Process construction method and device, storage medium and program product

Abstract

The invention provides a process construction method and device, a storage medium and a program product, relates to the technical field of data processing, and can construct a 5G message Chatboot process. The method comprises the following steps: receiving demand information of a first user for a target process; the demand information comprises a process requirement for the target process and an application scene of the target process; the target process is used for indicating Chatpot to interact with a second user; based on the process requirement and the application scene, generating process data; the process data comprises a plurality of process nodes and message data corresponding to each process node; and constructing a target process based on the process node and the message data.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a process construction method, device, storage medium and program product. Background Art

[0002] With the iterative development of mobile communication networks, network operators provide users with more and more powerful network functions. In order to meet users' requirements for exchanging various forms of information, network operators have begun to study upgrading SMS services to the fifth generation mobile communication technology (5th generation mobile networks, 5G) message services. Through the 5G message service, rich media information can be transmitted between different users, and corporate users can also transmit rich media messages to individual users by building 5G message chatbots.

[0003] However, in the process of building the 5G message Chatbot process, enterprise users need to repeatedly test and debug the 5G message chatbot, resulting in high construction and maintenance costs of the 5G message Chatbot process. Summary of the invention

[0004] The present application provides a process construction method, device, storage medium and program product, which can efficiently and accurately construct a 5G message Chatbot process.

[0005] In order to achieve the above purpose, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a process construction method, the method comprising: receiving demand information of a first user for a target process; the demand information comprises process requirements for the target process, and an application scenario of the target process; the target process is used to instruct the Chatbot to interact with a second user; based on the process requirements and application scenarios, process data is generated; the process data comprises multiple process nodes, and message data corresponding to each process node; and based on the process nodes and the message data, the target process is constructed.

[0007] Based on the above technical solution, the present application can efficiently and accurately generate the target process by receiving the first user's demand information for the target process and based on the process construction device through the demand information of the target process, thereby avoiding the time-consuming and labor-intensive problem of building Chatbot processes in related technologies, making the process of building Chatbot processes simple, fast and low-cost.

[0008] In one possible approach, process data is generated based on process requirements and application scenarios, including: generating prompts based on process requirements and application scenarios; prompts are used to guide the large model to generate process data that meets process requirements and application scenarios; and generating process data based on the large model and prompts.

[0009] In one possible method, a prompt is generated based on process requirements and application scenarios, including: determining target node information from a target database based on permission information of a first user; the target node information is used to connect process requirements and application scenarios; and a prompt is generated based on the target node information, process requirements and application scenarios.

[0010] In one possible approach, a target process is constructed based on process nodes and message data, including: parsing process nodes to determine node relationships between process nodes; the node relationships include at least one of a sequence relationship and a dependency relationship; and constructing a target process based on the node relationships and message data.

[0011] In one possible approach, a target process is constructed based on node relationships and message data, including: based on the node relationships, connecting multiple process nodes to obtain an initial process; based on the process nodes corresponding to the message data, encapsulating the message data into the initial process to obtain a target process.

[0012] In one possible embodiment, the method further includes: displaying an effect corresponding to the target process, and receiving a selection operation of the first user on the effect corresponding to the target process; and in response to the selection operation of the first user, saving the target process to a preset storage address or modifying the target process.

[0013] In the second aspect, the present application provides a process construction device, which includes: a receiving unit, a generating unit and a building unit; the receiving unit is used to receive the demand information of the first user for the target process; the demand information includes the process requirements for the target process, and the application scenario of the target process; the target process is used to instruct the Chatbot to interact with the second user; the generating unit is used to generate process data based on the process requirements and application scenarios; the process data includes multiple process nodes, and message data corresponding to each process node; the building unit is used to build the target process based on the process nodes and the message data.

[0014] In one possible approach, the generation unit is specifically used to: generate prompts based on process requirements and application scenarios; prompts are used to guide the large model to generate process data that meets the process requirements and application scenarios; and generate process data based on the large model and prompts.

[0015] In one possible manner, the generating unit is specifically used to: determine target node information from a target database according to permission information of a first user; the target node information is used to connect process requirements and application scenarios; and generate a Prompt based on the target node information, process requirements and application scenarios.

[0016] In one possible manner, the construction unit is specifically used to: parse the process nodes to determine the node relationship between each process node; the node relationship includes at least one of a sequence relationship and a dependency relationship; and construct a target process based on the node relationship and message data.

[0017] In one possible manner, the construction unit is specifically used to: connect multiple process nodes based on node relationships to obtain an initial process; and encapsulate the message data into the initial process based on the process nodes corresponding to the message data to obtain a target process.

[0018] In one possible embodiment, the device also includes: a display unit and a processing unit; the display unit is used to display the effect corresponding to the target process and receive the selection operation of the first user on the effect corresponding to the target process; the processing unit is used to save the target process to a preset storage address or modify the target process in response to the selection operation of the first user.

[0019] In a third aspect, the present application provides a process construction device, comprising: a processor and a communication interface; the communication interface and the processor are coupled, and the processor is used to run a computer program or instructions to implement the process construction method described in the first aspect and any possible implementation method of the first aspect.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal, the terminal executes the process construction method described in the first aspect and any possible implementation of the first aspect.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product runs on a process construction device, the process construction device executes the process construction method described in the first aspect and any possible implementation of the first aspect.

[0022] In a sixth aspect, an embodiment of the present application provides a chip, the chip including a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run a computer program or instructions to implement the process construction method described in the first aspect and any possible implementation method of the first aspect.

[0023] Specifically, the chip provided in the embodiment of the present application also includes a memory for storing computer programs or instructions.

[0024] In this application, the name of the above-mentioned process construction device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.

[0025] These and other aspects of the present application will become more apparent from the following description.

[0026] Based on any of the above aspects, the technical solution provided by this application brings at least the following beneficial effects:

[0027] By receiving the first user's demand information for the target process and based on the process construction device, the target process can be generated efficiently and accurately, avoiding the time-consuming and labor-intensive problem of building Chatbot processes in related technologies, making the process of building Chatbot processes simple, fast and low-cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A schematic diagram of an enterprise user using 5G messaging provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the structure of a process construction system provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the hardware structure of a process construction device provided in an embodiment of the present application;

[0031] Figure 4 A flowchart of a process construction method provided in an embodiment of the present application;

[0032] Figure 5 A schematic diagram of the software structure of a process construction system provided in an embodiment of the present application;

[0033] Figure 6 An interactive schematic diagram of a process construction method provided in an embodiment of the present application;

[0034] Figure 7 An interactive schematic diagram of another process construction method provided in an embodiment of the present application;

[0035] Figure 8 An interactive schematic diagram of another process construction method provided in an embodiment of the present application;

[0036] Fig. 9 An interactive schematic diagram of another process construction method provided in an embodiment of the present application;

[0037] Fig.10A schematic diagram of the structure of a process construction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The process construction method and device provided in the embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0039] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0040] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0041] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0042] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0043] First, some of the terms and related technologies involved in this application are explained to facilitate understanding by those skilled in the art.

[0044] Chatbot: Chatbot is an artificial intelligence program that simulates human conversation. Chatbot can interact with users in various forms such as text, voice or images through natural language processing technology, understand the user's intentions and respond accordingly. Chatbot is widely used in online chat, social media, mobile applications, e-commerce, smart homes and customer service, aiming to improve communication efficiency, enhance user experience, and provide convenient services for enterprises and individuals.

[0045] Prompt: In the field of artificial intelligence, prompt refers to an injected instruction used to "command" artificial intelligence to think about problems and output content according to preset ideas. Prompt is an instruction or information used to guide or trigger the artificial intelligence system to respond. In addition, prompt engineering is the development and optimization of prompt words to help users use large language models in various scenarios and research fields.

[0046] The above is a description of the technical terms involved in the embodiments of the present application, which will not be repeated below.

[0047] With the continuous evolution of communication technology, mobile communication networks have gone through the rapid development stages of the second generation mobile communication technology (2G), the third generation mobile communication technology (3G) and the fourth generation mobile communication technology (4G). The network infrastructure capabilities provided by operators have been significantly enhanced, and the network bandwidth has continued to expand.

[0048] In the high-speed network environment, the basic communication services provided by operators have not changed fundamentally. At the same time, the mobile terminal devices in the hands of users are changing with each passing day, and their functions are becoming more and more powerful, which has promoted the diversified development of users' needs for information exchange.

[0049] In the past, operators' SMS services were popular with users for their strong accessibility, high security, and global interconnection. However, due to the limitations of the service experience, SMS can only transmit limited text information, causing a large number of individual users to choose other information exchange methods. Although some corporate users continue to use SMS to send necessary information to their users, this method can no longer meet their growing business needs.

[0050] For communication operators, meeting users' communication needs is their most basic service purpose. With the advent of the 5G era, global operators have reached a broad consensus under the GSMA framework that SMS services need to be upgraded to rich media messaging services, which we call 5G messaging services.

[0051] 5G messaging services not only support multimedia messaging interactions between individual users, but also provide corporate customers with a new way of interactive digital services based on rich media. According to GSMA's plan, all future 5G terminals will support 5G messaging services, and relevant standards have been formulated. The launch of 5G messaging services will bring unprecedented service experience to mobile phone users, and also bring valuable development opportunities to corporate users and related industries.

[0052] For enterprise users, 5G messaging services provide the following functions:

[0053] Enterprise users can interact with individual users through the operator network in the form of chatbots. The messages sent by individual users to enterprise users' Chatbots can contain multiple media formats such as text, pictures, audio, video, emoticons, locations, and contacts. Enterprise users' Chatbots can send messages containing the above media formats as well as rich media cards and option lists (including "suggested replies" and "suggested actions") to individual users through point-to-point and group messaging.

[0054] In terms of Chatbot services, users can trigger message interactions with Chatbot in a variety of ways, such as searching, clicking on web links, scanning QR codes, entering Chatbot IDs, etc. After triggering, users can enter the message interaction interface with Chatbot.

[0055] In terms of viewing the detailed information of Chatbot, users can view the information such as Chatbot account, name, avatar, service description and customer service phone number obtained by the terminal. This information can be stored locally on the terminal and can be deleted at any time. In order to ensure the reliability of the source of the message, the terminal will query the operator network to verify the details of this Chatbot after receiving the message from the Chatbot for the first time. If the Chatbot is not found, the source of this message is considered unreliable and will not be displayed to the user.

[0056] In terms of message operations, individual users can interact with Chatbot through "suggested replies" and "suggested operations". "Suggested replies" and "suggested operations" are displayed as clickable buttons on the interface. When the user clicks these buttons, the terminal will perform the corresponding operations, such as sending messages, opening web pages or apps, making phone calls, querying and sending geographic locations, adding calendar events, etc. There are three ways to present buttons in messages sent by Chatbot: floating buttons, buttons built into rich media cards, and fixed buttons at the bottom of the message dialogue interface. Users can click the corresponding buttons to perform operations as needed.

[0057] For example, Figure 1 As shown, Figure 1 A schematic diagram of an enterprise user using 5G messaging.

[0058] in, Figure 1 It includes Chatbot, Messaging as a Platform (MaaP) platform, 5G message channel and end users.

[0059] Chatbot: Enterprise users access the MaaP system in the form of Chatbot, using HyperText Transfer Protocol (HTTP) to send and receive messages. When Chatbot sends a message, it calls the group messaging interface.

[0060] MaaP: MaaP is the carrier of interactive 5G messaging services. It mainly undertakes core functions such as access to MaaP services for government and enterprise customers, storage and management of message content, and review of messages and material files.

[0061] 5G message channel: The 5G message channel not only has the ability to process traditional short messages and basic multimedia messages, but also adds a network interface with MaaP to access new 5G message industry customers and provide message sending and receiving services for terminal devices that support 5G messages.

[0062] End users: refers to the consumer group that uses 5G messaging services.

[0063] At present, 5G messaging has not yet achieved large-scale market application, and its application methods mainly include group messaging and robots. If enterprise users want to build robot applications according to business needs, they often need to build and debug multiple times without reference, which not only leads to high labor costs, but also faces maintenance difficulties and difficulties in getting started.

[0064] In addition, in the process of building a Chatbot based on 5G messaging, there are the following significant defects:

[0065] High production cost: The production of 5G messaging chatbot requires a lot of time and cost. Because it is highly interactive and contains multiple states and buttons, a lot of complex content needs to be configured according to specific demand scenarios. Compared with the simple way of configuring text information for traditional robots, this undoubtedly increases the complexity and time-consumingness of production.

[0066] Lack of industry references: Currently, 5G messaging is still in the initial stage of market launch and has not yet formed a mature industry application scenario. Therefore, when making a 5G messaging Chatbot, there is a lack of industry solutions that can be referenced, making the production process more difficult and difficult to get started quickly.

[0067] High maintenance cost: Creating a chatbot through the 5G messaging chatbot development platform often requires multiple modifications and debugging to achieve the desired effect. This process is not only time-consuming and labor-intensive, but also increases maintenance costs and reduces production efficiency.

[0068] In response to the above-mentioned technical defects, the process construction method provided in the present application can efficiently and accurately generate the target process by receiving the first user's demand information for the target process and based on the process construction device using the demand information of the target process, thereby avoiding the time-consuming and labor-intensive problem of constructing Chatbot processes in related technologies, making the process of constructing Chatbot processes simple, fast and low-cost.

[0069] Based on this, the present application can efficiently and accurately generate the target process by receiving the first user's demand information for the target process and based on the process construction device through the demand information of the target process, thereby avoiding the time-consuming and labor-intensive problem of building Chatbot processes in related technologies, making the process of building Chatbot processes simple, fast and low-cost.

[0070] For example, Figure 2 , which is a schematic diagram of a process construction system 200 provided in an embodiment of the present application. The process construction system 200 may include a process construction device 201 and a data collection device 202. A communication connection may be established between the process construction device 201 and the data collection device 202.

[0071] In practical applications, the process construction device 201 may be communicatively connected with one or more data acquisition devices 202 .

[0072] For ease of understanding, the present application takes the communication connection between a process construction device 201 and a data acquisition device 202 as an example for explanation.

[0073] Optional, Figure 2 The process construction device 201 and the data collection device 202 may be functional modules integrated into the same device, or may be two devices independently provided. This application does not impose any limitation on this.

[0074] It is easy to understand that when the process construction device 201 and the data acquisition device 202 are functional modules integrated in the same device, the communication method between the process construction device 201 and the data acquisition device 202 is the communication between the internal modules of the device. In this case, the communication process between the two is the same as "the communication process between the process construction device 201 and the data acquisition device 202 when they are independently set up".

[0075] For ease of understanding, the present application is mainly described by taking the example that the process construction device 201 and the data acquisition device 202 are independently configured.

[0076] Figure 2The process construction device 201 can obtain the user's demand information for the target process collected by the data collection device 202, and generate process data based on the process requirements and application scenarios, so as to further construct the target process based on multiple process nodes and message data.

[0077] Optionally, Figure 2 The process construction device 201 and the data collection device 202 may be terminals, servers, or other types of electronic devices. Figure 1 What is shown in the figure is only an example of the device form of the process construction device 201 and the data acquisition device 202, and does not constitute a limitation thereto.

[0078] In the case where the process construction device 201 and the data collection device 202 are terminals, the terminal can be a device for providing voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. The terminal can communicate with one or more core networks via a radio access network (RAN). The terminal can be a mobile terminal, such as a computer with a mobile terminal, or a portable, pocket-sized, handheld, or computer-built-in mobile device that exchanges language and / or data with a radio access network, such as a mobile phone, a tablet computer, a laptop computer, a netbook, or a personal digital assistant (PDA). This application does not impose any restrictions on this.

[0079] When the process construction device 201 and the data collection device 202 are servers, the server may be a single server, or a server cluster composed of multiple servers. In some implementations, the server cluster may also be a distributed cluster. This application does not impose any restrictions on this.

[0080] like Figure 3 , which is a schematic diagram of a hardware structure of a process construction device provided in an embodiment of the present application. The process construction device includes a processor 31, a memory 32, a communication interface 33, and a bus 34. The processor 31, the memory 32, and the communication interface 33 can be connected via a bus 34.

[0081] The processor 31 is the control center of the process construction device, which can be a processor or a general term for multiple processing elements. For example, the processor 31 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0082] As an embodiment, the processor 31 may include one or more CPUs, such as Figure 3 CPU 0 and CPU 1 are shown in .

[0083] The memory 32 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0084] In a possible implementation, the memory 32 may exist independently of the processor 31, and the memory 32 may be connected to the processor 31 via a bus 34 to store instructions or program codes. When the processor 31 calls and executes the instructions or program codes stored in the memory 32, the process construction method provided in the following embodiments of the present application can be implemented.

[0085] In another possible implementation, the memory 32 may also be integrated with the processor 31 .

[0086] The communication interface 33 is used to connect the process construction device to other devices through a communication network, and the communication network may be Ethernet, wireless access network, wireless local area network (WLAN), etc. The communication interface 33 may include a receiving unit for receiving data and a sending unit for sending data.

[0087] The bus 34 may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0088] It should be pointed out that Figure 3The structure shown in the figure does not constitute a limitation on the process construction device, except Figure 3 In addition to the components shown, the process construction device may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0089] like Figure 4 The figure is a flow chart of a process construction method provided in an embodiment of the present application. The process construction method can be applied to Figure 2 The process construction device 201 of the process construction system 200 is shown. The process construction method includes: S401-S403.

[0090] S401: Receive demand information of a first user for a target process.

[0091] The requirement information may include process requirements for the target process and application scenarios of the target process. The target process may be used to instruct the Chatbot to interact with the second user.

