Chat process management method and system, electronic equipment and storage medium

Abstract

The invention discloses a chat process management method and system, an electronic device and a storage medium, a chat process comprises an introduction communication stage and an in-depth communication stage, in the introduction communication stage, existing user information related to a user is acquired; taking guiding to select a chat theme as a target, generating first guiding information according to the existing user information, sending the first guiding information to the user, obtaining first content replied by the user for the first guiding information, and adding the first content into the existing user information; determining a chat theme and a chat model in a chat robot based on the existing user information; in the deep communication stage, the chat theme is dominated, and conversation with the user is carried out through the chat model. The chat model determines the strategy when the chat robot chats with the user, and the chat theme can guide the dialogue content of the chat model and the user, so that when the chat theme is dominated and the dialogue with the user is carried out through the chat model, the chat process can better fit the interest, character and the like of the user, and the chat experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent chat technology, and in particular to a chat process management method, system, electronic device and storage medium. Background Art

[0002] Human-to-human conversations are essentially about building and deepening relationships, reflecting human emotional needs and the fundamental principles of social interaction. This interaction isn't just about exchanging information, but also about connecting emotions and building relationships. Similarly, conversations between machines and humans can draw on these principles to refine the content of bot chats, though the format and objectives differ.

[0003] Existing technologies focus on evaluating the capabilities of general large models. The evaluation content is overly focused on knowledge understanding and ignores user experience, resulting in poor user experience. Summary of the Invention

[0004] The present invention provides a chat process management method to solve the problem that the existing chat model ignores user experience.

[0005] In a first aspect, the present invention provides a chat process management method, wherein the chat process includes an introduction communication stage and an in-depth communication stage, and the method includes:

[0006] In the introduction and communication phase, existing user information related to the user is obtained;

[0007] With the goal of guiding the user to select a chat topic, generating first guidance information based on the existing user information and sending the first guidance information to the user;

[0008] Obtaining first content of the user's reply to the first guidance information and adding it to the existing user information;

[0009] Determining a chat topic and a chat model in the chat robot based on the existing user information;

[0010] In the in-depth communication stage, the chat topic is taken as the main topic and a conversation is conducted with the user through the chat model.

[0011] In a second aspect, the present invention provides a chat process management system, wherein the chat process includes an introduction communication stage and an in-depth communication stage, and the system includes:

[0012] The information acquisition phase is used to obtain existing user information related to the user during the introduction and communication phase;

[0013] A first guidance information generating module is configured to generate a first guidance message based on the existing user information and send the first guidance message to the user, with the goal of guiding the user to select a chat topic;

[0014] an existing user information updating module, configured to obtain the first content of the user's reply to the first guidance information and add the content to the existing user information;

[0015] A topic and model determination module, configured to determine a chat topic and a chat model in the chatbot based on the existing user information;

[0016] The dialogue module is used to conduct a dialogue with the user through the chat model, taking the chat topic as the main subject, during the in-depth communication stage.

[0017] In a third aspect, the present invention provides an electronic device, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the chat process management method described in the first aspect of the present invention.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, which are used to enable a processor to implement the chat process management method described in the first aspect of the present invention when executed.

[0022] An embodiment of the present invention provides a chat process management method, wherein the chat process includes an introduction communication phase and an in-depth communication phase. In the introduction communication phase, existing user information related to the user is obtained; with the goal of guiding the selection of a chat topic, a first guidance message is generated based on the existing user information and sent to the user; the first content of the user's reply to the first guidance message is obtained and added to the existing user information; a chat topic and a chat model in a chat robot are determined based on the existing user information; in the in-depth communication phase, a conversation is conducted with the user using the chat model, with the chat topic as the main guide. The existing user information can reflect user characteristics such as user interests and personality to a certain extent. Therefore, the chat model and chat topic determined based on the existing user information are consistent with the user characteristics. The chat model determines the chat robot's strategy when chatting with the user. The chat topic can guide the content of the conversation between the chat model and the user. Therefore, when the chat topic is the main guide and the conversation is conducted with the user through the chat model, the interaction process between the chat robot and the user can be more in line with the user's interests and personality, thereby improving the user's chat experience.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 This is a flowchart of a chat process management method provided by an embodiment of the present invention;

