Dialogue interaction method and device, electronic equipment and storage medium
By acquiring the conversation content of multiple participants, retrieving the target's historical memory from the memory database, and outputting the response content, the interaction problem of in-vehicle chat AI tools in multi-person driving scenarios is solved, realizing effective interaction and privacy protection in multi-person chat.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG GEELY HLDG GRP CO LTD
- Filing Date
- 2026-04-22
- Publication Date
- 2026-07-21
AI Technical Summary
Existing in-vehicle chat AI tools cannot effectively interact in multi-person driving scenarios and cannot adapt to the interaction needs of multiple drivers and passengers.
By acquiring the dialogue content of multiple interlocutors, the target historical memory is retrieved from the memory database, and the response content is output to conduct dialogue interaction. The target historical memory is only related to multiple interlocutors and matches the dialogue content.
It enables effective dialogue and interaction in multi-person chat scenarios, meets the needs of multi-person interaction, and avoids the leakage of others' privacy.
Smart Images
Figure CN122432286A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of chat technology, and in particular to a dialogue interaction method, device, electronic device and storage medium. Background Technology
[0002] To enhance the intelligent experience of vehicles, they are typically equipped with in-vehicle chat AI tools. Currently, the interaction mode of in-vehicle chat AI tools is mostly limited to single-person scenarios, that is, it only supports one-to-one dialogue interaction between a single driver or passenger and the AI.
[0003] In real-world driving scenarios, there are usually multiple people in the vehicle cabin, such as families traveling together, colleagues commuting, and friends traveling together. In these situations, the in-car chat AI tool cannot effectively interact with multiple passengers. It is evident that current vehicles struggle to meet the interaction needs of multiple passengers. Summary of the Invention
[0004] This application provides a dialogue interaction method, apparatus, electronic device, and storage medium, which can solve the problem that vehicles are difficult to adapt to the interaction needs of multiple drivers and passengers. Therefore, the first objective of this application is to provide a dialogue interaction method, the method comprising: Get the conversation content of multiple people in a conversation; Based on the dialogue content, target historical memories are retrieved from the memory database. These target historical memories are only related to the multiple dialogue participants and match the dialogue content. Based on the target's historical memory and the dialogue content, the response content of the dialogue content is output to conduct dialogue interaction.
[0005] In some optional embodiments, the target historical memory includes: individual historical memories of each of the conversation participants that match the conversation content, and group historical memories of each combination of participants that match the conversation content. The personnel group includes at least two of the dialogue participants.
[0006] In some optional embodiments, the storage space of the memory database includes: multiple storage areas corresponding one-to-one with multiple objects, each object being the person or combination of people in the conversation; retrieving the target historical memory from the memory database based on the conversation content includes: Based on the dialogue content, historical memories matching the dialogue content are retrieved from each of the storage areas to obtain the target historical memory.
[0007] In some optional embodiments, the method further includes: The dialogue content is extracted to obtain the current memory of each individual in the dialogue and the current memory of the group of each combination of the individuals. The step of retrieving historical memories matching the dialogue content from each of the storage areas to obtain the target historical memory includes: Based on the current memory of each of the objects, historical memories that match the current memory of the object are retrieved from the storage area corresponding to each of the objects, so as to obtain the historical memories of the object that match the dialogue content.
[0008] In some optional embodiments, the method further includes: Based on the current memory of each of the objects, process the historical memory in the storage area corresponding to the object; The processing includes at least one of updating, adding, and deleting.
[0009] In some optional embodiments, the step of outputting a response based on the target historical memory and the dialogue content includes: Obtain background information, which includes: personality information of each of the dialogue participants, and at least one of the interpersonal relationships among the multiple dialogue participants; Based on the target's historical memory, the dialogue content, and the background information, output the response content to the dialogue content.
[0010] A second objective of this application is to provide a dialogue interaction device, the device comprising: The acquisition module is used to acquire the dialogue content of multiple people in a conversation; The retrieval module is used to retrieve target historical memories from the memory database based on the dialogue content. The target historical memories are only related to the multiple dialogue participants and match the dialogue content. The interaction module is used to output a response to the dialogue content based on the target's historical memory and the dialogue content, so as to conduct dialogue interaction.
[0011] A third objective of this application is to provide an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the dialogue interaction method as described above.
[0012] The fourth objective of this application is to provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dialogue interaction method as described above.