[0092] Optionally, the first user may be a corporate user or an individual user. In the case where the first user is a corporate user, the first user may be an e-commerce corporate user or a restaurant corporate user. This application does not impose any specific restrictions on this.

[0093] In some examples, when the first user is a restaurant enterprise user, the demand information input by the first user may be to create an ordering process so as to provide ordering services to users through Chatbot on the 5G messaging platform. The restaurant enterprise user hopes that this shopping process will require confirmation of the user's name, contact number, number of diners, and dining time in the process. The process construction device may determine that the application scenario of the ordering process is an ordering scenario based on the demand information input by the restaurant enterprise user, and the process requirements of the ordering process may include the need to confirm the user's name, contact number, number of diners, dining time, and other information in the process.

[0094] Alternatively, when the first user is an e-commerce enterprise user, the demand information input by the first user may be to create a shopping process so as to provide users with shopping experiences such as product browsing, purchasing, ordering and payment through its Chatbot on the 5G messaging platform. The e-commerce enterprise hopes that this shopping process can display products, select products, view the shopping cart, fill in the receipt, select the payment method, confirm the order and pay, etc. The process construction device can determine that the application scenario of the shopping process is a shopping scenario based on the demand information input by the e-commerce enterprise user, and the process requirements of the shopping process may include displaying products, selecting products, viewing the shopping cart, filling in the receipt, selecting the payment method, confirming the order and paying, etc.

[0095] In a possible implementation, the process construction device may include a front-end interface and a back-end interface. The process construction device may receive user demand information for the target process based on an intention collection module composed of the front-end interface and the back-end interface.

[0096] S402: Generate process data based on process requirements and application scenarios.

[0097] The process data may include multiple process nodes and message data corresponding to each process node.

[0098] In a possible implementation, the process construction device can generate a prompt based on the process requirements and application scenarios. The process construction device can generate process data based on the large model and the prompt. The specific implementation method of the process construction device generating process data based on the process requirements and application scenarios can refer to S501-S502 below. It will not be repeated here.

[0099] S403: Build a target process based on process nodes and message data.

[0100] In a possible implementation, the process construction device can parse the process nodes to determine the node relationship between each process node. The process construction device can construct the target process based on the node relationship and the message data. The specific implementation method of the process construction device to construct the target process based on the process nodes and the message data can refer to the following S601-S602. It will not be repeated here.

[0101] In one possible implementation, after completing the construction target, the process construction device can configure a preview module to render the target process to further show the effect corresponding to the target process to the first user through the front-end interface, and display a selection button through the front-end interface.

[0102] Optionally, the effect corresponding to the target process can be set according to actual needs. The effect corresponding to the target process can be a flowchart or a specific effect achieved by the Chatbot based on the target process. This application does not make specific restrictions on this.

[0103] Optionally, the selection button can be set according to actual needs. For example, the selection button may include meeting the needs and not meeting the needs. This application does not make specific restrictions on this.

[0104] In another possible implementation, the first user can select whether the currently constructed target process meets the requirements based on the selection button displayed on the front-end interface. The process construction device can save the target process to a preset storage address or modify the target process in response to the selection operation of the first user.

[0105] Exemplarily, when the user selects a button that meets the requirements, the process construction device may determine that the currently constructed target process meets the requirements of the first user, and save the target process to a preset storage address.

[0106] Alternatively, when the user selects a button that does not meet the requirements, the process construction device can continue to receive user requirements and modify or delete the currently constructed target process.

[0107] Optionally, the preset storage address can be set according to actual needs. For example, the preset storage address can be a private database of the first user or a public database. This application does not make specific restrictions on this.

[0108] In one embodiment, when constructing a target process based on process nodes and message data, the process construction method provided in the embodiment of the present application further includes: S501-S502.

[0109] S501. Generate a prompt based on process requirements and application scenarios.

[0110] Among them, Prompt can be used to guide the large model to generate process data that meets process requirements and application scenarios.

[0111] In a possible implementation manner, the process construction device may determine the target node information from the target database according to the permission information of the first user.

[0112] Among them, the target node information is used to connect process requirements and application scenarios.

[0113] Specifically, the process construction device may be configured with a storage module. The storage module may store node usage permissions of multiple first users. The process construction device may determine the identity information of the current first user to determine the permission information of the current first user. The process construction device may determine the target node information that the first user can use from the target database based on the permission information of the first user.

[0114] In a possible implementation, the process construction device may generate a prompt based on target node information, process requirements, and application scenarios.