[0026] Figure 2 This is a flowchart of a chat process management method provided by an embodiment of the present invention;

[0027] Figure 3 This is a structural diagram of a chat process management system provided by an embodiment of the present invention;

[0028] Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0030] Figure 1 This is a flowchart of a chat process management method provided by an embodiment of the present invention. This embodiment is applicable to chat process management. The method can be executed by a chat process management system. The chat process management system can be implemented in the form of hardware and / or software. The chat process management system can be configured in an electronic device. The chat process includes an introduction communication stage and an in-depth communication stage. Figure 1 As shown, the chat process management method includes:

[0031] S101. In the introduction and communication phase, existing user information related to the user is obtained.

[0032] Before the introduction of the communication stage, the chat process also includes an opening stage. In the opening stage, the user can actively initiate a chat request on the chat interface, or the chat robot can actively initiate a chat invitation to the user. The situation where the chat robot actively initiates a chat invitation to the user is usually limited to the case where the user has already registered or there is historical interaction content between the chat robot and the user.

[0033] Existing user information is the information currently available about the user, including interest tags, basic information, current input content, and historical replies. To interact with a chatbot, users typically need to register. During the registration process, users are required to fill in basic information and interest tags. For users interacting with a chatbot for the first time, existing user information includes interest tags and basic information.

[0034] S102: With the goal of guiding the user to select a chat topic, first guidance information is generated based on existing user information and sent to the user.

[0035] The chatbot's chat topics are typically quite limited, for example, they can include music and games. In this step, the amount and type of existing user information may be limited, insufficient to determine a chat topic based on the existing user information. Therefore, the chatbot generates first guidance information with the goal of guiding the user to select a chat topic.

[0036] S103: Obtain the first content of the user's reply to the first guidance information and add it to the existing user information.

[0037] After receiving the first guidance information, the user replies, and the first content of the user's reply is added to the existing user information, that is, the existing user information is preliminarily expanded.

[0038] S102-S103 is equivalent to the small talk process, which has not yet officially entered the chat stage. Currently, the chat robot cannot fully determine the user's user characteristics. Therefore, in the current small talk stage, the user is guided to provide additional information. For example, the guidance process is as follows:

[0039] Robot: Do you like music?

[0040] User: I like it.

[0041] Robot: Do you like Zhou xx’s songs?

[0042] User: It’s okay, but I prefer Li XX’s songs.

[0043] It can be seen that in the chat stage, firstly, questions are asked to define whether the user is interested in music, and secondly, guiding questions are used to determine the type of music the user is interested in. All this information can represent the user characteristics of the user.

[0044] S104: Determine a chat topic and a chat model in the chat robot based on the existing user information.

[0045] The chatbot includes multiple chat models, each of which corresponds to a different chat topic, that is, each chat model has different knowledge reserves and question-and-answer functions. For example, the music-related chat model is good at music-related topics, and the painting-related chat model is good at painting-related topics.

[0046] By collecting the above existing user information, the existing user information can better represent the user characteristics of the user, and the chat robot can determine the chat topic and the chat model in the chat robot based on the existing user information.

[0047] S105. In the in-depth communication stage, the chat topic is taken as the main topic and the conversation with the user is carried out through the chat model.

[0048] Human conversation is essentially about building and deepening relationships, and the chat process reflects users' need for emotional interaction. This interaction is not just about exchanging information, but also about sharing emotions and building relationships. Similarly, conversations between chatbots and users can also draw on these principles, although the format and goals may differ.

[0049] The chat model determines the strategy of the chatbot when chatting with users. The chat topic can guide the content of the conversation between the chat model and the user. When the chat topic is taken as the main factor and the chat model is used to communicate with the user, the interaction process between the chatbot and the user can be more in line with the user's interests and personality, which is conducive to the user and the chatbot to have good emotional exchanges and build a good relationship, thereby improving the user's chat experience.

