 (en) | Artificial intelligence (AI) framework to identify object-relational mapping issues in real-time |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |