Intelligent agent session processing method and device

Abstract

The embodiment of the invention provides an agent session processing method and device, and the method comprises the steps: carrying out the detection of interaction parameters of a session record of a session instance which carries out the session interaction with an agent, and carrying out the switching of the session interaction of the agent under the condition that the obtained interaction parameters trigger a threshold interval of the session interaction switching of the agent. Generating a session switching prompt based on the session record, sending the session switching prompt to an access end of the agent, displaying the session switching prompt on a session instance interface, newly establishing a session instance according to a triggering instruction of the session switching prompt to obtain a newly established session instance, and performing session data migration for the newly established session instance, in this way, session instance creation and session data migration are achieved by detecting the interaction parameters of the session records of the session instances of the agents.

Description

Technical Field

[0001] This document relates to the field of data processing technology, and in particular to a method and apparatus for processing conversations of an intelligent agent. Background Technology

[0002] With the continuous development of internet technology and artificial intelligence, intelligent agents are rapidly emerging as a prominent new force. The application of intelligent agents can provide users with convenient service implementation methods. An intelligent agent is a complex system with autonomous learning, analysis, and decision-making capabilities. The application of intelligent agents in online services provided by the internet is becoming increasingly widespread, bringing a certain amount of user traffic to online service providers. As users' requirements for intelligent agents and online services continue to increase, it also brings certain pressures and challenges to various online service providers. Summary of the Invention

[0003] This specification provides one or more embodiments of a method for processing a conversation with an intelligent agent, comprising: detecting interaction parameters in the conversation records of a conversation instance interacting with the intelligent agent; if the detected interaction parameters trigger a threshold range for switching the conversation interaction of the intelligent agent, performing structured extraction on the conversation records to obtain structured data; generating a conversation switching prompt based on the structured data and sending it to the access terminal of the intelligent agent for display on the conversation instance interface; creating a new conversation instance according to the trigger instruction of the conversation switching prompt, and migrating the conversation data for the new conversation instance.

[0004] This specification provides one or more embodiments of another method for handling sessions with an intelligent agent, including: receiving a session switching prompt from a server of the intelligent agent; rendering and displaying the session switching prompt on the session instance interface of the intelligent agent; obtaining a trigger instruction for the session switching prompt and submitting it to the server to create a new session instance and migrate session data for the newly created session instance; and switching session interactions on the session instance interface according to the session migration data synchronized by the server.

[0005] This specification provides one or more embodiments of a smart agent's session processing apparatus, comprising: a parameter detection module configured to detect interaction parameters in session records of session instances interacting with the smart agent; an extraction module configured to perform structured extraction on the session records to obtain structured data if the detected interaction parameters trigger a threshold range for session interaction switching of the smart agent; a prompt sending module configured to generate a session switching prompt based on the structured data and send it to the smart agent's access terminal for display on the session instance interface; and an instance creation module configured to create a new session instance based on the trigger instruction of the session switching prompt and perform session data migration for the new session instance.

[0006] This specification provides one or more embodiments of another intelligent agent session processing apparatus, including: a prompt receiving module configured to receive a session switching prompt from a server of the intelligent agent; a prompt display module configured to render and display the session switching prompt on the session instance interface of the intelligent agent; an instruction submission module configured to obtain a trigger instruction for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; and an interaction switching module configured to switch the session interaction on the session instance interface according to the session migration data synchronized by the server.

[0007] This specification provides one or more embodiments of a smart agent's session processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: detect interaction parameters in session records of session instances interacting with the smart agent; if the detected interaction parameters trigger a threshold range for switching the smart agent's session interaction, perform structured extraction on the session records to obtain structured data; generate a session switching prompt based on the structured data and send it to the smart agent's access terminal for display on the session instance interface; create a new session instance according to the trigger instruction of the session switching prompt, and perform session data migration for the new session instance.

[0008] This specification provides one or more embodiments of another intelligent agent session processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: receive a session switching prompt from a server of the intelligent agent; render and display the session switching prompt on the session instance interface of the intelligent agent; obtain a trigger instruction for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; and switch session interactions on the session instance interface according to session migration data synchronized by the server.

[0009] This specification provides one or more embodiments of a computer-readable storage medium for storing computer-executable instructions, which, when executed, perform the following steps: detecting interaction parameters in the session records of a session instance interacting with an agent; if the detected interaction parameters trigger a threshold range for switching the agent's session interaction, performing structured extraction on the session records to obtain structured data; generating a session switching prompt based on the structured data and sending it to the agent's access terminal for display on the session instance interface; creating a new session instance based on the trigger instruction of the session switching prompt, and migrating session data for the new session instance.

[0010] This specification provides one or more embodiments of another computer-readable storage medium for storing computer-executable instructions, which, when executed, perform the following steps: receiving a session switching prompt from a server of the agent; rendering and displaying the session switching prompt on the session instance interface of the agent; obtaining a trigger instruction for the session switching prompt and submitting it to the server to create a new session instance and migrate session data for the newly created session instance; and switching the session interaction on the session instance interface according to the session migration data synchronized by the server. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 A schematic diagram illustrating the implementation environment of a session processing method for an intelligent agent provided in one or more embodiments of this specification; Figure 2A flowchart illustrating a session processing method for an intelligent agent provided in one or more embodiments of this specification; Figure 3 A schematic diagram of a session instance interface provided for one or more embodiments of this specification; Figure 4 A schematic diagram of a session instance interface for creating a new session instance provided in one or more embodiments of this specification; Figure 5 A timing diagram illustrating a session processing method for an intelligent agent applied to an intelligent agent session scenario, provided in one or more embodiments of this specification. Figure 6 A flowchart illustrating another intelligent agent's session processing method provided in one or more embodiments of this specification; Figure 7 A schematic diagram of an embodiment of a session processing device for an intelligent agent provided in one or more embodiments of this specification; Figure 8 A schematic diagram of another embodiment of a session processing apparatus for an intelligent agent provided in one or more embodiments of this specification; Figure 9 A schematic diagram of the structure of a session processing device for an intelligent agent provided in one or more embodiments of this specification; Figure 10 This is a schematic diagram of the structure of another intelligent agent's session processing device provided in one or more embodiments of this specification. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0013] The session processing method for intelligent agents provided in one or more embodiments of this specification is applicable to the implementation environment of intelligent agents. (Refer to...) Figure 1 The implementation environment includes at least: The server of the intelligent agent is 101, and the access point of the intelligent agent is 102; The server 101 of the intelligent agent is used to detect interaction parameters in the session records of the session instances that interact with the intelligent agent. When the detected interaction parameters trigger the threshold range of the session interaction switching of the intelligent agent, a session switching prompt is generated based on the session records and sent to the access terminal of the intelligent agent. According to the triggering instruction of the session switching prompt, a new session instance is created and a new session instance is obtained. The session data is migrated for the new session instance. The server 101 of the intelligent agent can be deployed on a server, which can be one or more servers, a server cluster composed of several servers, or a cloud server of a cloud computing platform. The access terminal 102 of the intelligent agent is used to render and display the session switching prompt on the session instance interface of the intelligent agent, submit the trigger command for the session switching prompt to the server of the intelligent agent, and switch the session interaction on the session instance interface according to the session migration data synchronized by the server of the intelligent agent. The access terminal 102 of the intelligent agent can be deployed on the user terminal, which can be a mobile phone, personal computer, tablet computer, e-book reader, wearable device, device for information interaction based on AR (Augmented Reality) / VR (Virtual Reality), and laptop computer, etc. In addition, the implementation environment may also include a session database 103, which can store structured data obtained by structured extraction of session records; the session database 103 can be deployed on a server or on other servers; In this implementation environment, the server 101 of the agent performs interaction parameter detection on the session records of the session instances that interact with the agent. If the detected interaction parameters trigger the threshold range for switching the agent's session interaction, a session switching prompt is generated based on the session records and sent to the access terminal 102 of the agent for display on the session instance interface. The new session instance is created according to the trigger command of the session switching prompt, and the session data is migrated for the new session instance. In this way, the creation of session instances and the migration of session data are realized by detecting the interaction parameters of the session records of the agent's session instances.

[0014] One or more embodiments of a session processing method for an intelligent agent provided in this specification are as follows: Reference Figure 2 The session processing method for intelligent agents provided in this embodiment can be applied to the server side of intelligent agents, specifically including steps S202 to S208.

[0015] Step S202: Detect interaction parameters in the session records of the session instances that interact with the agent.

[0016] The intelligent agent described in this embodiment refers to an agent that can perceive the environment and take actions to achieve a specific goal. The intelligent agent can be software, hardware, or a system. By perceiving changes in the environment, it makes judgments and decisions based on its learned knowledge and algorithms, and then performs actions to influence the environment or achieve a predetermined goal. The session instance can be an independent running entity or session container created for a single or multiple continuous interaction process between the user and the intelligent agent. The session instance can be used to define the session context and / or manage the interaction state.

[0017] A session record can be a record or stream of sessions formed by a user and an agent interacting with each other. The session record may include the user’s session content and / or the agent’s session content.

[0018] In practical applications, during conversational interactions between users and intelligent agents, there may be situations where the conversation reaches its limit. To address this, in order to smoothly switch conversational interactions after the intelligent agent reaches its limit, avoid losing key information during the conversational interaction process, and improve the user's conversational interaction experience, interaction parameter detection can be performed on the conversation records of conversational instances interacting with the intelligent agent. Specifically, in one optional implementation of this embodiment, during the process of detecting interaction parameters on the conversation records of conversational instances interacting with the intelligent agent, the following operations are performed: interaction length detection, interaction duration detection, and / or interaction round detection are performed on the conversation records.

[0019] In addition, semantic relevance detection, topic deviation detection, computing power utilization detection, and / or session cache utilization detection can be performed on session records.

[0020] Step S204: If the detected interaction parameters trigger a threshold range for the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data.

[0021] The above-mentioned interaction parameter detection is performed on the session records of the session instance interacting with the agent. In this step, if the detected interaction parameters do not trigger the threshold range for the agent to switch the session interaction, no processing is required, or the current user text is input into the large language model integrated with the agent to generate the answer text and send it to the agent's access terminal for display on the session instance interface. If the detected interaction parameters trigger the threshold range for the agent to switch the session interaction, the session records are extracted in a structured manner to obtain structured data. This structured extraction enables the session record to be summarized, allowing for proactive and orderly summarization of the session records when the session instance needs to be switched, thus facilitating subsequent new sessions.

[0022] The interaction parameters described in this embodiment may include interaction length, interaction duration, interaction rounds, semantic relevance, number of times the conversation topic deviates, computing power utilization rate, and / or conversation cache utilization rate. Optionally, the threshold range for triggering the agent's conversation interaction switching based on the interaction parameters includes: the detected interaction length being within the interaction switching length range for the agent's conversation interaction switching, the detected interaction duration being within the interaction switching duration range for the agent's conversation interaction switching, and / or, the detected interaction rounds being within the interaction switching round range for the agent's conversation interaction switching.

[0023] The interaction length refers to the total length of the input and / or output text that the agent can record and incorporate into the calculation during a single or multiple session interactions; the interaction switching length range can be the context length range of the agent. Semantic relevance can be the semantic similarity between the current user-inputted conversation text and other conversation texts of the conversation instance; conversation topic deviation count can be the cumulative number of deviations from the conversation topic of the conversation instance during the conversation interaction; computing power utilization can be the agent's GPU memory utilization, CPU utilization, and / or inference latency; conversation cache utilization can be the cache space utilization of the conversation instance; the threshold range for interaction parameters to trigger the agent's conversation interaction switching can be the parameter threshold range for the agent's conversation interaction switching.

[0024] In practice, if the detected interaction parameters trigger the threshold range of the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data.

[0025] In the specific execution process, in order to improve the efficiency of subsequent session interaction switching and to enable smooth session switching, the following operation is performed in an optional implementation method provided in this embodiment: The session records are input into the session analysis engine to perform session analysis according to the structured fields, and the field summaries corresponding to the structured fields are obtained.

[0026] Optionally, the structured fields include at least one of the following: a conversation topic field, an interaction consensus field between the user and the agent for conversational interaction on the conversation topic, a pending issue field for the conversation topic, and a conversational interaction suggestion field; in addition, the structured fields may also include a conversation dispute field, that is, a conversation field in which there is a dispute during the conversational interaction between the agent and the user.

[0027] The conversation topic field can be a conversation issue field for interaction with the agent; the consensus field can be a key point field where the user and the agent have reached a consensus on the conversation topic. The conversation analysis engine can be a large language model (LLM), which can be a deep learning model trained on massive amounts of text data. The model architecture of the large language model can be any model architecture, such as a large language model with a Transformer model architecture; there can be one or more structured fields, and the field summary corresponding to the structured field can be the key information corresponding to each structured field in the conversation record.

[0028] Specifically, during the conversational interaction between the agent and the user, the conversation analysis engine performs real-time conversation analysis on the input conversation records according to the structured fields to obtain the field summaries corresponding to the structured fields; in addition, the conversation analysis engine can also perform user emotion recognition based on the conversation records to obtain emotion recognition results.

[0029] Based on this, in an optional implementation of this embodiment, during the process of extracting structured data from session records, the following operation is performed: generating structured data in a preset data format based on field summaries.

[0030] The preset data format can be a pre-set data format, and the preset data format can be any form of data format, such as JSON (JavaScript Object Notation) format.

[0031] In addition to obtaining emotion recognition results by performing user emotion recognition based on the aforementioned conversation analysis engine, the engine can also merge the field summaries corresponding to each structured field with the emotion recognition results to obtain structured data in a preset data format.

[0032] It should be noted that the process of extracting structured data from the session records to obtain structured data if the detected interaction parameters trigger the threshold range of the agent's session interaction switching can be replaced by extracting structured data from the session records based on the detected interaction parameters, and combining this with other processing steps provided in this embodiment to form a new implementation method.

[0033] Step S206: Generate a session switching prompt based on the structured data and send it to the access terminal of the agent for display on the session instance interface.

[0034] In the case of triggering the threshold range of the intelligent agent's session interaction switching based on the detected interaction parameters, the session records are extracted in a structured manner to obtain structured data. In this step, a session switching prompt is generated based on the structured data and sent to the intelligent agent's access terminal. This is to prevent the intelligent agent from losing historical session content and causing interruption of session logic through the session switching prompt, thereby improving the automation of session interaction switching. Correspondingly, the intelligent agent's access terminal can receive the intelligent agent's session switching prompt sent by the intelligent agent's server, render and display the session switching prompt on the intelligent agent's session instance interface, obtain the trigger command for the session switching prompt, and submit it to the intelligent agent's server.

[0035] The session switching prompt described in this embodiment can be a prompt message indicating a session switch for the current session. The session switching prompt may include a session switching reminder and / or structured data, or it may include a session switching reminder and / or session summary text. The session instance interface can be the session interface corresponding to the session instance.

[0036] In practice, a session switching prompt is generated based on structured data and sent to the access point of the intelligent agent for display on the session instance interface. Specifically, the session switching prompt can be generated based on both the session switching reminder and the structured data. Alternatively, a session summary text can be generated based on the structured data, and then the session switching prompt can be generated based on both the reminder and the summary text. For example, the session summary text might read, "This session has reached its limit. The system has generated a session summary for you. You can choose to continue to a new session, save the current content, or ignore the summary." The session switching reminder might read, "In this session, you mainly shared that you are x1, x2 years old, and that you haven't been sleeping well lately, which started last month. We discussed related emotional experiences and coping strategies, laying the foundation for further in-depth communication."

[0037] The session transition prompt or session summary text can be associated with a transition reminder control. This transition reminder control can be configured with transition sub-controls, save sub-controls, and / or skip sub-controls. The save sub-control allows submission of save commands, and the skip sub-control allows submission of skip commands for the session transition prompt, for example, through... Figure 3 The "Ignore" control in the middle submits a skip instruction.

[0038] In the specific implementation process, in order to improve the intuitiveness of the session switching prompt and enable users to intuitively understand the relevant information of the session switching, in an optional implementation method provided in this embodiment, the following operations are performed during the process of generating the session switching prompt based on structured data: The initial session switching prompt is generated based on structured data, and the keywords in the initial session switching prompt are marked based on preset marker elements; The obtained session switching prompts can be edited to obtain session switching prompts.

[0039] Among them, the preset marker element can be a highlighted marker element; the keyword can be key information in the initial session switching prompt, such as the field summary corresponding to the session interaction suggestion field in the initial session switching prompt.

[0040] In addition, during the process of generating session switching prompts based on structured data, an initial session summary text can also be generated based on structured data. The text keywords in the initial session summary text can be marked based on preset marker elements to obtain the session summary text. The session summary text can be configured to be editable to obtain an editable summary text. The session switching prompt can be generated based on the editable summary text and the session switching reminder.

[0041] For example Figure 3 The session instance interface shown is as follows: 301 is a session switching reminder, and 302 is an editable summary text, which is in an editable state.

[0042] Based on this, in order to avoid discrepancies between the session switching prompts generated by the agent and the actual situation of the user, and to improve the convenience for the user to edit the prompts, thereby increasing the success rate of resolving user problems after the user interacts with the agent in a session; in an optional implementation of this embodiment, after the access terminal displays the session switching prompt on the session instance interface, it performs the following operation: based on the editing instructions of the session switching prompt, it edits the session switching prompt to obtain the edited switching prompt and displays it.

[0043] The editing commands can be text deletion commands, text addition commands, and / or text modification commands.

[0044] Specifically, after the client edits the session switching prompt and obtains the edit switching prompt, it can also send the edit switching prompt to the agent's server.

[0045] In addition, since the session switching prompt can include editable summary text and session switching reminder, after the session switching prompt is displayed on the session instance interface on the access end, the editable summary text can be edited based on the editing instructions to obtain the edited summary text and then displayed. After that, the edited summary text can also be sent to the server.

[0046] For example Figure 3 As shown, 302 is an editable summary text. Based on the editing instructions of the editable summary text 302, the editable summary text is edited to obtain editing switching prompts and display them.

[0047] When displaying conversation switching prompts, editing switching prompts, or editing summary text in the conversation instance interface, these prompts can be displayed in a preset manner. Specifically, they can be displayed as lightweight tags embedded in the conversation, non-modal pop-ups, or slide-out sidebars. This preset display method avoids forcibly interrupting the user's current conversation and clearly and seamlessly guides the user into a new conversation while the user is engaged in the current conversation, minimizing disruption to the user's conversation.

[0048] In practical applications, after displaying a session switching prompt on the session instance interface, users may not immediately initiate a new session. To address this, and to meet the diverse needs of users interacting with the agent and improve the user experience, this embodiment provides an optional implementation where, after generating the session switching prompt based on structured data and sending it to the agent's access point for display on the session instance interface, the structured data can be configured according to the storage instructions of the session switching prompt to obtain the session configuration type. The session configuration type and structured data are then stored in the user's session database for easy access and initiation of new sessions later. Specifically, the following operations can also be performed: Based on the storage instructions prompted by the session switching, the session call type is obtained by configuring the session call on the structured data; Establish the association between session call types and structured data, and store the association in the user's session database.

[0049] The stored instruction for the session switching prompt here can be replaced with an editable switching prompt, editable summary text, or editable summary text. The session call type refers to the usage type when subsequently using structured data. For example, session call types include session appointment call types and / or session instant call types. Session appointment call types can include commuting appointment call types, and session instant call types can include office instant call types. The process of configuring session calls to obtain the session call type for structured data described above can be replaced with configuring session calls to obtain the session call type for either the session summary text or the editable summary text. Subsequent processes can adaptively modify the structured data.

[0050] For example Figure 3 In the session instance interface shown, the user triggers the "Save" control 303 to submit a storage instruction for the session switching prompt. Based on the storage instruction, the user configures the session call type for the structured data, establishes the association between the session call type and the structured data, and stores the association in the user's session database.

[0051] Based on this, in the first optional implementation provided in this embodiment, during the process of configuring the session call type for structured data according to the storage instruction prompted by the session switching, if the storage instruction carries a cross-end call identifier for the structured data, the session call type is obtained by configuring the session call for the structured data according to the scheduled call time in the storage instruction. Specifically, the session call configuration can be performed in the following manner: If the stored instruction carries a cross-end call identifier for structured data, read the scheduled call time from the stored instruction; The session appointment call type is obtained by configuring the session appointment call to structured data based on the scheduled call time.

