Conversation content generation method and device, equipment, storage medium and program product

Abstract

The invention relates to the technical field of computers, and discloses a dialogue content generation method and device, equipment, a storage medium and a program product.The method comprises the steps that object attribute information is obtained, and the object attribute information comprises attribute information of at least one to-be-configured object; in response to the knowledge configuration operation for each to-be-configured object, determining a dialogue knowledge base associated with the to-be-configured object; in response to a robot configuration operation for each to-be-configured object, determining a target robot associated with the to-be-configured object, the target robot being a virtual object for executing a dialogue operation; and when the to-be-configured object receives the session information, dialogue content corresponding to the session information is generated based on the target robot and the dialogue knowledge base. According to the technical scheme, the generation efficiency and the generation matching degree of the dialogue content are improved, the dialogue effect between the target robot and the dialogue object is guaranteed, and therefore the service consultation experience of a user is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, equipment, storage medium and program product for generating dialogue content. Background Art

[0002] At present, there are two main types of customer service reception in commercialization: manual customer service and intelligent customer service. However, manual customer service has problems such as poor user experience and low service efficiency. Although intelligent customer service can overcome some of the shortcomings of manual customer service, the existing intelligent customer service lacks humanity and has a low problem-solving rate. It is difficult to have intelligent conversations with conversation partners based on business demands, resulting in rigid generation of conversation content and difficulty in ensuring accuracy, which affects the user's conversation experience. Summary of the invention

[0003] In view of this, the present disclosure provides a method, apparatus, device, storage medium and program product for generating conversation content to solve the problem of poor conversation content generation effect.

[0004] In a first aspect, the present disclosure provides a method for generating dialogue content, comprising: acquiring object attribute information, the object attribute information including attribute information of at least one object to be configured; determining a dialogue knowledge base associated with the object to be configured in response to a knowledge configuration operation for each object to be configured; determining a target robot associated with the object to be configured in response to a robot configuration operation for each object to be configured, the target robot being a virtual object for performing dialogue operations; when the object to be configured receives session information, generating dialogue content corresponding to the session information based on the target robot and the dialogue knowledge base.

[0005] In a second aspect, the present disclosure provides a device for generating dialogue content, including: an acquisition module, used to acquire object attribute information, the object attribute information including attribute information of at least one object to be configured; a knowledge base configuration module, used to determine a dialogue knowledge base associated with the object to be configured in response to a knowledge configuration operation for each object to be configured; a robot configuration operation, used to determine a target robot associated with the object to be configured in response to a robot configuration operation for each object to be configured, the target robot being a virtual object for performing dialogue operations; and a dialogue generation module, used to generate dialogue content corresponding to the session information based on the target robot and the dialogue knowledge base when the object to be configured receives the session information.

[0006] In a third aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for generating dialogue content of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0007] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for generating dialogue content of the first aspect or any corresponding embodiment thereof.

[0008] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, which are used to enable a computer to execute the method for generating dialogue content of the above-mentioned first aspect or any corresponding embodiment.

[0009] The method, apparatus, device, storage medium and program product for generating conversation content provided by the embodiments of the present disclosure perform knowledge configuration and robot configuration on each object to be configured to obtain a conversation knowledge base and a target robot associated with the object to be configured. When receiving conversation information, the target robot can reply according to the conversation knowledge base, so that the reply of the target robot is more in line with actual business needs, thereby improving the generation efficiency and generation matching degree of the conversation content, ensuring the conversation effect between the target robot and the conversation object, and thus improving the user's business consulting experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 is an architecture diagram of a question-and-answer application system according to an embodiment of the present disclosure;

[0012] Figure 2 is a flowchart of a method for generating conversation content according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram showing attribute information of an object to be configured according to an embodiment of the present disclosure;

[0014] Figure 4 is a schematic diagram of the configuration of a knowledge base according to an embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram of a configuration interface of a robot according to an embodiment of the present disclosure;

[0016] Figure 6 is a flowchart of another method for generating conversation content according to an embodiment of the present disclosure;

[0017] Figure 7is a schematic diagram of a robot version according to an embodiment of the present disclosure;

[0018] Figure 8 is a schematic diagram of the association between a robot and a dialogue knowledge base according to an embodiment of the present disclosure;

[0019] Fig. 9 is a flowchart of another method for generating dialogue content according to an embodiment of the present disclosure;

[0020] Fig.10 is a flowchart of logging into the question-and-answer application system according to an embodiment of the present disclosure;

[0021] Fig.11 is a schematic diagram of a conversation interface according to an embodiment of the present disclosure;

[0022] Fig.12 is a schematic diagram of session management according to an embodiment of the present disclosure;

[0023] Fig.13 It is a schematic diagram of implementing message push according to an embodiment of the present disclosure;

[0024] Fig.14 is a structural block diagram of a device for generating dialogue content according to an embodiment of the present disclosure;

[0025] Fig.15 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] With the development of artificial intelligence technology, its application in the commercial field is becoming more and more extensive. Many businesses in related technologies have the demand for customer service reception. Customer service reception in related technologies is mainly manual reception, but manual reception has the following problems:

[0033] (1) Poor user experience: During peak traffic periods, manual customer service is prone to problems such as delayed reception, difficulty in being online all day, and uncontrollable reception quality.

[0034] (2) High cost and low service efficiency: The high turnover of human customer service leads to high training / management costs; a large number of consultations are simple and repetitive, resulting in low reception efficiency.

[0035] Based on this, with the development of Natural Language Processing (NLP) algorithms, intelligent customer service has gradually emerged. Intelligent customer service replaces manual customer service, which to a certain extent reduces the workload of manual customer service and liberates manpower. However, there are still some problems:

[0036] (1) Low problem solving rate: Intelligent customer service needs to build an intent library in advance and use keyword matching or semantic similarity calculation to identify user intent. The problem solving rate depends to a large extent on the coverage and accuracy of the intent library.

