Information processing method, system, equipment and medium

Abstract

The invention provides an information processing method, system and device and a medium, which are applied to a server of a digital assistant, and the method comprises the following steps: receiving a first request which is sent by a client of the digital assistant and is associated with a first task theme; according to the first request, meta-information of the first task theme is determined, and the meta-information of the first task theme is stored in a server side of the digital assistant; and processing the first request according to the meta-information of the first task theme. According to the method, the server side of the digital assistant can support functions related to the task theme, scenario of the digital assistant is achieved, and then the use scenario of the digital assistant is expanded.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to an information processing method, system, electronic device, and computer-readable storage medium. Background Art

[0002] With the rapid development of computer technology, digital assistants have emerged as the times require. Digital assistants usually have natural language processing capabilities, and users can interact with digital assistants through human-computer conversations.

[0003] Specifically, users can send request information through the client of the digital assistant. The server of the digital assistant processes the request information, generates response information, and returns the response information to the client of the digital assistant, thereby realizing human-computer conversation.

[0004] However, most users are difficult to actively explore the rich usage scenarios of digital assistants. How to enrich the user experience of using digital assistants has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides an information processing method. This method can implement a series of functions of scenario conversation in digital assistants. This application also provides a system, an electronic device, a computer-readable storage medium, and a computer program product corresponding to the above method.

[0006] In a first aspect, this application provides an information processing method, which is applied to the server of a digital assistant. The method includes:

[0007] Receiving a first request associated with a first task theme sent by the client of the digital assistant;

[0008] Determining meta-information of the first task theme according to the first request, where the meta-information of the first task theme is stored in the server of the digital assistant;

[0009] Processing the first request according to the meta-information of the first task theme.

[0010] In a second aspect, this application provides an information processing system, and the system includes:

[0011] A communication module, configured to receive a first request associated with a first task theme sent by the client of the digital assistant;

[0012] A determining module, configured to determine meta-information of the first task theme according to the first request, where the meta-information of the first task theme is stored in the server of the digital assistant;

[0013] A processing module, configured to process the first request according to the meta-information of the first task theme.

[0014] In a third aspect, the present application provides an electronic device, which includes a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory so that the electronic device executes the information processing method as described in the first aspect or any implementation manner of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and the instructions direct an electronic device to execute the information processing method as described in the above first aspect or any implementation manner of the first aspect.

[0016] In a fifth aspect, the present application provides a computer program product including instructions, which, when running on an electronic device, cause the electronic device to execute the information processing method as described in the above first aspect or any implementation manner of the first aspect.

[0017] Based on the implementation manners provided in the above aspects of the present application, further combinations can be made to provide more implementation manners.

[0018] From the above technical solutions, it can be seen that the present application has the following advantages:

[0019] The present application provides an information processing method, which is applied to the server side of a digital assistant. The server side of the digital assistant receives a first request associated with a first task theme sent by the client side of the digital assistant, and determines the meta information of the first task theme according to the first request, where the meta information of the first task theme is stored in the server side of the digital assistant. Then, the server side of the digital assistant processes the first request according to the meta information of the first task theme.

[0020] In this method, by storing the meta information of the task theme in the server side of the digital assistant, when the server side of the digital assistant receives a request associated with the task theme, it can use the meta information of the task theme to process the request. In this way, the server side of the digital assistant can support functions related to the task theme, realize the sceneization of the digital assistant, and further expand the usage scenarios of the digital assistant. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below.

[0022] Figure 1 It is a schematic diagram of the architecture of an information processing system provided by an embodiment of the present application;

[0023] Figure 2 It is a schematic flowchart of an information processing method provided by an embodiment of the present application;

[0024] Figure 3 A schematic flow chart of creating a task theme provided by an embodiment of the present application;

[0025] Figure 4 A schematic flow chart of editing a task theme provided by an embodiment of the present application;

[0026] Figure 5 A schematic flow chart of deactivating a task theme provided by an embodiment of the present application;

[0027] Figure 6 A schematic flow chart of starting a new session provided by an embodiment of the present application;

[0028] Figure 7 A schematic flow chart of sharing a task theme provided by an embodiment of the present application;

[0029] Figure 8 A schematic flow chart of joining a task theme provided by an embodiment of the present application;

[0030] Figure 9 A schematic flow chart of human - machine dialogue provided by an embodiment of the present application;

[0031] Figure 10 A schematic flow chart of human - machine dialogue provided by an embodiment of the present application;

[0032] Figure 11 A schematic structural diagram of an information processing system provided by an embodiment of the present application;

[0033] Figure 12 A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0034] The terms "first" and "second" in the embodiments of the present application are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0035] First, some technical terms involved in the embodiments of the present application are introduced.

[0036] A digital assistant, also known as a dialogue robot or chat robot, usually has natural language processing capabilities, and users can interact with the digital assistant through human - machine dialogue.