[0050] An embodiment of the present invention provides a chat process management method, wherein the chat process includes an introduction communication phase and an in-depth communication phase. In the introduction communication phase, existing user information related to the user is obtained; with the goal of guiding the selection of a chat topic, a first guidance message is generated based on the existing user information and sent to the user; the first content of the user's reply to the first guidance message is obtained and added to the existing user information; a chat topic and a chat model in a chat robot are determined based on the existing user information; in the in-depth communication phase, a conversation is conducted with the user using the chat model, with the chat topic as the main guide. The existing user information can reflect user characteristics such as user interests and personality to a certain extent. Therefore, the chat model and chat topic determined based on the existing user information are consistent with the user characteristics. The chat model determines the chat robot's strategy when chatting with the user. The chat topic can guide the conversation content of the chat model. Therefore, when the chat topic is the main guide and the chat model is used to conduct a conversation with the user, the interaction process between the chat robot and the user can be more in line with the user's interests and personality, thereby improving the user's chat experience.

[0051] During a chat, the relationship between a chatbot and its user progresses through four key stages: initialization, acquaintance, companionship, and distancing. Considering that in real relationships, the development of interpersonal relationship indicators such as trust and dependence is not necessarily linear, judgments are often based on information gathered from the conversation itself.

[0052] In an optional embodiment, the in-depth communication stage includes an initial stage, an acquaintance stage, and a companionship stage, in which the interactive relationship progresses in sequence. In the in-depth communication stage, a conversation with the user is conducted through a chat model, with the chat topic as the main topic, including:

[0053] In the initial stage, the information type of user information required to improve user characteristics is determined; under the limitation of the chat topic, the second guidance information is generated by combining the information type and the chat model and sent to the user; the second content of the user's reply to the second guidance information is received and added to the existing user information.

[0054] The introduction of the communication stage is equivalent to the first meeting and chatting stage between strangers. Due to the limited amount of information communicated, the actual amount of existing user information that can be obtained is still relatively small, and it is impossible to fully portray the user portrait (i.e. user characteristics). The initial stage is equivalent to strangers beginning to develop a friendship after the initial chat, so the amount of information exchange between each other will be increased to increase understanding of each other.

[0055] In the initial stage, the main goal is to obtain relevant information about users in multiple dimensions, including the following aspects:

[0056] 1. Biometric and identity information: usually basic characteristics of personal identity and does not change over time:

[0057] Biometrics include date of birth, gender, and genetic information, while identity information includes name and nationality.

[0058] 2. Background and emotional experience: This information is accumulated and updated over time:

[0059] Education and work experience include family background, growing environment, educational experience (specific school and major), work experience (position and company), and career development path; emotional experience includes marital status and important romantic relationships.

[0060] 3. Dynamic social and life information: updated as time and personal experience change:

[0061] Lifestyle and status: address, phone number, eating habits, exercise habits, leisure activities, health status (including chronic diseases or health problems)

[0062] Social relationships include family members, circle of friends, and social habits.

[0063] 4. Subjective psychological and evaluative information: This information reflects an individual’s inherent traits and subjective cognition, and may change due to the individual’s self-perception and external environmental influences.

[0064] Personality and character include personality traits (such as extroversion, introversion, stability, impulsiveness, etc.), core values, beliefs and moral concepts; values ​​and beliefs include values ​​and beliefs in life, family, career, etc., and attitudes towards social responsibility and public welfare activities.

[0065] 5. Hobbies and Interests: Recreational activities and hobbies (such as music, movies, sports), favorite books, art or cultural activities.

[0066] 6. Intelligence and ability: intelligence level (such as IQ test results), learning ability and cognitive ability, professional skills, and the ability to solve problems and cope with challenges.

[0067] 7. Emotional and psychological state: ways of dealing with stress and frustration, mental health status, attitudes and expectations towards social relationships.

[0068] 8. Future plans and expectations: career planning, personal development goals, expectations for family, marriage, and children’s education.

[0069] Optionally, under the limitation of the chat topic, a second guidance message is generated in combination with the information type and sent to the user, including: prioritizing the information types; determining the information types with higher priorities that do not meet the information collection conditions in turn to obtain the target information type; under the limitation of the chat topic, a second guidance message is generated in turn according to each target information and sent to the user.