[0052] Among them, the cross-terminal call identifier can be a unique identifier that represents the transfer of the conversational interaction with the intelligent agent from the access terminal to other devices, such as the associated device of the access terminal. The associated device can be a device that logs into the same user account as the access terminal, a device that has established a Bluetooth connection with the access terminal, or a device that has established a near-field communication connection with the access terminal; the scheduled call time can be the scheduled time for conversational interaction based on structured data.

[0053] Specifically, in the process of obtaining the session appointment call type by configuring the session appointment call on structured data based on the appointment call time, the user's location at the appointment call time can be determined based on the historical user location. If the user's location matches the target commuting location on the user's commuting route, the session appointment call type of the structured data, session summary text, or edited summary text can be configured as the commuting appointment call type, so as to conveniently schedule session interactions with the user according to the user's needs.

[0054] Furthermore, in practical application scenarios, users may need to initiate new conversations during their free time, such as during their commute. Therefore, providing users with a commuting appointment call method allows them to initiate new conversations during their commute, improving the accuracy of conversation interactions under the commuting appointment call type. In the first optional implementation of this embodiment, after establishing the association between the conversation call type and the structured data and storing the association in the user's conversation database, if the conversation appointment call type is a commuting appointment call type and the device location of the associated device at the access end matches the appointment call time with the user's commuting route, the new dialogue content of the intelligent agent is generated based on the structured data in the conversation database and sent to the associated device. Specifically, the following operations can also be performed: When the session appointment call type is the commuting appointment call type, check whether the device location of the associated device on the access end matches the user's commuting route at the appointment call time; If so, read structured data from the session database, generate new dialogue content for the agent based on the reading results, and send it to the associated device; Optionally, the associated device generates a dialogue message based on the newly created dialogue content, and performs voice broadcast of the newly created dialogue content after the dialogue message is triggered.

[0055] Here, reading structured data from the conversation database can be replaced by reading conversation summary text from the conversation database or editing the summary text; the convenience of conversational interaction during commuting is improved by the voice broadcast of dialogue messages, so that users can know the dialogue messages of the intelligent agent in a timely manner.

[0056] In addition, users may also need to initiate a new session immediately during the submission of a storage instruction. To address this need, in the second optional implementation of this embodiment, during the process of configuring the session call type for structured data according to the storage instruction prompted by the session switching, if the storage instruction carries an immediate call field, the session immediate call type is obtained by configuring the session immediate call based on the call decision result obtained from the session call decision based on user profile data and / or user access data to the agent. Specifically, the session call configuration can be performed in the following manner: When the stored instruction carries an immediate invocation field, the session invocation decision is made based on user profile data and / or user access data to the agent. The session-based instant call type is obtained by configuring the call to make instant calls to structured data based on the call decision results.

[0057] Among them, user profile data can be user attribute data, such as the user's birth time, occupation, and salary; user access data to the intelligent agent can include the access location of the intelligent agent at the historical time point corresponding to the current time; the instant session call type can be the type of instant session interaction based on structured data, and the scheduled session call type can be the type of scheduled session interaction based on structured data.

[0058] Specifically, in the process of making session invocation decisions based on user profile data and / or user access data to the intelligent agent, the predicted access location of the user to the intelligent agent at the current time can be determined based on the user profile data and / or user access data to the intelligent agent; in the process of obtaining the session instant invocation type by configuring the session instant invocation of structured data based on the invocation decision results, if the predicted access location is an office location, the session instant invocation type of the structured data can be configured as the office instant invocation type.

[0059] Based on this, in the second optional implementation provided in this embodiment, after establishing the association between the session call type and the structured data, and storing the association in the user's session database, if the session instant call type is the office instant call type and the access terminal is connected to the organization network of the user's organization, the session interaction messages of the intelligent agent in the session instance interface of the newly created session instance are synchronized to the access terminal according to the structured data in the session database; specifically, after storing the association in the user's session database, the following operations can also be performed: When the session instant call type is office instant call type, check whether the access terminal is connected to the organization network of the user's organization; If so, read structured data from the session database and synchronize the session interaction messages of the agent in the session instance interface of the newly created session instance to the access end based on the reading results.

[0060] The organizational network of the user's organization can be a wireless network, such as Wi-Fi (Wireless Fidelity).

[0061] Specifically, during the process of synchronizing the agent's session interaction messages in the session instance interface of the newly created session instance with the access terminal based on the reading results, the agent's session interaction messages in the session instance interface of the newly created session instance can be generated based on the reading results and sent to the access terminal for display in the session instance interface of the newly created session instance; the structured data here can be replaced with session summary text, editable summary text, or editable summary text.

[0062] It should be noted that the above-mentioned operation of generating a session switching prompt based on structured data and sending it to the access end of the intelligent agent for display on the session instance interface can be replaced by generating a session switching prompt based on structured data and sending it to the access end of the intelligent agent, and forming a new implementation method with other processing steps provided in this embodiment.

[0063] Step S208: Create a new session instance according to the trigger command of the session switching prompt, and migrate session data for the new session instance.

[0064] The above-mentioned generation of session switching prompts based on structured data and sending them to the access terminal of the agent. In this step, a new session instance is created according to the trigger instruction of the session switching prompt, and session data migration is performed on the new session instance to automatically realize the establishment of the new session. Through session data migration, the key data in the session instance can be completely preserved, improving the continuity of the session interaction of the new session instance. Correspondingly, the access terminal of the agent can switch the session interaction of the session instance interface according to the session migration data synchronized by the server.

[0065] The newly created session instance described in this embodiment can be an independent running entity or session container created for user-agent session interaction.

[0066] In practice, a new session instance is created based on the trigger command of the session switching prompt, and session data migration is performed on the new session instance. Specifically, during the session data migration process for the new session instance, session data migration can be based on structured data, session switching prompts, session summary text, and / or edited summary text. The trigger command for the session switching prompt can be submitted through a switching sub-control configured by the switching reminder control associated with the session switching prompt, session summary text, or edited summary text; that is, the trigger command for the session switching prompt can be replaced with the trigger command for the session summary text or edited summary text. For example... Figure 3 In the session instance interface shown, the user submits a session switching prompt, session summary text, or edit summary text trigger command by triggering control 304 "Continue New Session".

[0067] In the specific execution process, in order to improve the accuracy of session data migration and reduce user operation costs, based on the above-mentioned editing instructions based on session switching prompts, this embodiment provides an optional implementation where, in the process of creating a new session instance based on the trigger instructions of the session switching prompts and migrating session data for the new session instance, a new session instance is created according to the trigger instructions of the switching sub-controls configured in the switching reminder control associated with the editing switching prompts, and the session interaction suggestions of the smart agent generated based on the editing switching prompts in the new session instance are migrated to the new session instance. Specifically, the session instance creation and session data migration can be performed in the following ways: Create a new session instance based on the trigger command of the switching child control configured in the switching reminder control associated with the editing switching prompt; Based on the edit switching prompts, generate conversation interaction suggestions for the agent in the newly created conversation instance, and migrate the conversation interaction suggestions to the newly created conversation instance.

