Interaction method, device, electronic device and storage medium

Abstract

The present disclosure provides an interactive method, device, electronic device and storage medium, which relate to the fields of computer technology, in particular to the fields of natural language processing technology and information flow technology. The specific implementation scheme is: displaying a dialogue interaction interface of a resource delivery platform; obtaining resource delivery demand information input into the dialogue interaction interface; executing the arrangement logic matching the resource delivery demand information to obtain the execution result; and displaying the execution result in the dialogue interaction interface.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to the field of natural language processing technology and information flow technology. Background Art

[0002] Resource delivery may refer to pushing resources that need to be disseminated, such as advertisements and questionnaire survey information, to relevant users according to a preset resource delivery strategy, so as to help relevant users quickly understand the resources, thereby achieving the goal of effectively and accurately disseminating resources to resource delivery. Summary of the invention

[0003] The present disclosure provides an interaction method, an apparatus, an electronic device and a storage medium.

[0004] According to one aspect of the present disclosure, an interaction method is provided, including: displaying a dialogue interaction interface of a resource delivery platform; obtaining resource delivery demand information input into the dialogue interaction interface; executing an orchestration logic matching the resource delivery demand information to obtain an execution result; and displaying the execution result in the dialogue interaction interface.

[0005] According to another aspect of the present disclosure, an interactive device is provided, including: a dialogue interaction interface display module, used to display the dialogue interaction interface of the resource delivery platform; an acquisition module, used to acquire resource delivery demand information input into the dialogue interaction interface; an execution result acquisition module, used to execute the orchestration logic matching the resource delivery demand information to obtain the execution result; and an execution result display module, used to display the execution result in the dialogue interaction interface.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided according to an embodiment of the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method provided according to an embodiment of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method provided according to the embodiment of the present disclosure is implemented.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 Schematically illustrates an exemplary system architecture of an interactive method and device according to an embodiment of the present disclosure;

[0012] Figure 2 A flowchart of an interaction method according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 The application scenario diagram of the interaction method according to the embodiment of the present disclosure is schematically shown;

[0014] Figure 4 A schematic diagram showing an application scenario of an interaction method according to another embodiment of the present disclosure is shown;

[0015] Figure 5 A diagram schematically shows an application scenario of an interaction method according to another embodiment of the present disclosure;

[0016] Figure 6 A schematic diagram showing an application scenario of an interaction method according to another embodiment of the present disclosure is shown;

[0017] Figure 7 The schematic diagram shows a principle diagram of an interaction method according to an embodiment of the present disclosure;

[0018] Figure 8 A schematic diagram of an interaction method according to another embodiment of the present disclosure is shown;

[0019] Fig. 9 The schematic diagram shows the architecture of the front end for executing the interactive method of the embodiment of the present disclosure;

[0020] Fig.10 A block diagram schematically shows an interaction device according to an embodiment of the present disclosure; and

[0021] Fig.11 A schematic block diagram showing an example electronic device that can be used to implement an embodiment of the present disclosure DETAILED DESCRIPTION

[0022] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] In the technical solution disclosed in the present invention, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations, necessary confidentiality measures are taken, and do not violate public order and good morals.

[0024] The inventors have found that conventional resource delivery methods require users to spend a lot of learning costs, and the interaction process with users is relatively complicated, which has a significant impact on resource delivery efficiency.

[0025] Embodiments of the present disclosure provide an interactive method, an apparatus, an electronic device, a storage medium, and a computer program product. The interactive method includes: displaying a dialog interactive interface of a resource delivery platform; obtaining resource delivery demand information input into the dialog interactive interface; executing an orchestration logic matching the resource delivery demand information to obtain an execution result; and displaying the execution result in the dialog interactive interface.

[0026] According to the embodiments of the present disclosure, by obtaining resource delivery demand information from the dialogue interaction interface and executing the orchestration logic that matches the resource delivery demand information, it is possible to execute the orchestration logic through the information input by the user, thereby efficiently completing the orchestration task of the resource delivery demand, avoiding the problem of long resource delivery strategy construction time caused by users operating on complex orchestration views, improving the construction efficiency of resource delivery strategies, reducing the learning cost of users operating the resource delivery platform, and improving resource delivery efficiency.

[0027] Figure 1 An exemplary system architecture of an interactive method and apparatus according to an embodiment of the present disclosure is schematically shown.

[0028] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the interactive method and apparatus can be applied may include a terminal device, but the terminal device may implement the interactive method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0029] like Figure 1As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0030] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0031] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0032] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for the content browsed by the user using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0033] The server can also be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server can also be a server of a distributed system, or a server combined with blockchain.

[0034] It should be noted that the interaction method provided in the embodiment of the present disclosure can generally be executed by the terminal device 101, 102, or 103. Accordingly, the interaction device provided in the embodiment of the present disclosure can also be set in the terminal device 101, 102, or 103.

[0035] Alternatively, the interactive method provided in the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the interactive device provided in the embodiment of the present disclosure may generally be arranged in the server 105. The interactive method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the interactive device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0036] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0037] Figure 2 The flowchart of the interaction method according to the embodiment of the present disclosure is schematically shown.

[0038] like Figure 2 As shown, the method includes operations S210 to S240.

[0039] In operation S210, a dialog interaction interface of the resource delivery platform is displayed.

[0040] In operation S220, resource delivery demand information input into the dialog interaction interface is obtained.

[0041] In operation S230, the orchestration logic matching the resource delivery demand information is executed to obtain an execution result.

[0042] In operation S240, the execution result is displayed in the dialog interaction interface.

[0043] According to the embodiments of the present disclosure, the resource delivery platform can be used to formulate resource delivery strategies and view resource delivery effects. The resource delivery platform can deliver any type of resources such as advertising resources and questionnaire survey resources. The embodiments of the present disclosure do not limit the specific types of resources delivered by the resource delivery platform, and those skilled in the art can select according to actual needs.

[0044] According to an embodiment of the present disclosure, the dialogue interaction interface may be an interaction interface with dialogue information input and reply information display, and the user may input resource delivery demand information through the dialogue interaction interface.

[0045] According to an embodiment of the present disclosure, resource delivery demand information may include natural language information input by a user that represents resource delivery demand. The orchestration logic may include one or more tasks to be executed that match the demand semantic attributes of the resource delivery demand information. Executing the orchestration logic according to the natural language information input by the user can avoid the complicated operation process generated by the user manually querying the tasks to be executed, and realize the efficient execution of tasks for resource delivery demand.