[0115] Specifically, the process construction device can connect the process requirements and application scenarios together through the target node information, and generate a prompt for guiding the output of the large model.

[0116] S502: Generate process data based on the large model and prompt.

[0117] In one possible implementation, the process construction device may input a prompt into the large model, so as to guide the large model to generate process data that meets process requirements and application scenarios through the prompt.

[0118] It is understandable that in the process of generating process data, the big model can use the various knowledge, rules and patterns it has learned during the training process to ensure that the generated process data is both logical and easy to understand and execute. At the same time, the big model may also have the ability to self-adjust and optimize, and can generate more practical process data based on subtle changes in prompts or new application scenario requirements.

[0119] Based on the above technical solution, this application can generate highly targeted prompts by clarifying process requirements and application scenarios. This prompt can accurately guide the large model to understand and generate process data that meets specific needs. Compared with traditional manual creation or template-based generation methods, this method can more accurately capture and apply business logic, reduce errors, and the process data generated based on the large model and prompt can be closer to the user's actual needs and operating habits.

[0120] In one embodiment, when constructing a target process based on process nodes and message data, the process construction method provided in the embodiment of the present application further includes: S601-S602.

[0121] S601, parsing the process nodes to determine the node relationship between each process node.

[0122] The node relationship may include at least one of a sequence relationship and a dependency relationship.

[0123] In one possible implementation, the process construction device may split and parse the process data, determine standard node information according to the information structure of each process node, and determine the node relationship between each process node.

[0124] For example, in combination with the example of the meal ordering process in S401, the first process node is preset to determine the dining personnel information, and the second process node is preset to confirm the meal information. There is a sequential relationship between the first process node and the second process node. That is, after determining the dining personnel information, the next process node can confirm the meal information.

[0125] S602: Build a target process based on node relationships and message data.

[0126] In a possible implementation, the process construction device can connect multiple process nodes based on the node relationship to obtain the initial process.

[0127] Specifically, the process construction device can connect nodes with relationships based on the order relationship, dependency relationship, etc. between the node relationships, that is, in subsequent use, after completing a process node, one or more related nodes can be triggered. The process construction device can connect multiple process nodes to obtain an initial process.

[0128] In a possible implementation, the process construction device may encapsulate the message data into the initial process based on the process node corresponding to the message data to obtain the target process.

[0129] It can be understood that the process construction device can connect the message data to the corresponding process node, so that when the target process is used, when a certain process is triggered, the Chatbot can output the message data corresponding to the process.

[0130] For example, in conjunction with the example of the meal ordering process in S401, when confirming the diners' information in the meal ordering process, the Chatbot may output message data such as the confirmed user's name, contact number, number of diners, dining time, etc., to prompt the user to enter information.

[0131] Based on this, the present application can clarify the relationship between each node through in-depth analysis of the process nodes. Based on these relationships, it can ensure that each step in the process is executed according to the predetermined order and conditions, thereby improving the accuracy of process construction.

[0132] In one embodiment, Figure 5 The figure shows a software structure diagram of a process construction system.

[0133] In one possible implementation, Figure 5 In the structure shown, the dotted area is the core functional module of the embodiment of the present application, and the outside of the dotted line is the upstream and downstream devices or components associated with the embodiment of the present application. The embodiment of the present application provides a method for process construction, which can combine a large language model with prompt engineering technology to guide the large model to understand and pre-construct a Chatbot process that meets the user's description of the scenario and needs, and save it as a Chatbot process that can be actually applied after the user previews and confirms it.

[0134] In one possible implementation, Figure 5 The process construction system shown includes: intention collection module, prompt assembly module, large model docking module, large model parsing module, robot process production module, robot event node library and process library.

[0135] The intention collection module can be composed of a front-end user interface and a back-end interface service, and is responsible for receiving the process type and scenario information input by the user. The user can input their own needs through the intention collection module, and the process construction system can generate the corresponding process according to the user's input demand information.

[0136] The prompt assembly module can store multiple prompt templates and dynamically assemble a complete prompt based on the user's input demand information and the user's node usage permissions.

[0137] The large model docking module can be responsible for docking with the request interface of the large language model, while managing and storing sensitive information such as request parameters and keys related to the large model service.

[0138] The large model parsing module can receive the information returned by the large language model, namely the process data, and extract the implied standardized process data (usually in the format of JSON, XML, etc.). The large model parsing module is also responsible for processing redundant information such as unnecessary machine hallucinations.