[0068] The previous approach of generating conversation interaction suggestions for the agent in a new conversation instance based on edit switching prompts and then migrating these suggestions to the new conversation instance can be replaced with generating conversation interaction content for the agent in a new conversation instance based on edit summary text and then migrating this content to the new conversation instance. The conversation interaction content can include conversation summary text, edit summary text, and / or conversation interaction suggestions. This allows the agent to start a new conversation in the new conversation instance based on the key content of the previous conversation record, improving the continuity of conversation interaction in the new conversation and avoiding the loss of important user interaction information.

[0069] For example Figure 4 The session instance interface for the newly created session shown in the image has a 401 error message displaying the session interaction content, specifically: "We are continuing our previous discussion. Based on the summary, in this session, you mainly shared that you are x1, x2 years old, and have been having trouble sleeping lately, which started last month. We explored related emotional experiences and coping strategies, laying the foundation for further in-depth communication. Next, we will focus on the key issues you mentioned. Where should we begin?"

[0070] After migrating session data for a newly created session instance, the agent's server can synchronize the obtained session migration data to the agent's client. The agent's client can switch the session interaction on the session instance interface based on the session migration data synchronized by the server. Specifically, the client can synchronize session interaction suggestions or session interaction content to the client. The agent's client can switch the session instance interface and display the session interaction suggestions or session interaction content on the newly created session instance interface after the switch.

[0071] It should also be noted that the user-related data obtained in this specification, such as session records, device location of the associated device of the access terminal, user profile data, and user access data to the intelligent agent, are authorized by the user and do not involve user privacy. Specifically, authorization can be granted during the user's first access to the intelligent agent or during each subsequent access to the intelligent agent. The intelligent agent in this embodiment can be an intelligent agent embedded in an application, web application, or subroutine, or it can be an intelligent agent application, intelligent agent web application, or intelligent agent subroutine. That is, the session instance interface can be displayed within an application, web application, or subroutine.

[0072] It should be added that each optional implementation method and each feasible execution method in steps S202 to S208 provided in this embodiment can be executed independently as needed, or they can be combined and referenced with each other. At the same time, each specific execution step in each optional implementation method or each feasible execution method can also be executed independently or combined as needed. The execution conditions of "if" or "under what circumstances" involved in each step or operation can be directly deleted, and subsequent operations can be executed. This embodiment does not make specific limitations on this.

[0073] It should also be added that, depending on the actual application scenario, any step S202 and any of the subsequent steps S204 to S208 can be deleted, or any feature in any step can be deleted. For example, the agent in step S202 can be deleted, and the execution order of steps S202 to S208 can also be arbitrary.

[0074] In summary, the conversation processing method for one or more intelligent agents provided in this embodiment firstly detects interaction parameters in the conversation records of conversation instances interacting with the intelligent agent. If the detected interaction parameters trigger a threshold range for switching the intelligent agent's conversation interaction, the conversation records are structurally extracted to obtain structured data. An initial conversation summary text is generated based on the structured data. Text keywords in the initial conversation summary text are marked based on preset marking elements to obtain a conversation summary text. The conversation summary text is configured to be editable to obtain an editable summary text. A conversation switching prompt is generated based on the editable summary text and the conversation switching reminder. In this way, the significance and intuitiveness of the conversation summary text are improved through marking processing. By setting the conversation summary text to an editable state, the editing needs of users for editing conversation summaries can be met, making the conversation summary text more closely aligned with the user's actual conversation interaction scenario with the intelligent agent. Secondly, the session switching prompt is sent to the agent's access end for display on the session instance interface. Based on the trigger command of the switching sub-control configured by the switching reminder control associated with the editable summary text obtained by editing the editable summary text, a new session instance is created. Based on the edited summary text, the agent generates session interaction suggestions for the new session instance and migrates the session interaction suggestions to the new session instance. This allows the agent to start a new session in the new session instance based on the key content of the previous session record, improving the continuity of the new session interaction and avoiding the loss of important user interaction information.

[0075] The implementation process of the above-described intelligent agent session processing method can be executed by the server of the intelligent agent. The implementation process of the other intelligent agent session processing method provided in the following method embodiment can be executed by the access end of the intelligent agent. The two can cooperate with each other during the execution process. Therefore, when reading the above implementation process, you can refer to the corresponding content of the following other intelligent agent session processing method embodiment. Correspondingly, when reading the following other intelligent agent session processing method embodiment, you can also refer to the corresponding content of the above method embodiment.

[0076] The following description uses the application of the agent conversation processing method provided in this embodiment in an agent conversation scenario as an example to further illustrate the agent conversation processing method provided in this embodiment. (See also...) Figure 5 The method for handling agent conversations in intelligent agent conversation scenarios includes the following steps.

[0077] Step S502: Detect interaction parameters in the session records of the session instances that interact with the agent.

[0078] Step S504: If the detected interaction parameters trigger the threshold range of the agent's session interaction switching, perform structured extraction on the session records to obtain structured data.

[0079] Step S506: Generate an initial conversation summary text based on structured data, and mark the text keywords in the initial conversation summary text based on preset marker elements to obtain the conversation summary text.

[0080] Step S508: Configure the conversation summary text to be editable to obtain editable summary text, generate a conversation switching prompt based on the editable summary text and conversation switching reminder, and send it to the access terminal of the agent.

[0081] Step S518: Create a new session instance based on the trigger command of the switching sub-control configured in the switching reminder control, and generate session interaction suggestions for the agent in the new session instance based on the edited summary text.

[0082] Step S520: migrate the session interaction suggestions to the newly created session instance, and synchronize the session interaction suggestions to the agent's access terminal.

[0083] Steps S502 to S508 and S518 to S520 provided in this embodiment are executed by the server of the intelligent agent. It should be noted that the steps S502 to S508 and S518 to S520 executed by the server of the intelligent agent can cooperate with steps S510 to S516 and S522 executed by the access terminal of the intelligent agent in the following embodiment during execution. Therefore, when reading this embodiment, please refer to the corresponding content of steps S510 to S516 and S522 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding content of steps S502 to S508 and S518 to S520 provided in this embodiment.

[0084] It should be noted that any one or more of steps S502 to S508 and steps S518 to S520 can be replaced with the corresponding technical means provided by steps S202 to S208 as needed for implementation and deployment. Any one or more of steps S502 to S508 and steps S518 to S520 can also be combined into a new implementation method as needed for implementation and deployment. Furthermore, any one or more of steps S502 to S508 and steps S518 to S520 can also be combined with one or more of the steps provided by steps S202 to S208 to form a new implementation method, or combined with one or more of the optional implementation methods provided by steps S202 to S208 to form a new implementation method, as needed for actual deployment. These will not be elaborated on here.

[0085] One or more embodiments of another intelligent agent session processing method provided in this specification are as follows: Reference Figure 6 The session processing method for intelligent agents provided in this embodiment can be applied to the access end of intelligent agents, specifically including steps S602 to S608.

[0086] Step S602: Receive the session switching prompt from the agent's server.