[0046] According to an embodiment of the present disclosure, the orchestration logic that matches the resource delivery demand information can be executed according to a deep learning algorithm. For example, the resource delivery demand information can be processed by a natural language processing algorithm (such as a transformer algorithm) to achieve semantic understanding and keyword extraction of the resource delivery demand information, and then the extracted keywords are automatically filled into a task template that matches the semantic attributes to achieve the execution of at least one task in the orchestration logic. Alternatively, the orchestration logic can also be executed in combination with the deep learning algorithm and subsequent operations performed by the user.

[0047] It should be noted that the deep learning algorithm may include any algorithm type, such as a convolutional neural network algorithm, a recurrent neural network algorithm, and other neural network algorithms, but is not limited thereto, and may also include other types of algorithms. The embodiments of the present disclosure do not limit the specific types of deep learning algorithms, and those skilled in the art may select them according to actual needs. It should be understood that the deep learning model may be an algorithm model constructed based on the deep learning algorithm.

[0048] According to an embodiment of the present disclosure, executing the orchestration logic that matches the resource delivery demand information to obtain the execution result may include: performing intent recognition on the resource delivery demand information to obtain the intent recognition result; executing the orchestration logic that matches the intent recognition result to obtain the execution result.

[0049] According to the embodiments of the present disclosure, the intent recognition result can characterize the demand intent of the input resource delivery demand information, for example, it can include the intent for the resource delivery scenario, the intent for the resource type, the intent for the resource delivery task, etc. By executing the orchestration logic that matches the intent recognition result, the tasks related to the resource delivery demand attributes can be further accurately executed, achieving accurate matching of the user's resource delivery demand and efficient execution of tasks, and improving the efficient operation of the resource delivery platform.

[0050] According to an embodiment of the present disclosure, the intent recognition result includes a demand scenario.

[0051] According to the embodiments of the present disclosure, the demand scenario may represent a scenario for performing actual operations on the delivered resources, such as a scenario for creating a resource delivery strategy, etc. The embodiments of the present disclosure do not limit the specific types of demand scenarios, and those skilled in the art may make a selection based on actual needs.

[0052] According to an embodiment of the present disclosure, executing the orchestration logic that matches the intent recognition result to obtain the execution result may include: when the demand scenario matches the historical scenario, determining at least one first target task from the first task of the first orchestration logic associated with the historical scenario, the orchestration logic including the first orchestration logic; and executing the at least one first target task to obtain the first target task execution result.

[0053] According to an embodiment of the present disclosure, the execution result includes the first target task execution result, and the historical scenario is determined based on the historical resource delivery demand information obtained in the historical time period.

[0054] According to an embodiment of the present disclosure, historical resource delivery demand information may be resource delivery demand information input into the dialogue interaction interface at a historical moment before the current moment, for example, it may be the first resource delivery demand information input into the dialogue interaction interface. By performing intent recognition on the historical resource delivery demand information and obtaining the historical scene, the orchestration logic matching the historical scene may be determined. When the demand scene matches the historical scene, the consistency between the demand scene of the current resource delivery demand information and the historical scene may be determined, so that the first task in the first orchestration logic may continue to be executed, thereby avoiding the process of repeatedly loading the new orchestration logic, saving computing overhead and improving computing efficiency.

[0055] According to the embodiments of the present disclosure, the first target task may include the first task that has not been completed in the first orchestration logic, and at least one first target task may be determined from the first tasks of the first orchestration logic associated with the historical scenario based on any rule. For example, the first target task may be determined based on a random rule, or may be determined based on the orchestration order between multiple first tasks in the first orchestration logic, or may be determined based on the semantic attribute information of the resource delivery demand information. The embodiments of the present disclosure do not limit the specific rules for determining the first target task.

[0056] According to an embodiment of the present disclosure, a demand scenario represents an intention for a resource delivery demand scenario, and a resource delivery demand scenario includes at least one of the following: a resource delivery strategy creation scenario, a resource delivery strategy modification scenario, and a resource delivery effect query scenario.

[0057] According to an embodiment of the present disclosure, a resource delivery strategy creation scenario may be to create a resource delivery strategy for resources. For example, resource delivery time periods, resource delivery costs, core performance of resources, and other resource delivery strategies may be created in the task of the orchestration logic, so that the resource delivery platform may automatically generate corresponding delivery advertisements based on the resource delivery strategy, and deliver the delivery advertisements precisely according to the resource delivery strategy.

[0058] According to an embodiment of the present disclosure, a resource delivery strategy modification scenario can be a scenario in which an already created resource delivery strategy is modified to form a new resource delivery strategy. A new resource delivery strategy can be obtained by modifying the relevant task information of a task in the orchestration logic, thereby facilitating users to adjust the resource delivery strategy in a timely manner and improving the delivery effect of resources.

[0059] According to an embodiment of the present disclosure, the resource delivery effect query scenario can be a scenario for querying the delivery effects of resources that have already been delivered. For example, the delivery effects such as the conversion rate of delivered advertisements and the consumption rate of resource delivery costs can be queried, so that users can timely grasp the real-time resource delivery status.

[0060] Figure 3 The application scenario diagram of the interaction method according to the embodiment of the present disclosure is schematically shown.

[0061] like Figure 3 As shown, the dialogue interaction interface 300 of the resource delivery platform may include an information output box 310 and display boxes 321, 322, 323 and 324 representing demand scenarios in the first display state. The user can input the resource delivery demand information "Please create a product promotion strategy for product A" in the information output box 310, and the resource delivery platform can perform intent recognition on the resource delivery demand information to obtain the demand scenario. According to the demand scenario, the first arrangement logic matching the demand scenario is determined, and the dialogue interaction interface 300 is jumped to the second display state.

[0062] The dialogue interaction interface 300 in the second display state may include historical resource demand information 331 obtained at a historical moment, “Please create a product promotion strategy for product A”. The dialogue interaction interface 300 in the second display state may also generate a reply message 341, “OK, a resource delivery strategy has been created, please describe product A: for example: the core value, innovative performance, etc. of product A”, based on the historical resource demand information 331. This allows the user to input subsequent resource delivery demand information through the information output box 350 of the dialogue interaction interface 300 in the second display state, so as to execute the first arrangement logic.

[0063] According to an embodiment of the present disclosure, the intention recognition result also includes required task information.

