Page configuration method, device, readable medium, electronic device and program product

Abstract

A page configuration method, device, readable medium, electronic device and program product. The method comprises: in response to a configuration operation of a trigger mode in a first configuration page, determining a trigger mode of a target processing flow to be created, wherein the trigger mode comprises a model trigger mode based on a first machine learning model; displaying a second configuration page for the target processing flow, and in response to a configuration operation of a flow node in the target processing flow in the second configuration page, determining a target flow node configured for the target processing flow; and obtaining a target processing flow in a smart object page according to the trigger mode and the target flow node of the target processing flow. Thus, the user input content can be identified by the first machine learning model, and then the corresponding processing flow can be triggered based on the identification result, so that corresponding logical processing can be performed for various forms of user input content, and then the user's interactive operation can be responded to, thereby improving the user experience.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a page configuration method, device, readable medium, electronic device, and program product. Background Art

[0002] In the actual application of the application, for different front-end scenarios, the corresponding processing flow needs to be set according to the back-end logic.

[0003] For the processing flow of simple scenarios, the exhaustive method can be used to cover all processing logics. However, for the processing flow of complex scenarios, such as the smart object page for users to interact with smart objects, due to the diverse forms of user input content, it is difficult to perform corresponding logical processing on all input content, which leads to the inability to respond to user interaction operations and poor user experience. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a page configuration method, the page configuration method comprising: Displaying a first configuration page, wherein the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, wherein the first machine learning model is used to recognize input content of the second user in the smart object page, and the recognition result is used to trigger a corresponding processing flow; In response to the configuration operation of the trigger mode in the first configuration page, determining the trigger mode of the target processing flow to be created; displaying a second configuration page for the target processing flow, and determining a target process node configured for the target processing flow in response to a configuration operation on a process node in the target processing flow in the second configuration page; The target processing flow in the smart object page is obtained according to the triggering mode of the target processing flow and the target flow node.

[0006] In a second aspect, the present disclosure provides a page configuration device, the page configuration device comprising: A first display module, configured to display a first configuration page, wherein the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, wherein the first machine learning model is used to recognize input content of the second user in the smart object page, and the recognition result is used to trigger a corresponding processing flow; A response module, configured to determine a triggering mode of a target processing flow to be created in response to a configuration operation of the triggering mode in the first configuration page; A second display module is used to display a second configuration page for the target processing flow, and determine a target process node configured for the target processing flow in response to a configuration operation on a process node in the target processing flow in the second configuration page; The process determination module is used to obtain the target processing process in the smart object page according to the triggering mode of the target processing process and the target process node.

[0007] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when the program is executed by a processing device.

[0008] In a fourth aspect, the present disclosure provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the method in the first aspect.

[0009] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0010] Through the above technical solution, in response to the configuration operation of the trigger mode in the first configuration page, the trigger mode of the target processing flow to be created can be determined, wherein the trigger mode includes a model trigger mode based on the first machine learning model, and in response to the configuration operation of the flow node in the target processing flow in the second configuration page, the target flow node configured for the target processing flow can be determined, and then the target processing flow in the smart object page is obtained according to the trigger mode and the target flow node of the target processing flow. With this method, the user input content can be identified through the first machine learning model, and then the corresponding processing flow can be triggered based on the identification result, so that corresponding logical processing can be performed for various forms of user input content, and then the user's interactive operation can be responded to to improve the user experience.

[0011] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 is a flow chart of a page configuration method according to an exemplary embodiment of the present disclosure; Figure 2 is a schematic diagram of a first configuration page according to an exemplary embodiment of the present disclosure; Figure 3 is a schematic diagram of a smart object page according to an exemplary embodiment of the present disclosure; Figure 4 is a schematic diagram showing a second configuration page according to an exemplary embodiment of the present disclosure; Figure 5 is a schematic diagram of a configuration of a first process node according to an exemplary embodiment of the present disclosure; Figure 6 is a schematic diagram of a configuration of a second process node according to an exemplary embodiment of the present disclosure; Figure 7 is a schematic diagram of another smart object page according to an exemplary embodiment of the present disclosure; Figure 8 is a schematic diagram of a configuration of a model node according to an exemplary embodiment of the present disclosure; Fig. 9 is a schematic diagram of a configuration of a code node according to an exemplary embodiment of the present disclosure; Fig.10 is a structural block diagram of a page configuration device according to an exemplary embodiment of the present disclosure; Fig.11 It is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0014] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0015] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] At the same time, it is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] For the processing flow of simple scenarios, such as the login page, there may be situations such as successful login, unregistered account, wrong account or password, forgotten password, etc., and the exhaustive method can be used to cover all processing logic. However, for the processing flow of complex scenarios, such as the smart object page for users to interact with smart objects, due to the diverse forms of user input content, it is difficult to perform corresponding logical processing on all input content, which leads to the inability to respond to user interaction operations and poor user experience.

[0025] In view of this, the present disclosure provides a page configuration method, device, readable medium, electronic device and program product to solve the above technical problems.

[0026] The embodiments of the present disclosure are further explained below with reference to the accompanying drawings.

[0027] Figure 1 is a flow chart of a page configuration method according to an exemplary embodiment of the present disclosure, referring to Figure 1 , the page configuration method may include the following steps: S101: Display a first configuration page, where the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, and the first machine learning model is used to recognize input content of the second user in the smart object page, and the recognition result is used to trigger a corresponding processing flow.

[0028] The first user is a developer who configures the processing flow of the smart object page, and the second user is a user of the smart object page. The input content can be text content, image content, audio content, etc., and the present disclosure does not limit this. The first machine learning model can be a large language model (LLM), a neural network model, a deep learning model, etc., and the present disclosure does not limit this.

[0029] It should be noted that in the related art, the knowledge question-answering type smart object only needs to output the corresponding answer according to the question input by the user, and the processing flow is single. However, the functional smart object can provide a variety of different functions, and the processing flows corresponding to different functions are different. The smart object of the embodiment of the present disclosure can be a functional smart object of different platforms, such as a customer service robot, etc., and the present disclosure does not limit this.

[0030] S102: In response to the configuration operation of the trigger mode in the first configuration page, determine the trigger mode of the target processing flow to be created.

[0031] In a possible manner, the triggering method also includes a keyword triggering method based on keywords, and in response to the configuration operation of the triggering method in the first configuration page, the triggering method of the target processing flow to be created is determined, including: in response to the configuration operation of the keyword in the first configuration page, the configured target keyword is determined, and the triggering method of the target processing flow is determined to be a keyword triggering method based on the target keyword, wherein, when the second user enters the target keyword in the smart object page, the target processing flow is triggered.

[0032] For example, Figure 2 As shown, the process configuration page is used to display the configured processing flow. Triggering the "Create" control displays the first configuration page. The target keywords can be configured on the first configuration page to determine that the triggering method corresponding to the processing flow is a keyword triggering method based on the target keywords. You can also check "Whether it is decided by a large model" on the first configuration page to determine that the processing flow enables the model triggering method. Unchecking "Whether it is decided by a large model" indicates that the processing flow does not enable the model triggering method. The display style of the first configuration page can be determined according to demand. For example, you can also set a selection box for the keyword. Checking it means enabling the keyword triggering method, unchecking it means not enabling the keyword triggering method, and so on. The present disclosure does not limit this.

[0033] For example, taking the customer service robot of the content delivery platform as an example, you can create a processing flow for querying delivery orders, and then set the keyword trigger method, with the keyword being "query delivery orders". In this way, when the user enters "query delivery order x" on the smart object page, the processing flow for querying delivery orders is triggered because the input content contains the set keywords.

[0034] For example, a model triggering method can also be set. For example, if a user inputs "How is the delivery order x now?", the first machine learning model can perform semantic recognition on the user's input content, and then determine that the user's actual demand is to query the delivery order, and then trigger the processing flow of querying the delivery order. In this way, the processing logic corresponding to various forms of user input content can be covered.

[0035] In a possible manner, the triggering method also includes an action-based action triggering method, and the method also includes: in response to the configuration operation of the triggering action of the target processing flow, determining the target action corresponding to the target processing flow, wherein when the smart object page executes the target action, the target processing flow is triggered.

[0036] For example, the user can trigger the corresponding processing flow through the interactive controls in the smart object page. Figure 3 As shown, the user can trigger the processing flow of transferring to manual customer service by triggering the "manual" control. When building a smart object page, by binding the interactive control with the corresponding processing flow, the triggering method of the processing flow is the action triggering method, and the triggering action is the action corresponding to the control. Here, the smart object page can be built in a low-code manner or in a code manner. The present disclosure does not limit this. In this way, when the user's operation on the smart object page triggers the corresponding action, the corresponding processing flow of the action is triggered.

[0037] It should be noted that if Figure 3 As shown in the solid line flow in , the corresponding processing flow can be directly triggered in response to the user triggering the interactive control. Figure 3 As shown in the dotted line flow in , in response to the user triggering the interactive control, the preset content corresponding to the interactive control is first triggered to be sent, and then in response to the action of receiving the preset content, the corresponding processing flow is triggered. Of course, Figure 3 The dotted line process in the figure can also be implemented by keyword triggering, and the present disclosure does not limit this.

[0038] It is worth noting that one or more of the three triggering methods mentioned above can be configured for the same processing flow, and the present disclosure does not impose any restrictions on this. When using the action triggering method, you can specify the processing flow corresponding to the action from the existing processing flow, or you can create a new processing flow. The present disclosure does not impose any restrictions on this. When using the keyword triggering method, it is necessary to maintain the mapping relationship between the keywords and the processing flow. When using the model triggering method, it is necessary to call the first machine learning model to identify the user input content to determine the processing flow to be called in the next step, and the parameter structure required for the processing flow can be generated by function calling. The present disclosure does not impose any restrictions on this.

[0039] S103: Display a second configuration page for the target processing flow, and determine the target process node configured for the target processing flow in response to the configuration operation on the process node in the target processing flow in the second configuration page, wherein the second configuration page is used for the first user to configure the process node of the target processing flow in a low-code manner.

[0040] For example, taking the above-mentioned processing flow of querying the delivery order as an example, there may be situations such as whether the user has logged into the account, whether the user account does not have the authority to query the delivery order, whether the delivery order exists, etc. It is necessary to configure the process nodes of the processing flow according to the above-mentioned situations. The configuration can be carried out specifically according to the actual processing logic, and the present disclosure does not impose any restrictions on this.

[0041] S104: Obtain the target processing flow in the smart object page according to the triggering mode and target flow node of the target processing flow.

[0042] By adopting the above method, the user input content can be identified through the first machine learning model, and then the corresponding processing flow can be triggered based on the identification result, so that corresponding logical processing can be performed on user input content in various forms, and then the user's interactive operations can be responded to, thereby improving the user experience.

[0043] In a possible manner, the second configuration page includes a first area, a second area, and a third area, wherein the first area is used to display different types of process nodes, the second area is used for the first user to configure the process nodes of the target processing flow in a low-code manner, and the third area is used to display the configuration panel corresponding to the process node. In response to the configuration operation of the process node in the target processing flow in the second configuration page, the target process node configured for the target processing flow is determined, including: in response to the selection operation of the process node displayed in the first area, the target process node corresponding to the selection operation is displayed in the second area; in response to the configuration operation of the target process node in the second area, the target configuration panel corresponding to the target process node is displayed in the third area; in response to the configuration operation in the target configuration panel, the configuration information corresponding to the target process node is determined, and the target process node configured for the target processing flow is obtained.

[0044] For example, you can trigger Figure 2 The edit control corresponding to the processing flow is displayed as follows Figure 4 The second configuration page shown includes a first area, a second area and a third area, wherein the triggering mode and page distribution of the second configuration page can be set according to requirements, and the present disclosure does not limit this.

[0045] In a possible manner, the second configuration page is used for the first user to configure the process nodes of the target processing flow in a low-code manner, the target process nodes including judgment nodes, and in response to the configuration operation of the process nodes in the target processing flow in the second configuration page, the target process nodes configured for the target processing flow are determined, including: in response to the configuration operation of the judgment node in the second configuration page, a judgment configuration panel corresponding to the judgment node is displayed on the second configuration page, wherein the judgment configuration panel is used for the first user to configure the judgment branch corresponding to the judgment node; in response to the configuration operation in the judgment configuration panel, the judgment branch corresponding to the judgment node and the judgment condition for triggering the judgment branch are determined to obtain the judgment node configured for the target processing flow.

[0046] For example, Figure 4 As shown, the judgment node can be dragged from the first area into the second area, and the second area has a start node by default. Then, the judgment node can be configured, such as setting the node name, node branch, input parameters and other configuration information, which can be set according to needs, and the present disclosure does not limit this. Thus, a processing flow with judgment logic can be configured to improve the configuration efficiency of the processing flow, thereby improving the efficiency of page development.

[0047] For example, the judgment condition corresponding to each judgment branch can be configured, for example, the judgment condition of branch 1 is "when the parameter value of input parameter X is x1", so when the judgment node is triggered, when the parameter value of input parameter X is x1, the step corresponding to branch 1 is executed. Multiple combinations of judgment conditions can be set to meet different judgment conditions, and subsequent process nodes can be connected to nodes of different judgment branches.

[0048] For example, a fallback branch can also be set, so that when the judgment conditions corresponding to other judgment branches are not met, or when the judgment node fails to execute, the fallback branch steps can be executed. For example, the fallback branch can output a failure prompt message to prompt the user to re-perform the interactive operation. It can be set specifically according to needs, and the present disclosure does not limit this.

[0049] In a possible manner, the second configuration page is used for the first user to configure the process nodes of the target processing flow in a low-code manner, the target process nodes include a first process node for calling the created processing flow, and in response to the configuration operation of the process node in the target processing flow in the second configuration page, the target process node configured for the target processing flow is determined, including: in response to the configuration operation of the first process node in the second configuration page, displaying the first configuration panel corresponding to the first process node on the second configuration page, wherein the first configuration panel is used for the first user to configure the calling process information of the first process node; in response to the configuration operation in the first configuration panel, determining the calling process information of the first process node, and obtaining the first process node configured for the target processing flow.

[0050] For example, Figure 5 As shown, the first process node can be a sub-process node for calling a created processing flow as a sub-process of the current processing flow. In addition, configuration information such as input parameters, output parameters, parameter mapping, etc. can also be configured, which can be set specifically according to needs, and the present disclosure does not limit this. Among them, the input parameters can be selected from the parameters obtained by the process node before the process node. For example, if the calling process is an order query process and the input parameters are order identification parameters, then in actual applications, the order query process is called based on the order identification to obtain the order information corresponding to the order identification returned by the order query process. The output parameters are used to configure the parameter information output by the process node after calling the sub-process, which can be specifically configured according to the return parameters provided by the sub-process, and the present disclosure does not limit this.

[0051] For example, Figure 5 As shown, the target process node may also include a call node for calling an application programming interface (Application Programming Interface, API). The call node is similar to the sub-process node, but the difference is that the object of the call is different.

[0052] It should be noted that the call node and the sub-process node can be set separately, or the call node and the sub-process node can be integrated into one node, and then during configuration, by selecting the call object, it is determined whether the process node calls the interface or calls the sub-process. The specific setting can be based on the needs, and the present disclosure does not limit this. In this way, the processing logic of the current processing flow can be implemented by using the existing interface or processing flow, improving the configuration efficiency of the processing flow, and thus improving the efficiency of page development.

[0053] In a possible manner, the second configuration page is used for the first user to configure the process nodes of the target processing flow in a low-code manner, the target process nodes include a second process node for displaying content in a smart object page, and in response to the configuration operation of the process node in the target processing flow in the second configuration page, the target process node configured for the target processing flow is determined, including: in response to the configuration operation of the second process node in the second configuration page, displaying a second configuration panel corresponding to the second process node on the second configuration page, wherein the second configuration panel is used for the first user to configure the display content corresponding to the second process node; in response to the configuration operation in the second configuration panel, determining the target display content corresponding to the second process node, and obtaining the second process node configured for the target processing flow, wherein the target display content is displayed in the smart object page when the second process node is executed.

[0054] For example, the second process node may be Figure 4 Interaction nodes or output nodes as shown. Figure 6 Taking the interactive node shown as an example, in addition to configuring the display content corresponding to the interactive node, you can also configure input parameters, output parameters, etc. The input parameters and output parameters can be configured according to the parameters obtained from the process node before the interactive node. The specific settings can be based on the needs, and the present disclosure does not impose any restrictions on this.

[0055] For example, in a smart object page, display content is usually displayed in the form of cards, so the display content can also be called an output card. Figure 6 As shown, the "Edit" control of the output card can be triggered to display the configuration page for configuring the output card. For example, you can drag components from the component library to the component preview area to build a card, and configure component style and other information in the component configuration area. In other words, it supports the low-code method to build output cards.