[0087] The server of the intelligent agent can detect the interaction parameters of the session records of the session instances that interact with the intelligent agent. If the detected interaction parameters trigger the threshold range for switching the intelligent agent's session interaction, the server can extract the structured data from the session records, generate a session switching prompt based on the structured data, and send it to the intelligent agent's access terminal. Correspondingly, in this step, the server can receive the intelligent agent's session switching prompt sent by the intelligent agent's server.

[0088] Step S604: Render and display the session switching prompt on the session instance interface of the agent.

[0089] In practice, the client of the agent can render and display a session switching prompt on the session instance interface of the agent.

[0090] Step S606: Obtain the trigger instruction for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance.

[0091] Step S608: Switch the session interaction of the session instance interface according to the session migration data synchronized by the server.

[0092] In practice, the interface of the session instance can be switched based on the session migration data synchronized by the server, and the session migration data can be displayed on the session instance interface of the newly created session instance after the switch. Specifically, the access end of the smart agent can switch the interface of the session instance and display session interaction suggestions or session interaction content on the session instance interface of the newly created session instance after the switch.

[0093] The following description uses the application of the agent conversation processing method provided in this embodiment in an agent conversation scenario as an example to further illustrate the agent conversation processing method provided in this embodiment. (See also...) Figure 5 The method for handling agent conversations in intelligent agent conversation scenarios includes the following steps.

[0094] Step S510: Receive a session switching prompt from the agent's server.

[0095] Step S512: Render and display a session switching prompt on the session instance interface of the agent.

[0096] Step S514: Based on the editing instructions of the editable summary text in the session switching prompt, edit the editable summary text to obtain the edited summary text and display it.

[0097] Step S516: Obtain the trigger command of the switching sub-control configured for the switching reminder control associated with the edit summary text and submit it to the server.

[0098] Step S522: Generate a session instance interface for the newly created session instance based on the session interaction suggestions synchronized by the server, and render and display the session interaction suggestions on the session instance interface of the newly created session instance.

[0099] It should be noted that any one or more of steps S510 to S516 and S522 can be replaced with the corresponding technical means provided in steps S602 to S608 as needed for implementation and deployment. Any one or more of steps S510 to S516 and S522 can also be combined into a new implementation method as needed for implementation and deployment. Furthermore, any one or more of steps S510 to S516 and S522 can also be combined with one or more of the steps provided in steps S602 to S608 to form a new implementation method, or combined with one or more of the optional implementation methods provided in steps S602 to S608 to form a new implementation method, as needed for actual deployment. These will not be elaborated on here.

[0100] The following is an embodiment of a session processing device for an intelligent agent provided in this specification: In the above embodiments, a method for processing a conversation of an intelligent agent is provided, and correspondingly, a device for processing a conversation of an intelligent agent is also provided, which will be described below with reference to the accompanying drawings.

[0101] Reference Figure 7 This illustration shows a schematic diagram of an embodiment of a conversation processing device for an intelligent agent provided in this embodiment.

[0102] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0103] This embodiment provides a session processing device for an intelligent agent, including: The parameter detection module 702 is configured to detect interaction parameters in the session records of the session instance that interacts with the agent. The extraction module 704 is configured to perform structured extraction on the session record to obtain structured data if the detected interaction parameters trigger a threshold range for the session interaction switching of the agent. The prompt sending module 706 is configured to generate a session switching prompt based on the structured data and send it to the access terminal of the smart agent for display on the session instance interface; The instance creation module 708 is configured to create a new session instance based on the trigger command of the session switching prompt, and to perform session data migration for the new session instance.

[0104] Another embodiment of the intelligent agent's session processing device provided in this specification is as follows: In the above embodiments, another method for processing conversations of an intelligent agent is provided, and correspondingly, another device for processing conversations of an intelligent agent is also provided, which will be described below with reference to the accompanying drawings.

[0105] Reference Figure 8 This illustration shows a schematic diagram of an embodiment of a conversation processing device for an intelligent agent provided in this embodiment.

[0106] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0107] This embodiment provides a session processing device for an intelligent agent, including: The prompt receiving module 802 is configured to receive the session switching prompt of the intelligent agent sent by the server of the intelligent agent; The prompt display module 804 is configured to render and display the session switching prompt on the session instance interface of the agent; The instruction submission module 806 is configured to obtain the trigger instruction for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance. The interaction switching module 808 is configured to switch the session interaction of the session instance interface according to the session migration data synchronized by the server.

[0108] For ease of description, the above devices are described by dividing them into various modules or units based on their functions. Of course, when implementing one or more of these specifications, the functions of each module or unit can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0109] This specification provides an example of a session processing device for an intelligent agent as follows: Corresponding to the agent-based session processing method described above, and based on the same technical concept, one or more embodiments of this specification also provide an agent-based session processing device, which is used to execute the agent-based session processing method provided above. Figure 9 This is a schematic diagram of the structure of a session processing device for an intelligent agent provided in one or more embodiments of this specification.

[0110] This embodiment provides a session processing device for an intelligent agent, comprising: like Figure 9As shown, device 900 mainly consists of a communication interface 902, a user interface 904, a processor 906, and a data storage 908. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 910. Communication interface 902 enables device 900 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, communication interface 902 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, communication interface 902 can be a wired interface such as Ethernet, Token Ring, or USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or wide area wireless interface (e.g., WiMAX or LTE). Of course, communication interface 902 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. Communication interface 902 may also include multiple physical communication interfaces, such as Wi-Fi, Bluetooth, and wide area wireless interfaces. User interface 904 includes receiving user input and providing output to the user. Therefore, user interface 904 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 904 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 904 may include software, circuitry, or other forms of logic capable of transmitting data to and receiving data from external user input / output devices. Additionally or alternatively, device 900 may support remote access from other devices via communication interface 902 or another physical interface (not shown). User interface 904 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 904 may also be configured as a display device for rendering or displaying text fragments.

[0111] Processor 906 may include one or more general-purpose processors and / or special-purpose processors. Data storage 908 may include one or more volatile and / or non-volatile storage components, and may be integrated wholly or partially with processor 906. Data storage 908 may include removable and non-removable components.

[0112] Processor 906 is capable of executing program instructions 918 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 908 to perform the various functions described herein. Data storage 908 may contain a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 900, enable device 900 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 918 by processor 906 may result in processor 906 using data 912. For example, program instructions 918 may include an operating system 922 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 900 and one or more application programs 920 (e.g., a browser, social application, or game application). Similarly, data 912 may include operating system data 916 and application data 914. Operating system data 916 is primarily accessible to operating system 922, while application data 914 is primarily accessible to one or more application programs 920. Application data 914 may reside in a file system visible or hidden from the user of device 900. Application 920 can communicate with operating system 922 through one or more application programming interfaces (APIs). These APIs facilitate application 920 reading and / or writing application data 914, transmitting or receiving information via communication interface 902, and receiving or displaying information on user interface 904. In some terms, application 920 may be simply referred to as "app". Furthermore, application 920 can be downloaded to device 900 through one or more online application stores or app markets. However, applications can also be installed on device 900 in other ways, such as through a web browser or a physical interface on device 900 (e.g., a USB port).