[0037] In this application, the concept of task theme is proposed. Task theme, also known as dialogue scenario, can be understood as the subject of the human-computer dialogue between the user and the digital assistant. Taking into account that it is difficult for most users to actively explore the rich usage scenarios of digital assistants, digital assistants can provide users with targeted guidance. Moreover, in the related art, when users need to use digital assistants to perform tasks in different scenarios, users often need to interact with different digital assistants (that is, each digital assistant is only used to perform tasks in one scenario), which can cause information to not be saved in one place, and these multiple digital assistants cannot share information, reducing the flexibility of the digital assistant's interactive function.

[0038] Therefore, the digital assistant can support users to conduct human-computer dialogue for specific scenarios. For example, the digital assistant can support users to select a task topic according to actual needs and start a dialogue under the task topic (also known as starting a scene dialogue).

[0039] A task theme is configured with corresponding configuration information to perform tasks of corresponding types. The configuration information may include at least one of the following: task theme setting information and plug-in information. The task theme setting information is used to describe information related to the corresponding task theme, and the plug-in information indicates at least one plug-in used to perform tasks under the corresponding task theme.

[0040] In some embodiments, the task theme setting information can be used to construct a prompt input (prompt) to be provided to the language model used under the corresponding task theme, and the reply information for the user can be determined based on the output of the language model. The task theme setting information can include at least one of the following: a description of the corresponding type of task, a digital assistant reply style under the task theme, a definition of the workflow to be executed under the corresponding task theme, or a definition of the digital assistant reply format under the corresponding task theme.

[0041] In other embodiments, the configuration information of a task theme may include, in addition to task theme setting information and plug-in information, at least one of the following: an indication of a selected language model, which is called to determine a reply to the user under the corresponding task theme; task theme guidance information, which is presented to the user after the corresponding task theme is selected; and at least one recommended question for the digital assistant, which is presented to the user for selection after the corresponding task theme is selected.

[0042] In response to receiving a selection operation for a first task topic among at least one task topic, the interaction between the user and the digital assistant can be performed based on the configuration information of the first task topic in the interaction page between the user and the digital assistant to realize the selection of the task topic (also called scene selection).

[0043] For conversations initiated by the user under different task topics, the digital assistant can handle them differently. Specifically, for conversations initiated by the user under different task topics, the prompt information in the language model utilized by the digital assistant can be different, and the prompt information can include descriptive information related to the task topic. For example, when the task topic is the "schedule topic", the prompt information can include descriptive information related to the schedule (such as function description information related to the schedule, parameter description information, etc.).

[0044] In addition, for conversations initiated by the user under different task topics, the processing tools invoked by the digital assistant can also be different, and the processing tools can include tools related to the task topic. For example, when the task topic is the "schedule topic", the processing tool invoked by the digital assistant can be a schedule plugin. Another example is that when the task topic is the "document topic", the processing tool invoked by the digital assistant can be a document plugin.

[0045] After the user selects the first task topic, the first task topic can be initiated in the interaction page with the digital assistant. For example, the interaction page can present a dividing line between the first task topic and the previous task topic, and in response to the interaction between the user and the digital assistant within the first task topic, the identifier of the first task topic is presented in the associated area of the dividing line, thereby achieving the distinction of different task topics (also referred to as different scenarios).

[0046] In the related art, before initiating a conversation with the digital assistant, the user needs to select the processing tool (i.e., the plugin) by themselves. However, the above method requires the user to have a certain understanding of different plugins and is extremely error-prone. In the conversation under the task topic, by configuring the plugin information in the task topic, the threshold for the user to use the digital assistant is reduced, and the user's operation is simplified.

[0047] However, how to implement a series of functions of scenario conversations in the digital assistant has become an urgent problem to be solved.

[0048] In view of this, the present application provides an information processing method. This method is applied to the server of the digital assistant. The server of the digital assistant receives a first request associated with the first task topic sent by the client of the digital assistant, determines the meta information of the first task topic according to this first request, where the meta information of the first task topic is stored in the server of the digital assistant, and then, the server of the digital assistant processes the first request according to the meta information of the first task topic.

[0049] In this method, by storing the meta-information related to the task topic in the server of the digital assistant, when the server of the digital assistant receives a request associated with the task topic, it can process the request using the meta-information of the task topic. In this way, the server of the digital assistant can support functions related to the task topic, realize the scenario-based digital assistant, and further expand the usage scenarios of the digital assistant.

[0050] To facilitate the understanding of the technical solutions provided by the embodiments of the present application, the following will be described with reference to the accompanying drawings.

[0051] See Figure 1 The schematic diagram of the architecture of an information processing system shown in the figure. The information processing system 10 includes the client 101 of the digital assistant, the server 102 of the digital assistant, the third server 103, and the management server 104.

[0052] The client 101 of the digital assistant can have a human-computer conversation with the server 102 of the digital assistant. In some embodiments, the digital assistant can be an independent software system, and the client 101 of the digital assistant can have a human-computer conversation with the independent server 102 of the digital assistant. In other embodiments, the digital assistant can also be deployed in other systems (such as a business platform), and the digital assistant can be used as a system module to provide a human-computer conversation function in other systems. The client 101 of the digital assistant can have a human-computer conversation with the server 102 of the digital assistant module.