[0013] The fourth objective of this application is to provide a computer program product comprising a computer program that, when executed by a processor, implements the dialogue interaction method as described above.
[0014] The beneficial effects of the technical solution provided in this application include at least the following: This application provides a dialogue interaction method, apparatus, electronic device, and storage medium. The method can acquire the dialogue content of multiple participants and retrieve a target historical memory matching the dialogue content from a memory database. Then, based on the target historical memory and the dialogue content, it outputs a response to the dialogue content. Therefore, the method provided by this application can achieve effective dialogue interaction with multiple participants in a multi-person chat scenario, meeting the needs of multi-person interaction. Furthermore, since the target historical memory is only related to a few participants, it avoids using memories of other people in the memory database as background knowledge for outputting the response content, thereby preventing the leakage of others' privacy.
[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0016] Figure 1 This is a flowchart of a dialogue interaction method provided in an embodiment of this application; Figure 2 This is a flowchart of another dialogue interaction method provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of a chat memory agent provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a dialogue interaction device provided in an embodiment of this application; Figure 5 This is a schematic diagram of another dialogue interaction device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0017] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0018] This application provides a dialogue interaction method that can be applied to electronic devices, such as a chat-memory intelligent agent deployed in an electronic device. Optionally, the electronic device can be a terminal, a vehicle, or a cloud server. The terminal can be a mobile terminal or a fixed terminal. The cloud server can be a single server, a server cluster consisting of several servers, or a cloud computing service center. See also Figure 1 The method includes: Step 101: Obtain the dialogue content of multiple people in the conversation.
[0019] When multiple people are having a conversation, the intelligent agent in the electronic device can control the sound acquisition component to collect the conversation content of the multiple people.
[0020] Step 102: Based on the dialogue content, retrieve the target historical memory from the memory database.
[0021] Among them, the target historical memory is only related to multiple conversation participants and matches the conversation content.
[0022] Step 103: Based on the target's historical memory and dialogue content, output the response content of the dialogue content to conduct dialogue interaction.
[0023] After acquiring the target's historical memory, the intelligent agent can use that historical memory as its knowledge background, combined with the dialogue content, to determine and output the response content to the dialogue content in order to conduct dialogue interaction.
[0024] In summary, this application provides a dialogue interaction method. This method can acquire the dialogue content of multiple participants and retrieve a target historical memory matching the dialogue content from a memory database. Then, based on the target historical memory and the dialogue content, it outputs a response to the dialogue content. Therefore, the method provided by this application can achieve effective dialogue interaction with multiple participants in a multi-person chat scenario, meeting the needs of multi-person interaction. Furthermore, since the target historical memory is only related to a few participants, it avoids using memories of other people in the memory database as background knowledge for outputting the response content, thereby preventing the leakage of others' privacy.
[0025] It should be understood that the method provided in this application is applicable to multi-person chat scenarios, which can be either virtual or physical, to meet diverse application needs. Therefore, the method provided in this application has strong versatility. A virtual scenario refers to an interactive environment in a non-physical space constructed based on network communication, such as a virtual group chat scenario with multiple participants, an online conference room scenario for remote communication, and a virtual interactive scenario based on real-time audio and video transmission.
[0026] The actual physical setting refers to the real physical space where the participants are engaged in a conversation, such as a physical meeting room for group discussions, an indoor room for daily communication or leisure interaction, or the cockpit of a vehicle for interaction during travel. In an actual physical setting, participants can directly communicate face-to-face within the same space.
[0027] Taking the chat method provided in this application as an example, applied to a scenario of multi-person in-vehicle chat, and with the chat memory agent deployed on a cloud server, the chat method will be described exemplarily. See [link to documentation]. Figure 2 The method may include: Step 201: Control the vehicle to collect the dialogue content of multiple people in conversation.
[0028] In the embodiments of this application, see Figure 3 The cloud server's chat memory intelligent agent includes: a dialogue acquisition and distribution module 01. This dialogue acquisition and distribution module 01 can control the vehicle and collect the dialogue content of multiple people in the conversation.
[0029] Specifically, the vehicle may include a sound acquisition component, and the dialogue acquisition and distribution module can control the sound acquisition component to acquire the dialogue content of multiple people in the cabin and upload the acquired dialogue content to the dialogue acquisition and distribution module 01.
[0030] In this embodiment, at least some participants in the conversation have pre-registered on the vehicle. During registration, the vehicle can obtain the participants' biometric information and basic information, and store them accordingly. The biometric information may include at least one of facial features, fingerprint features, and voiceprint features. The basic information may include at least one of the following: name, and may also include at least one of gender, age, and relationships with other registered participants.