[0070] The initial phase begins with a user's first use of a chatbot, gradually familiarizing themselves with the system and establishing an interactive relationship. This process allows for a comprehensive understanding of the user's information. The chat model organizes this information based on its stability, dynamics, and subjective and objective properties, thereby identifying user characteristics.

[0071] It is known that when two people have accumulated a certain level of knowledge about each other, their relationship will generally be further enhanced. Therefore, in an optional embodiment, after receiving the second content of the user's reply to the second guidance information and adding it to the existing user information, the method further includes:

[0072] After the preset time period, the information completion degree is determined based on the existing user information and the preset required information type; it is judged whether the information completion degree reaches the preset ratio threshold; if so, it is determined to enter the acquaintance stage; if not, the current conversation on the chat topic is ended.

[0073] The information completion degree indicates the degree of understanding of the user by the chatbot (chat model), and the degree of understanding is proportional to the information completion degree. When the information completion degree is high, the degree of understanding is also high. Therefore, when the information completion degree reaches the preset ratio threshold, it is determined to enter the stage of knowing each other at a deeper level of relationship. The knowing each other stage is a progressive stage of the initial stage, which means that the interactive relationship between the user and the chatbot is enhanced, and the user's dependence on and trust in the robot is also improved. When the information completion degree does not reach the preset ratio threshold, it is determined to enter the end stage. The main reasons why the information completion degree does not reach the preset ratio threshold are: first, it means that the user cannot trust the chatbot within the preset time, and the user does not want to discuss topics related to his or her own information, resulting in low information completion; second, the user is not interested in the chatbot's topic, and the user's reply frequency and reply content are less, resulting in low information completion; therefore, the current conversation on the chat topic is ended.

[0074] The preset duration can be 30 minutes or 10 days, and can be set according to actual needs. The present invention is not limited to this.

[0075] Of course, in the initial stage, the user can also take the initiative to end the conversation of the current chat topic. Specifically, the user can end the conversation of the current chat topic by exiting the chat interface, canceling the account, or sending content including the semantics of ending the chat to the chat robot.

[0076] Optionally, in the in-depth communication stage, the conversation with the user is conducted with the chat model taking the chat topic as the main topic, and further includes:

[0077] In the getting-to-know-you stage, user characteristics are determined based on the updated existing user information; the chat role of the chat robot is determined based on the user characteristics; a conversation is conducted with the user through the chat model within the framework of the chat role, with the chat topic as the main focus, and the conversation content is updated to the existing user information.

[0078] During this initial phase, the amount of existing user information can be significantly expanded, and this existing user information encompasses multiple dimensions. Therefore, the chat model can use this existing user information to determine user characteristics, i.e., a relatively complete user profile. Different user characteristics correspond to different personalities, interests, hobbies, and topics of interest. The chatbot's chat persona is determined based on these user characteristics. Different chat personas correspond to different character personalities and personas, effectively creating a personality for the chatbot that aligns with the user's interests, aiming to establish common topics and interests with the user.

[0079] Optionally, when the conversation is conducted with the user through the chat model under the framework of the chat role and with the chat topic as the main subject, the method further includes:

[0080] In the getting-to-know-you stage, the preset emotional hourglass model is used to evaluate the intensity values ​​of the user's emotional states related to interaction in multiple dimensions during the chat process. The emotional states include the user's enjoyment of the interaction method, the user's interest in the interaction content, the user's comfort with the interaction dynamics, and the user's confidence in the benefits of the interaction. When the intensity value of the interaction emotional state in each dimension reaches the upper limit value of the corresponding preset dimension threshold, it is confirmed that the user has entered the accompanying stage. When the intensity value of the interaction emotional state in each dimension is lower than the lower limit value of the corresponding preset dimension threshold, it is confirmed that the user has entered the ending stage.