[0139] The robot process production module is the core of the core, which includes multiple sub-modules such as production instruction parsing module, process assembly module, 5G message assembly module, preview module and process creation module.

[0140] The production instruction parsing module can split the data returned by the large language model and supplement the standard node information according to the information structure of each node.

[0141] The process assembly module can supplement the standard connection information based on the node relationships output by the large language model and return the improved process data.

[0142] The 5G message assembly module can encapsulate the part of the process involving sending messages according to the 5G message structure.

[0143] The preview module can be used to render and display the flowchart effect for users to review, and perform subsequent operations based on user feedback (abandon or confirm creation).

[0144] The process creation module can format the process data confirmed by the user and store it in the process library corresponding to the user account to complete the process creation.

[0145] The robot event node library can store the event-encapsulated composite robot action node information and data structure for the process assembly module to call.

[0146] The process library can be used to store robot processes created by users, making it easier for users to manage and use them later.

[0147] In actual implementation, Figure 2 The functions of the process construction device 201 and the data acquisition device 202 can be obtained by Figure 5 The intention collection module, prompt assembly module, large model docking module, large model parsing module, robot process production module, robot event node library and process library are implemented. The specific execution process can refer to the description of the method part in the above embodiment, which will not be repeated here.

[0148] In one embodiment, combining Figure 5 ,like Figure 6 As shown, Figure 6 Interaction diagram of a process building approach.

[0149] In one possible implementation, the intention collection module can obtain the demand information input by the user and send the demand information to the Prompt assembly module. The Prompt assembly module can query the robot nodes that the user currently has the authority to use. The robot event node library sends the robot nodes and function descriptions that the user currently has the authority to use to the Prompt assembly module. The Prompt assembly module determines the Prompt based on the demand information and the robot node. The Prompt assembly module can send the Prompt to the large model docking module. The large model docking module can send a generation request to the corresponding large model.

[0150] In one embodiment, combining Figure 6 ,like Figure 7 As shown, Figure 7 Interaction diagram of the method for building yet another process.

[0151] In a possible implementation, the big model can generate process data based on the prompt, and send the process data to the big model parsing module. The big model parsing module can parse the process data to obtain process production instructions. The big model parsing module can send the process production instructions to the robot process production module.

[0152] In one embodiment, combining Figure 7 ,like Figure 8 As shown, Figure 8 Interaction diagram of the method for building yet another process.

[0153] In one possible implementation, the robot process production module can send the process production instruction to the production instruction parsing module. The production instruction parsing module can split the process nodes and message data in the process production instruction, and build complete node data according to the standard of the process construction system. The process production instruction can send the message data to the 5G message assembly module. The 5G message assembly module can perform standardized encapsulation of the message data. The 5G message assembly module can send the encapsulated message data to the process assembly module. The production instruction parsing module can send the node data to the process assembly module. The process assembly module can create connection data based on the node relationship in the node data to build the target process.

[0154] In one embodiment, combining Figure 8 ,like Fig. 9 As shown, Fig. 9 Interaction diagram of the method for building yet another process.

[0155] In a possible implementation, the process assembly module can send the target process to the preview module. The preview module can render the target data according to the standard process. The preview module can display the target data. After receiving the user's confirmation operation, the preview module sends the target process to the process creation module. The process creation module can store the target process in the library according to the data model granularity. The target process can be saved to the preset storage address of the current user.

[0156] For example, a catering enterprise user tried to create a 5G message Chatbot process for the first time. The catering enterprise user described the scenario it needed to handle, specifically building a meal ordering process. In this process, key information such as the user's name, contact number, number of diners, and meal time must be confirmed.

[0157] After receiving the customer's description, the process construction system matches the information provided by the customer with the node information preset in the system, and then assembles a complete prompt. Subsequently, the process construction system initiates a request to the big model through the prompt. Based on the request content, the big model returns a processed ordering process data that meets the customer's needs.

[0158] After receiving the ordering process data from the large model, the process construction system uses built-in logic to convert it into a specific ordering process that can be assembled through existing robot capability nodes.

[0159] The catering enterprise user previews the generated ordering process in the process building system and after careful inspection, believes that the process meets its actual needs. Therefore, the catering enterprise user clicks the Save button to save the process to his personal process management library for future use and management.

[0160] For example, Fig.10 FIG. 1 is a schematic diagram of a process construction device provided in an embodiment of the present application. The process construction device is used to execute the process construction method provided in the present application. For example, the above Figure 4 The process construction method. The process construction device may include: a receiving unit 701, a generating unit 702, a construction unit 703, a display unit 704 and a processing unit 705.