[0064] According to an embodiment of the present disclosure, the demand task information can represent the task that the user needs to perform, and the demand task information can be expressed in natural language, for example, "create a delivery time". The resource delivery demand information can be processed by calling a deep learning model to obtain an intent recognition result including the demand task information and the demand scenario.

[0065] According to an embodiment of the present disclosure, determining at least one first target task from a first task of a first orchestration logic associated with a historical scenario may include: determining a first target task matching the required task information from the first orchestration logic.

[0066] According to an embodiment of the present disclosure, the first target task may include a first task in the first orchestration logic that matches the semantics of the required task information, so that a task that meets the user's needs can be automatically selected for the user based on the natural language input by the user, thereby realizing the automatic flow of tasks in the orchestration logic according to user needs, and the execution order of tasks in the orchestration logic can be automatically adjusted according to the information input by the user, thereby realizing the adjustment of the execution order of the first task, which allows the user to complete the execution of the orchestration logic during the conversation process, meet the user's actual editing needs or query needs of the resource delivery strategy, and improve user satisfaction.

[0067] According to an embodiment of the present disclosure, resource delivery demand information can be processed by calling a deep learning model, thereby achieving updating of the first target task according to the demand content information.

[0068] According to the embodiments of the present disclosure, when the first orchestration logic is determined by historical resource delivery demand information, the first orchestration logic can be loaded into a cache area corresponding to the historical scenario, so that the subsequent user can quickly call the first target task from the cache area after inputting the resource delivery demand information. In this way, the first task in the first orchestration logic can be executed step by step until the first orchestration logic is completed, thereby improving the user's resource delivery work efficiency for business scenarios.

[0069] According to an embodiment of the present disclosure, the resource delivery demand information also includes demand content information.

[0070] According to an embodiment of the present disclosure, the demand content information may represent content information related to the delivery demand in the resource delivery demand information, for example, it may include delivery cost amount, delivery time period information, and the like.

[0071] According to an embodiment of the present disclosure, executing the first target task may include: executing the first target task according to demand content information.

[0072] According to an embodiment of the present disclosure, resource placement demand information can be processed by calling a deep learning model, thereby achieving execution of the first target task according to the demand content information.

[0073] According to an embodiment of the present disclosure, executing at least one first target task may include: updating the first target task according to the demand content information in the resource delivery demand information, and obtaining the first target execution result. The data of the first target task may be in a component data format, and the configuration items of the component data may be updated by the demand content information to realize the execution of the first target task, and the obtained first target task execution result may be the updated component data, so as to facilitate rendering the updated component data in the dialogue interaction interface, realize the automatic configuration of the resource delivery strategy according to the resource delivery demand information, and improve the editing efficiency of the resource delivery strategy.

[0074] According to an embodiment of the present disclosure, executing at least one first target task may also include: generating a target task window corresponding to the first target task in the dialogue interaction interface; and in response to an editing operation on the target task window, executing the first target task according to the editing operation.

[0075] According to the embodiments of the present disclosure, the editing operation may include any type of operation, such as an input operation, a selection operation, a drag operation, etc. The embodiments of the present disclosure do not limit the specific operation type of the editing operation.

[0076] Figure 4 An application scenario diagram of an interaction method according to another embodiment of the present disclosure is schematically shown.

[0077] like Figure 4 As shown, the dialog interaction interface 400 of the resource delivery platform in the application scenario may include a dialog area 410, a preview area 420, and an information input box 430. The user may input resource delivery demand information in the information output box 430.

[0078] like Figure 4 As shown, for example, the user inputs historical resource delivery demand information 411 "Please create a product promotion strategy for product A" at a historical moment, and the resource delivery platform can call the deep learning model to process the historical resource delivery demand information 411 and determine the first orchestration logic. The first orchestration logic may include multiple first tasks, and the multiple first tasks may be displayed in the preview area 420. That is, the task execution results 421, 422, 423, and 424 of the multiple preview first tasks can be obtained. While determining the first orchestration logic, the resource delivery platform can display a reply message 411' in the dialogue area 410: "Okay, the resource delivery strategy has been created. Please describe product A: For example: the core value of product A, innovative performance... etc." to prompt the user to enter the resource delivery strategy creation scenario.

[0079] like Figure 4 As shown, the user can input resource delivery demand information 412: "Product A is a new energy vehicle, with innovative performance of XXX kilometers of endurance, and a price starting from XX million..." The resource delivery platform can call the deep learning model to process the resource delivery demand information 412, determine that the demand scenario corresponding to the resource delivery demand information 412 matches the historical scenario (resource delivery strategy creation scenario), and can determine through the deep learning model that the first target task corresponding to the resource delivery demand information 412 can be the first task corresponding to the first task execution result 421. According to the semantic understanding ability and text prediction ability of the deep learning model, the deep learning model can be called to process the resource delivery demand information 412, and then according to the demand content information in the resource delivery demand information 412, such as "XXX kilometers of endurance function", "price starting from XX million", etc., the first target task is automatically updated to obtain the first task execution result 421. It should be understood that the first task execution result 421 can be an execution completion state.

[0080] like Figure 4 As shown, when the first task execution result 421 is in the execution completion state, the resource delivery platform can generate a reply message in the dialogue area 410, that is, it can generate a target task window 412' corresponding to the next first target task, so that after the user inputs the resource delivery demand information 412, he can conveniently execute the next first target task with a high degree of relevance to the resource delivery demand information 412. The user can perform an editing operation on the target task window 412', for example, by selecting the page promotion example 4121' to execute the first target task, or can also edit the text content of the page promotion example 4121' to execute the first target task, or can also execute the first target task in combination with the operation button for "confirm use".

[0081] It should be noted that Figure 4 The task execution status of each of the task execution results 422, 423, and 424 shown can be an unfinished state. By displaying the execution status of each of the first tasks in the preview area 420, the user can quickly browse the task execution results and be prompted to continue to complete subsequent operations of the resource delivery strategy, thereby improving the user experience.

[0082] According to an embodiment of the present disclosure, the interaction method may further include: when it is detected that the input of resource delivery demand information into the dialogue interaction interface is completed, locking the information input box in the dialogue interaction interface so that the information input box is in a locked state; and when a reply message is generated in the dialogue interaction interface, unlocking the information input box.

[0083] According to an embodiment of the present disclosure, the information input box can be locked to prevent the user from inputting information again during the process of generating a reply message. This can avoid the omission of the information input by the user through a "question-and-answer" approach, thereby improving the ability to accurately process the information input by the user.