[0053] Specifically, the client 101 of the digital assistant can have a human-computer conversation with the server 102 of the digital assistant in different modes. For example, the client 101 of the digital assistant can have a human-computer conversation with the server 102 of the digital assistant in a dialogue mode, or in a floating window mode. Among them, the dialogue mode can be a human-computer conversation in the dialogue page provided by the server 102 of the digital assistant, and the floating window mode can be a human-computer conversation in other system modules (such as a document module) through the floating window component provided by the server 102 of the digital assistant.

[0054] The server 102 of the digital assistant can maintain the human-computer conversation logic. Among them, the human-computer conversation logic can be understood as the logic related to the interaction process of the human-computer conversation. For example, the logic of providing guiding words to the client 101 of the digital assistant, the logic of having a human-computer conversation in the form of "one question and one answer", etc.

[0055] The server 102 of the digital assistant can provide multiple task topics so that the client 101 of the digital assistant can conduct human-machine conversations under specific task topics. In the embodiments of the present application, the meta-information of the task topic is stored in the server 102 of the digital assistant, where the meta-information of the task topic can be understood as the basic information related to the attributes of the task topic. By maintaining the human-machine conversation logic and storing the meta-information of the task topic in the server 102 of the digital assistant, the server 102 of the digital assistant can implement functions related to the task topic. Moreover, when changes to the human-machine conversation logic are involved in certain task topics, developers can directly make changes in the server 102 of the digital assistant without involving other servers.

[0056] The third server 103 can be used to process the request information during the human-machine conversation of the client 101 of the digital assistant. Considering that the request information of the client 101 of the digital assistant during the human-machine conversation is natural language content, therefore, the third server 103 can have natural language processing capabilities.

[0057] The specific processing logic for the third server 103 to process the request information can be related to the creator of the task topic. It can be understood that during the process of creating the task topic, the creator of the task topic can select from the set of natural language processing capabilities provided by different third servers 103 (such as language models for natural language processing, plugins related to the task topic, etc.). In this way, during the human-machine conversation between the client 101 of the digital assistant and the server 102 of the digital assistant, the server 102 of the digital assistant can utilize the natural language processing capabilities of the selected third server 103 for natural language processing, enabling the third server 103 to generate response information, thereby completing the human-machine conversation.

[0058] In some embodiments, the third server 103 can be the processing server of the business platform, and this processing server can be used to process natural language content. That is to say, when the server 102 of the digital assistant is deployed on the business platform, the business platform can provide a set of natural language processing capabilities, and the creator of the task topic can select from the set of natural language processing capabilities provided by the business platform. In this way, during the human-machine conversation, the server 102 of the digital assistant can use the processing server of the business platform to process natural language content.

[0059] In some other embodiments, the third server 103 may be the server of a system module in the business platform. It can be understood that some system modules in the business platform can provide functions related to natural language processing. For example, the document module can provide functions such as summarizing, optimizing, and translating document content. At this time, the system modules in the business platform can provide a set of natural language processing capabilities. The creator of the task topic can select from the set of natural language processing capabilities provided by the system modules in the business platform. In this way, during the human-machine dialogue process, the server 102 of the digital assistant can use the server of the system module in the business platform to process natural language content.

[0060] In some other embodiments, the third server 103 may be an external server. Taking the external server as a low-code development platform (application platform as a service, aPaaS) for illustration, the low-code development platform can provide a set of natural language processing capabilities. The creator of the task topic can select from the set of natural language processing capabilities provided by the low-code development platform. In this way, during the human-machine dialogue process, the server 102 of the digital assistant can use the external server to process natural language content.

[0061] The management server 104 can be used to manage the relevant information of the human-machine dialogue under the task topic. For example, the management server 104 can review the creation of a new task topic. For another example, the management server 104 can manage the client version that provides the task topic. For yet another example, the management server 104 can manage the visibility of the topic dialogue (such as tenant visibility, sharing visibility, etc.).

[0062] The advantages of the information processing system architecture provided in the embodiments of the present application will be described below. In another architecture different from the system architecture provided in the embodiments of the present application, the meta-information of the task topic is stored in the management server. Since the meta-information of the task topic can be quickly updated and iterated, the human-machine dialogue logic will also change frequently. In this architecture, the human-machine dialogue logic is controlled by the server of the digital assistant, and the meta-information of the task topic is stored in the management server. Therefore, when the meta-information of the task topic changes and the human-machine dialogue logic needs to be modified accordingly, the developers responsible for the server of the digital assistant and the developers responsible for the management server need to jointly design the solution and develop the code. In the architecture of the information processing system provided in the embodiments of the present application, the server of the digital assistant not only controls the human-machine dialogue logic but also stores the meta-information of the task topic. Therefore, when the meta-information of the task topic changes and the human-machine dialogue logic needs to be modified accordingly, only the developers responsible for the server of the digital assistant need to handle it, with lower development costs and higher efficiency.