[0161] In a possible manner, the receiving unit 701 is configured to receive demand information of a first user for a target process.

[0162] In one possible manner, the generating unit 702 is used to generate process data based on process requirements and application scenarios.

[0163] In one possible manner, the construction unit 703 is used to construct a target process based on the process nodes and the message data.

[0164] In a possible manner, the generating unit 702 is specifically configured to: generate a prompt based on process requirements and application scenarios, and generate process data based on the large model and the prompt.

[0165] In a possible manner, the generating unit 702 is specifically configured to: determine target node information from a target database according to the permission information of the first user, and generate a prompt based on the target node information, process requirements, and application scenarios.

[0166] In a possible manner, the construction unit 702 is specifically used to: parse the process nodes, determine the node relationship between each process node, and construct the target process based on the node relationship and the message data.

[0167] In a possible manner, the construction unit 703 is specifically configured to: connect multiple process nodes based on the node relationship to obtain an initial process; and encapsulate the message data into the initial process based on the process node corresponding to the message data to obtain a target process.

[0168] In a possible manner, the display unit 704 is used to display the effect corresponding to the target process and receive a selection operation of the first user on the effect corresponding to the target process.

[0169] In a possible manner, the processing unit 705 is configured to save the target process to a preset storage address or modify the target process in response to a selection operation of the first user.

[0170] also, Fig.10 The technical effects of the process construction device can refer to the technical effects of the process construction method in the above embodiment, and will not be repeated here.

[0171] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0172] An embodiment of the present application provides a computer program product including instructions. When the computer program product is run on a computer, the computer is enabled to execute the process construction method in the above method embodiment.

[0173] An embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the process construction method in the method process shown in the above method embodiment.

[0174] Among them, the computer readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0175] Since the process construction device, computer-readable storage medium, and computer program product in the embodiments of the present application can be applied to the above-mentioned method, the technical effects that can be obtained can also refer to the above-mentioned method embodiments, and the embodiments of the present application will not be repeated here.

[0176] The above is only a specific real-time method of the present application, but the protection scope of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A process construction method, characterized in that: include: Receiving demand information of a first user for a target process; The demand information includes process requirements for the target process and application scenarios of the target process; The target process is used to instruct the Chatbot to interact with the second user; Based on the process requirements and the application scenarios, generate process data; The process data includes multiple process nodes and message data corresponding to each process node; The target process is constructed based on the process node and the message data.

2. The method according to claim 1, characterized in that The generating process data based on the process requirements and the application scenario includes: Based on the process requirements and the application scenario, a prompt is generated; the prompt is used to guide the large model to generate the process data that meets the process requirements and the application scenario; The process data is generated based on the large model and the prompt.

3. The method according to claim 2, characterized in that The generating a prompt based on the process requirements and the application scenario includes: Determine target node information from a target database according to the permission information of the first user; the target node information is used to connect the process requirement and the application scenario; The Prompt is generated based on the target node information, the process requirements and the application scenario.

4. The method according to claim 1, characterized in that: The step of constructing the target process based on the process node and the message data includes: Parsing the process nodes to determine the node relationship between the various process nodes; the node relationship includes at least one of a sequence relationship and a dependency relationship; The target process is constructed based on the node relationship and the message data.

5. The method according to claim 4, characterized in that Based on the node relationship and the message data, constructing the target process includes: Based on the node relationship, connecting the multiple process nodes to obtain an initial process; Based on the process node corresponding to the message data, the message data is encapsulated into the initial process to obtain the target process.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Displaying the effect corresponding to the target process, and receiving a selection operation of the first user on the effect corresponding to the target process; In response to the selection operation of the first user, the target process is saved to a preset storage address or the target process is modified.

7. A process construction device, characterized in that: The device comprises: a receiving unit, a generating unit and a constructing unit; The receiving unit is used to receive the first user's demand information for the target process; the demand information includes the process requirements for the target process and the application scenario of the target process; the target process is used to instruct the Chatbot to interact with the second user; The generating unit is used to generate process data based on the process requirements and the application scenario; the process data includes a plurality of process nodes and message data corresponding to each process node; The construction unit is used to construct the target process based on the process node and the message data.

8. A process construction device, characterized in that: include: A processor and a communication interface; the communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement the process construction method as described in any one of claims 1-6.

9. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, characterized in that: When a computer executes the instruction, the computer executes the process construction method described in any one of claims 1 to 6.

10. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer, the computer is enabled to execute the process construction method according to any one of claims 1 to 6.

Images