[0081] During the getting-to-know-you phase, chatbots can use the emotional hourglass model to assess the user's emotional state during the chat, ensuring that the user's trust and confidence in the interaction reach a certain threshold, thereby determining whether to enter the next phase—the companionship phase. If this phase is not crossed, the chat may become boring and the companionship process will gradually end. The emotional hourglass model covers four key dimensions, including:

[0082] a. User Pleasantness

[0083] b. User interest in interactive content (Attention)

[0084] c. User Sensitivity to Interaction Dynamics

[0085] d. User confidence in the benefits of the interaction (Aptitude)

[0086] Each of the above emotional dimensions has six intensities, called "emotion levels", which represent the intensity thresholds for expressing emotions.

[0087] Optionally, in the in-depth communication stage, the conversation with the user is conducted with the chat topic as the main topic and through the chat model, further comprising:

[0088] In the accompanying stage, long-term knowledge memory and short-term knowledge memory are distinguished based on the existing user information; the long-term knowledge memory and the short-term knowledge memory are called to communicate with the user through the chat model; it is determined whether any preset alienation condition is met, and the alienation condition includes that the user does not initiate a dialogue request within a preset time, the user's response frequency to the chat robot is less than a preset frequency, and the user's reply content includes semantic information to end the chat; when any of the alienation conditions is met, the current dialogue on the chat topic is ended.

[0089] Among them, the existing user information includes the current chat content or the existing user information stored in history; the long-term knowledge memory is used as the valid information accumulated by the user within a certain period, and the short-term knowledge memory is used as the user's non-fixed and non-periodic random information.

[0090] Entering the companionship stage, chatbots will gradually become integrated into users' daily lives, playing a more prominent role. Users may view the robot as a close companion or even a confidant. During this period, the frequency of user-bot interactions will increase significantly, and the content of these conversations will become more diverse, covering topics ranging from daily trivia to personal emotions. Furthermore, chatbots will be able to adapt in real time to users' emotional fluctuations, demonstrating a high degree of empathy, further strengthening users' trust and emotional dependence, and deepening the interactive experience between both parties.

[0091] During this phase, chatbots should prioritize optimizing their long-term memory and learning capabilities. They need to be able to continuously memorize and update information about users' personal preferences, important events, and interaction habits, ensuring that each conversation builds on previous interactions and demonstrates a deep understanding of the user's needs. This memory capability not only makes users feel valued and understood, but also strengthens their emotional attachment to the chatbot. Furthermore, the chatbot should possess a dynamic learning mechanism, continuously refining its understanding of the user with each interaction. Based on the information gathered during the conversation, it should adopt a style and strategy that aligns with cognitive principles, allowing for reasonable changes. This continuous optimization capability allows the chatbot to gradually adapt to changes in the user, responding flexibly to emotional fluctuations and shifts in interests.

[0092] Through this long-term memory and learning, chatbots will gradually develop the role of a trustworthy "companion" or "confidant", which can not only provide personalized support in daily companionship, but also accurately provide users with emotional comfort and advice at critical moments, thereby enhancing the depth and satisfaction of the user experience.

[0093] Optionally, the chat process management method of the present invention further includes:

[0094] When ending the current conversation of the chat topic, determine whether to switch the chat topic; if so, return to the step of obtaining existing user information related to the user in the introduction communication stage; if not, enter the ending stage, and the ending stage indicates that the interactive relationship between the user and the chat robot has weakened; in the ending stage, a farewell message is generated and sent to the user in combination with the preset mild context and the user characteristics.

[0095] The chatbot can involve multiple chat topics. When ending the conversation on the current chat topic, in order to enhance user stickiness, it can also actively ask the user whether the chat topic needs to be switched. If so, it will re-enter the introduction and communication phase with the chat topic. If not, it will enter the ending phase.

[0096] The interaction between chatbots and users follows the same lifecycle pattern. If a user is offline or has not interacted with the chatbot for an extended period (the specific criteria for this are determined based on user behavior patterns, online time, interaction frequency, and other factors), the journey will be considered to have entered the alienation phase.

[0097] In practice, establishing criteria for the end phase is particularly important. These criteria can include: the user not initiating a conversation request within a certain period of time, a gradual decrease in responses to the robot, or the user clearly stating that they no longer require the companionship service. To avoid misjudgments, the system can send reminders or greetings during the initial phase when the user is offline, giving them an opportunity to continue using the service. If there is still no response, the system will gradually archive the current conversation, marking the end of the companionship lifecycle, where it awaits reawakening.