[0063] In another architecture that is different from the system architecture provided in the embodiment of the present application, the meta-information of the task subject is stored in the processing server of the business platform. At this time, the processing flow involved in the human-computer dialogue between the client of the digital assistant and the server of the digital assistant can be controlled by the processing server of the business platform, and the server of the digital assistant can only focus on the interaction process with the client of the digital assistant (for example, receiving request information, sending reply information, etc.). In this architecture, it is necessary to design a universal agent (Agent) protocol to adapt to different third servers, and the development cost is relatively high. In the architecture of the information processing system provided in the embodiment of the present application, the server of the digital assistant is used to conduct human-computer dialogue with the client of the digital assistant, and the third server is used to process the request information in the human-computer dialogue process, decoupling the two and improving the rationality of the information processing system architecture.

[0064] See also Figure 2 The embodiment of the present application provides a flow chart of an information processing method, which can be applied to the server of a digital assistant. The method specifically includes:

[0065] S201: Receive a first request associated with a first task topic sent by a client of a digital assistant.

[0066] The task theme, also known as the dialogue scenario, can be understood as the theme or scenario of the human-computer dialogue between the digital assistant client and the digital assistant server. The digital assistant client can select the task theme before the dialogue starts. Through the selection of the task theme by the digital assistant client, the digital assistant server can conduct a targeted human-computer dialogue under the task theme selected by the user, thereby improving the accuracy of the response.

[0067] The task topic can be built-in to the server of the digital assistant, that is, pre-configured by the developer responsible for the server of the digital assistant, or it can be created by the creator.

[0068] The following takes the first task topic as an example to introduce the creation process of the task topic in the embodiment of the present application. The server of the digital assistant receives the creation request of the first task topic, extracts the meta information of the first task topic from the creation request, and creates the first task topic according to the meta information of the first task topic and the sender of the creation request.

[0069] Among them, the sender of the creation request can be the client of the digital assistant or the second server, and the second server can be understood as an external third-party server. In other words, in an embodiment of the present application, it supports users of digital assistants (i.e., clients of digital assistants) and external applications (i.e., third-party servers) to create task topics. When the user of the digital assistant has a need for scene dialogue, he can create task topics by himself to enrich the scenarios in which users use the digital assistant.

[0070] When the sender of the creation request is the client of the digital assistant, refer to Figure 3 The schematic flow diagram of creating a task topic shown below. The client of the digital assistant can trigger a creation request for the first task topic. In this creation request, information of the client of the digital assistant and information related to the first task topic (such as information of the third server for processing request information under the first task topic) can be carried. When the server of the digital assistant is deployed on the business platform and the third server is the processing server of the business platform, the server of the digital assistant can obtain the natural language processing capability set from the third server and return the natural language processing capability set to the client of the digital assistant for the client of the digital assistant to select.

[0071] When the sender of the creation request is the third server, the third server can send a creation request for the first task topic by calling the creation interface of the server of the digital assistant. In this creation request, information of the third server and information related to the first task topic (such as information of the third server for processing request information under the first task topic) can be carried.

[0072] In some embodiments, before the server of the digital assistant extracts the meta-information of the first task topic, the server of the digital assistant can also authenticate the creation request for the first task topic. For example, the server of the digital assistant can authenticate the sender of the creation request to determine whether the sender of the creation request has the permission to create the task topic.

[0073] Then, after the authentication passes, the server of the digital assistant can extract the meta-information of the first task topic. The meta-information of the first task topic can be understood as the basic information related to the attributes of the task topic. In some possible implementation manners, the meta-information of the first task topic can include at least one of the following: the identity information (identity, ID) of the first task topic, the type information of the task topic, and the storage location information of the task topic. In this way, the server of the digital assistant can generate the correspondence between the first task topic and the sender of the creation request to indicate that the first task topic is created by the sender of the creation request of the first task topic. In addition, when the server of the digital assistant is deployed on the business platform and the third server is the processing server of the business platform, the third server can also create a first task topic entity to indicate the natural language ability of the third server used under the first task topic.

[0074] Furthermore, after the creation of the first task topic is completed, the creator of the first task topic can also edit the first task topic. When specifically implemented, such as Figure 4As shown, the server of the digital assistant can receive an editing request for the first task topic sent by the creator of the first task topic, and modify the meta-information of the first task topic according to the editing request.

[0075] In addition, when the server of the digital assistant is deployed on the business platform and the third server is the processing server of the business platform, the server of the digital assistant can also send the editing request for the first task topic to the third server, so that the third server can modify the first task topic entity.

[0076] In some possible implementation manners, before modifying the meta-information of the first task topic, the server of the digital assistant can also perform authentication for the editing request. For example, the server of the digital assistant can authenticate the first task topic to determine whether the first task topic supports editing.

[0077] In addition, the creator of the first task topic can also deactivate the first task topic. Specifically, as Figure 5 shown, the server of the digital assistant can receive a deactivation request for the first task topic sent by the creator of the first task topic, and according to the deactivation request, delete the meta-information of the first task topic, and delete the corresponding relationship between the first task topic and the client of the digital assistant using the first task topic.

[0078] In some embodiments, when the server of the digital assistant deletes the meta-information of the first task topic, it can adopt the method of soft deletion. Among them, soft deletion can be understood as that the information is not actually deleted from the database, but through some processing means, the information to be deleted is hidden. For example, the database of the server of the digital assistant can include a field "whether deleted", and by modifying the field value of this field corresponding to the meta-information of the first task topic to yes, the meta-information of the first task topic is hidden in the database to achieve the effect of soft deletion.