[0031] When each participant boards the vehicle, the vehicle can collect their biometric information. If the vehicle determines that the biometric information is registered, it can then use the corresponding basic information as the participant's basic information. Thus, the basic information of at least one target participant can be obtained.
[0032] If the vehicle determines that the biometric information is not registered, it can identify the person speaking to as unregistered and issue a notification. This notification alerts the vehicle to the presence of a new, unregistered person (i.e., a new user) and prompts them to register. Understandably, new users can input their relationship with already registered users during registration. In other words, after registration, new users can be matched with existing registered users.
[0033] Subsequently, the vehicle can also upload the basic information of each person in the conversation to the conversation acquisition and distribution module 01. Thus, the conversation acquisition and distribution module 01 can interact with the vehicle to obtain the conversation content of multiple people in the cabin, as well as the basic information of each person in the cabin.
[0034] Step 202: Extract the individual current memory of each person in the dialogue, as well as the group current memory of each person combination from the dialogue content.
[0035] Individual current memory refers to information involving only a single individual, such as basic preferences, occupation, gender, and name. Group current memory refers to information involving multiple people in a conversation.
[0036] Each group of people includes at least two people in the conversation. In this embodiment of the application, multiple people in the conversation can be combined using an integer greater than 1 and less than or equal to a number of people in the conversation to obtain combination schemes that include two, three, or even all people in the conversation, thereby obtaining all the group of people.
[0037] Please continue reading Figure 3 The chat memory agent also includes a memory production module 02. The dialogue acquisition and distribution module 01 can send the dialogue content of multiple participants and the identifiers of each participant in the cabin to the memory production module 02. Based on the identifiers of each participant, the memory production module 02 can extract the individual current memory of each participant and the group current memory of each participant combination from the dialogue content. The identifier of each participant is used to uniquely identify them among multiple participants; for example, the identifier of each participant can be their name.
[0038] Specifically, the memory production module 02 is equipped with a large language model (LLM). This LLM can extract the individual current memory of each person in the conversation, as well as the group current memory of each person combination, from the conversation content based on the identifiers of each person in the conversation.
[0039] For example, LLM can first break down the dialogue content into multiple independent dialogue units, and extract key information from the dialogue units to obtain the individual current memory of each dialogue participant, as well as the group current memory of each participant combination.
[0040] For example, assuming the multiple conversation participants are Xiaoming, Xiaohong, and Xiaolan, then the combinations of these participants can be Xiaoming & Xiaohong, Xiaoming & Xiaolan, Xiaohong & Xiaolan, and Xiaoming & Xiaohong & Xiaolan. Correspondingly, the memory production module can extract Xiaoming's individual current memory, Xiaohong's individual current memory, Xiaolan's individual current memory, Xiaoming & Xiaohong's group current memory, Xiaoming & Xiaolan's group current memory, Xiaohong & Xiaolan's group current memory, and Xiaoming & Xiaohong & Xiaolan's group current memory.
[0041] Step 203: Based on the individual current memory of each person in the dialogue and the group current memory of each person combination, retrieve the target historical memory from the memory database.
[0042] The target historical memory includes: individual historical memories of each person in the dialogue that match the content of the dialogue, and group historical memories of each combination of people that match the content of the dialogue.
[0043] like Figure 3 As shown, the chat memory agent also includes a multi-person memory management module 03. The memory production module 02 can send the extracted individual current memories of each person in the conversation, as well as the group current memories of each person's combination, to the multi-person memory management module 03.
[0044] The memory database storage space includes multiple storage areas corresponding one-to-one with multiple objects. Each object is a person or group of people in a conversation. The storage area corresponding to a person in a conversation stores the historical memories of that person, and the storage area corresponding to a group of people stores the historical memories of that group. Therefore, the multi-person memory management module 03 can effectively isolate (i.e., differentiate) and manage the memories of multiple people, thus providing a foundation for protecting privacy.
[0045] The multi-person memory management module 03 can retrieve historical memories that match the current memory of each individual from the corresponding storage area, thus obtaining the historical memories that match the dialogue content and ultimately the target historical memory. This allows for partitioned memory retrieval, thereby preventing the leakage of privacy for individuals other than the individuals involved in the conversation.