[0056] For example, the configuration process of the output node is the same as the configuration process of the above-mentioned interactive node, and the present disclosure will not repeat them here.

[0057] In a possible manner, the target display content includes an interactive component, and in response to a configuration operation in a second configuration panel, the target display content corresponding to the second process node is determined, and the second process node configured for the target processing process is obtained, including: in response to the configuration operation in the second configuration panel, the interactive component corresponding to the second process node is determined, and the second process node configured for the target processing process is obtained, wherein the interactive component is used to trigger the next process node of the second process node.

[0058] For example, compared with the output node, the interactive node can also be configured to trigger the interactive component of the next process node. Figure 6 As shown, the interactive component can be a button component, a text component, etc., and the trigger event that triggers the next process node can be configured for the interactive component. Figure 7 As shown, the output card corresponding to the interactive node includes a "My Order" button for triggering the next process node. Assuming that the next process node is an output node, after the user triggers the "My Order" button and selects an order on the order page, the output card corresponding to the output node is displayed according to the operation result. If the user does not trigger the "My Order" button, the next process node will not be triggered, so that the output of the interactive content can be controlled by configuring the component event.

[0059] In a possible manner, the second configuration page is used for the first user to configure the process nodes of the target processing flow in a low-code manner, the target process nodes include a third process node for calling the machine learning model, and in response to the configuration operation of the process nodes in the target processing flow in the second configuration page, the target process node configured for the target processing flow is determined, including: in response to the configuration operation of the third process node in the second configuration page, displaying a third configuration panel corresponding to the third process node on the second configuration page, wherein the third configuration panel is used for the first user to configure model information associated with the third process node; in response to the configuration operation in the third configuration panel, determining the target model information associated with the third process node, and obtaining the third process node configured for the target processing flow, wherein the target model information is used to characterize information of the second machine learning model associated with the third process node, and the second machine learning model is used to perform model inference based on input information of the third process node.

[0060] For example, the third process node may be Figure 4 The model nodes shown. Figure 8 As shown, in addition to configuring the model information associated with the model node, you can also configure input parameters, output parameters, etc. The input parameters can be configured according to the parameters obtained by the process node before the model node, and the output parameters can be configured according to the parameters corresponding to the model reasoning results. The specific settings can be based on the needs, and the present disclosure does not impose any restrictions on this.

[0061] In a possible manner, the target model information includes at least one of a first prompt word and a second prompt word, wherein the first prompt word is used to indicate a model property of a second machine learning model, and the second prompt word is used to indicate that the second machine learning model performs model inference.

[0062] For example, Figure 8 As shown, the target model information may include the associated machine learning model, the model version and model type of the model, etc. The model type includes a single-round dialogue type and a multi-round dialogue type. It should be noted that the second machine learning model can be a large language model, a neural network model, a deep learning model, etc., and the present disclosure does not limit this. In addition, the second machine learning model can be the same as the first machine learning model, or it can be different, which is determined according to the user's choice, and the present disclosure does not limit this.

[0063] Furthermore, model information such as model parameters, first prompt words, and second prompt words can also be set. Among them, model parameters are used to control the model, the first prompt word is used to set the model attributes such as the role and reply logic of the model, and the second prompt word is used to provide the model with instructions for model reasoning, such as querying according to user input content, etc., which are determined according to needs and are not limited by the present disclosure. Therefore, model nodes can be introduced into the processing flow of the smart object page to improve the processing capability of the smart object.

[0064] In a possible manner, the second configuration page is used for the first user to configure the process nodes of the target processing flow in a low-code manner, the target process nodes include code nodes for writing code, and in response to the configuration operation of the process nodes in the target processing flow in the second configuration page, the target process nodes configured for the target processing flow are determined, including: in response to the configuration operation of the code node in the second configuration page, a code configuration panel corresponding to the code node is displayed on the second configuration page, wherein the code configuration panel is used for the first user to configure the code; in response to the configuration operation in the code configuration panel, the target code corresponding to the code node is determined, and the code node configured for the target processing flow is obtained.

[0065] For example, Fig. 9 As shown, the code node can also be configured with input parameters, output parameters, etc., wherein the input parameters can be configured according to the parameters obtained by the process node before the code node, and the output parameters can be configured according to the code execution result and the parameters obtained by the process node before the code node. The target code is at least used to perform data processing on the parameter values ​​of the input parameters to obtain the parameter values ​​of the output parameters, which can be specifically set according to the needs, and the present disclosure does not limit this.