[0084] According to an embodiment of the present disclosure, executing the orchestration logic that matches the intent recognition result and obtaining the execution result may also include: when the demand scenario does not match the historical scenario, determining a second orchestration logic that matches the demand scenario, the orchestration logic including the second orchestration logic; determining at least one second target task from the second task of the second orchestration logic; and executing at least one second target task to obtain a second target task execution result, wherein the execution result includes the second target task execution result.

[0085] According to the embodiments of the present disclosure, by determining that the demand scenario does not match the historical scenario, the scenario that the user needs to operate can be isolated, and then by determining the second orchestration logic that matches the demand scenario, the historical scenario in the dialogue interaction interface can be converted into the demand scenario required by the current user. Through the exit and entry mechanism of the scene, the user can switch between multiple scenes in the same dialogue interaction interface, thereby improving the switching speed of the scene for user resource delivery. At the same time, the first target task that has been executed can be saved by determining the second orchestration logic, thereby improving the efficiency of the user's resource delivery as a whole, avoiding the user from searching for the respective orchestration logic of multiple scenes by searching for pages, and reducing the user's learning cost for the resource delivery platform.

[0086] According to an embodiment of the present disclosure, when the conversation interaction interface receives resource delivery demand information for the first time, the first received resource delivery demand information is subjected to intent recognition, and a first intent recognition result can be obtained, and the first intent recognition result can include a first demand scenario. It should be noted that, when the first demand scenario is obtained, the situation where the demand scenario does not match the historical scenario can include the situation where the first demand scenario is obtained.

[0087] For example, when the first demand scenario is obtained, the historical demand scenario may be an empty character, and there is no match between the first demand scenario and the empty character.

[0088] Or, for another example, the situation where the first demand scenario is obtained can be directly determined as a situation where the demand scenario does not match the historical scenario, so that a second orchestration logic matching the demand scenario can be determined, and the second orchestration logic can be executed to obtain an execution result.

[0089] According to an embodiment of the present disclosure, the second orchestration logic matching the demand scenario may be determined by calling a deep learning model.

[0090] According to an embodiment of the present disclosure, executing at least one second target task includes:

[0091] Generating a target task window corresponding to the second target task in the dialogue interaction interface;

[0092] In response to an editing operation on the target task window, a second target task is executed according to the editing operation.

[0093] According to an embodiment of the present disclosure, executing the second target task may include: executing the second target task according to the required content information.

[0094] Figure 5 An application scenario diagram of an interaction method according to yet another embodiment of the present disclosure is schematically shown.

[0095] like Figure 5 As shown, in this application scenario, the dialogue interaction interface 500 of the resource delivery platform may include a dialogue area 510 , a preview area 520 , and an information input box 530 .

[0096] like Figure 5 As shown, for example, a user inputs historical resource delivery demand information 511 "Please query the advertising delivery effect of product B" at a historical moment, and the resource delivery platform can call a deep learning model to process the historical resource delivery demand information 511 and determine the first arrangement logic. While determining the first arrangement logic, the resource delivery platform can display a reply message 511' in the dialogue area 510: "OK, please describe the time period to be queried: for example: from x month 1 to y month 1, 20xx", to prompt the user to enter the resource delivery effect query scene.

[0097] like Figure 5As shown, the user can input resource delivery demand information 512: "Create a promotion strategy for product A, product A is a new energy vehicle, the innovative performance is to have a XXX km endurance function, and the price starts from XX million...", the resource delivery platform can call the deep learning model to process the resource delivery demand information 512, determine that the demand scenario (resource delivery strategy creation scenario) corresponding to the resource delivery demand information 512 does not match the historical scenario (resource delivery effect query scenario), and determine the second orchestration logic corresponding to the resource delivery demand information 512 by calling the deep learning model. The second orchestration logic includes multiple second tasks, and the task execution results 521, 522 and 523 corresponding to the second task can be displayed in the preview area 520. According to the semantic understanding ability and text prediction ability of the deep learning model, the deep learning model can be called to process the resource delivery demand information 512, and then according to the demand content information in the resource delivery demand information 512, such as "XXX km endurance function", "price starts from XX million", etc., the second target task is automatically updated to obtain the second task execution result 521. It should be understood that the second task execution result 521 can be an execution completion state.

[0098] like Figure 5 As shown, when the second task execution result 521 is in the execution completion state, the resource delivery platform can generate a reply message in the dialogue area 510, that is, it can generate a target task window 512' corresponding to the next second target task, so that after the user inputs the resource delivery demand information 512, he can conveniently execute the next first target task with a high degree of relevance to the resource delivery demand information 512. The user can perform an editing operation on the target task window 512', for example, by selecting the page promotion example 5121' to execute the second target task, or can also edit the text content of the page promotion example 5121' to execute the second target task, or can also execute the second target task in combination with the operation button for "confirm use".

[0099] According to an embodiment of the present disclosure, before generating the scene transition prompt information, the interaction method may further include: generating scene transition inquiry information in the dialogue interaction interface.

[0100] According to an embodiment of the present disclosure, the scene conversion inquiry information can be used to inquire the user whether the historical scene needs to be converted into the demand scene. In this way, when there is an error in the resource delivery demand information input by the user, the user can be promptly prompted whether to continue to execute the first orchestration logic for the current scene, thereby reducing task execution errors caused by erroneous operations input by the user.

[0101] According to an embodiment of the present disclosure, the interaction method may further include: generating scene conversion prompt information representing the demand scene in the dialogue interaction interface.

[0102] According to an embodiment of the present disclosure, when the demand scenario of the resource delivery demand information input by the user does not match the historical scenario, a scene conversion prompt message can be generated to prompt the user that the user has entered a new demand scenario, thereby facilitating the user to perform scene query in the dialogue interaction interface and facilitating the user to quickly switch the orchestration logic to be executed according to actual business work needs.

[0103] It should be understood that the reply information generated by the resource delivery platform may include scene transition prompt information and scene transition inquiry information.

[0104] According to an embodiment of the present disclosure, the editing operation includes a data editing operation;

[0105] According to an embodiment of the present disclosure, executing the first target task or the second target task according to the editing operation may include: updating the data corresponding to the data editing operation according to the target data attributes associated with the first target task or the second target task to obtain the target data; and executing the first target task or the second target task according to the target data.