[0079] In addition, when the server of the digital assistant is deployed on the business platform and the third server is the processing server of the business platform, the server of the digital assistant can also send the deactivation request for the first task topic to the third server, so that the third server can delete the first task topic entity.

[0080] In some possible implementation manners, before deleting the meta-information of the first task topic and deleting the corresponding relationship between the first task topic and the client of the digital assistant using the first task topic, the server of the digital assistant can also perform authentication for the deletion request. For example, the server of the digital assistant can authenticate the sender of the deletion request to determine whether the sender of the deletion request has the deletion permission for the first task topic.

[0081] The first request associated with the first task topic can be understood as a request related to the first task topic among multiple task topics. For example, the first request may include a request from the client of the digital assistant to start a first session under the first task topic, a sharing request from the client of the digital assistant for the first task topic, an addition request from the client of the digital assistant for the first task topic, an information input request from the client of the digital assistant under the first task topic, etc.

[0082] S202: Determine the meta-information of the first task topic according to the first request.

[0083] In the embodiment of the present application, the meta-information of the first task topic is stored in the server of the digital assistant. Therefore, after the server of the digital assistant receives the first request associated with the first task topic, it can quickly determine the meta-information of the first task topic for subsequent processing using the meta-information of the first task topic.

[0084] S203: Process the first request according to the meta-information of the first task topic.

[0085] Since the first request is associated with the first task topic, the server of the digital assistant can process the first request according to the meta-information of the first task topic, thereby implementing the related functions under the first task topic.

[0086] For example, when the first request is a request from the client of the digital assistant to start a first session under the first task topic, the server of the digital assistant can bind the first task topic and the first session by processing the first request. For another example, when the first request is a sharing request from the client of the digital assistant for the first task topic, the server of the digital assistant can generate a link for task topic sharing by processing the first request. For yet another example, when the first request is an addition request from the first client of the digital assistant for the first task topic, the server of the digital assistant can add the first task topic to the second client of the digital assistant by processing the first request. For still another example, when the first request is an information input request from the client of the digital assistant under the first task topic, the server of the digital assistant can return a reply message by processing the first request.

[0087] Based on the above description, the embodiment of the present application provides an information processing method. This method is applied to the server of the digital assistant. The server of the digital assistant receives a first request sent by the client of the digital assistant and associated with the first task topic, determines the meta-information of the first task topic according to this first request, where the meta-information of the first task topic is stored in the server of the digital assistant, and then the server of the digital assistant processes the first request according to the meta-information of the first task topic.

[0088] In this method, by storing the meta-information related to the task topic in the server of the digital assistant, when the server of the digital assistant receives a request associated with the task topic, it can process the request using the meta-information of the task topic. In this way, the server of the digital assistant can support functions related to the task topic, realize the scene-based digital assistant, and further expand the usage scenarios of the digital assistant.

[0089] The following will elaborate on the process of the server of the digital assistant processing the first request for different first requests.

[0090] In some embodiments, the first request associated with the first task topic may be a request for the client of the digital assistant to start a session under the first task topic. Specifically, when implemented, as Figure 6 shown, the server of the digital assistant can respond to the call request of the client of the digital assistant for the first interface and receive the request to start the first session under the first task topic.

[0091] That is to say, when the client of the digital assistant wants to start a new session (also known as a new topic), the client of the digital assistant can request by calling the first interface (such as the newtopic interface), and by carrying the identifier of the first task topic in the call request for the first interface. In this way, the server of the digital assistant can determine the meta-information of the first task topic through the identifier of the first task topic.

[0092] Next, the server of the digital assistant can generate the correspondence between the first task topic and the first session according to the meta-information of the first task topic. It can be understood that when the client of the digital assistant starts a new session under the first task topic, the server of the digital assistant can bind the first task topic to the started first session. For example, it binds the scene_id of the first task topic to the session_id of the first session to clarify the task topic to which the current session belongs. Since the client of the digital assistant requests to start a session by calling the first interface, the client of the digital assistant does not need to perceive the information related to the first session, saving the computing resources of the client of the digital assistant.

[0093] In other embodiments, the first request associated with the first task topic may be a sharing request of the client of the digital assistant for the first task topic. As Figure 7 shown, the client of the digital assistant can generate a sharing request for the first task topic in response to the triggering operation of the sharing control. It can be understood that the sharing request may carry the identifier of the first task topic, and the server of the digital assistant can determine the meta-information of the first task topic through the identifier of the first task topic.

[0094] Next, the server of the digital assistant can generate a first token based on the meta-information of the first task topic and return the first token to the client of the digital assistant. Among them, the link indicated by the first token (token) can be used to add the first task topic.

[0095] That is to say, when the client of the digital assistant wants to share the first task topic with other clients, the server of the digital assistant can, in response to the sharing request, generate a first token by using the meta-information of the first task topic, so that the client of the digital assistant can send the first token to other clients to achieve the sharing of the task topic. In this way, the client of the digital assistant does not need to generate the first token, saving the computing resources of the client of the digital assistant. Moreover, only when the server of the digital assistant receives the sharing request will it generate the first token, saving the storage resources of the client of the digital assistant.