[0046] In this context, "matching" refers to a semantic relevance exceeding a relevance threshold, which can be pre-stored by the multi-person memory management module 03. If the object is a single person in the conversation, then the object's current memory is the individual current memory of that person, and the object's historical memory matching the conversation content is the individual historical memory matching the conversation content. If the object is a group of people, then the object's current memory is the group's current memory, and the object's historical memory matching the conversation content is the group's historical memory matching the conversation content.
[0047] In this embodiment of the application, for each object, the multi-person memory management module 03 can convert the object's current memory into text, and then use the text as a search term to search in the storage area corresponding to the object, so as to obtain the historical memory that matches the object's current memory.
[0048] Optionally, a retrieval agent can be deployed in the multi-person memory management module 03. This retrieval agent can search in each storage area to obtain the target historical memory.
[0049] Step 204: Based on the target's historical memory and dialogue content, control the vehicle to output the response content of the dialogue content in order to conduct dialogue interaction.
[0050] like Figure 3 As shown, the chat memory agent may further include a chat module 04. The multi-user memory management module 03 can transmit retrieved target historical memories to the chat module 04. The chat module 04 can, based on the target historical memory and the dialogue content, control the vehicle to output response content for the dialogue content, thus facilitating dialogue interaction. For example, the chat module 04 may be equipped with a dialogue agent that outputs response content based on the target historical memory and the dialogue content.
[0051] Specifically, the vehicle may include a sound playback component. The chat module 04 can retrieve the response content based on the target's historical memory and conversation content. Subsequently, the chat module 04 can control the vehicle's sound playback component to play the response content, enabling interactive conversations with multiple people inside the vehicle.
[0052] Optionally, the chat module 04 can also obtain background information, which may include: the personality information of each person in the conversation, and at least one of the relationships between the multiple people in the conversation. For example, the background information includes the personality information of each person in the conversation, and the relationships between the multiple people in the conversation.
[0053] At this point, chat module 04 can control the vehicle to output responses based on the target's historical memory, dialogue content, and background information. The personality information of each participant is used to represent their personality preferences. Optionally, the relationships between multiple participants are represented using a relationship graph.
[0054] Considering the personality information of the conversation participants when responding can, on the one hand, make the responses more aligned with user preferences, improving the naturalness of the interaction and the intelligence of the chat memory agent; on the other hand, it can use the personality information of each participant as background noise in multi-person chats, thus better connecting and expanding conversation topics. Furthermore, considering the relationships between the participants when responding ensures the accuracy and rationality of the interactive content, making the responses more consistent with real-world social logic, thereby improving the fluency and realism of the interaction, and enhancing the intelligence of the chat memory agent.
[0055] Please continue reading Figure 3 The chat memory agent may further include a user identification module 05 and a personality generation module 06. The user identification module 05 can acquire the relationships between multiple participants in a conversation and transmit these relationships to the chat module 04. The personality generation module 06 can acquire the personality information of each participant in the conversation and transmit this personality information to the chat module 04. Accordingly, the chat module 04 can then acquire the relationships and personality information.
[0056] In this embodiment, the user identification module 05 can acquire the dialogue content of multiple participants sent by the dialogue acquisition and distribution module 01, as well as the basic information of each participant. In cases where relationships between some participants are missing, such as when no relationship was entered during registration, the user identification module 05 can still identify the relationships between multiple participants based on the dialogue content. Furthermore, the user identification module 05 can store these relationships in a relational database.
[0057] The personality generation module 06 operates using a combination of active and passive triggering. Active triggering involves periodically summarizing and generating new personality information for each participant based on their existing memories; then, a judgment is made between the existing and new personality information to determine if an update is needed; if an update is required, the existing personality information is updated to the new information. Passive triggering involves triggering the recording of significant events when participants discuss them, and updating their personality information based on the impact of these significant events on their personalities.
[0058] Existing memories include: individual memories of the people involved in the conversation, and memories associated with the people involved in the conversation within existing group memories (i.e., multi-person events). Significant events can include: marriage, childbirth, and the death of relatives or friends.
[0059] Optionally, the personality generation module 06 can simulate and generate personality information of the interlocutors based on their existing memories, internal activity data, and external data. External data refers to data obtained by retrieving relevant information through a search platform based on key personality information and then randomly filtering it.
[0060] Using external data to supplement the existing memories of the conversation participants to generate personality information can ensure that the generated personality information is more accurate and more consistent with the actual personality preferences of the conversation participants.