[0106] According to an embodiment of the present disclosure, the target data attributes may include attributes such as amount and duration, such as "yuan", "hours", etc. The data input by the user through the data editing operation may be "90 minutes", and then the target data attribute "hours" may be used to automatically update "90 minutes" to "1.5 hours", thereby realizing automatic update of the target data.

[0107] According to the embodiments of the present disclosure, a deep learning model can be called to understand the data attributes of data corresponding to the data editing operation, and then standardized target data can be obtained according to the target data attributes, thereby avoiding the need for users to adjust the input data by learning the target data attributes, simplifying the user's editing operation process and improving the user's interaction efficiency.

[0108] Figure 6 An application scenario diagram of an interaction method according to yet another embodiment of the present disclosure is schematically shown.

[0109] like Figure 6As shown, the dialogue interaction interface 600 of the resource delivery platform in the application scenario may include a dialogue area 610 and a preview area 620. In the dialogue area 610, the demand scenario can be determined as a resource delivery effect query scenario based on the resource delivery demand information input by the user. Then, the arrangement logic that matches the resource delivery demand information can be determined, which may be a delivery effect query logic. In the dialogue area 610, the task execution results (i.e., the first target task execution results) of the three display tasks of "key indicators", "data interpretation" and "crowd audience" can be displayed, so that users can easily query the resource delivery effect. The target task window 611 can also be displayed in the dialogue area 610, so that the user can continue to obtain the task execution results of the next first target task by performing an editing operation on the target task window 611.

[0110] like Figure 6 As shown, the preview area 620 can also display thumbnails of resource delivery effects of other types of products related to the user, for example, thumbnails of resource delivery effects of model A car, model B car, and model C car can be displayed, so that the user can quickly query the resource delivery effects of each product.

[0111] According to an embodiment of the present disclosure, executing the orchestration logic that matches the resource delivery demand information also includes: when the intent recognition result is an intent recognition exception, generating intent guidance information related to the resource delivery demand in the dialogue interaction interface; obtaining new resource delivery demand information corresponding to the intent guidance information; and executing the orchestration logic that matches the new resource delivery demand information, wherein the intent recognition exception represents that the current resource delivery demand information is irrelevant to the preset candidate intent recognition result.

[0112] According to the embodiments of the present disclosure, the intention recognition anomaly can indicate that the demand scenario and / or demand task information for the resource delivery demand information is not recognized, so the orchestration logic that matches the resource delivery demand information cannot be determined, or the target task that matches the resource delivery demand information cannot be determined. By generating intention guidance information in the dialogue interaction interface, such as generating "You need to create a resource delivery strategy", it can help users to understand the specific functions of the resource delivery platform in a timely manner, and then quickly enter the work scenario of resource delivery by inputting new resource delivery demand information, thereby improving the efficiency of human-computer interaction.

[0113] According to the interactive method provided in the embodiment of the present disclosure, creation, modification, query and other workflows can be initiated in a chat-driven manner, so that users can be guided to quickly complete the flow of multiple orchestration logic tasks with the assistance of the chat stream, thereby achieving efficient execution of orchestration logic.

[0114] According to an embodiment of the present disclosure, the interaction method may further include: calling a deep learning algorithm to process an execution result to obtain a processing result; and determining the execution degree of the task performed in the current round of dialogue according to the processing result.

[0115] According to an embodiment of the present disclosure, the execution result may include any one of the first target task execution result and the second target task execution result, or may also include the execution result of the first orchestration logic or the first orchestration logic as a whole.

[0116] It should be noted that according to the interactive method provided in the embodiment of the present disclosure, the execution results can be processed from the deep learning model deployed in the local server, or the deep learning model can be called remotely to process the execution results. The embodiment of the present disclosure does not limit the specific deployment method of the deep learning model.

[0117] According to an embodiment of the present disclosure, a deep learning algorithm may include a pre-trained deep learning model, and by calling the deep learning model to process the execution result, it is possible to quickly determine whether the execution result meets the business requirements through the processing result. If the business requirements are met, the processing degree (execution status) of the processing result can be determined as completed, and if the business requirements are not met, the processing degree (execution status) of the processing result can be determined as incomplete. In the case where the processing degree is incomplete, the resource delivery platform can regenerate reply information for the incomplete task to guide the user to complete the target task, thereby assisting the user to input accurate resource delivery demand information, improving the overall execution efficiency of the orchestration logic, and avoiding errors in the resource delivery strategy caused by the incomplete execution of some tasks in the orchestration logic.

[0118] According to the interactive method provided by the embodiment of the present disclosure, a reply message based on a GUI (Graphical User Interface, GUI for short) can be generated to help the user to execute the arrangement logic by operating the GUI. The interactive method can be implemented based on the following human-computer interaction mode, for example.

[0119] Through human-computer dialogue, it is discovered that GUI assistance is needed, and instructions are sent to indicate the GUI that needs xx function. The GUI is refined based on user operations or deep learning models, and the resource delivery demand information that needs to be processed is associated with the GUI. The GUI is based on the resource delivery demand information and the user's editing operations such as clicks and drags to complete the processing and execute the results. By sending a reply message to the dialogue interaction interface back to the dialogue flow, all execution results in the orchestration logic continue to be completed according to the dialogue flow.

[0120] According to the interactive method provided by the embodiment of the present disclosure, the GUI interactive process can be replaced based on the deep learning model, which reflects the function of supporting the operation of the resource delivery platform based on the deep learning algorithm. It avoids completing the resource delivery work through multi-level interactive units such as the option menu bar, improves the response accuracy to the user's free expression needs, and at the same time improves the interaction efficiency based on the semantic understanding ability and text prediction ability of the deep learning model.

[0121] Figure 7 The principle diagram of the interaction method according to the embodiment of the present disclosure is schematically shown.

[0122] like Figure 7 As shown, the interactive method 700 of this embodiment can be an operation step executed by a computer backend. After obtaining the resource delivery demand information (query) input by the user, the query is preprocessed, and the preprocessed query is judged whether the demand scenario has been created at the current moment. If it is judged to be no, the scenario can be identified according to the preprocessed query, the demand scenario can be determined, and the orchestration logic matching the demand scenario can be loaded, and the tasks to be executed can be orchestrated according to the orchestration logic, and then a reply message can be sent to the dialogue interaction interface to facilitate the user to continue to input the query.