[0066] For example, Fig. 9 As shown, in order to facilitate the user to write code, you can jump to the code writing page to write code. By introducing code nodes in the processing flow of the smart object page, the processing capability of the smart object can be further improved.

[0067] It is worth noting that for each process node, a fallback solution can be set, so that when the process node fails to execute, the fallback solution corresponding to the process node can be executed. For example, the fallback solution can output a failure prompt message to prompt the user to re-perform the interactive operation. The specific setting can be based on demand, and the present disclosure does not limit this.

[0068] The following is an example description in conjunction with a specific processing flow. Continuing with the above-mentioned processing flow for querying a delivery order as an example, the user enters "query delivery order x" on the smart object page to trigger the processing flow for querying a delivery order. The call node is executed, and it can be determined by calling an authentication interface to determine whether the user account does not have the authority to query the delivery order, by calling the delivery order interface to determine whether the delivery order exists, and so on. The present disclosure does not limit this. Then the judgment node is executed, and the corresponding judgment branch is executed according to different situations. For example, if the user account does not have the authority to query the delivery order, the output node under the corresponding judgment branch is executed to display a prompt message on the smart object page indicating that the user account does not have the authority to query the delivery order. The remaining process nodes can refer to the corresponding embodiments, and the present disclosure will not repeat them here.

[0069] By adopting the above method, the matching logic of triggering the processing flow according to the user input content can be realized through different triggering methods. The processing flow of different process nodes can be set according to the needs, and a quick response can be made according to the user input content. And by building the processing flow of the smart object page in a low-code way, the processing flow can be quickly built according to the actual business scenario, improving the efficiency of page building.

[0070] It should be noted that the configuration page, page layout, node name, node configuration information, etc. of the processing flow provided in the drawings of the present disclosure are determined according to specific needs, and the present disclosure does not limit this. For example, the first configuration page and the second configuration page can be merged, that is, the creation of the processing flow, the triggering method and the configuration of the process node are performed on the same page, and the present disclosure does not limit this.

[0071] Based on the same concept, the present disclosure provides a page configuration device, such as Fig.10 As shown, the page configuration device 1000 includes: A first display module 1001 is used to display a first configuration page, wherein the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, wherein the first machine learning model is used to recognize input content of the second user in the smart object page, and the recognition result is used to trigger a corresponding processing flow; A response module 1002, configured to determine a triggering mode of a target processing flow to be created in response to a configuration operation of the triggering mode in the first configuration page; A second display module 1003 is used to display a second configuration page for the target processing flow, and determine a target process node configured for the target processing flow in response to a configuration operation on a process node in the target processing flow in the second configuration page; The process determination module 1004 is used to obtain the target processing process in the smart object page according to the triggering mode of the target processing process and the target process node.

[0072] Optionally, the second configuration page is used for the first user to configure a process node of the target processing flow in a low-code manner, the target process node includes a first process node for calling a created processing flow, and the second display module 1003 is used to: In response to a configuration operation on the first process node in the second configuration page, displaying a first configuration panel corresponding to the first process node on the second configuration page, wherein the first configuration panel is used for the first user to configure call process information of the first process node; In response to the configuration operation in the first configuration panel, the calling process information of the first process node is determined to obtain the first process node configured for the target processing flow.

[0073] Optionally, the second configuration page is used for the first user to configure a process node of the target processing flow in a low-code manner, the target process node includes a second process node for displaying content in the smart object page, and the second display module 1003 is used to: In response to a configuration operation on the second process node in the second configuration page, displaying a second configuration panel corresponding to the second process node on the second configuration page, wherein the second configuration panel is used for the first user to configure display content corresponding to the second process node; In response to the configuration operation in the second configuration panel, the target display content corresponding to the second process node is determined, and the second process node configured for the target processing process is obtained, wherein the target display content is displayed in the smart object page when the second process node is executed.

[0074] Optionally, the target display content includes an interactive component, and the second display module 1003 is used to: In response to the configuration operation in the second configuration panel, the interactive component corresponding to the second process node is determined to obtain the second process node configured for the target processing flow, wherein the interactive component is used to trigger the next process node of the second process node.