[0037] (2) Lack of humanity: The responses of intelligent customer service are rigid and lack personalization, which lacks the sense of real-life conversation and affects the user experience.

[0038] (3) High maintenance cost: The knowledge base, intent recognition configuration, etc. need to be continuously optimized and iterated, resulting in high maintenance costs.

[0039] Based on this, the disclosed technical solution greatly improves the customer service reception efficiency and chat effect by accessing the large model and multi-agent model mode. By encapsulating the dialogue knowledge base, customizing the speech, and providing business customization functions, the access cost of the large model is greatly reduced. By accessing websocket, real-time message push is achieved, so that the agent object can intervene in the chat reception in real time on the management interface. By splitting the customer's intention recognition, slot questioning, knowledge questions and answers, and large model replies, the complexity of each model is reduced, and targeted replies can be given, thereby improving the accuracy of the model reply and reducing the large model illusion.

[0040] The present disclosure provides a question-and-answer application system. Figure 1 As shown, the system includes a front-end FE, a gateway layer BFF, an application layer, a domain layer, and an infrastructure layer.

[0041] Among them, the front end includes the front-end page and the client front end.

[0042] The gateway layer includes account login, permission verification and file upload.

[0043] The application layer mainly includes document management, channel management, robot configuration management and session configuration. Document management includes FAQ tags, multi-knowledge base management, add / delete / modify / check, batch import / delete, etc. Channel management includes expiration reminders, duplicate binding verification, add / delete / modify / check, automatic account renewal, etc. Robot configuration management includes active contact configuration, manual configuration, add / delete / modify / check, speech instructions, etc. Session configuration mainly includes retention management, session debugging, session management, session, etc.

[0044] The domain layer mainly includes the collection of knowledge and corpus, the basic configuration of the robot, knowledge / corpus configuration, the creation and reading of instructions, the creation and reading of sessions, the creation of session messages, etc.

[0045] The infrastructure layer mainly includes key management, security audit, model middle platform, log storage and database storage, among which database storage mainly includes MySQL database, Redis database, Mongo database, etc. Among them, key management is used to manage the key resources of the question-and-answer application system to ensure that only authorized personnel can access key resources; security audit is used to conduct regular audits of the question-and-answer application system to ensure system security; the model middle platform is a centralized platform for model development, model management and model deployment, such as the development, management and deployment of large language models; log storage is used to record the activities of the question-and-answer application system to generate the operation log of the question-and-answer application system; database storage is used to store and manage the key data generated by the question-and-answer application system to ensure the integrity and availability of the data.

[0046] According to an embodiment of the present disclosure, an embodiment of a method for generating conversation content is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0047] In this embodiment, a method for generating dialogue content is provided, which can be used in a computer device, such as a mobile phone, a tablet computer, a computer, etc., in which the above-mentioned question-and-answer application system is deployed. Figure 2 is a flow chart of a method for generating dialogue content according to an embodiment of the present disclosure, such as Figure 2 As shown, the process includes the following steps:

[0048] Step S101: acquiring object attribute information, where the object attribute information includes attribute information of at least one object to be configured.

[0049] The object to be configured is the object that needs to configure a robot to implement automatic replies. Specifically, the object to be configured can be a merchant, a store manager, an enterprise account owner, etc.

[0050] The object attribute information is used to represent the user identity information of the object to be configured, and the object attribute information includes the attribute information of at least one object. Specifically, the attribute information of each object included in the object attribute information can be represented in the form of a list, and the object attribute information can include the object name, object identification number, object status, and object binding time, etc. Figure 3 shown.

[0051] In a specific example, the proxy object logs in to the question and answer application system to set the attribute information of the object to be configured. Among them, the proxy object is the object that communicates with the customer on behalf of the object to be configured; the question and answer application system can be an application embedded in the web page, and the question and answer application system can be entered through a URL link; it can also be an application installed in a computer device, and the question and answer application system can be entered by triggering the corresponding icon; it can also be a small program embedded in other applications. There is no specific limitation on the deployment method of the question and answer application system here. A proxy object can act as an agent for multiple objects to be configured at the same time. The account information of the objects to be configured and their associated attribute information are stored in the database corresponding to the question and answer application system. After the proxy object logs in to the question and answer application system using the account information of the object to be configured, the question and answer application system obtains the corresponding attribute information by querying the database.

[0052] Step S102: In response to the knowledge configuration operation for each object to be configured, determining a dialog knowledge base associated with the object to be configured.

[0053] The dialogue knowledge base is a knowledge base that matches the object to be configured. The dialogue knowledge base includes multiple questions and answers related to the business of the object to be configured. For example, if the object to be configured is the owner of a photography shop, the dialogue knowledge base includes multiple knowledge bases related to photography, such as knowledge base A for sample question and answer information, knowledge base B for clothing question and answer information, knowledge base C for discount question and answer information, etc.

[0054] Knowledge configuration operation is to configure the knowledge base. The question and answer application system can provide a knowledge base configuration interface, such as Figure 4 As shown, the proxy object can configure the knowledge base required by the object to be configured in the configuration interface of the knowledge base to obtain the dialog knowledge base associated with the object to be configured.

[0055] Step S103, in response to the robot configuration operation for each object, determining a target robot associated with the object, where the target robot is a virtual object used to perform a dialogue operation.

[0056] The target robot is a virtual object configured by the proxy object to conduct a conversation with the client (i.e., the conversation object corresponding to the object to be configured). That is, the target robot automatically performs the conversation operation to realize the conversation with the client on behalf of the object to be configured. Figure 5 As shown, the binding relationship between the target robot and the object to be configured is determined through the "Channel Binding" control.

[0057] The robot configuration operation is to configure the robot for dialogue. The question-and-answer application system can provide a robot configuration interface, such as Figure 5 As shown, the proxy object can configure the robot bound to the object to be configured in the robot configuration interface to obtain the target robot associated with the object to be configured.