[0061] Step 205: Based on the current memory of each object, process the historical memory in the storage area corresponding to that object.
[0062] The processing includes at least one of updating, adding, and deleting. For example, for individual people, the processing may include updating, adding, and deleting. For groups of people, the processing may include updating and adding. Updating historical memory refers to updating at least one of the following: the content of the historical memory, the update time, and its importance.
[0063] In this embodiment, the multi-user memory management module can retrieve information from the corresponding storage area based on the current memory of each object. For example, the multi-user memory management module can deploy a retrieval model, which can be used to retrieve information from the storage area. If the multi-user memory management module retrieves a key memory related to the current memory from the storage area, it can determine whether to update or add a memory based on the meaning of the key memory and the meaning of the current memory.
[0064] Specifically, if the multi-user memory management module determines, through LLM (Learning Management Model), that the meaning of a key memory is the same as or similar to the meaning of the current memory, then the importance of that key memory can be updated through LLM. If the multi-user memory management module determines, through LLM, that the meaning of a key memory has been further expanded compared to the meaning of the current memory, then the memory content, update time, and importance of that key memory can be updated (e.g., through LLM). The updated key memory is obtained by summing the key memory before the update and the current memory. The update time can be the time of this update.
[0065] If the multi-user memory management module determines, through LLM, that the meaning of a key memory differs significantly from the meaning of the current memory, and that they are independent of each other, then the current memory can be added to the storage area. The creation and update times of the current memory can then be initialized using LLM, and a score can be assigned to determine its importance. The initialized creation and update times are the same, for example, the generation time of the current memory.
[0066] If the multi-user memory management module does not find any memory related to the current memory in the storage area, it can add the current memory to the storage area, initialize the creation time and update time of the current memory through LLM, and score the current memory through LLM to obtain the importance of the current memory.
[0067] For each memory in the storage area, if the multi-user memory management module determines that the importance of the memory is below a preset threshold, the memory can be deleted, thus achieving memory forgetting. The preset threshold can be pre-stored by the multi-user memory management module. Therefore, the multi-user memory management module can effectively manage the memories in the memory database.
[0068] It is understood that the order of the steps in the dialogue interaction method provided in the embodiments of this application can be appropriately adjusted, and the steps can also be added or removed as appropriate. For example, step 205 can also be deleted as appropriate. Any variations that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application, and therefore will not be described in detail.
[0069] In summary, this application provides a dialogue interaction method. This method can acquire the dialogue content of multiple participants and retrieve a target historical memory matching the dialogue content from a memory database. Then, based on the target historical memory and the dialogue content, it outputs a response to the dialogue content. Therefore, the method provided by this application can achieve effective dialogue interaction with multiple participants in a multi-person chat scenario, meeting the needs of multi-person interaction. Furthermore, since the target historical memory is only related to a few participants, it avoids using memories of other people in the memory database as background knowledge for outputting the response content, thereby preventing the leakage of others' privacy.
[0070] This application provides a dialogue interaction device that can be used to execute the methods provided in the above-described method embodiments. See also Figure 4 The device 300 includes: The acquisition module 301 is used to acquire the dialogue content of multiple people in the conversation.
[0071] The retrieval module 302 is used to retrieve target historical memories from the memory database based on the dialogue content. The target historical memories are only related to multiple dialogue participants and match the dialogue content.
[0072] The interaction module 303 is used to output a response to the dialogue based on the target's historical memory and dialogue content, so as to conduct dialogue interaction.
[0073] In some optional embodiments, the target historical memory includes: individual historical memories of each person in the conversation that match the content of the conversation, and group historical memories of each combination of people that match the content of the conversation. The personnel combination includes at least two people in the dialogue.
[0074] In some optional embodiments, the storage space of the memory database includes multiple storage areas corresponding one-to-one with multiple objects, each object being a person or group of people in a conversation. The retrieval module 302 can be used for: Based on the dialogue content, historical memories that match the dialogue content are retrieved from each storage area to obtain the target historical memory.
[0075] In some alternative embodiments, see Figure 5 The device 300 may further include: The extraction module 304 is used to extract the dialogue content to obtain the current memory of each individual in the dialogue and the current memory of the group of each person combination.
[0076] The retrieval module 303 can be used for: Based on the current memory of each object, historical memories that match the current memory of the object are retrieved from the storage area corresponding to each object, thus obtaining the historical memories of the object that match the dialogue content.