[0075] Optionally, the second configuration page is used for the first user to configure a process node of the target processing process in a low-code manner, the target process node includes a third process node for calling a machine learning model, and the second display module 1003 is used to: In response to a configuration operation on the third process node in the second configuration page, displaying a third configuration panel corresponding to the third process node on the second configuration page, wherein the third configuration panel is used for the first user to configure model information associated with the third process node; In response to the configuration operation in the third configuration panel, the target model information associated with the third process node is determined, and the third process node configured for the target processing process is obtained, wherein the target model information is used to characterize the information of the second machine learning model associated with the third process node, and the second machine learning model is used to perform model inference based on the input information of the third process node.

[0076] Optionally, the target model information includes at least one of a first prompt word and a second prompt word, wherein the first prompt word is used to indicate a model property of the second machine learning model, and the second prompt word is used to indicate that the second machine learning model performs model inference.

[0077] Optionally, the triggering method further includes a keyword triggering method based on keywords, and the response module 1002 is used to: In response to the configuration operation of the keyword in the first configuration page, the configured target keyword is determined, and the triggering method of the target processing flow is determined to be a keyword triggering method based on the target keyword, wherein when the second user enters the target keyword in the smart object page, the target processing flow is triggered.

[0078] Optionally, the triggering mode further includes an action-based action triggering mode, and the page configuration device 1000 further includes: In response to a configuration operation of a trigger action of the target processing flow, a target action corresponding to the target processing flow is determined, wherein when the smart object page executes the target action, the target processing flow is triggered.

[0079] Based on the same concept, an embodiment of the present disclosure further provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the above-mentioned page configuration method are implemented.

[0080] Based on the same concept, the present disclosure also provides an electronic device, which may include: a storage device having a computer program stored thereon; The processing device is used to execute the computer program in the storage device to implement the steps of the above-mentioned page configuration method.

[0081] Based on the same concept, an embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the steps of the above page configuration method when executed by a processor.

[0082] Reference below Fig.11 , which shows a schematic diagram of the structure of an electronic device 110 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.11 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0083] like Fig.11 As shown, the electronic device 110 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 111, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 112 or a program loaded from a storage device 118 to a random access memory (RAM) 113. In the RAM 113, various programs and data required for the operation of the electronic device 110 are also stored. The processing device 111, the ROM 112, and the RAM 113 are connected to each other via a bus 114. An input / output (I / O) interface 115 is also connected to the bus 114.

[0084] Typically, the following devices may be connected to the I / O interface 115: an input device 116 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 117 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 118 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 119. The communication device 119 may allow the electronic device 110 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.11 The electronic device 110 is shown with various devices, but it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have instead.

[0085] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 119, or installed from the storage device 118, or installed from the ROM 112. When the computer program is executed by the processing device 111, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0086] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may 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 may include, but are not limited to: 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 or flash memory), 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. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0087] In some embodiments, any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) can be used for communication, and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0088] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0089] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: displays a first configuration page, the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, the first machine learning model is used to recognize the input content of the second user in the smart object page, and the recognition result is used to trigger the corresponding processing flow; in response to the configuration operation of the triggering method in the first configuration page, the triggering method of the target processing flow to be created is determined; a second configuration page for the target processing flow is displayed, and in response to the configuration operation of the process node in the target processing flow in the second configuration page, the target process node configured for the target processing flow is determined; according to the triggering method of the target processing flow and the target process node, the target processing flow in the smart object page is obtained.

[0090] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0091] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0092] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a module does not, in some cases, limit the module itself.

[0093] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0094] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), 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 foregoing.

[0095] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0096] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0097] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A page configuration method, characterized in that: The page configuration method comprises: Displaying a first configuration page, wherein the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, wherein the first machine learning model is used to recognize input content of the second user in the smart object page, and the recognition result is used to trigger a corresponding processing flow; In response to the configuration operation of the trigger mode in the first configuration page, determining the trigger mode of the target processing flow to be created; displaying a second configuration page for the target processing flow, and determining a target process node configured for the target processing flow in response to a configuration operation on a process node in the target processing flow in the second configuration page; The target processing flow in the smart object page is obtained according to the triggering mode of the target processing flow and the target flow node.