[0058] Step S104, when the object to be configured receives the conversation information, a conversation content corresponding to the conversation information is generated based on the target robot and the conversation knowledge base.

[0059] The conversation information is the information sent by the conversation object to the object to be configured; the conversation content is the reply content given by the target robot to the conversation information. When the object to be configured receives the information sent by the conversation object, the target robot can compare the conversation information with the question and answer information in the conversation knowledge base to determine whether the conversation information hits the conversation knowledge base. When the conversation information hits the conversation knowledge base, the target robot can reply to the conversation information according to the conversation knowledge base and generate the corresponding conversation content.

[0060] The method for generating conversation content provided in this embodiment performs knowledge configuration and robot configuration on each object to be configured to obtain a conversation knowledge base and a target robot associated with the object to be configured. When receiving conversation information, the target robot can reply according to the conversation knowledge base, so that the reply of the target robot is more in line with actual business needs, thereby improving the generation efficiency and generation matching degree of the conversation content, ensuring the conversation effect between the target robot and the conversation object, and thus improving the user's business consulting experience.

[0061] In this embodiment, a method for generating dialogue content is provided, which can be used in a computer device, such as a mobile phone, a tablet computer, a computer, etc., in which the above-mentioned question-and-answer application system is deployed. Figure 6 is a flow chart of a method for generating dialogue content according to an embodiment of the present disclosure, such as Figure 6 As shown, the process includes the following steps:

[0062] Step S201: Obtain object attribute information, which includes attribute information of at least one object to be configured. Figure 2 Step S101 of the illustrated embodiment will not be described in detail here.

[0063] Step S202: In response to the knowledge configuration operation for each object, determine the dialog knowledge base associated with the object. Figure 2 Step S102 of the illustrated embodiment will not be described in detail here.

[0064] Step S203, in response to the robot configuration operation for each object, determining a target robot associated with the object, where the target robot is a virtual object used to perform a dialogue operation.

[0065] Specifically, the above step S203 includes:

[0066] Step S2031, in response to the active reach configuration operation for the robot, generate active reach information corresponding to the robot.

[0067] Active reach information is information generated when the target robot performs active reach. Figure 5As shown, an active contact control is set in the robot configuration interface. When the proxy object clicks the active contact control, the active contact content configuration interface is displayed. The active contact content that attracts the conversation object is designed in the content configuration interface, such as greetings, message texts, links, pictures or other related information, and sent to the conversation object through in-app messages. At the same time, the time, frequency and conditions of active contact are set in the content configuration interface, and the generation of active contact information can be triggered according to the behavior, preferences or specific events of the conversation object. For example, when it is detected that the conversation object enters the conversation interface of the conversation information for the first time, the target robot can actively contact the greeting (such as "Welcome"); when it is detected that the conversation object has not given a reply within the set time interval, the target robot can actively contact the question (such as "Dear, I see that you have no reply, do you have any concerns?") and so on. Of course, different active contact information can be set for different scenarios, and it is not specifically limited here.

[0068] Step S2032: In response to the instruction guidance configuration operation for the target robot, a guidance instruction corresponding to the target robot is generated, wherein the guidance instruction is used to guide the conversation object to input a question associated with the guidance instruction.

[0069] The robot configuration interface is provided with a role configuration interface, and the role configuration interface is provided with a role configuration control (such as Figure 5 The "Task" control, "Industry" control, and "Name" control shown) and the instruction guide control (such as Figure 5 Add Script Guidance control shown).

[0070] Specifically, the agent object can click on the role configuration control to determine the task, industry, and name associated with the object to be configured, etc. Thus, the role configuration of the target robot is realized so that the target robot can perform the dialogue operation corresponding to its role.

[0071] The proxy object can also click the instruction guidance control to edit the guidance instruction and obtain the guidance instruction corresponding to the target robot, so that the target robot guides the conversation object to provide corresponding content according to the guidance instruction. Specifically, when there are multiple guidance instructions, the order of the multiple guidance instructions can be edited so that the target robot guides the conversation object to provide corresponding content in sequence according to the order of the guidance instructions.

[0072] If the object to be configured is the operator of a baby photography store, the guidance instructions may include "contact information", "baby age", "shooting location", "shooting scene", "number of negatives", "number of retouched photos", etc. Of course, other guidance instructions may be added according to the tasks of the object to be configured, and no specific limitation is made at this time.

[0073] Step S2033, in response to the reply object conversion configuration operation for the target robot, generating object conversion configuration information, wherein the object conversion configuration information is used to convert the reply object from the target robot to the proxy object when the target keyword exists in the conversation information.

[0074] The robot configuration interface is provided with a reply object conversion configuration interface, in which the conditions for triggering the conversion of reply objects are provided, such as keyword triggering. The proxy object can input the triggering conditions (for example, keyword triggering reaches 5 times) in the reply object conversion configuration interface. When the triggering conditions are met, the target robot will automatically be converted to the proxy object, so that the proxy object can participate in the generation of the conversation content.

[0075] Step S2034, determining a target robot associated with the object based on at least one of the active reach information, the guidance instruction and the object conversion configuration information.

[0076] After completing the configuration of at least one of the active reach information, guidance instructions and object conversion configuration information, one or more of the configured active reach information, guidance instructions and object conversion configuration information are integrated into the target robot so that the target robot performs dialogue operations according to the active reach information, guidance instructions and object conversion configuration information.

[0077] Specifically, when the active contact conditions are met, the target robot can automatically generate active contact information in the conversation interface; the target robot can also use guidance instructions to guide the conversation object to respond and obtain corresponding conversation content; when the object conversion conditions are met, the target robot can also actively convert the reply object so that the reply object can respond according to the conversation object's questions and generate corresponding conversation content.