[0123] It is determined whether a demand scenario has been created for the preprocessed query at the current moment. If the judgment is yes, the first orchestration logic is determined, and it is determined whether to enter the historical scenario. If the judgment result is yes, multiple demand task information of the query can be identified, and inquiry guidance information is returned to the dialogue interaction interface based on the identified multiple demand task information to help the user obtain the first target task that needs to be executed.

[0124] When the result of judging whether to enter the historical scene is no, the intent of the query is identified. If the intent identification result is a new demand scene, the second orchestration logic matching the new demand scene is executed, and the second orchestration logic is reloaded. At the same time, the scene conversion prompt information and the second target task in the second orchestration logic are returned to the dialogue interaction interface.

[0125] When the intent recognition result obtained is an intent recognition exception, that is, the intent recognition result is irrelevant to the selected intent recognition result, a reply message can be generated according to the second task in the second orchestration logic, and the user can be gradually guided to select the second target task to be executed.

[0126] Figure 8 A principle diagram of an interaction method according to another embodiment of the present disclosure is schematically shown.

[0127] like Figure 8As shown, the interaction method 800 of this embodiment can be an operation step performed by a computer front end. After obtaining the automatically or manually input query, an event stream request can be sent to the back end, and the query transmitted by the user can be detected. In the case of detecting that the query has not been transmitted, it can be determined whether it is a dialogue flow. In the case of determining that it is not a dialogue flow, it can return to the transmission detection step. In the case of determining that it is a dialogue flow, streaming rendering can be performed on the dialogue interaction interface.

[0128] If it is determined that the transmission has been completed, the text content of the query entered by the user can be rendered in the dialogue interaction interface, and the target task matching the query can be determined. If it is determined that there is a target task matching the query, the task component can be loaded and the example can be assembled, and the assembled example can be rendered into a target task window in the dialogue interaction interface, and if there is a user's instruction, the instruction can be sent to the backend so that the user can see the reply information and initiate the next dialogue. If no instruction is received, the operation can also be terminated so that the user can initiate the next dialogue based on the reply information.

[0129] It should be noted that Figure 7 The interactive methods and Figure 8 The interaction method executed by the backend shown can be applied to interact in devices such as computers to implement the interaction method provided by the embodiments of the present disclosure.

[0130] Fig. 9 The schematic diagram shows an architecture diagram of a front end for executing the interactive method according to an embodiment of the present disclosure.

[0131] like Fig. 9 As shown, the front end 900 may include a global state module 910, an instruction module 920, an SDK (Software Development Kit, software development kit) module and a GUI module 940. The instruction module 920 may include a global instruction unit, an instruction interpretation unit, and an instruction collection unit. The SDK module 930 may include a conversation software development kit (chat-SDK) instance and task components (Action slots), and the task components may include task components such as page example components, budget components, price components, and creative copywriting components. The GUI module 940 may include scene libraries such as a creation scene library, an overview scene library, a detail scene library, and a material scene library.

[0132] The global state module 910 can generate reply information in the dialogue interaction interface by calling the SDK module 930. For example, the target task window can be obtained by rendering the task component in the dialogue interaction interface. According to the resource delivery demand information input by the user, the SDK module 930 can request the GUI module for a scene library that matches the resource delivery demand information to obtain the arrangement logic.

[0133] For example, if the resource delivery demand information is: "I want to view a certain plan", the detail scene can be called and the corresponding content can be generated in the dialogue interaction interface.

[0134] For another example, if the resource placement demand information is: "I want to modify the creative idea for a certain plan", the material scene library can be called to generate the corresponding image or video.

[0135] The instruction module 920 may load the content in the scene library into the storage area or unload it from the storage area by parsing the loading instruction or the unloading instruction.

[0136] Fig.10 A block diagram of an interaction device according to an embodiment of the present disclosure is schematically shown.

[0137] like Fig.10 As shown, the interactive device 1000 includes: a dialogue interaction interface display module 1010 , an acquisition module 1020 , an execution result acquisition module 1030 and an execution result display module 1040 .

[0138] The dialogue interaction interface display module 1010 is used to display the dialogue interaction interface of the resource delivery platform.

[0139] The acquisition module 1020 is used to acquire the resource delivery demand information input into the dialogue interaction interface.

[0140] The execution result obtaining module 1030 is used to execute the arrangement logic matching the resource delivery demand information to obtain the execution result.

[0141] The execution result display module 1040 is used to display the execution result in the dialogue interaction interface.

[0142] According to an embodiment of the present disclosure, the execution result obtaining module includes: an intention recognition submodule and an execution result obtaining submodule.

[0143] The intent recognition submodule is used to perform intent recognition on resource placement demand information and obtain intent recognition results.

[0144] The execution result acquisition submodule is used to execute the orchestration logic that matches the intent recognition result to obtain the execution result.

[0145] According to an embodiment of the present disclosure, the intent recognition result includes a demand scenario.

[0146] Among them, the execution result acquisition submodule includes: a first target task determination unit and a first execution unit.

[0147] The first target task determining unit is used to determine at least one first target task from the first tasks of the first orchestration logic associated with the historical scenario when the demand scenario matches the historical scenario, and the orchestration logic includes the first orchestration logic.

[0148] The first execution unit is used to execute at least one first target task and obtain the first target task execution result, wherein the execution result includes the first target task execution result, and the historical scenario is determined according to the historical resource delivery demand information obtained in the historical time period.

[0149] According to an embodiment of the present disclosure, the intention recognition result also includes required task information.

[0150] Among them, the first target task determination unit includes a first target task determination subunit.

[0151] The first target task determination subunit is used to determine a first target task matching the required task information from the first orchestration logic.

[0152] According to an embodiment of the present disclosure, the intent recognition result includes a demand scenario.

[0153] Among them, the execution result acquisition submodule includes: a second orchestration logic determination unit, a second target task determination unit and a second execution unit.

[0154] The second orchestration logic determining unit is used to determine a second orchestration logic that matches the demand scenario when the demand scenario does not match the historical scenario, and the orchestration logic includes the second orchestration logic.

[0155] The second target task determining unit is configured to determine at least one second target task from the second tasks in the second orchestration logic.

[0156] The second execution unit is used to execute at least one second target task and obtain the execution result of the second target task, wherein the execution result includes the execution result of the second target task.

[0157] According to an embodiment of the present disclosure, the interaction device also includes a scene transition prompt information generation module.

[0158] The scene transition prompt information generation module is used to generate scene transition prompt information representing the required scene in the dialogue interaction interface.