[0077] In some alternative embodiments, the device 300 may further include: The memory processing module 305 is used to process the historical memory in the storage area corresponding to each object based on the current memory of each object. The processing includes at least one of the following: updating, adding, and deleting.
[0078] In some alternative embodiments, the interaction module 303 can be used to: Obtain background information, which includes: personality information of each person in the conversation, and at least one of the relationships between the multiple people in the conversation; Based on the target's historical memory, dialogue content, and background information, output the response content of the dialogue content.
[0079] In summary, this application provides a dialogue interaction device that can acquire the dialogue content of multiple participants and retrieve a target historical memory matching the dialogue content from a memory database. Then, based on the target historical memory and the dialogue content, it outputs a response to the dialogue content. Therefore, the device provided by this application can achieve effective dialogue interaction with multiple participants in a multi-person chat scenario, meeting the needs of multi-person interaction. Furthermore, since the target historical memory is only related to a few participants, it avoids using memories of other people in the memory database as background knowledge for outputting the response content, thereby preventing the leakage of others' privacy.
[0080] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 6 As shown, the electronic device 400 includes a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, for example, via a bus 402. Optionally, the electronic device 400 may also include a transceiver 404. It should be noted that in practical applications, the transceiver 404 is not limited to one type, and the structure of this electronic device 400 does not constitute a limitation on the embodiments of this application.
[0081] Processor 401 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0082] Bus 402 may include a pathway for transmitting information between the aforementioned components. Bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 402 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0083] The memory 403 stores a computer program corresponding to the dialogue interaction method provided in the above embodiments of this application. This computer program is controlled and executed by the processor 401. The processor 401 executes the computer program stored in the memory 403 to implement the content shown in the foregoing method embodiments.
[0084] This application provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the dialogue interaction method described above. For example, Figure 1 or Figure 2 The method shown.
[0085] This application provides a computer program product, which includes a computer program that, when executed by a processor, implements the dialogue interaction method described above. For example, Figure 1 or Figure 2 The method shown.
[0086] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0087] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0088] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0089] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0090] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.
[0091] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.
Claims
1. A dialogue interaction method, characterized in that, The method includes: Get the conversation content of multiple people in a conversation; Based on the dialogue content, target historical memories are retrieved from the memory database. These target historical memories are only related to the multiple dialogue participants and match the dialogue content. Based on the target's historical memory and the dialogue content, the response content of the dialogue content is output to conduct dialogue interaction.
2. The method according to claim 1, characterized in that, The target historical memory includes: individual historical memories of each person in the dialogue that match the content of the dialogue, and group historical memories of each combination of persons that match the content of the dialogue. The personnel group includes at least two of the dialogue participants.
3. The method according to claim 2, characterized in that, The memory database storage space includes: multiple storage areas corresponding one-to-one with multiple objects, each object being the person or combination of persons in the conversation; retrieving the target historical memory from the memory database based on the conversation content includes: Based on the dialogue content, historical memories matching the dialogue content are retrieved from each of the storage areas to obtain the target historical memory.
4. The method according to claim 3, characterized in that, The method further includes: The dialogue content is extracted to obtain the current memory of each individual in the dialogue and the current memory of the group of each combination of the individuals. The step of retrieving historical memories matching the dialogue content from each of the storage areas to obtain the target historical memory includes: Based on the current memory of each of the objects, historical memories that match the current memory of the object are retrieved from the storage area corresponding to each of the objects, so as to obtain the historical memories of the object that match the dialogue content.
5. The method according to claim 4, characterized in that, The method further includes: Based on the current memory of each of the objects, process the historical memory in the storage area corresponding to the object; The processing includes at least one of updating, adding, and deleting.
6. The method according to any one of claims 1 to 5, characterized in that, The step of outputting a response based on the target historical memory and the dialogue content includes: Obtain background information, which includes: personality information of each of the dialogue participants, and at least one of the interpersonal relationships among the multiple dialogue participants; Based on the target's historical memory, the dialogue content, and the background information, output the response content to the dialogue content.
7. A dialogue interaction device, characterized in that, The device includes: The acquisition module is used to acquire the dialogue content of multiple people in a conversation; The retrieval module is used to retrieve target historical memories from the memory database based on the dialogue content. The target historical memories are only related to the multiple dialogue participants and match the dialogue content. The interaction module is used to output a response to the dialogue content based on the target's historical memory and the dialogue content, so as to conduct dialogue interaction.
8. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.