2. The page configuration method according to claim 1, characterized in that: The second configuration page is used for the first user to configure the process node of the target processing flow in a low-code manner, the target process node includes a first process node for calling the created processing flow, and the response to the configuration operation of the process node in the target processing flow in the second configuration page determines the target process node configured for the target processing flow, including: In response to a configuration operation on the first process node in the second configuration page, displaying a first configuration panel corresponding to the first process node on the second configuration page, wherein the first configuration panel is used for the first user to configure call process information of the first process node; In response to the configuration operation in the first configuration panel, the calling process information of the first process node is determined to obtain the first process node configured for the target processing flow.

3. The page configuration method according to claim 1, characterized in that: The second configuration page is used for the first user to configure the process node of the target processing flow in a low-code manner, the target process node includes a second process node for displaying content in the smart object page, and the response to the configuration operation of the process node in the target processing flow in the second configuration page is to determine the target process node configured for the target processing flow, including: In response to a configuration operation on the second process node in the second configuration page, displaying a second configuration panel corresponding to the second process node on the second configuration page, wherein the second configuration panel is used for the first user to configure display content corresponding to the second process node; In response to the configuration operation in the second configuration panel, the target display content corresponding to the second process node is determined, and the second process node configured for the target processing process is obtained, wherein the target display content is displayed in the smart object page when the second process node is executed.

4. The page configuration method according to claim 3, characterized in that: The target display content includes an interactive component, and the response to the configuration operation in the second configuration panel, determining the target display content corresponding to the second process node, and obtaining the second process node configured for the target processing process, includes: In response to the configuration operation in the second configuration panel, the interactive component corresponding to the second process node is determined to obtain the second process node configured for the target processing flow, wherein the interactive component is used to trigger the next process node of the second process node.

5. The page configuration method according to claim 1, characterized in that: The second configuration page is used for the first user to configure a process node of the target processing flow in a low-code manner, the target process node includes a third process node for calling a machine learning model, and the response to the configuration operation of the process node in the target processing flow in the second configuration page determines the target process node configured for the target processing flow, including: In response to a configuration operation on the third process node in the second configuration page, displaying a third configuration panel corresponding to the third process node on the second configuration page, wherein the third configuration panel is used for the first user to configure model information associated with the third process node; In response to the configuration operation in the third configuration panel, the target model information associated with the third process node is determined, and the third process node configured for the target processing process is obtained, wherein the target model information is used to characterize the information of the second machine learning model associated with the third process node, and the second machine learning model is used to perform model inference based on the input information of the third process node.

6. The page configuration method according to claim 5, characterized in that: The target model information includes at least one of a first prompt word and a second prompt word, wherein the first prompt word is used to indicate a model property of the second machine learning model, and the second prompt word is used to indicate that the second machine learning model performs model inference.

7. The page configuration method according to any one of claims 1 to 6, characterized in that: The triggering method further includes a keyword triggering method based on a keyword, and the triggering method of the target processing flow to be created is determined in response to the configuration operation of the triggering method in the first configuration page, including: In response to the configuration operation of the keyword in the first configuration page, the configured target keyword is determined, and the triggering method of the target processing flow is determined to be a keyword triggering method based on the target keyword, wherein when the second user enters the target keyword in the smart object page, the target processing flow is triggered.

8. The page configuration method according to any one of claims 1 to 6, characterized in that: The triggering mode also includes an action triggering mode based on an action, and the method further includes: In response to a configuration operation of a trigger action of the target processing flow, a target action corresponding to the target processing flow is determined, wherein when the smart object page executes the target action, the target processing flow is triggered.

9. A page configuration device, characterized in that: The page configuration device comprises: A first display module, configured to display a first configuration page, wherein the first configuration page is at least used for a first user to create a processing flow for a smart object page and configure a triggering method for the processing flow, wherein the smart object page is used for a second user to interact with the smart object, and the triggering method includes a model triggering method based on a first machine learning model, wherein the first machine learning model is used to recognize input content of the second user in the smart object page, and the recognition result is used to trigger a corresponding processing flow; A response module, configured to determine a triggering mode of a target processing flow to be created in response to a configuration operation of the triggering mode in the first configuration page; A second display module is used to display a second configuration page for the target processing flow, and determine a target process node configured for the target processing flow in response to a configuration operation on a process node in the target processing flow in the second configuration page; The process determination module is used to obtain the target processing process in the smart object page according to the triggering mode of the target processing process and the target process node.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 8 are implemented.

11. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images