[0113] In one specific embodiment, the agent's session processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the agent's session processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Detect interaction parameters in the session records of session instances that interact with the agent. If the detected interaction parameters trigger a threshold range for the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data. Based on the structured data, a session switching prompt is generated and sent to the access terminal of the intelligent agent for display on the session instance interface; A new session instance is created based on the trigger command of the session switching prompt, and session data migration is performed on the new session instance.

[0114] Another embodiment of the intelligent agent's session processing device provided in this specification is as follows: Corresponding to the other intelligent agent session processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another intelligent agent session processing device, which is used to execute the other intelligent agent session processing method provided above. Figure 10 This is a schematic diagram of the structure of a session processing device for an intelligent agent provided in one or more embodiments of this specification.

[0115] This embodiment provides a session processing device for an intelligent agent, comprising: like Figure 10As shown, device 1000 mainly consists of a communication interface 1002, a user interface 1004, a processor 1006, and a data storage 1008. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 1010. The communication interface 1002 enables device 1000 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, the communication interface 1002 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, the communication interface 1002 can be a wired interface such as Ethernet, Token Ring, or a USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or a wide-area wireless interface (e.g., WiMAX or LTE). Of course, the communication interface 1002 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. The communication interface 1002 may also include multiple physical communication interfaces, such as Wi-Fi, Bluetooth, and wide-area wireless interfaces. The user interface 1004 includes receiving user input and providing output to the user. Therefore, the user interface 1004 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. The user interface 1004 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, the user interface 1004 may include software, circuitry, or other forms of logic capable of transmitting data to and receiving data from external user input / output devices. Additionally or alternatively, the device 1000 may support remote access from other devices via communication interface 1002 or another physical interface (not shown). The user interface 1004 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. The user interface 1004 may also be configured as a display device for rendering or displaying text fragments.

[0116] Processor 1006 may include one or more general-purpose processors and / or dedicated processors. Data storage 1008 may include one or more volatile and / or non-volatile storage components, and may be integrated wholly or partially with processor 1006. Data storage 1008 may include removable and non-removable components.

[0117] Processor 1006 is capable of executing program instructions 1018 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 1008 to perform the various functions described herein. Data storage 1008 may contain a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 1000, enable device 1000 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 1018 by processor 1006 may result in processor 1006 using data 1012. For example, program instructions 1018 may include an operating system 1022 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 1000 and one or more application programs 1020 (e.g., a browser, social application, or game application). Similarly, data 1012 may include operating system data 1016 and application data 1014. Operating system data 1016 is primarily accessible to operating system 1022, while application data 1014 is primarily accessible to one or more application programs 1020. Application data 1014 may reside in a file system visible or hidden by the user of device 1000. Application 1020 may communicate with operating system 1022 via one or more application programming interfaces (APIs). These APIs facilitate application 1020 reading and / or writing application data 1014, transmitting or receiving information via communication interface 1002, receiving or displaying information on user interface 1004, etc. In some terms, application 1020 may be simply referred to as an "app". Furthermore, application 1020 may be downloaded to device 1000 through one or more online app stores or app markets. However, applications may also be installed on device 1000 in other ways, such as through a web browser or a physical interface on device 1000 (e.g., a USB port).

[0118] In one specific embodiment, the agent's session processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the agent's session processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Receive the session switching prompt for the intelligent agent sent by the server; The session switching prompt is rendered and displayed on the session instance interface of the agent; Obtain the trigger command for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; The session interaction of the session instance interface is switched based on the session migration data synchronized by the server.

[0119] This specification provides an embodiment of a computer-readable storage medium as follows: Corresponding to the above-described method for processing conversations of an intelligent agent, based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0120] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed, perform the following steps: Detect interaction parameters in the session records of session instances that interact with the agent. If the detected interaction parameters trigger a threshold range for the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data. Based on the structured data, a session switching prompt is generated and sent to the access terminal of the intelligent agent for display on the session instance interface; A new session instance is created based on the trigger command of the session switching prompt, and session data migration is performed on the new session instance.

[0121] It should be noted that the embodiments of a computer-readable storage medium described in this specification and the embodiments of a conversation processing method for an intelligent agent described in this specification are based on the same inventive concept. Therefore, the specific implementation of the embodiments can be referred to the implementation of the corresponding methods described above, and the repeated parts will not be described again.

[0122] Another embodiment of a computer-readable storage medium provided in this specification is as follows: Corresponding to the other intelligent agent session processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another computer-readable storage medium.

[0123] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed, perform the following steps: Receive the session switching prompt for the intelligent agent sent by the server; The session switching prompt is rendered and displayed on the session instance interface of the agent; Obtain the trigger command for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; The session interaction of the session instance interface is switched based on the session migration data synchronized by the server.

[0124] It should be noted that the embodiments of another computer-readable storage medium described in this specification and the embodiments of another intelligent agent's session processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0125] This specification provides an example of a computer program product as follows: Corresponding to the above-described method for processing conversations of an intelligent agent, based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0126] A computer program product includes a computer program / instructions that, when executed by a processor, perform the following steps: Detect interaction parameters in the session records of session instances that interact with the agent. If the detected interaction parameters trigger a threshold range for the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data. Based on the structured data, a session switching prompt is generated and sent to the access terminal of the intelligent agent for display on the session instance interface; A new session instance is created based on the trigger command of the session switching prompt, and session data migration is performed on the new session instance.

[0127] It should be noted that the embodiments of a computer program product described in this specification and the embodiments of a conversation processing method for an intelligent agent described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0128] Another example of a computer program product provided in this specification is as follows: Corresponding to the other intelligent agent session processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another computer program product.

[0129] A computer program product includes a computer program / instructions that, when executed by a processor, perform the following steps: Receive the session switching prompt for the intelligent agent sent by the server; The session switching prompt is rendered and displayed on the session instance interface of the agent; Obtain the trigger command for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; The session interaction of the session instance interface is switched based on the session migration data synchronized by the server.

[0130] It should be noted that the embodiments of another computer program product described in this specification and the embodiments of another intelligent agent's session processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0131] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments. For example, the device embodiment, equipment embodiment and computer-readable storage medium embodiment are all similar to the method embodiment, so the description is relatively simple. When reading the relevant content of the device embodiment, equipment embodiment and computer-readable storage medium embodiment, please refer to the description of the method embodiment.

[0132] Although one or more embodiments of this specification provide method steps as described in the embodiments or flowcharts, it is understood that the order of steps listed in the embodiments or flowcharts is only one of many possible execution orders and does not represent the only execution order. Therefore, when the claims involve method steps, any changes or adjustments to the order of such steps, or the parallelism between steps, are also within the scope of protection of the claims.

[0133] This specification uses specific terms to describe embodiments thereof. Terms such as "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of those different embodiments or examples, without contradiction.