[0096] In some possible implementation manners, the first token can be generated based on a symmetric encryption and decryption algorithm, and the key of the symmetric encryption and decryption algorithm can be encrypted and stored in the distributed transaction framework. When the key is needed to decrypt the first token, the server of the digital assistant can obtain the key in real time, saving the storage cost of the server of the digital assistant.

[0097] In some embodiments, as Figure 8 shown, the first client of the digital assistant sends the first token to the second client of the digital assistant, that is, the first client of the digital assistant shares the first task topic to the second client of the digital assistant. After receiving the first token sent by the first client of the digital assistant, the second client of the digital assistant can add the first task topic to the second client. At this time, the server of the digital assistant can, in response to the call request of the second client of the digital assistant for the second interface, receive the addition request for the first task topic. Among them, the call request for the second interface can be triggered by generating the first token.

[0098] That is to say, when the second client of the digital assistant wants to add the first task topic, the second client of the digital assistant can trigger the first token, call the second interface of the server of the digital assistant, and send an addition request for the first task topic to the server of the digital assistant. It can be understood that the addition request can carry the identifier of the first task topic, and the server of the digital assistant can determine the meta-information of the first task topic through the identifier of the first task topic.

[0099] Next, the server of the digital assistant can generate the correspondence between the second client of the digital assistant and the first task topic according to the meta-information of the first task topic. In this way, by generating the correspondence between the second client and the first task topic in the server of the digital assistant, it is indicated that the task topic of the second client of the digital assistant includes the first task topic, realizing the addition of the task topic.

[0100] In some other embodiments, the first request associated with the first task topic may be an information input request of the client of the digital assistant under the first task topic. When specifically implemented, as Figure 9 shown, the server of the digital assistant can receive the information input request of the client of the digital assistant under the first task topic and obtain the first request information sent by the client of the digital assistant.

[0101] That is to say, when the client of the digital assistant wants to send request information to the server of the digital assistant for a human-machine conversation, the server of the digital assistant can obtain the first request information for subsequent processing of the first request information. It can be understood that the first request information is usually natural language content.

[0102] Next, the server of the digital assistant can determine the third server for processing the request information under the first task topic according to the meta-information of the first task topic, send the first request information to the third server, receive the reply information returned by the third server, and send the reply information to the client of the digital assistant.

[0103] Since the servers for processing request information may be different under different task topics. Therefore, the server of the digital assistant can determine the corresponding third server according to the meta-information of the first task topic through the correspondence relationship, so that the third server processes the first request information. For example, the third server uses a language model to perform semantic recognition on the first request information and generates a reply information according to the semantic recognition result. By the third server returning the reply information, the server of the digital assistant can send the reply information to the client of the digital assistant to complete the reply to the first request information and realize the human-machine conversation.

[0104] In some other embodiments, the first request associated with the first task topic may be a deletion request of the client of the digital assistant for the first task topic. As Figure 10 shown, it can be understood that the deletion request may carry the identifier of the first task topic, and the server of the digital assistant can determine the meta-information of the first task topic through the identifier of the first task topic.

[0105] Next, the server of the digital assistant can delete the correspondence between the client of the digital assistant and the first task topic according to the meta-information of the first task topic. In this way, by deleting the correspondence, the first task topic is deleted from the task topics of the client of the digital assistant.

[0106] In addition, the task topics added by the client of the digital assistant can be displayed on the client of the digital assistant, so that the client of the digital assistant can select from the task topics, thereby starting a human-machine conversation under a specific task topic. The embodiments of the present application support the server of the digital assistant to pull task topics in different ways. In some possible implementation manners, the server of the digital assistant can determine the task topics added by the client of the digital assistant (such as the identifiers of multiple task topics) according to the information of the client of the digital assistant (such as the identifier of the client of the digital assistant), and combine the page size of the client of the digital assistant and the number of task topics obtained each time to obtain task topics in slices, so as to implement the pulling of task topics.

[0107] In other possible implementation manners, the server of the digital assistant can also parse out the identifier of the task topic through a token, and then obtain the task topic corresponding to the identifier of the task topic, so as to implement the pulling of the task topic. In addition, the server of the digital assistant can also directly use the identifiers of multiple task topics to batch obtain task topics and implement the batch pulling of task topics. The embodiments of the present application do not limit this.

[0108] As described above in conjunction with Figures 1 to 10 the information processing method provided by the embodiments of the present application has been introduced in detail. Next, the systems and devices provided by the embodiments of the present application will be introduced in conjunction with the accompanying drawings.

[0109] See Figure 11 the structural schematic diagram of the information processing system shown. The system 110 includes:

[0110] A communication module 1101, configured to receive a first request associated with a first task topic sent by a client of the digital assistant;

[0111] A determination module 1102, configured to determine, according to the first request, meta-information of the first task topic, where the meta-information of the first task topic is stored in the server of the digital assistant;

[0112] A processing module 1103, configured to process the first request according to the meta-information of the first task topic.