[0078] like Figure 5 As shown, a preview interface can also be provided in the robot configuration interface to display the dialogue information generated by the target robot based on the active reach information, guidance instructions and object conversion configuration information.

[0079] In the above implementation, the active contact configuration for the robot is supported, which improves the consultation willingness of the conversation object and is conducive to improving the consultation experience of the user. The command guidance configuration is supported to facilitate guiding the conversation object to leave consultation information, improve the intelligent dialogue between the target robot and the conversation object, and make the conversation content more humane. It supports switching the reply object so that when the target robot cannot meet the conversation needs of the conversation object, it can be switched to the human in time, further improving the interactive experience of the conversation object.

[0080] In some optional embodiments, such as Figure 4As shown, the robot configuration interface can also set the robot working cycle, such as fixed cycle, repeated cycle, etc. The robot working cycle configuration supports setting the working date and working time.

[0081] In some optional implementations, the target robot has a first version and a second version. The first version is used for reply debugging. After reply debugging, the second version of the target robot is obtained, and the conversation information is replied based on the second version to generate dialogue content.

[0082] like Figure 7 As shown, the target robot has a first version and a second version, wherein the first version is an open version used for reply debugging, and supports editing and testing of the replies of the first version of the target robot during the debugging process; the second version is an online version used for conversation replies.

[0083] Specifically, when the test results of the first version meet the reply requirements, it can be determined that the debugging of the target robot has been completed. At this time, the debugged target robot can be released online so that the target robot can make online conversation replies. When the second version of the target robot makes conversation replies, if it is found that the reply of the second version of the target robot is insufficient, the first version of the target robot can be re-debugged without interrupting the second version, so as to re-release the new version after the debugging is completed. By distinguishing the open version from the online version, the isolation of robot debugging and robot online operation is achieved, ensuring that debugging and online use do not affect each other.

[0084] Step S204, when the object receives the conversation information, a conversation content corresponding to the conversation information is generated based on the target robot and the conversation knowledge base.

[0085] Specifically, the above step S204 includes: associating the target robot associated with the object to be configured with the dialogue knowledge base, so that the target robot responds to the conversation information according to the dialogue knowledge base to generate dialogue content.

[0086] When configuring the target robot and the conversation knowledge base, the target robot is bound to the conversation knowledge base to achieve the association between the target robot and the conversation knowledge base. Then, when receiving the conversation information, the target robot can make a conversation reply according to the conversation knowledge base associated with it and generate the corresponding conversation content. Specifically, the same robot can be bound to multiple conversation knowledge bases, and different robots can be associated and bound to the same conversation knowledge base, such as Figure 8 shown.

[0087] In some optional implementations, the configuration interface of the dialogue knowledge base includes a robot binding control, and the robot binding control is used to bind the current dialogue knowledge base to the target robot. Accordingly, the above step S204 includes:

[0088] Step a1, in response to a trigger operation on a robot binding control, determining a target robot to be bound to the dialogue knowledge base, so that the target robot responds to the conversation information according to the dialogue knowledge base and generates dialogue content.

[0089] The agent object clicks the robot binding control (such as Figure 5 The "bound robot" shown in the figure shows multiple robots associated with the question-answering application system, and each robot has a unique identifier. According to the unique identifier of the robot, the target robot associated with the object to be configured is retrieved from the multiple robots, and the target robot is selected as the robot bound to the dialogue knowledge base. In this way, the target robot can respond to the conversation information according to the dialogue knowledge base and generate dialogue content.

[0090] In some optional implementations, the robot configuration interface includes a knowledge base binding control, which is used to bind the current target robot to the dialogue knowledge base. Accordingly, the above step S204 also includes:

[0091] Step a2, in response to the trigger operation on the knowledge base binding control, determine the dialogue knowledge base to be bound to the target robot, so that the target robot responds to the conversation information according to the dialogue knowledge base and generates dialogue content.

[0092] The agent object clicks the knowledge base binding control (such as Figure 4 The "knowledge base" shown in the figure shows multiple knowledge bases entered into the question-answering application system, and each knowledge base has a unique knowledge base identifier. According to the unique knowledge base identifier, one or more knowledge bases associated with the object to be configured are retrieved from the multiple knowledge bases, and the one or more knowledge bases are used as the dialogue knowledge base bound to the target robot. As a result, the target robot can respond to the conversation information according to the dialogue knowledge base and generate dialogue content.

[0093] The method for generating dialogue content provided in this embodiment associates the target robot with the dialogue knowledge base, so that when the conversation object hits the content of the dialogue knowledge base, the target robot can respond as expected, thereby improving the response efficiency and response accuracy.

[0094] In this embodiment, a method for generating dialogue content is provided, which can be used in a computer device, such as a mobile phone, a tablet computer, a computer, etc., in which the above-mentioned question-and-answer application system is deployed. Fig. 9 is a flow chart of a method for generating dialogue content according to an embodiment of the present disclosure, such as Fig. 9 As shown, the process includes the following steps:

[0095] Step S301: Obtain object attribute information, where the object attribute information includes attribute information of at least one object to be configured.

[0096] Specifically, the above step S301 includes:

[0097] Step S3011, obtaining authorization attribute information of the object to be configured.

[0098] The authorization attribute information is the attribute information that the object to be configured authorizes the proxy object to perform account login to act as its agent for dialog interaction with the session object.

[0099] Specifically, when the object to be configured authorizes the proxy object to act as its proxy service, it can send the authorization attribute information to the computer device of the proxy object, and the computer device of the proxy object can receive and store the authorization attribute information. Fig.10 As shown, when configuring the object to be configured, the proxy object can input the authorization attribute information of the object to be configured to be bound in the front-end page of the question-and-answer application system, and accordingly, the front-end page of the question-and-answer application system can obtain the authorization attribute information.

[0100] Step S3012: displaying an authorization login page based on the authorization attribute information.