[0134] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0135] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0136] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0137] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0138] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0139] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable test processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable test processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0141] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable test processing equipment to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable test processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0143] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0144] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0145] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0146] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of features includes not only those features but also other features not expressly listed, or features inherent to such process, method, article, or apparatus. Without further limitations, a feature defined by the phrase "comprising one..." does not exclude the presence of other identical features in the process, method, article, or apparatus that includes said feature.

[0147] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0148] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0149] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A method for processing conversations of an intelligent agent, comprising: Detect interaction parameters in the session records of session instances that interact with the agent. If the detected interaction parameters trigger a threshold range for the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data. Based on the structured data, a session switching prompt is generated and sent to the access terminal of the intelligent agent for display on the session instance interface; A new session instance is created based on the trigger command of the session switching prompt, and session data migration is performed on the new session instance.

2. The session processing method for an intelligent agent according to claim 1, wherein generating a session switching prompt based on the structured data includes: An initial session switching prompt is generated based on the structured data, and keywords in the initial session switching prompt are marked based on preset marker elements; The obtained session switching prompt is configured to be editable.

3. The session processing method for an intelligent agent according to claim 2, after the access terminal displays the session switching prompt on the session instance interface, it performs the following operations: Based on the editing instructions of the session switching prompt, the session switching prompt is edited to obtain an edited switching prompt and then displayed.

4. The session processing method for an intelligent agent according to claim 3, wherein the step of creating a new session instance based on the trigger instruction of the session switching prompt, and performing session data migration for the new session instance, includes: Based on the trigger command of the switching sub-control configured in the switching reminder control associated with the edit switching prompt, create the new session instance; Based on the edit switching prompt, the agent generates a session interaction suggestion for the newly created session instance, and then migrates the session interaction suggestion to the newly created session instance.

5. The session processing method for an intelligent agent according to claim 1, after the step of generating a session switching prompt based on the structured data and sending it to the access terminal of the intelligent agent for display on the session instance interface, further includes: Based on the storage instructions of the session switching prompt, the session call type is obtained by configuring the session call on the structured data; Establish the association between the session call type and the structured data, and store the association in the user's session database.

6. The session processing method for an intelligent agent according to claim 5, wherein obtaining the session call type by configuring the structured data for session call according to the storage instruction of the session switching prompt includes: If the storage instruction carries a cross-end call identifier for the structured data, the scheduled call time is read from the storage instruction; Based on the scheduled call time, the structured data is configured to perform a session scheduled call, and the session scheduled call type is obtained.

7. The session processing method for an intelligent agent according to claim 6, further comprising, after the step of establishing the association between the session call type and the structured data and storing the association in the user's session database, the following steps are performed: If the session appointment call type is a commuter appointment call type, check whether the device location of the associated device of the access terminal matches the user's commuter route at the appointment call time; If so, read the structured data from the session database, generate new dialogue content for the agent based on the reading result, and send it to the associated device; The associated device generates a dialogue message based on the newly created dialogue content, and broadcasts the newly created dialogue content via voice after the dialogue message is triggered.

8. The session processing method for an intelligent agent according to claim 5, wherein obtaining the session call type by configuring the structured data for session call according to the storage instruction of the session switching prompt includes: When the storage instruction carries an immediate invocation field, a session invocation decision is made based on user profile data and / or the user's access data to the agent; Based on the invocation decision result, the invocation configuration for the structured data is performed to obtain the instant invocation type.

9. The session processing method for an intelligent agent according to claim 8, further comprising, after the step of establishing the association between the session call type and the structured data and storing the association in the user's session database, the following steps are performed: If the session instant call type is office instant call type, detect whether the access terminal is connected to the organization network of the user's organization; If so, read the structured data from the session database, and synchronize the session interaction messages of the agent on the session instance interface of the newly created session instance to the access terminal according to the reading result.

10. The session processing method for an intelligent agent according to claim 1, the method further comprising: The session records are input into the session analysis engine to perform session analysis according to the structured fields, and the field summaries corresponding to the structured fields are obtained. The step of extracting structured data from the session records includes: Structured data in a preset data format is generated based on the field summary.

11. The session processing method for an intelligent agent according to claim 10, wherein the structured field includes at least one of the following: The fields include: conversation topic field, interaction consensus field for user and agent interaction on the conversation topic, pending issue field for the conversation topic, and conversation interaction suggestion field.

12. The session processing method for an intelligent agent according to claim 1, wherein the step of detecting interaction parameters in the session records of session instances that interact with the intelligent agent includes: The session records are subjected to interaction length detection, interaction duration detection, and / or interaction round detection. The threshold range for the interaction parameters to trigger the switching of the agent's session interaction includes: The detected interaction length is within the interaction switching length range of the agent's session interaction switching, the detected interaction duration is within the interaction switching duration range of the agent's session interaction switching, and / or, the detected interaction rounds are within the interaction switching rounds range of the agent's session interaction switching.

13. A method for processing conversations of an intelligent agent, comprising: Receive the session switching prompt for the intelligent agent sent by the server; The session switching prompt is rendered and displayed on the session instance interface of the agent; Obtain the trigger command for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; The session interaction of the session instance interface is switched based on the session migration data synchronized by the server.

14. A conversation processing device for an intelligent agent, comprising: The parameter detection module is configured to detect interaction parameters in the session records of session instances that interact with the agent. The extraction module is configured to perform structured extraction on the session records to obtain structured data if the detected interaction parameters trigger a threshold range for the agent's session interaction switching. The prompt sending module is configured to generate a session switching prompt based on the structured data and send it to the access terminal of the smart agent for display on the session instance interface; The instance creation module is configured to create a new session instance based on the trigger command of the session switching prompt, and to perform session data migration for the new session instance.

15. A conversation processing apparatus for an intelligent agent, comprising: The prompt receiving module is configured to receive session switching prompts for the intelligent agent sent by the server of the intelligent agent; The prompt display module is configured to render and display the session switching prompt on the session instance interface of the agent; The instruction submission module is configured to obtain the trigger instruction for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance. The interaction switching module is configured to switch the session interaction of the session instance interface based on the session migration data synchronized by the server.

16. A conversation processing device for an intelligent agent, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Detect interaction parameters in the session records of session instances that interact with the agent. If the detected interaction parameters trigger a threshold range for the agent's session interaction switching, the session records are extracted in a structured manner to obtain structured data. Based on the structured data, a session switching prompt is generated and sent to the access terminal of the intelligent agent for display on the session instance interface; A new session instance is created based on the trigger command of the session switching prompt, and session data migration is performed on the new session instance.

17. A conversation processing device for an intelligent agent, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Receive the session switching prompt for the intelligent agent sent by the server; The session switching prompt is rendered and displayed on the session instance interface of the agent; Obtain the trigger command for the session switching prompt and submit it to the server to create a new session instance and migrate session data for the newly created session instance; The session interaction of the session instance interface is switched based on the session migration data synchronized by the server.

18. A computer-readable storage medium for storing computer-executable instructions that, when executed, implement the steps of the method of claim 1 or 13.

Images