[0113] In some possible implementation manners, the first task topic is created through the following steps:

[0114] Receive a creation request for the first task topic, where the sender of the creation request is the client of the digital assistant or the second server;

[0115] Extract the meta information of the first task topic from the creation request;

[0116] Create the first task topic according to the meta information of the first task topic and the sender of the creation request.

[0117] In some possible implementation manners, the communication module 1101 is further configured to:

[0118] Receive an edit request for the first task topic sent by the creator of the first task topic;

[0119] The processing module 1103 is further configured to:

[0120] Modify the meta information of the first task topic according to the edit request.

[0121] In some possible implementation manners, the communication module 1101 is further configured to:

[0122] Receive a deactivation request for the first task topic sent by the creator of the first task topic;

[0123] The processing module 1103 is further configured to:

[0124] Delete the meta information of the first task topic according to the deactivation request, and delete the corresponding relationship between the first task topic and the client of the digital assistant using the first task topic.

[0125] In some possible implementation manners, the communication module 1101 is specifically configured to:

[0126] In response to a call request from the client of the digital assistant for the first interface, receive a request to start a first session under the first task topic.

[0127] In some possible implementation manners, the first request associated with the first task topic sent by the client of the digital assistant includes a request to start a first session under the first task topic. The processing module 1103 is specifically configured to:

[0128] Generate a corresponding relationship between the first task topic and the first session according to the meta information of the first task topic.

[0129] In some possible implementation manners, the first request associated with the first task topic sent by the client of the digital assistant includes a sharing request for the first task topic. The processing module 1103 is specifically configured to:

[0130] Generate a first token according to the meta information of the first task topic, and the link indicated by the first token is used to add the first task topic;

[0131] Return the first token to the client of the digital assistant.

[0132] In some possible implementation manners, when the second client of the digital assistant receives the first token sent by the first client of the digital assistant, and the link indicated by the first token is used to add the first task topic, the communication module 1101 is specifically configured to:

[0133] In response to the call request of the second client of the digital assistant for the second interface, receive the addition request for the first task topic, and the call request for the second interface is generated by triggering the first token;

[0134] The processing module 1103 is specifically configured to:

[0135] Generate the correspondence between the second client of the digital assistant and the first task topic according to the meta information of the first task topic.

[0136] In some possible implementation manners, the communication module 1101 is specifically configured to:

[0137] Receive the information input request of the client of the digital assistant under the first task topic;

[0138] The system 110 further includes an acquisition module, and the acquisition module is used for:

[0139] Acquire the first request information sent by the client of the digital assistant.

[0140] In some possible implementation manners, the first request associated with the first task topic sent by the client of the digital assistant includes the information input request of the client of the digital assistant under the first task topic, and the information input request corresponds to the first request information. The processing module 1103 is specifically configured to:

[0141] Determine a third server according to the meta information of the first task topic, and the third server is used to process the request information under the first task topic;

[0142] Send the first request information to the third server, and receive the reply information returned by the third server;

[0143] Send the reply information to the client of the digital assistant.

[0144] In some possible implementation manners, the first request associated with the first task topic sent by the client of the digital assistant includes a deletion request of the client of the digital assistant for the first task topic. Specifically, the processing module 1103 is configured to:

[0145] Delete the corresponding relationship between the client of the digital assistant and the first task topic according to the meta information of the first task topic.

[0146] In some possible implementation manners, the meta information of the first task topic includes at least one of the following: identification information of the first task topic, type information of the first task topic, and storage location information of the first task topic.

[0147] The information processing system 110 according to the embodiment of the present application may correspond to execute the methods described in the embodiments of the present application, and the above and other operations and / or functions of each module / unit of the information processing system 110 are respectively for implementing Figure 2 the corresponding processes of the respective methods in the illustrated embodiments. For the sake of brevity, they will not be described herein again.

[0148] The embodiment of the present application further provides an electronic device. The electronic device is specifically configured to implement the functions of the information processing system 110 in the Figure 11 illustrated embodiment.

[0149] Figure 12 A schematic structural diagram of an electronic device 1200 is provided. As Figure 12 shown, the electronic device 1200 includes a bus 1201, a processor 1202, a communication interface 1203, and a memory 1204. The processor 1202, the memory 1204, and the communication interface 1203 communicate with each other through the bus 1201.

[0150] The bus 1201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 12 only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0151] The processor 1202 can be any one or more of processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0152] The communication interface 1203 is used for external communication. For example, the communication interface 1203 can be used for communicating with a terminal.

[0153] The memory 1204 can include volatile memory, such as random access memory (RAM). The memory 1204 can also include non-volatile memory, such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0154] Executable code is stored in the memory 1204, and the processor 1202 executes the executable code to perform the foregoing information processing method.

[0155] Specifically, in the case of implementing Figure 11 the illustrated embodiments, and Figure 11 when each module or unit of the information processing system 110 described in the embodiments is implemented by software, the software or program code required to execute the functions of each module / unit in Figure 11 can be partially or fully stored in the memory 1204. The processor 1202 executes the program code corresponding to each unit stored in the memory 1204 to perform the foregoing information processing method.

[0156] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store or a data storage device such as a data center that includes one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state drive). The computer-readable storage medium includes instructions that direct the computing device to execute the foregoing information processing method applied to the information processing system 110.