[0101] The question-and-answer application system generates a login request based on the authorization attribute information and triggers the display of the authorization login page based on the login request. Fig.10 As shown, the question-and-answer application system configures the robot's authorization login page's web link according to the authorization attribute information request (the web resource address of the authorization login page is represented by the Uniform Resource Locator (URL)), and after receiving the web link feedback from the robot service, directly enters the web link to access and display the authorization login page.

[0102] Step S3013, in response to the login operation on the authorized login page, obtaining a login result.

[0103] A login information entry area is provided in the authorization login page, and the proxy object can enter the login account and login password authorized by the object to be configured in the login information entry area to log in; a login control is provided on the authorization login page, and after completing the entry of the login information, the proxy object can trigger the login control to log in to the question and answer application system, and accordingly, the question and answer application system can respond to the login operation triggered by the proxy object and generate a corresponding login result.

[0104] Of course, the login identification code integrated with the login information can also be displayed on the authorization login page, and the login identification code is sent to the object to be configured so that the object to be configured can open the login permission. After obtaining the login permission opened by the object to be configured, log in to the Q&A application system, such as Fig.10 As shown. Accordingly, the client in the question-and-answer application system can respond to the login operation triggered by the proxy object and generate the corresponding login result. Then, the client in the question-and-answer application system can call back the authorization service, and the robot service requests the client to obtain the authorization credential (token) according to the authorization service, and sends the authorization credential to the robot service, which can store the authorization credential for subsequent robot configuration for the object to be configured.

[0105] Step S3014: if the login result indicates that the login is successful, then obtaining object attribute information of the object to be configured.

[0106] The login result is verified to determine whether the Q&A application system has successfully logged in. When the login result indicates that the Q&A application system has successfully logged in, it can be determined that the Q&A application system has the authority to communicate with the client on behalf of the object to be configured. At this time, the Q&A application system can obtain the object attribute information associated with the current login account.

[0107] In the above implementation, the authorization login page is displayed by triggering the authorization attribute information, thereby achieving authentication for the login object and ensuring login security. Further, when the login is successful, the object attribute information of the object to be configured is obtained, ensuring the information security of the object to be configured.

[0108] Step S302: In response to the knowledge configuration operation for each object to be configured, determine the dialog knowledge base associated with the object to be configured.

[0109] Specifically, the knowledge configuration operation includes at least one of a document import operation, an information entry operation, and a batch editing operation. Accordingly, the above step S302 includes:

[0110] Step S3021, in response to the document import operation for the question and answer file, extract the first question and answer information from the imported question and answer file, and add the first question and answer information to the dialogue knowledge base.

[0111] The question and answer file is a file associated with the business undertaken by the object to be configured. The question and answer file can be pre-written or collected online. The method for obtaining the question and answer file is not specifically limited here. Figure 3 As shown, an import control is set on the configuration page of the knowledge base, and the agent object can click the import control to display the document import interface, and then import the question and answer file into the question and answer application system. Accordingly, the question and answer application system can respond to the agent object's document import operation on the question and answer file, obtain the question and answer file, and parse the content in the question and answer file based on a large language model, natural language processing, etc., determine the first question and answer information carried by the question and answer file, and add the parsed first question and answer information to the dialogue knowledge base.

[0112] Step S3022, in response to the information entry operation for the question and answer, obtain the entered second question and answer information, and add the entered second question and answer information to the dialogue knowledge base.

[0113] There are information adding controls in the knowledge base configuration page, such as Figure 3 The "Add Q&A" control shown. The agent object can click the information adding control to display the Q&A editing interface, and enter business-related questions and their corresponding answers in the Q&A editing interface. Accordingly, the Q&A application system can respond to the agent object's information import operation on the Q&A, generate corresponding second Q&A information, and add the generated second Q&A information to the dialogue knowledge base.

[0114] Step S3023, in response to the batch editing operation on the questions and answers, the edited third question and answer information is obtained, and the third question and answer information is determined as the dialogue knowledge base.

[0115] There are batch operation controls on the knowledge base configuration page, such as Figure 3 As shown. The agent object can click the batch operation control to batch edit the currently existing question and answer information, such as batch delete. Correspondingly, the question and answer application system can respond to the agent object's batch editing operation on the question and answer, obtain the adjusted third question and answer information, and determine the third question and answer information as the currently required dialogue knowledge base.

[0116] In some optional implementations, the above method further includes:

[0117] Step b1, in response to a marking operation on question and answer information, obtaining marked target question and answer information.

[0118] Step b2: determining the target question and answer information as key question and answer information.

[0119] Key Q&A information is common Q&A information associated with a business. Each Q&A information has a corresponding display area. For example, each Q&A information can be displayed in the form of a card in the corresponding display area. A marking control is set in the display area corresponding to each Q&A information. The agent object can click the marking control to mark the Q&A information. Accordingly, the Q&A application system can respond to the agent object's marking operation on the Q&A information, determine the marked target Q&A information, and determine the target Q&A information as key Q&A information. Figure 3 As shown, a key question and answer information display area and other question and answer information display areas are set in the configuration interface of the knowledge base. The target question and answer information with marks is displayed in the key question and answer information display area, and the target question and answer information without marks is displayed in the other question and answer information display area.

[0120] In the above implementation, the marking of question and answer information is supported, which is convenient for marking key question and answer information according to actual needs, and is conducive to achieving targeted follow-up questions and replies based on the key question and answer information, so as to effectively identify the intention of the conversation partner, and further improve the accuracy of the generation of question and answer information.

[0121] Step S303: In response to the robot configuration operation for each object to be configured, determine the target robot associated with the object to be configured, where the target robot is a virtual object used to perform the dialogue operation. Figure 6 Step S203 of the illustrated embodiment will not be described in detail here.