[0098] This process should be as gentle and respectful as possible. The robot can deliver a friendly farewell message or offer a return option based on the user's personalized information to ensure the user's experience remains complete. Ultimately, the lifecycle of this round of companionship will naturally close based on the user's choices and actions, leaving room for potential future interactions.

[0099] Optionally, after entering the end phase, the chatbot can proactively send reminders to the user based on the current environment, user characteristics, and current hot events. The reminders can be greetings, such as: "It's been raining a lot lately, please remember to bring an umbrella when you go out." This ensures that the user retains a positive impression of the chatbot after entering the end phase, leaving room for potential future interactions.

[0100] In order to systematically describe the chat process management method of the present invention, Figure 2 And the following example illustrates, Figure 2 This is a flow chart of a chat process management method, such as Figure 2 As shown in Figure 1, the chat process includes the opening stage, the introduction communication stage, the in-depth communication stage and the ending stage.

[0101] In the opening phase, a conversation is initiated by a user or a chatbot. For chatbots initiating conversations, the bot needs to determine whether it is a reminder message, meaning a reminder message after entering the closing phase. If so, it proceeds directly to relationship judgment. Since the chat phase must have already occurred before the closing phase, it can skip the chat phase and proceed to relationship judgment.

[0102] During the initial communication phase, users typically begin chatting, gathering user profile information. Based on this information, the user's relationship is then assessed to determine the current relationship stage. Different chat modules correspond to different relationship stages. For first-time users, the initial stage begins. For those not chatting for the first time, assessments can often lead to the acquaintance or companionship stages.

[0103] In the in-depth communication stage, each chat module is used to conduct a dialogue with the user, and it is determined whether to progress to the next stage. Specifically, when the relationship in the initial stage progresses to the acquaintance stage, the initial chat module is replaced with the acquaintance chat module. When the relationship in the acquaintance stage progresses to the companionship stage, the acquaintance chat module is replaced with the companionship chat module. When the companionship stage can be maintained, the companionship stage is maintained. In each chat module, if the relationship cannot progress or cannot be maintained, it is determined whether to end the current chat. If so, it enters the end stage. If not, it is determined whether to switch the chat topic (for example, from music topic to game topic). If the chat topic is not switched, it enters the end stage. If the chat topic is switched, it returns to the introduction communication stage and restarts the communication.

[0104] At the end stage, a farewell message is generated by combining the preset gentle context and the user characteristics and sent to the user.

[0105] This embodiment of the present invention models the chat process from three perspectives: user relationship management, chat topics, and chat process management. User relationship management provides context for the conversation, while chat topics guide chat strategy (provided by corresponding chat models) and content. The conversation strategy employed during the chat process is determined by relationship needs. The rationally designed conversation flow and interaction strategy simulates human communication to a certain extent, providing a similar user experience.

[0106] Corresponding to the above-mentioned chat process management method, the present invention also provides a chat process management system, wherein the chat process includes an introduction communication stage and an in-depth communication stage. Figure 3 This is a structural diagram of a chat process management system provided by an embodiment of the present invention. Figure 3 As shown, the chat process management system includes:

[0107] The information acquisition stage 301 is used to acquire existing user information related to the user in the introduction and communication stage;

[0108] A first guidance information generating module 302 is configured to generate a first guidance information based on the existing user information and send it to the user, with the goal of guiding the user to select a chat topic;

[0109] An existing user information updating module 303 is configured to obtain the first content of the user's reply to the first guidance information and add it to the existing user information;

[0110] The topic and model determination module 304 is used to determine the chat topic and the chat model of the chat robot based on the existing user information;

[0111] The dialogue module 305 is used to conduct a dialogue with the user through the chat model, taking the chat topic as the main subject, during the in-depth communication stage.

[0112] Optionally, the in-depth communication stage includes an initial stage, a getting-to-know-you stage, and a companionship stage, which indicate that the interactive relationship is enhanced in sequence. The dialogue module 305 includes:

[0113] An information type determination submodule, configured to determine, in the initial stage, the type of user information required to improve user characteristics;

[0114] A second guidance information generating submodule is configured to generate a second guidance information based on the chat topic, the information type, and the chat model and send the second guidance information to the user;

[0115] The existing user information updating submodule is configured to receive the second content replied by the user to the second guidance information and add the second content to the existing user information.