[0157] An embodiment of the present application also provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, they wholly or partially generate the processes or functions described in the embodiments of the present application.

[0158] The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from a website, computer, or data center to another website, computer, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.).

[0159] When the computer program product is executed by a computer, the computer executes any of the foregoing information processing methods. The computer program product may be a software installation package. In the case where any of the foregoing information processing methods is required, the computer program product may be downloaded and executed on the computer.

[0160] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0161] The units described in the embodiments of the present application may be implemented in software or in hardware. Among them, the name of the unit / module does not constitute a limitation to the unit itself in some cases.

[0162] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate array (FPGA), application specific integrated circuit (ASIC), application specific standard product (ASSP), system on chip (SOC), complex programmable logic device (CPLD), and so on.

[0163] In the context of the embodiments of the present application, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. 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, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0164] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the systems or apparatuses disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0165] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B may be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one)" or its similar expression refers to any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c may mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c may be single or multiple.

[0166] It should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0167] The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be implemented directly in hardware, in a software module executed by a processor, or in a combination thereof. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the art.

[0168] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, characterized in that, applied to the server of a digital assistant, the method comprising: receiving a first request associated with a first task theme sent by a client of the digital assistant; determining meta information of the first task theme according to the first request, the meta information of the first task theme being stored in the server of the digital assistant; processing the first request according to the meta information of the first task theme.

2. The method according to claim 1, characterized in that, the first task theme is created through the following steps: receiving a creation request of the first task theme, the sender of the creation request being the client of the digital assistant or a second server; extracting the meta information of the first task theme from the creation request; creating the first task theme according to the meta information of the first task theme and the sender of the creation request.

3. The method according to claim 2, characterized in that, the method further comprises: receiving an edit request for the first task theme sent by the creator of the first task theme; modifying the meta information of the first task theme according to the edit request.

4. The method according to claim 2, characterized in that, the method further comprises: receiving a deactivation request for the first task theme sent by the creator of the first task theme; deleting the meta information of the first task theme according to the deactivation request, and deleting the corresponding relationship between the first task theme and the client of the digital assistant using the first task theme.

5. The method according to claim 1, characterized in that, the receiving a first request associated with a first task theme sent by a client of the digital assistant comprises: responding to a call request of the client of the digital assistant for a first interface, and receiving a request to start a first session under the first task theme.

6. The method according to claim 1, characterized in that, the first request sent by the client of the digital assistant and associated with the first task theme includes a request to start a first session under the first task theme, and the processing the first request according to the meta information of the first task theme comprises: generating a corresponding relationship between the first task theme and the first session according to the meta information of the first task theme.

7. The method according to claim 1, characterized in that, the first request sent by the client of the digital assistant and associated with the first task theme includes a sharing request for the first task theme, and the processing the first request according to the meta information of the first task theme comprises: generating a first token according to the meta information of the first task theme, the link indicated by the first token being used to add the first task theme; returning the first token to the client of the digital assistant.

8. The method according to claim 1, characterized in that, The second client of the digital assistant receives a first token sent by the first client of the digital assistant. The link indicated by the first token is used to add a first task topic. The receiving of the first request associated with the first task topic sent by the client of the digital assistant includes: In response to a call request of the second client of the digital assistant for a second interface, receiving an addition request for the first task topic. The call request for the second interface is generated by triggering the first token; The processing of the first request according to the meta-information of the first task topic includes: Generating a correspondence between the second client of the digital assistant and the first task topic according to the meta-information of the first task topic.

9. The method according to claim 1, wherein, the receiving of the first request associated with the first task topic sent by the client of the digital assistant includes: Receiving an information input request of the client of the digital assistant under the first task topic; The method further includes: Obtaining first request information sent by the client of the digital assistant.

10. The method according to claim 1, wherein, the first request associated with the first task topic sent by the client of the digital assistant includes an information input request of the client of the digital assistant under the first task topic. The information input request corresponds to first request information. The processing of the first request according to the meta-information of the first task topic includes: Determining a third server according to the meta-information of the first task topic. The third server is used to process request information under the first task topic; Sending the first request information to the third server and receiving reply information returned by the third server; Sending the reply information to the client of the digital assistant.

11. The method according to claim 1, wherein, the first request associated with the first task topic sent by the client of the digital assistant includes a deletion request of the client of the digital assistant for the first task topic. The processing of the first request according to the meta-information of the first task topic includes: Deleting the correspondence between the client of the digital assistant and the first task topic according to the meta-information of the first task topic.

12. The method according to any one of claims 1 to 11, wherein, the meta-information of the first task topic includes at least one of the following: identification information of the first task topic, type information of the first task topic, storage location information of the first task topic.

13. An information processing system, wherein, the system includes: A communication module for receiving a first request associated with a first task topic sent by a client of a digital assistant; A determination module for determining the meta-information of the first task topic according to the first request. The meta-information of the first task topic is stored in the server of the digital assistant; A processing module for processing the first request according to the meta-information of the first task topic.

14. An electronic device, wherein, The electronic device includes a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, it includes instructions for instructing an electronic device to execute the method according to any one of claims 1 to 12.

Images