[0122] Step S304: When the object to be configured receives the conversation information, it generates the conversation content corresponding to the conversation information based on the target robot and the conversation knowledge base. Figure 6 Step S204 of the illustrated embodiment will not be described in detail here.

[0123] Step S305, displaying a conversation interface of the conversation content, wherein the conversation interface includes an object display interface, a conversation information display interface, and a conversation record display interface.

[0124] In the question-and-answer application system, the conversation interface between the target robot and the conversation object (i.e., the customer) is displayed. Fig.11 As shown, the session interface includes an object display interface, a session information display interface and a session record display interface, wherein the object display interface is used to display the session object identifier, the session information display interface is used to display the conversation between the object to be configured and the session object, and the session record display interface is used to display the session record between the object to be configured and the session object.

[0125] Step S306: When the object to be configured receives the new session information, the session object identifier corresponding to the new session information is displayed on the object display interface.

[0126] The session object identifier is the object identifier of the session object that initiated the session information. The Q&A application system detects in real time whether each object to be configured has received new session information. When it is detected that the object to be configured has received new session information, the object identifier of the session object that initiated the new session information is displayed on the object display interface, such as Fig.11 As shown, this enables the proxy object to understand the service status of the target robot.

[0127] Step S307, in response to the triggering operation on the conversation object identifier, displaying the conversation information between the target robot and the conversation object in the conversation information display interface.

[0128] If the agent object needs to view the conversation content between the target robot and each conversation object, it can click the conversation object identifier in the object display interface. Correspondingly, the question-answering application system can respond to the trigger operation of the agent object on the conversation object identifier and display the conversation information between the target robot and the conversation object in the conversation information display interface, such as Fig.11 shown.

[0129] Step S308: displaying the session object identifier associated with the object to be configured and the latest information corresponding to the session object identifier in the session record display interface.

[0130] The question-and-answer application system can record the session information initiated by the session object associated with the object to be configured, and display it on the session record display interface. Fig.11 As shown, the session object identifier associated with the object to be configured and the latest information corresponding to the session object identifier are displayed in the session record display interface.

[0131] In a specific example, Fig.12 As shown, when the proxy object logs in to the Q&A application system, the Q&A application system authenticates the proxy object through the gateway to determine the proxy object's login authority. After authentication, the gateway feeds back the proxy object with information about successful authentication. Then, a long connection is established between the proxy object and the push service of the session, and the list of objects it represents and the list of sessions corresponding to each object (including unread information) are pulled. The gateway verifies the proxy object's access rights to the push service. After determining that the proxy object has access rights to the push service, a push channel is established between the push service and the proxy object. When pushing messages, broadcast messages are used to push messages to the proxy object.

[0132] Among them, the push of real-time messages is realized through the websocket service, such as Fig.13 As shown, when a message needs to be sent to the object 1 that the proxy object represents, the message is broadcast to each server (such as Fig.10The server 1, server 2, server 3, and server 4 shown in the figure broadcast, and then push the message to the object 1 through the server 1 in combination with the ping command and the pong command. In this way, the session management is realized through the question-and-answer application system.

[0133] In some optional implementations, the conversation interface includes a conversation intervention control, and the conversation intervention control is used for the proxy object to intervene in the conversation interaction between the target robot and the conversation object. Accordingly, the above method also includes: in response to a trigger operation on the conversation intervention control, converting the reply object from the target robot to the proxy object, and generating reply content in response to the reply operation of the proxy object.

[0134] When the agent object checks the dialogue information between the target robot and the conversation object and determines that the target robot is not suitable, it can trigger the dialogue intervention control to replace the target robot in the dialogue interaction with the conversation object. Accordingly, the question-and-answer application system can respond to the agent object's trigger operation on the dialogue intervention control, convert the reply object into a proxy object, and display the information input box. The agent object can then input the reply content in the information input box, and accordingly, the question-and-answer application system can respond to the agent object's reply operation in the information input box and generate the corresponding reply content.

[0135] In the above implementation, conversation intervention is supported, and deviations in conversation information can be interrupted in a timely manner, which is beneficial to improving the conversation experience of the conversation partner.

[0136] In some optional implementations, the above method further includes:

[0137] Step c1, in response to the information editing operation of the agent object in the conversation interface, obtaining the target conversation;

[0138] Step c2, in response to the sending trigger operation for the target session, sending the target session in the session interface; wherein the information editing operation includes at least one of a session entry operation, a session withdrawal operation, and a session rewriting operation.

[0139] The agent object can enter the conversation content in the information input box, and accordingly, the question-answering application system can respond to the agent object's conversation entry operation in the information input box and obtain the reply content entered by the agent object. After completing the entry of the reply content, click the send control to send the reply content to the conversation interface.

[0140] If the agent object finds that a reply in the conversation interface is incorrect or unsatisfactory, it can withdraw the reply. Accordingly, the question-and-answer application system can respond to the agent object's withdrawal operation on the reply content and withdraw the reply content to delete the reply content from the conversation interface.

[0141] For the withdrawn reply content, the proxy object is supported to rewrite the reply content. Specifically, if the proxy object needs to rewrite the withdrawn reply content, it can trigger the re-editing of the withdrawn reply content to display the withdrawn reply content in the information input box, and then the proxy object can rewrite the reply content. Accordingly, the question-and-answer application system can respond to the proxy object's conversation rewrite operation in the information input box to obtain the rewritten reply content. After completing the rewriting of the reply content, click the send control to send the rewritten reply content to the conversation interface.

[0142] By supporting the editing of session content, the flexible processing of session content is improved, which facilitates better management of session content and makes the session content more consistent with the session information sent by the session object.