[0116] Optionally, the dialogue module 305 further includes:

[0117] A completeness determination submodule is used to determine the information completeness based on the existing user information and the preset required information type after a preset time period;

[0118] The ratio threshold judgment submodule is used to judge whether the information completion degree reaches a preset ratio threshold; if so, it is determined to enter the acquaintance stage; if not, the current conversation of the chat topic is ended.

[0119] Optionally, the dialogue module 305 further includes:

[0120] A user feature determination submodule, configured to determine user features according to the updated existing user information during the acquaintance phase;

[0121] A chat role submodule, configured to determine the chat role of the chat robot based on the user characteristics;

[0122] The first dialogue submodule is used to conduct a dialogue with the user through the chat model under the framework of the chat role, taking the chat topic as the main subject, and updating the dialogue content to the existing user information.

[0123] Optionally, the dialogue module 305 further includes:

[0124] The getting-to-know-you chat submodule is used to evaluate the intensity values ​​of multiple dimensions of the user's emotional state related to the interaction during the getting-to-know-you phase using a preset emotional hourglass model. The emotional state includes the user's enjoyment of the interaction method, the user's interest in the interaction content, the user's comfort with the interaction dynamics, and the user's confidence in the benefits of the interaction.

[0125] Entering the acquaintance stage submodule, used to confirm entering the companionship stage when the intensity value of the interactive emotional state in each dimension reaches the upper limit value of the corresponding preset dimension threshold;

[0126] The first conversation ending submodule is used to end the conversation of the current chat topic when the intensity value of the interactive emotional state in each dimension is lower than the lower limit value of the corresponding preset dimension threshold.

[0127] Optionally, the dialogue module 305 further includes:

[0128] a memory differentiation submodule, configured to differentiate between long-term knowledge memory and short-term knowledge memory according to the existing user information during the accompanying phase;

[0129] A second dialogue submodule, configured to communicate with the user by calling the long-term knowledge memory and the short-term knowledge memory through the chat model;

[0130] A disengagement judgment submodule is used to judge whether any preset disengagement conditions are met, wherein the disengagement conditions include that the user has not initiated a conversation request within a preset time, the user's response frequency to the chatbot is less than a preset frequency, and the user's reply content includes semantic information to end the chat;

[0131] The second conversation ending submodule is used to end the conversation of the current chat topic when any of the alienation conditions is met.

[0132] Optionally, the chat process management system is further configured to perform the following steps:

[0133] When the current conversation of the chat topic ends, determining whether to switch the chat topic;

[0134] If so, return to the step of obtaining existing user information related to the user in the introduction and communication phase;

[0135] If not, the process enters the end phase, which indicates that the interaction between the user and the chatbot has weakened.

[0136] In the ending stage, a farewell message is generated by combining a preset mild context and the user characteristics and sent to the user.

[0137] The chat process management system provided by the embodiment of the present invention can execute the chat process management method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0138] Figure 4 A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0139] like Figure 4As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., which is communicatively connected to the at least one processor 41. The memory stores a computer program that can be executed by the at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. Various programs and data required for the operation of the electronic device 40 can also be stored in the RAM 43. The processor 41, ROM 42, and RAM 43 are connected to each other via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0140] Multiple components in the electronic device 40 are connected to the I / O interface 45, including an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0141] Processor 41 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. Processor 41 executes the various methods and processes described above, such as the chat flow management method.

[0142] In some embodiments, the chat flow management method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the chat flow management method described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to execute the chat flow management method in any other suitable manner (e.g., via firmware).

[0143] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0145] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0146] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a monitor having a cathode ray tube or a liquid crystal display) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0147] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0148] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0149] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0150] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A chat process management method, characterized in that: The chat process includes an introduction communication stage and an in-depth communication stage, and the method includes: In the introduction and communication phase, existing user information related to the user is obtained; With the goal of guiding the user to select a chat topic, generating first guidance information based on the existing user information and sending the first guidance information to the user; Obtaining first content of the user's reply to the first guidance information and adding it to the existing user information; Determining a chat topic and a chat model in the chat robot based on the existing user information; In the in-depth communication stage, the chat topic is taken as the main topic and a conversation is conducted with the user through the chat model.