[0159] According to an embodiment of the present disclosure, the interaction device further includes a scene transition inquiry information generation module.

[0160] The scene transition inquiry information generation module is used to generate scene transition inquiry information in the dialogue interaction interface.

[0161] According to an embodiment of the present disclosure, a demand scenario represents an intention for a resource delivery demand scenario, and a resource delivery demand scenario includes at least one of the following: a resource delivery strategy creation scenario, a resource delivery strategy modification scenario, and a resource delivery effect query scenario.

[0162] According to an embodiment of the present disclosure, the first execution unit or the second execution unit includes: a target task window generating subunit and a first task executing subunit.

[0163] The target task window generating subunit is used to generate a target task window corresponding to the first target task or the second target task in the dialogue interaction interface.

[0164] The first task execution subunit is used to respond to an editing operation on the target task window and execute the first target task or the second target task according to the editing operation.

[0165] According to an embodiment of the present disclosure, the editing operation includes a data editing operation.

[0166] Among them, the task execution subunit is further configured to: update the data corresponding to the data editing operation according to the target data attributes associated with the first target task or the second target task to obtain the target data; and execute the first target task or the second target task according to the target data.

[0167] According to an embodiment of the present disclosure, the resource delivery demand information also includes demand content information.

[0168] The first execution unit or the second execution unit includes: a second task execution subunit.

[0169] The second task execution subunit executes the first target task or the second target task according to the required content information.

[0170] According to an embodiment of the present disclosure, the execution result obtaining submodule further includes: an intention guidance information generating unit, a resource placement demand information acquiring unit and an orchestration logic executing unit.

[0171] The intention guidance information generation unit is used to generate intention guidance information related to resource delivery requirements in the dialogue interaction interface when the intention recognition result is an intention recognition exception.

[0172] The resource placement demand information acquisition unit is used to acquire new resource placement demand information corresponding to the intention guidance information.

[0173] The orchestration logic execution unit is used to execute the orchestration logic matching the new resource delivery demand information, wherein the intent recognition anomaly indicates that the current resource delivery demand information is irrelevant to the preset candidate intent recognition result.

[0174] According to an embodiment of the present disclosure, the interaction device further includes: a calling module and an execution degree determination module.

[0175] The calling module is used to call the deep learning algorithm to process the execution result and obtain the processing result.

[0176] The execution degree determination module is used to determine the execution degree of the task performed in the current round of dialogue according to the processing result.

[0177] According to an embodiment of the present disclosure, the interaction device further includes: a locking module and a releasing module.

[0178] A locking module, configured to lock the information input box in the dialogue interaction interface when detecting that the input of the resource delivery demand information input into the dialogue interaction interface is completed, so that the information input box is in a locked state; and

[0179] The unlocking module is used to unlock the locked state of the information input box when a reply message is generated in the dialogue interaction interface.

[0180] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0181] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0182] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method as described above.

[0183] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the method as described above.

[0184] Fig.11A schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0185] like Fig.11 As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0186] A number of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0187] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1101 performs the various methods and processes described above, such as interactive methods. For example, in some embodiments, the interactive method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the interactive method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the interactive method in any other appropriate manner (e.g., by means of firmware).

[0188] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0189] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0190] 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 equipment, 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.

[0191] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0192] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by 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), and the Internet.

[0193] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0194] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0195] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An interactive method, comprising: Display the interactive dialogue interface of the resource delivery platform; Acquiring resource delivery demand information input into the dialogue interaction interface; Performing intent recognition on the resource delivery demand information to obtain an intent recognition result, wherein the intent recognition result includes a demand scenario, wherein the demand scenario represents the intention for the resource delivery demand scenario, and the resource delivery demand scenario includes at least one of the following: a resource delivery strategy creation scenario, a resource delivery strategy modification scenario, and a resource delivery effect query scenario; Execute the orchestration logic matching the intention recognition result to obtain an execution result, wherein the orchestration logic includes a second orchestration logic matching the demand scenario, and the execution result includes a second target task execution result of a second target task in the second orchestration logic, wherein the second target task execution result is obtained by executing the second target task according to the second editing operation in response to a second editing operation on a target task window corresponding to the second target task, and the target task window corresponding to the second target task is in an execution completion state based on the second task execution result of at least one second task in the second orchestration logic, and is displayed on the dialog interaction interface; as well as The execution result is displayed in the dialog interaction interface.

2. The method according to claim 1, in, The executing the arrangement logic matching the intention recognition result to obtain the execution result includes: In a case where the demand scenario matches the historical scenario, determining at least one first target task from a first task of a first orchestration logic associated with the historical scenario, the orchestration logic including the first orchestration logic; and Execute at least one of the first target tasks to obtain a first target task execution result, wherein the execution result includes the first target task execution result, and the historical scenario is determined based on historical resource delivery demand information obtained in a historical time period.

3. The method according to claim 2, wherein: The intention recognition result also includes required task information; Wherein, determining at least one first target task from the first task of the first arrangement logic associated with the historical scene comprises: A first target task matching the required task information is determined from the first orchestration logic.

4. The method according to claim 1, in, The executing the arrangement logic matching the intention recognition result to obtain the execution result includes: In a case where the demand scenario does not match the historical scenario, determining a second orchestration logic that matches the demand scenario, the orchestration logic including the second orchestration logic; Determine at least one second target task from the second tasks of the second orchestration logic; and Execute at least one of the second target tasks to obtain a second target task execution result.

5. The method according to claim 4, further comprising: A scene conversion prompt information representing the required scene is generated in the dialogue interaction interface.

6. According to the method of claim 5, before generating the scene transition prompt information, the interaction method further comprises: Generate scene transition inquiry information in the dialogue interaction interface.

7. The method according to claim 2, wherein: The performing of at least one of the first target tasks comprises: Generating a target task window corresponding to the first target task in the dialogue interaction interface; In response to a first editing operation on the target task window corresponding to the first target task, the first target task is executed according to the first editing operation.

8. The method according to claim 7, wherein: The first editing operation includes a first data editing operation; The performing of the first target task according to the first editing operation includes: updating data corresponding to the first data editing operation according to a target data attribute associated with the first target task to obtain target data; and The first target task is performed according to the target data.

9. The method according to claim 1, wherein: The execution result of the second target task is obtained by executing the second target task based on target data, and the target data is obtained by updating data corresponding to a second data editing operation based on target data attributes associated with the second target task, and the second editing operation includes the second data editing operation.