[0143] The method for generating the conversation content provided in this embodiment supports document import, information entry and batch operation in the knowledge base configuration process, so that the agent object can customize the knowledge base according to the actual business needs, so that the target robot can accurately respond to the questions that hit the conversation knowledge base. At the same time, it can be flexibly configured in the configuration interface of the knowledge base, which reduces the access cost of the large model. By displaying the conversation object identifier, conversation information and conversation record in the conversation interface, it is beneficial for the agent object to understand the conversation interaction status between the target robot and the conversation object in real time, so as to intervene in time when the target robot responds inappropriately, and further improve the accuracy of the response.

[0144] In the present embodiment, a device for generating conversation content is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the descriptions that have been made are not repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented with software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0145] This embodiment provides a device for generating dialogue content, such as Fig.14 As shown, including:

[0146] The acquisition module 401 is used to acquire object attribute information, where the object attribute information includes attribute information of at least one object to be configured.

[0147] The knowledge base configuration module 402 is used to determine the dialog knowledge base associated with each object to be configured in response to the knowledge configuration operation for each object to be configured.

[0148] The robot configuration module 403 is used to determine a target robot associated with each object to be configured in response to a robot configuration operation for each object to be configured, where the target robot is a virtual object used to perform a dialogue operation.

[0149] The dialogue generation module 404 is used to generate dialogue content corresponding to the dialogue information based on the target robot and the dialogue knowledge base when the object to be configured receives the dialogue information.

[0150] In some optional implementations, the dialogue generation module 404 includes:

[0151] An associating unit is used to associate the target robot associated with the object to be configured with the dialogue knowledge base, so that the target robot responds to the conversation information according to the dialogue knowledge base to generate the dialogue content.

[0152] In some optional implementations, the configuration interface of the dialogue knowledge base includes a robot binding control, and / or the configuration interface of the robot includes a knowledge base binding control. Accordingly, the above-mentioned association unit includes:

[0153] The first association subunit is used to determine the target robot to be bound to the dialogue knowledge base in response to a trigger operation on the robot binding control.

[0154] The second association subunit is used to determine the dialogue knowledge base to be bound to the target robot in response to the trigger operation on the knowledge base binding control.

[0155] In some optional embodiments, the robot configuration module 403 includes:

[0156] The first configuration unit is used to generate active reach information corresponding to the robot in response to an active reach configuration operation for the robot.

[0157] The second configuration unit is used to generate a guidance instruction corresponding to the target robot in response to the instruction guidance configuration operation for the target robot, and the guidance instruction is used to guide the conversation object to input a question associated with the guidance instruction.

[0158] The third configuration unit is used to generate object conversion configuration information in response to a reply object conversion configuration operation for the target robot, wherein the object conversion configuration information is used to convert the reply object from the target robot to a proxy object when a target keyword exists in the session information.

[0159] A robot generation unit is used to determine a target robot associated with the object to be configured based on at least one of the active reach information, the guidance instruction and the object conversion configuration information.

[0160] In some optional embodiments, the target robot has a first version and a second version, the first version is used for reply debugging, and after the reply debugging, the second version of the target robot is obtained, and the session information is replied based on the second version to generate the conversation content.

[0161] In some optional implementations, the knowledge configuration operation includes at least one of a document import operation, an information entry operation, and a batch editing operation. Accordingly, the above-mentioned knowledge base configuration module 402 includes:

[0162] The importing unit is used to extract first question and answer information from the imported question and answer file in response to a document import operation on the question and answer file, and add the first question and answer information to the dialogue knowledge base.

[0163] The input unit is used to obtain the input second question and answer information in response to the information input operation for the question and answer, and add the input second question and answer information to the dialogue knowledge base.

[0164] The batch editing unit is used to respond to the batch editing operation on the questions and answers, obtain the edited third question and answer information, and determine the third question and answer information as the dialogue knowledge base.

[0165] In some optional embodiments, the above device further includes:

[0166] The marking module is used to obtain marked target question and answer information in response to a marking operation on the question and answer information.

[0167] The key information determination module is used to determine the target question and answer information as key question and answer information.

[0168] In some optional embodiments, the above device further includes:

[0169] The conversation display module is used to display the conversation interface of the conversation content, and the conversation interface includes an object display interface, a conversation information display interface and a conversation record display interface.

[0170] The object identification display module is used to display the session object identification corresponding to the new session information on the object display interface when the object to be configured receives the new session information.

[0171] The dialogue information display module is used to display the dialogue information between the target robot and the dialogue object in the dialogue information display interface in response to a trigger operation on the dialogue object identifier.

[0172] The session display module is used to display the session object identifier associated with the object to be configured and the latest information corresponding to the session object identifier in the session record display interface.

[0173] In some optional implementations, the conversation interface includes a conversation intervention control. Accordingly, the above device also includes:

[0174] The object conversion module is used to convert the reply object from the target robot to the proxy object in response to the trigger operation on the dialogue intervention control, and generate reply content in response to the reply operation of the proxy object.

[0175] In some optional embodiments, the above device further includes:

[0176] The session editing module is used to obtain a target session in response to an information editing operation of the proxy object on the session interface, wherein the information editing operation includes at least one of a session entry operation, a session withdrawal operation, and a session rewriting operation.

[0177] The session sending module is used to send the target session in the session interface in response to a sending trigger operation for the target session.

[0178] In some optional implementations, the acquisition module 401 includes:

[0179] The attribute acquisition unit is used to obtain the authorization attribute information of the object to be configured.

[0180] A login page display unit is used to display an authorized login page based on the authorization attribute information.

[0181] The login unit is used to obtain a login result in response to a login operation on the authorized login page.

[0182] The information acquisition unit is used to acquire the object attribute information of the object to be configured if the login result indicates that the login is successful.

[0183] The device for generating the conversation content in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and a memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0184] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0185] The device for generating conversation content provided in this embodiment obtains a conversation knowledge base and a target robot associated with the object to be configured by performing knowledge configuration and robot configuration on each object to be configured. When receiving conversation information, the target robot can reply according to the conversation knowledge base, so that the reply of the target robot is more in line with actual business needs, thereby improving the generation efficiency and generation matching degree of the conversation content, ensuring the conversation effect between the target robot and the conversation object, and thus improving the user's business consulting experience.