2. The method according to claim 1, wherein The in-depth communication stage includes an initial stage, an acquaintance stage, and a companionship stage, which represent sequentially enhanced interactive relationships. In the in-depth communication stage, a conversation is conducted with the user through the chat model, with the chat topic as the main focus, including: In the initial stage, the type of user information required to complete the user profile is determined; Under the chat topic limitation, combining the information type and using the chat model, generate a second guidance message and send it to the user; The second content replied by the user to the second guidance information is received and added to the existing user information.

3. The method according to claim 2, wherein After receiving the second content replied by the user to the second guidance information and adding it to the existing user information, the method further includes: After a preset time period, determine the information completion level based on the existing user information and the preset required information type; Determining whether the information completion rate reaches a preset ratio threshold; If so, it is determined to enter the acquaintance stage; If not, end the current conversation on the chat topic.

4. The method according to claim 2, wherein In the in-depth communication stage, the conversation with the user is conducted through the chat model with the chat topic as the main focus, and further includes: In the getting-to-know phase, determining user characteristics based on the updated existing user information; Determining a chat role of the chat robot based on the user characteristics; Taking the chat topic as the main subject and within the framework of the chat role, a conversation is conducted with the user through the chat model, and the conversation content is updated to the existing user information.

5. The method according to claim 4, wherein When the conversation is conducted with the user through the chat model under the framework of the chat role and with the chat topic as the main subject, the method further includes: During the acquaintance phase, a preset emotional hourglass model is used to evaluate the intensity of the user's emotional state in multiple dimensions related to interaction during the chat process. The emotional state includes the user's enjoyment of the interaction method, the user's interest in the interaction content, the user's comfort with the interaction dynamics, and the user's confidence in the benefits of the interaction. When the intensity value of the interactive emotional state in each dimension reaches the upper limit value of the corresponding preset dimension threshold, it is confirmed that the accompanying stage has been entered; When the intensity value of the interactive emotional state in each dimension is lower than the lower limit value of the corresponding preset dimension threshold, the current conversation of the chat topic is ended.

6. The method according to claim 5, wherein In the in-depth communication stage, the conversation with the user is conducted through the chat model with the chat topic as the main focus, and further includes: In the accompanying stage, long-term knowledge memory and short-term knowledge memory are distinguished according to the existing user information; Calling the long-term knowledge memory and the short-term knowledge memory to communicate with the user through the chat model; Determining whether any preset disengagement conditions are met, including the user not initiating a conversation request within a preset time, the user's response frequency to the chatbot being less than a preset frequency, and the user's reply content including semantic information indicating the end of the chat; When any of the alienation conditions is met, the current conversation on the chat topic is ended.

7. The method according to any one of claims 3 to 6, wherein: When ending the current conversation of the chat topic, it also includes: Determine whether to switch the chat topic; If so, return to the step of obtaining existing user information related to the user in the introduction and communication phase; If not, the process enters the end phase, which indicates that the interaction between the user and the chatbot has weakened. In the ending stage, a farewell message is generated by combining a preset mild context and the user characteristics and sent to the user.

8. A chat process management system, characterized in that: The chat process includes an introduction communication stage and an in-depth communication stage, and the system includes: The information acquisition phase is used to obtain existing user information related to the user during the introduction and communication phase; A first guidance information generating module is configured to generate a first guidance message based on the existing user information and send the first guidance message to the user, with the goal of guiding the user to select a chat topic; an existing user information updating module, configured to obtain the first content of the user's reply to the first guidance information and add the content to the existing user information; A topic and model determination module, configured to determine a chat topic and a chat model in the chatbot based on the existing user information; The dialogue module is used to conduct a dialogue with the user through the chat model, taking the chat topic as the main subject, during the in-depth communication stage.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the chat process management method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the chat process management method according to any one of claims 1 to 7 when executed.

Images