10. The method according to claim 2, wherein: The resource delivery demand information also includes demand content information; The performing of the first target task includes: Execute the first target task according to the required content information.

11. The method according to claim 4, wherein: The resource delivery demand information also includes demand content information; The performing of the second target task includes: Execute the second target task according to the required content information.

12. The method according to claim 1, wherein: The execution of the orchestration logic matching the resource delivery demand information further includes: In the case where the intention recognition result is an intention recognition exception, generating intention guidance information related to resource delivery requirements in the dialogue interaction interface; Acquire new resource delivery demand information corresponding to the intention guidance information; Execute the orchestration logic that matches the new resource delivery demand information, wherein the intent recognition anomaly represents that the current resource delivery demand information is irrelevant to the preset candidate intent recognition result.

13. The method according to claim 1, further comprising: Calling a deep learning algorithm to process the execution result to obtain a processing result; The execution degree of the task executed in the current round of dialogue is determined according to the processing result.

14. The method according to claim 1, further comprising: When it is detected that the input of the resource delivery demand information input into the dialogue interaction interface is completed, locking the information input box in the dialogue interaction interface so that the information input box is in a locked state; as well as When a reply message is generated in the dialog interaction interface, the lock state of the message input box is unlocked.

15. An interactive device, comprising: A dialogue interaction interface display module is used to display the dialogue interaction interface of the resource delivery platform; An acquisition module, used to acquire resource delivery demand information input into the dialogue interaction interface; An execution result obtaining module is used to execute the arrangement logic matching the resource delivery demand information to obtain the execution result; as well as An execution result display module, used to display the execution result in the dialogue interaction interface; Wherein, the execution result obtaining module includes: An intention recognition submodule is used to perform intention recognition on the resource delivery demand information to obtain an intention recognition result, wherein the intention recognition result includes a demand scenario, wherein the demand scenario represents the intention for the resource delivery demand scenario, and the resource delivery demand scenario includes at least one of the following: a resource delivery strategy creation scenario, a resource delivery strategy modification scenario, and a resource delivery effect query scenario; An execution result acquisition submodule is used to execute the orchestration logic matching the intention recognition result to obtain an execution result, wherein the orchestration logic includes a second orchestration logic matching the demand scenario, and the execution result includes a second target task execution result of the second target task in the second orchestration logic, wherein the second target task execution result is obtained in response to a second editing operation on a target task window corresponding to the second target task, and the second target task is executed according to the second editing operation, and the target task window corresponding to the second target task is in an execution completion state based on the second task execution result of at least one second task in the second orchestration logic, and is displayed on the dialogue interaction interface.

16. The device according to claim 15, in, The execution result obtaining submodule includes: a first target task determining unit, configured to determine at least one first target task from first tasks of a first orchestration logic associated with the historical scenario when the demand scenario matches the historical scenario, the orchestration logic including the first orchestration logic; and The first execution unit is used to execute at least one of the first target tasks and obtain a first target task execution result, wherein the execution result includes the first target task execution result, and the historical scenario is determined based on historical resource delivery demand information obtained in a historical time period.

17. The device according to claim 16, wherein: The intention recognition result also includes required task information; Wherein, the first target task determination unit includes: The first target task determining subunit is used to determine a first target task matching the required task information from the first orchestration logic.

18. The device according to claim 15, in, The execution result obtaining submodule includes: A second orchestration logic determining unit, configured to determine a second orchestration logic matching the demand scenario when the demand scenario does not match the historical scenario, the orchestration logic including the second orchestration logic; A second target task determining unit, configured to determine at least one second target task from the second tasks in the second orchestration logic; and The second execution unit is used to execute at least one of the second target tasks to obtain a second target task execution result, wherein the execution result includes the second target task execution result.

19. The apparatus according to claim 18, further comprising: The scene transition prompt information generation module is used to generate scene transition prompt information representing the required scene in the dialogue interaction interface.

20. The device according to claim 19, before generating the scene transition prompt information, the interaction device further comprises: The scene transition inquiry information generation module is used to generate scene transition inquiry information in the dialogue interaction interface.

21. The device according to claim 16, wherein: The first execution unit comprises: a target task window generating subunit, configured to generate a target task window corresponding to the first target task in the dialog interaction interface; The first task execution subunit is configured to respond to a first editing operation on the target task window corresponding to the first target task and execute the first target task according to the first editing operation.

22. The device according to claim 21, wherein The first editing operation includes a first data editing operation; Wherein, the first task execution subunit is further configured as follows: updating data corresponding to the first data editing operation according to a target data attribute associated with the first target task to obtain target data; and The first target task is performed according to the target data.

23. The device according to claim 15, wherein: The execution result of the second target task is obtained by executing the second target task based on target data, and the target data is obtained by updating data corresponding to a second data editing operation based on target data attributes associated with the second target task, and the second editing operation includes the second data editing operation.

24. The device according to claim 16, wherein: The resource delivery demand information also includes demand content information; Wherein, the first execution unit includes: The second task execution subunit is used to execute the first target task according to the required content information.

25. The apparatus of claim 18, wherein: The resource delivery demand information also includes demand content information; Wherein, the second execution unit is further configured as: Execute the second target task according to the required content information.

26. The device according to claim 15, wherein: The execution result obtaining submodule also includes: An intention guidance information generating unit, configured to generate intention guidance information related to resource delivery requirements in the dialogue interaction interface when the intention recognition result is an intention recognition abnormality; A resource placement demand information acquisition unit, used to acquire new resource placement demand information corresponding to the intention guidance information; An orchestration logic execution unit is used to execute an orchestration logic that matches the new resource delivery demand information, wherein the intent recognition anomaly represents that the current resource delivery demand information is irrelevant to a preset candidate intent recognition result.

27. The apparatus of claim 15, further comprising: A calling module, used for calling a deep learning algorithm to process the execution result and obtain a processing result; The execution degree determination module is used to determine the execution degree of the task performed in the current round of dialogue according to the processing result.

28. The apparatus of claim 15, further comprising: A locking module, configured to lock the information input box in the dialogue interaction interface when detecting that the input of the resource delivery demand information in the dialogue interaction interface is completed, so that the information input box is in a locked state; as well as The unlocking module is used to unlock the locked state of the information input box when a reply message is generated in the dialogue interaction interface.

29. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 14.

30. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-14.

31. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 14.

Images