[0186] The present disclosure also provides a computer device having the above Fig.14 A device for generating the dialogue content shown.

[0187] See also Fig.15 , Fig.15 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Fig.15 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.15 A processor 10 is taken as an example.

[0188] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0189] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0190] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0191] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0192] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig.15 The example of connecting through bus is taken in the following.

[0193] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0194] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0195] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0196] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for generating dialogue content, characterized in that: The method comprises: Acquire object attribute information, where the object attribute information includes attribute information of at least one object to be configured; In response to the knowledge configuration operation for each of the objects to be configured, determining a dialog knowledge base associated with the object to be configured; In response to the robot configuration operation for each of the objects to be configured, determining a target robot associated with the object to be configured, the target robot being a virtual object for performing a dialogue operation; When the object to be configured receives the conversation information, a conversation content corresponding to the conversation information is generated based on the target robot and the conversation knowledge base.

2. The method according to claim 1, characterized in that Generating a dialogue content corresponding to the conversation information based on the target robot and the dialogue knowledge base includes: The target robot associated with the object to be configured is associated with the dialogue knowledge base, so that the target robot responds to the conversation information according to the dialogue knowledge base to generate the dialogue content.

3. The method according to claim 2, characterized in that The configuration interface of the dialogue knowledge base includes a robot binding control, and / or the configuration interface of the robot includes a knowledge base binding control, and the target robot associated with the object to be configured is associated with the dialogue knowledge base, comprising: In response to a trigger operation on the robot binding control, determining a target robot to which the dialogue knowledge base is to be bound; and / or, In response to a trigger operation on the knowledge base binding control, a dialog knowledge base to be bound to the target robot is determined.

4. The method according to claim 1, characterized in that: The step of determining a target robot associated with each object to be configured in response to a robot configuration operation for each object to be configured comprises: In response to an active reach configuration operation for the robot, generating active reach information corresponding to the robot; In response to the instruction guidance configuration operation for the target robot, generating a guidance instruction corresponding to the target robot, wherein the guidance instruction is used to guide the conversation object to input a question associated with the guidance instruction; In response to a reply object conversion configuration operation for the target robot, generating object conversion configuration information, the object conversion configuration information being used to convert a reply object from the target robot to a proxy object when a target keyword exists in the conversation information; Based on at least one of the active reach information, the guidance instruction and the object conversion configuration information, a target robot associated with the object to be configured is determined.

5. The method according to claim 1 or 4, characterized in that: The target robot has a first version and a second version. The first version is used for reply debugging. After the reply debugging, the second version of the target robot is obtained. The session information is replied based on the second version to generate the dialogue content.

6. The method according to claim 1, characterized in that The knowledge configuration operation includes at least one of a document import operation, an information entry operation, and a batch editing operation; and in response to the knowledge configuration operation for each of the objects to be configured, determining the dialog knowledge base associated with the object to be configured includes: In response to a document import operation for a question and answer file, extracting first question and answer information from the imported question and answer file, and adding the first question and answer information to the dialogue knowledge base; and / or, In response to the information entry operation for the question and answer, obtaining the entered second question and answer information, and adding the entered second question and answer information to the dialogue knowledge base; and / or, In response to the batch editing operation on the questions and answers, edited third question and answer information is obtained, and the third question and answer information is determined as the dialogue knowledge base.

7. The method according to claim 6, characterized in that Also includes: In response to a marking operation on the question and answer information, obtaining marked target question and answer information; The target question and answer information is determined as key question and answer information.

8. The method according to claim 1, characterized in that Also includes: A conversation interface for displaying the conversation content, wherein the conversation interface includes an object display interface, a conversation information display interface, and a conversation record display interface; When the object to be configured receives the new session information, the session object identifier corresponding to the new session information is displayed on the object display interface; In response to a trigger operation on the conversation object identifier, displaying the conversation information between the target robot and the conversation object in the conversation information display interface; The session object identifier associated with the object to be configured and the latest information corresponding to the session object identifier are displayed in the session record display interface.

9. The method according to claim 8, characterized in that The conversation interface includes a conversation intervention control; the method further includes: In response to a trigger operation on the dialogue intervention control, the reply object is converted from the target robot to an agent object, and in response to the reply operation of the agent object, reply content is generated.

10. The method according to claim 9, characterized in that Also includes: In response to the information editing operation of the proxy object on the session interface, obtaining a target session; In response to a sending trigger operation for the target session, sending the target session in the session interface; The information editing operation includes at least one of a session entry operation, a session withdrawal operation, and a session rewriting operation.

11. The method according to claim 1, characterized in that The obtaining of the object attribute information to be configured includes: Get the authorization attribute information of the object to be configured; Displaying an authorization login page based on the authorization attribute information; In response to a login operation on the authorized login page, obtaining a login result; If the login result indicates that the login is successful, object attribute information of the object to be configured is obtained.

12. A device for generating dialogue content, characterized in that: The device comprises: An acquisition module, used to acquire object attribute information, wherein the object attribute information includes attribute information of at least one object to be configured; A knowledge base configuration module, configured to determine a dialog knowledge base associated with each object to be configured in response to a knowledge configuration operation for each object to be configured; A robot configuration operation, for determining a target robot associated with each object to be configured in response to a robot configuration operation for each object to be configured, wherein the target robot is a virtual object for performing a dialogue operation; The dialogue generation module is used to generate dialogue content corresponding to the conversation information based on the target robot and the conversation knowledge base when the object to be configured receives the conversation information.

13. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for generating dialogue content according to any one of claims 1 to 11 by executing the computer instructions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for generating dialogue content according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for generating dialogue content according to any one of claims 1 to 11.

Images